niobures/Vicuna
By niobures · ↓ 3 · ♥ 0 · Updated 2025-11-14
What's in this repo
This page lists the files in niobures/Vicuna, including decoder_model_merged.onnx, rank_0_medusa-v1.0-vicuna-7b-v1.5_decoder_merged_model_fp16.onnx, EtGlowExecutionProvider_GLOW_graph_Extracted_from_-Extracted_from_-Extracted_from_-torch_jit---_14597505079178574122_0_0_0.onnx and more.
- 10 ONNX models (.onnx files)
- 1800 files, including 280 .weight, 224 .qweight, 224 .qzeros, 224 .scales, 34 .json, 24 .gguf
- Last updated 2025-11-14
ONNX files
| File | Size | Download |
|---|---|---|
| Wizard-Vicuna-13B-Uncensored-HF-onnx/decoder_model_merged.onnx | — | Download |
| Wizard-Vicuna-7B-Uncensored-ONNX/decoder_model_merged.onnx | — | Download |
| medusa-v1.0-vicuna-7b-v1.5_decoder_merged_model_fp16-onnx/rank_0_medusa-v1.0-vicuna-7b-v1.5_decoder_merged_model_fp16.onnx | — | Download |
| vicuna-13b-v1.3-kvc-fp16-onnx/EtGlowExecutionProvider_GLOW_graph_Extracted_from_-Extracted_from_-Extracted_from_-torch_jit---_14597505079178574122_0_0_0.onnx | — | Download |
| vicuna-13b-v1.3-kvc-fp16-onnx/EtGlowExecutionProvider_GLOW_graph_Extracted_from_{Extracted_from_{torch_jit}}_82587814298613550_0_0_0.onnx | — | Download |
| vicuna-13b-v1.3-kvc-fp16-onnx/model.onnx | — | Download |
| vicuna-7b-v1.3-kvc-fp16-onnx/EtGlowExecutionProvider_GLOW_graph_Extracted_from_-Extracted_from_-Extracted_from_-torch_jit---_11400954490079449885_0_0_0.onnx | — | Download |
| vicuna-7b-v1.3-kvc-fp16-onnx/model.onnx | — | Download |
| vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.onnx | — | Download |
| vicuna-7b-v1.5-kvc-fp16-onnx/model.onnx | — | Download |
How to use
These ONNX files can be loaded with ONNX Runtime. To inspect a model graph, upload the file to the Netron viewer. Download links point to the original files on Hugging Face.
No README provided by the author.
Model info
onnx
gguf
endpoints_compatible
region:us
↓ 3
♥ 0
Created: 2025-11-13
Updated: 2025-11-14
View on Hugging FaceFiles (1800)
.gitattributes
Wizard-Vicuna-13B-Uncensored-GGUF/.gitattributes
Wizard-Vicuna-13B-Uncensored-GGUF/README.md
Wizard-Vicuna-13B-Uncensored-GGUF/Wizard-Vicuna-13B-Uncensored.Q2_K.gguf
Wizard-Vicuna-13B-Uncensored-GGUF/Wizard-Vicuna-13B-Uncensored.Q3_K_L.gguf
Wizard-Vicuna-13B-Uncensored-GGUF/Wizard-Vicuna-13B-Uncensored.Q3_K_M.gguf
Wizard-Vicuna-13B-Uncensored-GGUF/Wizard-Vicuna-13B-Uncensored.Q3_K_S.gguf
Wizard-Vicuna-13B-Uncensored-GGUF/Wizard-Vicuna-13B-Uncensored.Q4_0.gguf
Wizard-Vicuna-13B-Uncensored-GGUF/Wizard-Vicuna-13B-Uncensored.Q4_K_M.gguf
Wizard-Vicuna-13B-Uncensored-GGUF/Wizard-Vicuna-13B-Uncensored.Q4_K_S.gguf
Wizard-Vicuna-13B-Uncensored-GGUF/Wizard-Vicuna-13B-Uncensored.Q5_0.gguf
Wizard-Vicuna-13B-Uncensored-GGUF/Wizard-Vicuna-13B-Uncensored.Q5_K_M.gguf
Wizard-Vicuna-13B-Uncensored-GGUF/Wizard-Vicuna-13B-Uncensored.Q5_K_S.gguf
Wizard-Vicuna-13B-Uncensored-GGUF/Wizard-Vicuna-13B-Uncensored.Q6_K.gguf
Wizard-Vicuna-13B-Uncensored-GGUF/Wizard-Vicuna-13B-Uncensored.Q8_0.gguf
Wizard-Vicuna-13B-Uncensored-GGUF/config.json
Wizard-Vicuna-13B-Uncensored-GGUF/source.txt
Wizard-Vicuna-13B-Uncensored-HF-onnx/.gitattributes
Wizard-Vicuna-13B-Uncensored-HF-onnx/README.md
Wizard-Vicuna-13B-Uncensored-HF-onnx/config.json
Wizard-Vicuna-13B-Uncensored-HF-onnx/decoder_model_merged.onnx
ONNX
Wizard-Vicuna-13B-Uncensored-HF-onnx/decoder_model_merged.onnx_data
Wizard-Vicuna-13B-Uncensored-HF-onnx/generation_config.json
Wizard-Vicuna-13B-Uncensored-HF-onnx/source.txt
Wizard-Vicuna-13B-Uncensored-HF-onnx/special_tokens_map.json
Wizard-Vicuna-13B-Uncensored-HF-onnx/tokenizer.json
Wizard-Vicuna-13B-Uncensored-HF-onnx/tokenizer.model
Wizard-Vicuna-13B-Uncensored-HF-onnx/tokenizer_config.json
Wizard-Vicuna-13B-Uncensored-HF/.gitattributes
Wizard-Vicuna-13B-Uncensored-HF/README.md
Wizard-Vicuna-13B-Uncensored-HF/config.json
Wizard-Vicuna-13B-Uncensored-HF/generation_config.json
Wizard-Vicuna-13B-Uncensored-HF/pytorch_model-00001-of-00003.bin
Wizard-Vicuna-13B-Uncensored-HF/pytorch_model-00002-of-00003.bin
Wizard-Vicuna-13B-Uncensored-HF/pytorch_model-00003-of-00003.bin
Wizard-Vicuna-13B-Uncensored-HF/pytorch_model.bin.index.json
Wizard-Vicuna-13B-Uncensored-HF/source.txt
Wizard-Vicuna-13B-Uncensored-HF/special_tokens_map.json
Wizard-Vicuna-13B-Uncensored-HF/tokenizer.json
Wizard-Vicuna-13B-Uncensored-HF/tokenizer.model
Wizard-Vicuna-13B-Uncensored-HF/tokenizer_config.json
Wizard-Vicuna-7B-Uncensored-GGUF/.gitattributes
Wizard-Vicuna-7B-Uncensored-GGUF/README.md
Wizard-Vicuna-7B-Uncensored-GGUF/Wizard-Vicuna-7B-Uncensored.Q2_K.gguf
Wizard-Vicuna-7B-Uncensored-GGUF/Wizard-Vicuna-7B-Uncensored.Q3_K_L.gguf
Wizard-Vicuna-7B-Uncensored-GGUF/Wizard-Vicuna-7B-Uncensored.Q3_K_M.gguf
Wizard-Vicuna-7B-Uncensored-GGUF/Wizard-Vicuna-7B-Uncensored.Q3_K_S.gguf
Wizard-Vicuna-7B-Uncensored-GGUF/Wizard-Vicuna-7B-Uncensored.Q4_0.gguf
Wizard-Vicuna-7B-Uncensored-GGUF/Wizard-Vicuna-7B-Uncensored.Q4_K_M.gguf
Wizard-Vicuna-7B-Uncensored-GGUF/Wizard-Vicuna-7B-Uncensored.Q4_K_S.gguf
Wizard-Vicuna-7B-Uncensored-GGUF/Wizard-Vicuna-7B-Uncensored.Q5_0.gguf
Wizard-Vicuna-7B-Uncensored-GGUF/Wizard-Vicuna-7B-Uncensored.Q5_K_M.gguf
Wizard-Vicuna-7B-Uncensored-GGUF/Wizard-Vicuna-7B-Uncensored.Q5_K_S.gguf
Wizard-Vicuna-7B-Uncensored-GGUF/Wizard-Vicuna-7B-Uncensored.Q6_K.gguf
Wizard-Vicuna-7B-Uncensored-GGUF/Wizard-Vicuna-7B-Uncensored.Q8_0.gguf
Wizard-Vicuna-7B-Uncensored-GGUF/config.json
Wizard-Vicuna-7B-Uncensored-GGUF/source.txt
Wizard-Vicuna-7B-Uncensored-ONNX/.gitattributes
Wizard-Vicuna-7B-Uncensored-ONNX/README.md
Wizard-Vicuna-7B-Uncensored-ONNX/added_tokens.json
Wizard-Vicuna-7B-Uncensored-ONNX/config.json
Wizard-Vicuna-7B-Uncensored-ONNX/decoder_model_merged.onnx
ONNX
Wizard-Vicuna-7B-Uncensored-ONNX/decoder_model_merged.onnx_data
Wizard-Vicuna-7B-Uncensored-ONNX/generation_config.json
Wizard-Vicuna-7B-Uncensored-ONNX/source.txt
Wizard-Vicuna-7B-Uncensored-ONNX/special_tokens_map.json
Wizard-Vicuna-7B-Uncensored-ONNX/tokenizer.json
Wizard-Vicuna-7B-Uncensored-ONNX/tokenizer.model
Wizard-Vicuna-7B-Uncensored-ONNX/tokenizer_config.json
Wizard-Vicuna-7B-Uncensored/.gitattributes
Wizard-Vicuna-7B-Uncensored/README.md
Wizard-Vicuna-7B-Uncensored/config.json
Wizard-Vicuna-7B-Uncensored/generation_config.json
Wizard-Vicuna-7B-Uncensored/pytorch_model-00001-of-00003.bin
Wizard-Vicuna-7B-Uncensored/pytorch_model-00002-of-00003.bin
Wizard-Vicuna-7B-Uncensored/pytorch_model-00003-of-00003.bin
Wizard-Vicuna-7B-Uncensored/pytorch_model.bin.index.json
Wizard-Vicuna-7B-Uncensored/source.txt
Wizard-Vicuna-7B-Uncensored/special_tokens_map.json
Wizard-Vicuna-7B-Uncensored/tokenizer.json
Wizard-Vicuna-7B-Uncensored/tokenizer.model
Wizard-Vicuna-7B-Uncensored/tokenizer_config.json
Wizard-Vicuna-7B-Uncensored/trainer_state.json
Wizard-Vicuna-7B-Uncensored/training_args.bin
medusa-v1.0-vicuna-7b-v1.5_decoder_merged_model_fp16-onnx/.gitattributes
medusa-v1.0-vicuna-7b-v1.5_decoder_merged_model_fp16-onnx/medusa_lm_head.pt
medusa-v1.0-vicuna-7b-v1.5_decoder_merged_model_fp16-onnx/rank_0_medusa-v1.0-vicuna-7b-v1.5_decoder_merged_model_fp16.onnx
ONNX
medusa-v1.0-vicuna-7b-v1.5_decoder_merged_model_fp16-onnx/rank_0_medusa-v1.0-vicuna-7b-v1.5_decoder_merged_model_fp16.onnx.data
medusa-v1.0-vicuna-7b-v1.5_decoder_merged_model_fp16-onnx/source.txt
vicuna-13b-v1.3-kvc-fp16-onnx/.gitattributes
vicuna-13b-v1.3-kvc-fp16-onnx/EtGlowExecutionProvider_GLOW_graph_Extracted_from_-Extracted_from_-Extracted_from_-torch_jit---_14597505079178574122_0_0_0.onnx
ONNX
vicuna-13b-v1.3-kvc-fp16-onnx/EtGlowExecutionProvider_GLOW_graph_Extracted_from_{Extracted_from_{torch_jit}}_82587814298613550_0_0_0.onnx
ONNX
vicuna-13b-v1.3-kvc-fp16-onnx/model.embed_tokens.weight
vicuna-13b-v1.3-kvc-fp16-onnx/model.layers.0.input_layernorm.weight
vicuna-13b-v1.3-kvc-fp16-onnx/model.layers.0.post_attention_layernorm.weight
vicuna-13b-v1.3-kvc-fp16-onnx/model.layers.1.input_layernorm.weight
vicuna-13b-v1.3-kvc-fp16-onnx/model.layers.1.post_attention_layernorm.weight
vicuna-13b-v1.3-kvc-fp16-onnx/model.layers.10.input_layernorm.weight
vicuna-13b-v1.3-kvc-fp16-onnx/model.layers.10.post_attention_layernorm.weight
vicuna-13b-v1.3-kvc-fp16-onnx/model.layers.11.input_layernorm.weight
vicuna-13b-v1.3-kvc-fp16-onnx/model.layers.11.post_attention_layernorm.weight
vicuna-13b-v1.3-kvc-fp16-onnx/model.layers.12.input_layernorm.weight
vicuna-13b-v1.3-kvc-fp16-onnx/model.layers.12.post_attention_layernorm.weight
vicuna-13b-v1.3-kvc-fp16-onnx/model.layers.13.input_layernorm.weight
vicuna-13b-v1.3-kvc-fp16-onnx/model.layers.13.post_attention_layernorm.weight
vicuna-13b-v1.3-kvc-fp16-onnx/model.layers.14.input_layernorm.weight
vicuna-13b-v1.3-kvc-fp16-onnx/model.layers.14.post_attention_layernorm.weight
vicuna-13b-v1.3-kvc-fp16-onnx/model.layers.15.input_layernorm.weight
vicuna-13b-v1.3-kvc-fp16-onnx/model.layers.15.post_attention_layernorm.weight
vicuna-13b-v1.3-kvc-fp16-onnx/model.layers.16.input_layernorm.weight
vicuna-13b-v1.3-kvc-fp16-onnx/model.layers.16.post_attention_layernorm.weight
vicuna-13b-v1.3-kvc-fp16-onnx/model.layers.17.input_layernorm.weight
vicuna-13b-v1.3-kvc-fp16-onnx/model.layers.17.post_attention_layernorm.weight
vicuna-13b-v1.3-kvc-fp16-onnx/model.layers.18.input_layernorm.weight
vicuna-13b-v1.3-kvc-fp16-onnx/model.layers.18.post_attention_layernorm.weight
vicuna-13b-v1.3-kvc-fp16-onnx/model.layers.19.input_layernorm.weight
vicuna-13b-v1.3-kvc-fp16-onnx/model.layers.19.post_attention_layernorm.weight
vicuna-13b-v1.3-kvc-fp16-onnx/model.layers.2.input_layernorm.weight
vicuna-13b-v1.3-kvc-fp16-onnx/model.layers.2.post_attention_layernorm.weight
vicuna-13b-v1.3-kvc-fp16-onnx/model.layers.20.input_layernorm.weight
vicuna-13b-v1.3-kvc-fp16-onnx/model.layers.20.post_attention_layernorm.weight
vicuna-13b-v1.3-kvc-fp16-onnx/model.layers.21.input_layernorm.weight
vicuna-13b-v1.3-kvc-fp16-onnx/model.layers.21.post_attention_layernorm.weight
vicuna-13b-v1.3-kvc-fp16-onnx/model.layers.22.input_layernorm.weight
vicuna-13b-v1.3-kvc-fp16-onnx/model.layers.22.post_attention_layernorm.weight
vicuna-13b-v1.3-kvc-fp16-onnx/model.layers.23.input_layernorm.weight
vicuna-13b-v1.3-kvc-fp16-onnx/model.layers.23.post_attention_layernorm.weight
vicuna-13b-v1.3-kvc-fp16-onnx/model.layers.24.input_layernorm.weight
vicuna-13b-v1.3-kvc-fp16-onnx/model.layers.24.post_attention_layernorm.weight
vicuna-13b-v1.3-kvc-fp16-onnx/model.layers.25.input_layernorm.weight
vicuna-13b-v1.3-kvc-fp16-onnx/model.layers.25.post_attention_layernorm.weight
vicuna-13b-v1.3-kvc-fp16-onnx/model.layers.26.input_layernorm.weight
vicuna-13b-v1.3-kvc-fp16-onnx/model.layers.26.post_attention_layernorm.weight
vicuna-13b-v1.3-kvc-fp16-onnx/model.layers.27.input_layernorm.weight
vicuna-13b-v1.3-kvc-fp16-onnx/model.layers.27.post_attention_layernorm.weight
vicuna-13b-v1.3-kvc-fp16-onnx/model.layers.28.input_layernorm.weight
vicuna-13b-v1.3-kvc-fp16-onnx/model.layers.28.post_attention_layernorm.weight
vicuna-13b-v1.3-kvc-fp16-onnx/model.layers.29.input_layernorm.weight
vicuna-13b-v1.3-kvc-fp16-onnx/model.layers.29.post_attention_layernorm.weight
vicuna-13b-v1.3-kvc-fp16-onnx/model.layers.3.input_layernorm.weight
vicuna-13b-v1.3-kvc-fp16-onnx/model.layers.3.post_attention_layernorm.weight
vicuna-13b-v1.3-kvc-fp16-onnx/model.layers.30.input_layernorm.weight
vicuna-13b-v1.3-kvc-fp16-onnx/model.layers.30.post_attention_layernorm.weight
vicuna-13b-v1.3-kvc-fp16-onnx/model.layers.31.input_layernorm.weight
vicuna-13b-v1.3-kvc-fp16-onnx/model.layers.31.post_attention_layernorm.weight
vicuna-13b-v1.3-kvc-fp16-onnx/model.layers.32.input_layernorm.weight
vicuna-13b-v1.3-kvc-fp16-onnx/model.layers.32.post_attention_layernorm.weight
vicuna-13b-v1.3-kvc-fp16-onnx/model.layers.33.input_layernorm.weight
vicuna-13b-v1.3-kvc-fp16-onnx/model.layers.33.post_attention_layernorm.weight
vicuna-13b-v1.3-kvc-fp16-onnx/model.layers.34.input_layernorm.weight
vicuna-13b-v1.3-kvc-fp16-onnx/model.layers.34.post_attention_layernorm.weight
vicuna-13b-v1.3-kvc-fp16-onnx/model.layers.35.input_layernorm.weight
vicuna-13b-v1.3-kvc-fp16-onnx/model.layers.35.post_attention_layernorm.weight
vicuna-13b-v1.3-kvc-fp16-onnx/model.layers.36.input_layernorm.weight
vicuna-13b-v1.3-kvc-fp16-onnx/model.layers.36.post_attention_layernorm.weight
vicuna-13b-v1.3-kvc-fp16-onnx/model.layers.37.input_layernorm.weight
vicuna-13b-v1.3-kvc-fp16-onnx/model.layers.37.post_attention_layernorm.weight
vicuna-13b-v1.3-kvc-fp16-onnx/model.layers.38.input_layernorm.weight
vicuna-13b-v1.3-kvc-fp16-onnx/model.layers.38.post_attention_layernorm.weight
vicuna-13b-v1.3-kvc-fp16-onnx/model.layers.39.input_layernorm.weight
vicuna-13b-v1.3-kvc-fp16-onnx/model.layers.39.post_attention_layernorm.weight
vicuna-13b-v1.3-kvc-fp16-onnx/model.layers.4.input_layernorm.weight
vicuna-13b-v1.3-kvc-fp16-onnx/model.layers.4.post_attention_layernorm.weight
vicuna-13b-v1.3-kvc-fp16-onnx/model.layers.5.input_layernorm.weight
vicuna-13b-v1.3-kvc-fp16-onnx/model.layers.5.post_attention_layernorm.weight
vicuna-13b-v1.3-kvc-fp16-onnx/model.layers.6.input_layernorm.weight
vicuna-13b-v1.3-kvc-fp16-onnx/model.layers.6.post_attention_layernorm.weight
vicuna-13b-v1.3-kvc-fp16-onnx/model.layers.7.input_layernorm.weight
vicuna-13b-v1.3-kvc-fp16-onnx/model.layers.7.post_attention_layernorm.weight
vicuna-13b-v1.3-kvc-fp16-onnx/model.layers.8.input_layernorm.weight
vicuna-13b-v1.3-kvc-fp16-onnx/model.layers.8.post_attention_layernorm.weight
vicuna-13b-v1.3-kvc-fp16-onnx/model.layers.9.input_layernorm.weight
vicuna-13b-v1.3-kvc-fp16-onnx/model.layers.9.post_attention_layernorm.weight
vicuna-13b-v1.3-kvc-fp16-onnx/model.norm.weight
vicuna-13b-v1.3-kvc-fp16-onnx/model.onnx
ONNX
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_6576
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_6577
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_6578
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_6598
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_6600
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_6601
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_6602
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_6604
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_6605
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_6606
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_6626
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_6628
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_6629
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_6630
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_6632
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_6633
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_6634
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_6654
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_6656
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_6657
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_6658
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_6660
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_6661
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_6662
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_6682
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_6684
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_6685
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_6686
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_6688
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_6689
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_6690
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_6710
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_6712
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_6713
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_6714
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_6716
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_6717
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_6718
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_6738
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_6740
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_6741
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_6742
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_6744
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_6745
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_6746
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_6766
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_6768
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_6769
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_6770
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_6772
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_6773
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_6774
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_6794
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_6796
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_6797
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_6798
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_6800
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_6801
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_6802
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_6822
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_6824
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_6825
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_6826
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_6828
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_6829
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_6830
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_6850
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_6852
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_6853
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_6854
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_6856
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_6857
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_6858
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_6878
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_6880
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_6881
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_6882
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_6884
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_6885
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_6886
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_6906
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_6908
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_6909
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_6910
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_6912
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_6913
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_6914
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_6934
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_6936
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_6937
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_6938
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_6940
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_6941
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_6942
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_6962
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_6964
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_6965
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_6966
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_6968
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_6969
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_6970
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_6990
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_6992
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_6993
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_6994
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_6996
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_6997
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_6998
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7018
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7020
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7021
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7022
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7024
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7025
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7026
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7046
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7048
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7049
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7050
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7052
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7053
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7054
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7074
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7076
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7077
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7078
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7080
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7081
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7082
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7102
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7104
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7105
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7106
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7108
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7109
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7110
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7130
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7132
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7133
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7134
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7136
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7137
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7138
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7158
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7160
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7161
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7162
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7164
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7165
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7166
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7186
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7188
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7189
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7190
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7192
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7193
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7194
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7214
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7216
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7217
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7218
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7220
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7221
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7222
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7242
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7244
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7245
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7246
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7248
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7249
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7250
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7270
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7272
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7273
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7274
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7276
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7277
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7278
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7298
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7300
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7301
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7302
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7304
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7305
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7306
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7326
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7328
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7329
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7330
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7332
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7333
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7334
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7354
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7356
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7357
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7358
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7360
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7361
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7362
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7382
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7384
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7385
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7386
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7388
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7389
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7390
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7410
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7412
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7413
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7414
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7416
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7417
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7418
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7438
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7440
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7441
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7442
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7444
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7445
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7446
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7466
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7468
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7469
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7470
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7472
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7473
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7474
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7494
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7496
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7497
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7498
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7500
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7501
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7502
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7522
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7524
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7525
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7526
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7528
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7529
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7530
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7550
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7552
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7553
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7554
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7556
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7557
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7558
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7578
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7580
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7581
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7582
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7584
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7585
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7586
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7606
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7608
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7609
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7610
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7612
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7613
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7614
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7634
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7636
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7637
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7638
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7640
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7641
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7642
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7662
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7664
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7665
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7666
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7668
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7669
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7670
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7690
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7692
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7693
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7694
vicuna-13b-v1.3-kvc-fp16-onnx/onnx__MatMul_7696
vicuna-13b-v1.3-kvc-fp16-onnx/source.txt
vicuna-7b-v1.3-kvc-fp16-onnx/.gitattributes
vicuna-7b-v1.3-kvc-fp16-onnx/EtGlowExecutionProvider_GLOW_graph_Extracted_from_-Extracted_from_-Extracted_from_-torch_jit---_11400954490079449885_0_0_0.onnx
ONNX
vicuna-7b-v1.3-kvc-fp16-onnx/model.embed_tokens.weight
vicuna-7b-v1.3-kvc-fp16-onnx/model.layers.0.input_layernorm.weight
vicuna-7b-v1.3-kvc-fp16-onnx/model.layers.0.post_attention_layernorm.weight
vicuna-7b-v1.3-kvc-fp16-onnx/model.layers.1.input_layernorm.weight
vicuna-7b-v1.3-kvc-fp16-onnx/model.layers.1.post_attention_layernorm.weight
vicuna-7b-v1.3-kvc-fp16-onnx/model.layers.10.input_layernorm.weight
vicuna-7b-v1.3-kvc-fp16-onnx/model.layers.10.post_attention_layernorm.weight
vicuna-7b-v1.3-kvc-fp16-onnx/model.layers.11.input_layernorm.weight
vicuna-7b-v1.3-kvc-fp16-onnx/model.layers.11.post_attention_layernorm.weight
vicuna-7b-v1.3-kvc-fp16-onnx/model.layers.12.input_layernorm.weight
vicuna-7b-v1.3-kvc-fp16-onnx/model.layers.12.post_attention_layernorm.weight
vicuna-7b-v1.3-kvc-fp16-onnx/model.layers.13.input_layernorm.weight
vicuna-7b-v1.3-kvc-fp16-onnx/model.layers.13.post_attention_layernorm.weight
vicuna-7b-v1.3-kvc-fp16-onnx/model.layers.14.input_layernorm.weight
vicuna-7b-v1.3-kvc-fp16-onnx/model.layers.14.post_attention_layernorm.weight
vicuna-7b-v1.3-kvc-fp16-onnx/model.layers.15.input_layernorm.weight
vicuna-7b-v1.3-kvc-fp16-onnx/model.layers.15.post_attention_layernorm.weight
vicuna-7b-v1.3-kvc-fp16-onnx/model.layers.16.input_layernorm.weight
vicuna-7b-v1.3-kvc-fp16-onnx/model.layers.16.post_attention_layernorm.weight
vicuna-7b-v1.3-kvc-fp16-onnx/model.layers.17.input_layernorm.weight
vicuna-7b-v1.3-kvc-fp16-onnx/model.layers.17.post_attention_layernorm.weight
vicuna-7b-v1.3-kvc-fp16-onnx/model.layers.18.input_layernorm.weight
vicuna-7b-v1.3-kvc-fp16-onnx/model.layers.18.post_attention_layernorm.weight
vicuna-7b-v1.3-kvc-fp16-onnx/model.layers.19.input_layernorm.weight
vicuna-7b-v1.3-kvc-fp16-onnx/model.layers.19.post_attention_layernorm.weight
vicuna-7b-v1.3-kvc-fp16-onnx/model.layers.2.input_layernorm.weight
vicuna-7b-v1.3-kvc-fp16-onnx/model.layers.2.post_attention_layernorm.weight
vicuna-7b-v1.3-kvc-fp16-onnx/model.layers.20.input_layernorm.weight
vicuna-7b-v1.3-kvc-fp16-onnx/model.layers.20.post_attention_layernorm.weight
vicuna-7b-v1.3-kvc-fp16-onnx/model.layers.21.input_layernorm.weight
vicuna-7b-v1.3-kvc-fp16-onnx/model.layers.21.post_attention_layernorm.weight
vicuna-7b-v1.3-kvc-fp16-onnx/model.layers.22.input_layernorm.weight
vicuna-7b-v1.3-kvc-fp16-onnx/model.layers.22.post_attention_layernorm.weight
vicuna-7b-v1.3-kvc-fp16-onnx/model.layers.23.input_layernorm.weight
vicuna-7b-v1.3-kvc-fp16-onnx/model.layers.23.post_attention_layernorm.weight
vicuna-7b-v1.3-kvc-fp16-onnx/model.layers.24.input_layernorm.weight
vicuna-7b-v1.3-kvc-fp16-onnx/model.layers.24.post_attention_layernorm.weight
vicuna-7b-v1.3-kvc-fp16-onnx/model.layers.25.input_layernorm.weight
vicuna-7b-v1.3-kvc-fp16-onnx/model.layers.25.post_attention_layernorm.weight
vicuna-7b-v1.3-kvc-fp16-onnx/model.layers.26.input_layernorm.weight
vicuna-7b-v1.3-kvc-fp16-onnx/model.layers.26.post_attention_layernorm.weight
vicuna-7b-v1.3-kvc-fp16-onnx/model.layers.27.input_layernorm.weight
vicuna-7b-v1.3-kvc-fp16-onnx/model.layers.27.post_attention_layernorm.weight
vicuna-7b-v1.3-kvc-fp16-onnx/model.layers.28.input_layernorm.weight
vicuna-7b-v1.3-kvc-fp16-onnx/model.layers.28.post_attention_layernorm.weight
vicuna-7b-v1.3-kvc-fp16-onnx/model.layers.29.input_layernorm.weight
vicuna-7b-v1.3-kvc-fp16-onnx/model.layers.29.post_attention_layernorm.weight
vicuna-7b-v1.3-kvc-fp16-onnx/model.layers.3.input_layernorm.weight
vicuna-7b-v1.3-kvc-fp16-onnx/model.layers.3.post_attention_layernorm.weight
vicuna-7b-v1.3-kvc-fp16-onnx/model.layers.30.input_layernorm.weight
vicuna-7b-v1.3-kvc-fp16-onnx/model.layers.30.post_attention_layernorm.weight
vicuna-7b-v1.3-kvc-fp16-onnx/model.layers.31.input_layernorm.weight
vicuna-7b-v1.3-kvc-fp16-onnx/model.layers.31.post_attention_layernorm.weight
vicuna-7b-v1.3-kvc-fp16-onnx/model.layers.4.input_layernorm.weight
vicuna-7b-v1.3-kvc-fp16-onnx/model.layers.4.post_attention_layernorm.weight
vicuna-7b-v1.3-kvc-fp16-onnx/model.layers.5.input_layernorm.weight
vicuna-7b-v1.3-kvc-fp16-onnx/model.layers.5.post_attention_layernorm.weight
vicuna-7b-v1.3-kvc-fp16-onnx/model.layers.6.input_layernorm.weight
vicuna-7b-v1.3-kvc-fp16-onnx/model.layers.6.post_attention_layernorm.weight
vicuna-7b-v1.3-kvc-fp16-onnx/model.layers.7.input_layernorm.weight
vicuna-7b-v1.3-kvc-fp16-onnx/model.layers.7.post_attention_layernorm.weight
vicuna-7b-v1.3-kvc-fp16-onnx/model.layers.8.input_layernorm.weight
vicuna-7b-v1.3-kvc-fp16-onnx/model.layers.8.post_attention_layernorm.weight
vicuna-7b-v1.3-kvc-fp16-onnx/model.layers.9.input_layernorm.weight
vicuna-7b-v1.3-kvc-fp16-onnx/model.layers.9.post_attention_layernorm.weight
vicuna-7b-v1.3-kvc-fp16-onnx/model.norm.weight
vicuna-7b-v1.3-kvc-fp16-onnx/model.onnx
ONNX
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5288
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5289
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5290
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5310
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5312
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5313
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5314
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5316
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5317
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5318
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5338
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5340
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5341
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5342
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5344
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5345
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5346
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5366
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5368
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5369
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5370
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5372
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5373
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5374
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5394
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5396
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5397
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5398
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5400
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5401
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5402
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5422
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5424
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5425
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5426
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5428
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5429
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5430
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5450
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5452
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5453
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5454
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5456
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5457
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5458
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5478
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5480
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5481
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5482
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5484
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5485
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5486
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5506
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5508
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5509
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5510
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5512
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5513
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5514
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5534
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5536
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5537
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5538
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5540
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5541
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5542
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5562
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5564
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5565
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5566
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5568
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5569
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5570
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5590
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5592
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5593
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5594
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5596
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5597
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5598
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5618
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5620
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5621
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5622
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5624
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5625
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5626
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5646
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5648
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5649
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5650
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5652
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5653
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5654
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5674
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5676
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5677
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5678
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5680
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5681
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5682
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5702
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5704
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5705
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5706
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5708
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5709
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5710
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5730
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5732
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5733
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5734
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5736
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5737
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5738
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5758
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5760
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5761
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5762
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5764
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5765
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5766
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5786
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5788
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5789
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5790
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5792
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5793
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5794
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5814
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5816
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5817
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5818
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5820
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5821
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5822
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5842
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5844
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5845
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5846
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5848
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5849
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5850
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5870
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5872
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5873
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5874
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5876
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5877
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5878
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5898
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5900
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5901
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5902
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5904
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5905
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5906
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5926
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5928
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5929
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5930
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5932
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5933
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5934
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5954
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5956
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5957
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5958
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5960
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5961
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5962
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5982
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5984
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5985
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5986
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5988
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5989
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_5990
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_6010
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_6012
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_6013
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_6014
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_6016
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_6017
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_6018
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_6038
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_6040
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_6041
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_6042
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_6044
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_6045
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_6046
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_6066
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_6068
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_6069
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_6070
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_6072
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_6073
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_6074
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_6094
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_6096
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_6097
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_6098
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_6100
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_6101
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_6102
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_6122
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_6124
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_6125
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_6126
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_6128
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_6129
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_6130
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_6150
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_6152
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_6153
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_6154
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_6156
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_6157
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_6158
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_6178
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_6180
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_6181
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_6182
vicuna-7b-v1.3-kvc-fp16-onnx/onnx__MatMul_6184
vicuna-7b-v1.3-kvc-fp16-onnx/source.txt
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/.gitattributes
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/README.md
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/config.json
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.embed_tokens.weight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.0.input_layernorm.weight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.0.mlp.down_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.0.mlp.down_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.0.mlp.down_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.0.mlp.gate_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.0.mlp.gate_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.0.mlp.gate_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.0.mlp.up_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.0.mlp.up_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.0.mlp.up_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.0.post_attention_layernorm.weight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.0.self_attn.k_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.0.self_attn.k_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.0.self_attn.k_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.0.self_attn.o_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.0.self_attn.o_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.0.self_attn.o_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.0.self_attn.q_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.0.self_attn.q_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.0.self_attn.q_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.0.self_attn.v_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.0.self_attn.v_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.0.self_attn.v_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.1.input_layernorm.weight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.1.mlp.down_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.1.mlp.down_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.1.mlp.down_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.1.mlp.gate_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.1.mlp.gate_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.1.mlp.gate_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.1.mlp.up_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.1.mlp.up_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.1.mlp.up_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.1.post_attention_layernorm.weight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.1.self_attn.k_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.1.self_attn.k_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.1.self_attn.k_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.1.self_attn.o_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.1.self_attn.o_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.1.self_attn.o_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.1.self_attn.q_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.1.self_attn.q_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.1.self_attn.q_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.1.self_attn.v_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.1.self_attn.v_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.1.self_attn.v_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.10.input_layernorm.weight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.10.mlp.down_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.10.mlp.down_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.10.mlp.down_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.10.mlp.gate_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.10.mlp.gate_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.10.mlp.gate_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.10.mlp.up_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.10.mlp.up_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.10.mlp.up_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.10.post_attention_layernorm.weight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.10.self_attn.k_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.10.self_attn.k_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.10.self_attn.k_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.10.self_attn.o_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.10.self_attn.o_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.10.self_attn.o_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.10.self_attn.q_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.10.self_attn.q_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.10.self_attn.q_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.10.self_attn.v_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.10.self_attn.v_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.10.self_attn.v_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.11.input_layernorm.weight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.11.mlp.down_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.11.mlp.down_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.11.mlp.down_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.11.mlp.gate_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.11.mlp.gate_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.11.mlp.gate_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.11.mlp.up_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.11.mlp.up_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.11.mlp.up_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.11.post_attention_layernorm.weight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.11.self_attn.k_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.11.self_attn.k_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.11.self_attn.k_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.11.self_attn.o_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.11.self_attn.o_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.11.self_attn.o_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.11.self_attn.q_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.11.self_attn.q_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.11.self_attn.q_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.11.self_attn.v_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.11.self_attn.v_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.11.self_attn.v_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.12.input_layernorm.weight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.12.mlp.down_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.12.mlp.down_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.12.mlp.down_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.12.mlp.gate_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.12.mlp.gate_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.12.mlp.gate_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.12.mlp.up_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.12.mlp.up_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.12.mlp.up_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.12.post_attention_layernorm.weight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.12.self_attn.k_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.12.self_attn.k_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.12.self_attn.k_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.12.self_attn.o_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.12.self_attn.o_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.12.self_attn.o_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.12.self_attn.q_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.12.self_attn.q_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.12.self_attn.q_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.12.self_attn.v_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.12.self_attn.v_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.12.self_attn.v_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.13.input_layernorm.weight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.13.mlp.down_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.13.mlp.down_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.13.mlp.down_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.13.mlp.gate_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.13.mlp.gate_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.13.mlp.gate_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.13.mlp.up_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.13.mlp.up_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.13.mlp.up_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.13.post_attention_layernorm.weight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.13.self_attn.k_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.13.self_attn.k_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.13.self_attn.k_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.13.self_attn.o_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.13.self_attn.o_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.13.self_attn.o_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.13.self_attn.q_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.13.self_attn.q_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.13.self_attn.q_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.13.self_attn.v_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.13.self_attn.v_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.13.self_attn.v_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.14.input_layernorm.weight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.14.mlp.down_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.14.mlp.down_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.14.mlp.down_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.14.mlp.gate_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.14.mlp.gate_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.14.mlp.gate_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.14.mlp.up_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.14.mlp.up_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.14.mlp.up_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.14.post_attention_layernorm.weight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.14.self_attn.k_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.14.self_attn.k_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.14.self_attn.k_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.14.self_attn.o_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.14.self_attn.o_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.14.self_attn.o_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.14.self_attn.q_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.14.self_attn.q_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.14.self_attn.q_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.14.self_attn.v_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.14.self_attn.v_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.14.self_attn.v_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.15.input_layernorm.weight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.15.mlp.down_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.15.mlp.down_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.15.mlp.down_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.15.mlp.gate_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.15.mlp.gate_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.15.mlp.gate_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.15.mlp.up_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.15.mlp.up_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.15.mlp.up_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.15.post_attention_layernorm.weight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.15.self_attn.k_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.15.self_attn.k_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.15.self_attn.k_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.15.self_attn.o_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.15.self_attn.o_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.15.self_attn.o_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.15.self_attn.q_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.15.self_attn.q_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.15.self_attn.q_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.15.self_attn.v_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.15.self_attn.v_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.15.self_attn.v_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.16.input_layernorm.weight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.16.mlp.down_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.16.mlp.down_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.16.mlp.down_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.16.mlp.gate_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.16.mlp.gate_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.16.mlp.gate_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.16.mlp.up_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.16.mlp.up_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.16.mlp.up_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.16.post_attention_layernorm.weight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.16.self_attn.k_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.16.self_attn.k_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.16.self_attn.k_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.16.self_attn.o_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.16.self_attn.o_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.16.self_attn.o_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.16.self_attn.q_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.16.self_attn.q_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.16.self_attn.q_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.16.self_attn.v_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.16.self_attn.v_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.16.self_attn.v_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.17.input_layernorm.weight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.17.mlp.down_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.17.mlp.down_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.17.mlp.down_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.17.mlp.gate_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.17.mlp.gate_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.17.mlp.gate_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.17.mlp.up_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.17.mlp.up_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.17.mlp.up_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.17.post_attention_layernorm.weight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.17.self_attn.k_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.17.self_attn.k_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.17.self_attn.k_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.17.self_attn.o_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.17.self_attn.o_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.17.self_attn.o_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.17.self_attn.q_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.17.self_attn.q_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.17.self_attn.q_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.17.self_attn.v_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.17.self_attn.v_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.17.self_attn.v_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.18.input_layernorm.weight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.18.mlp.down_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.18.mlp.down_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.18.mlp.down_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.18.mlp.gate_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.18.mlp.gate_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.18.mlp.gate_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.18.mlp.up_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.18.mlp.up_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.18.mlp.up_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.18.post_attention_layernorm.weight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.18.self_attn.k_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.18.self_attn.k_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.18.self_attn.k_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.18.self_attn.o_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.18.self_attn.o_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.18.self_attn.o_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.18.self_attn.q_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.18.self_attn.q_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.18.self_attn.q_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.18.self_attn.v_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.18.self_attn.v_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.18.self_attn.v_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.19.input_layernorm.weight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.19.mlp.down_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.19.mlp.down_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.19.mlp.down_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.19.mlp.gate_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.19.mlp.gate_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.19.mlp.gate_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.19.mlp.up_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.19.mlp.up_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.19.mlp.up_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.19.post_attention_layernorm.weight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.19.self_attn.k_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.19.self_attn.k_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.19.self_attn.k_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.19.self_attn.o_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.19.self_attn.o_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.19.self_attn.o_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.19.self_attn.q_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.19.self_attn.q_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.19.self_attn.q_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.19.self_attn.v_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.19.self_attn.v_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.19.self_attn.v_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.2.input_layernorm.weight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.2.mlp.down_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.2.mlp.down_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.2.mlp.down_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.2.mlp.gate_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.2.mlp.gate_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.2.mlp.gate_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.2.mlp.up_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.2.mlp.up_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.2.mlp.up_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.2.post_attention_layernorm.weight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.2.self_attn.k_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.2.self_attn.k_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.2.self_attn.k_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.2.self_attn.o_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.2.self_attn.o_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.2.self_attn.o_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.2.self_attn.q_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.2.self_attn.q_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.2.self_attn.q_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.2.self_attn.v_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.2.self_attn.v_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.2.self_attn.v_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.20.input_layernorm.weight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.20.mlp.down_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.20.mlp.down_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.20.mlp.down_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.20.mlp.gate_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.20.mlp.gate_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.20.mlp.gate_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.20.mlp.up_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.20.mlp.up_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.20.mlp.up_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.20.post_attention_layernorm.weight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.20.self_attn.k_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.20.self_attn.k_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.20.self_attn.k_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.20.self_attn.o_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.20.self_attn.o_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.20.self_attn.o_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.20.self_attn.q_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.20.self_attn.q_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.20.self_attn.q_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.20.self_attn.v_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.20.self_attn.v_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.20.self_attn.v_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.21.input_layernorm.weight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.21.mlp.down_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.21.mlp.down_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.21.mlp.down_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.21.mlp.gate_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.21.mlp.gate_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.21.mlp.gate_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.21.mlp.up_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.21.mlp.up_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.21.mlp.up_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.21.post_attention_layernorm.weight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.21.self_attn.k_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.21.self_attn.k_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.21.self_attn.k_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.21.self_attn.o_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.21.self_attn.o_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.21.self_attn.o_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.21.self_attn.q_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.21.self_attn.q_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.21.self_attn.q_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.21.self_attn.v_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.21.self_attn.v_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.21.self_attn.v_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.22.input_layernorm.weight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.22.mlp.down_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.22.mlp.down_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.22.mlp.down_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.22.mlp.gate_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.22.mlp.gate_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.22.mlp.gate_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.22.mlp.up_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.22.mlp.up_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.22.mlp.up_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.22.post_attention_layernorm.weight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.22.self_attn.k_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.22.self_attn.k_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.22.self_attn.k_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.22.self_attn.o_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.22.self_attn.o_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.22.self_attn.o_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.22.self_attn.q_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.22.self_attn.q_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.22.self_attn.q_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.22.self_attn.v_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.22.self_attn.v_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.22.self_attn.v_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.23.input_layernorm.weight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.23.mlp.down_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.23.mlp.down_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.23.mlp.down_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.23.mlp.gate_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.23.mlp.gate_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.23.mlp.gate_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.23.mlp.up_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.23.mlp.up_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.23.mlp.up_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.23.post_attention_layernorm.weight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.23.self_attn.k_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.23.self_attn.k_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.23.self_attn.k_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.23.self_attn.o_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.23.self_attn.o_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.23.self_attn.o_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.23.self_attn.q_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.23.self_attn.q_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.23.self_attn.q_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.23.self_attn.v_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.23.self_attn.v_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.23.self_attn.v_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.24.input_layernorm.weight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.24.mlp.down_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.24.mlp.down_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.24.mlp.down_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.24.mlp.gate_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.24.mlp.gate_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.24.mlp.gate_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.24.mlp.up_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.24.mlp.up_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.24.mlp.up_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.24.post_attention_layernorm.weight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.24.self_attn.k_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.24.self_attn.k_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.24.self_attn.k_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.24.self_attn.o_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.24.self_attn.o_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.24.self_attn.o_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.24.self_attn.q_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.24.self_attn.q_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.24.self_attn.q_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.24.self_attn.v_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.24.self_attn.v_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.24.self_attn.v_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.25.input_layernorm.weight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.25.mlp.down_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.25.mlp.down_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.25.mlp.down_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.25.mlp.gate_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.25.mlp.gate_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.25.mlp.gate_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.25.mlp.up_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.25.mlp.up_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.25.mlp.up_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.25.post_attention_layernorm.weight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.25.self_attn.k_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.25.self_attn.k_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.25.self_attn.k_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.25.self_attn.o_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.25.self_attn.o_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.25.self_attn.o_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.25.self_attn.q_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.25.self_attn.q_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.25.self_attn.q_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.25.self_attn.v_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.25.self_attn.v_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.25.self_attn.v_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.26.input_layernorm.weight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.26.mlp.down_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.26.mlp.down_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.26.mlp.down_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.26.mlp.gate_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.26.mlp.gate_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.26.mlp.gate_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.26.mlp.up_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.26.mlp.up_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.26.mlp.up_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.26.post_attention_layernorm.weight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.26.self_attn.k_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.26.self_attn.k_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.26.self_attn.k_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.26.self_attn.o_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.26.self_attn.o_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.26.self_attn.o_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.26.self_attn.q_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.26.self_attn.q_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.26.self_attn.q_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.26.self_attn.v_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.26.self_attn.v_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.26.self_attn.v_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.27.input_layernorm.weight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.27.mlp.down_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.27.mlp.down_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.27.mlp.down_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.27.mlp.gate_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.27.mlp.gate_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.27.mlp.gate_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.27.mlp.up_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.27.mlp.up_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.27.mlp.up_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.27.post_attention_layernorm.weight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.27.self_attn.k_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.27.self_attn.k_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.27.self_attn.k_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.27.self_attn.o_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.27.self_attn.o_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.27.self_attn.o_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.27.self_attn.q_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.27.self_attn.q_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.27.self_attn.q_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.27.self_attn.v_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.27.self_attn.v_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.27.self_attn.v_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.28.input_layernorm.weight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.28.mlp.down_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.28.mlp.down_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.28.mlp.down_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.28.mlp.gate_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.28.mlp.gate_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.28.mlp.gate_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.28.mlp.up_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.28.mlp.up_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.28.mlp.up_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.28.post_attention_layernorm.weight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.28.self_attn.k_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.28.self_attn.k_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.28.self_attn.k_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.28.self_attn.o_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.28.self_attn.o_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.28.self_attn.o_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.28.self_attn.q_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.28.self_attn.q_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.28.self_attn.q_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.28.self_attn.v_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.28.self_attn.v_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.28.self_attn.v_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.29.input_layernorm.weight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.29.mlp.down_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.29.mlp.down_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.29.mlp.down_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.29.mlp.gate_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.29.mlp.gate_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.29.mlp.gate_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.29.mlp.up_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.29.mlp.up_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.29.mlp.up_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.29.post_attention_layernorm.weight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.29.self_attn.k_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.29.self_attn.k_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.29.self_attn.k_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.29.self_attn.o_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.29.self_attn.o_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.29.self_attn.o_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.29.self_attn.q_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.29.self_attn.q_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.29.self_attn.q_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.29.self_attn.v_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.29.self_attn.v_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.29.self_attn.v_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.3.input_layernorm.weight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.3.mlp.down_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.3.mlp.down_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.3.mlp.down_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.3.mlp.gate_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.3.mlp.gate_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.3.mlp.gate_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.3.mlp.up_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.3.mlp.up_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.3.mlp.up_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.3.post_attention_layernorm.weight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.3.self_attn.k_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.3.self_attn.k_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.3.self_attn.k_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.3.self_attn.o_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.3.self_attn.o_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.3.self_attn.o_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.3.self_attn.q_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.3.self_attn.q_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.3.self_attn.q_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.3.self_attn.v_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.3.self_attn.v_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.3.self_attn.v_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.30.input_layernorm.weight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.30.mlp.down_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.30.mlp.down_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.30.mlp.down_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.30.mlp.gate_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.30.mlp.gate_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.30.mlp.gate_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.30.mlp.up_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.30.mlp.up_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.30.mlp.up_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.30.post_attention_layernorm.weight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.30.self_attn.k_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.30.self_attn.k_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.30.self_attn.k_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.30.self_attn.o_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.30.self_attn.o_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.30.self_attn.o_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.30.self_attn.q_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.30.self_attn.q_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.30.self_attn.q_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.30.self_attn.v_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.30.self_attn.v_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.30.self_attn.v_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.31.input_layernorm.weight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.31.mlp.down_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.31.mlp.down_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.31.mlp.down_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.31.mlp.gate_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.31.mlp.gate_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.31.mlp.gate_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.31.mlp.up_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.31.mlp.up_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.31.mlp.up_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.31.post_attention_layernorm.weight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.31.self_attn.k_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.31.self_attn.k_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.31.self_attn.k_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.31.self_attn.o_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.31.self_attn.o_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.31.self_attn.o_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.31.self_attn.q_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.31.self_attn.q_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.31.self_attn.q_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.31.self_attn.v_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.31.self_attn.v_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.31.self_attn.v_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.4.input_layernorm.weight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.4.mlp.down_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.4.mlp.down_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.4.mlp.down_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.4.mlp.gate_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.4.mlp.gate_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.4.mlp.gate_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.4.mlp.up_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.4.mlp.up_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.4.mlp.up_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.4.post_attention_layernorm.weight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.4.self_attn.k_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.4.self_attn.k_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.4.self_attn.k_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.4.self_attn.o_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.4.self_attn.o_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.4.self_attn.o_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.4.self_attn.q_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.4.self_attn.q_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.4.self_attn.q_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.4.self_attn.v_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.4.self_attn.v_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.4.self_attn.v_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.5.input_layernorm.weight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.5.mlp.down_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.5.mlp.down_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.5.mlp.down_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.5.mlp.gate_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.5.mlp.gate_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.5.mlp.gate_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.5.mlp.up_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.5.mlp.up_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.5.mlp.up_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.5.post_attention_layernorm.weight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.5.self_attn.k_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.5.self_attn.k_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.5.self_attn.k_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.5.self_attn.o_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.5.self_attn.o_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.5.self_attn.o_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.5.self_attn.q_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.5.self_attn.q_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.5.self_attn.q_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.5.self_attn.v_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.5.self_attn.v_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.5.self_attn.v_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.6.input_layernorm.weight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.6.mlp.down_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.6.mlp.down_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.6.mlp.down_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.6.mlp.gate_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.6.mlp.gate_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.6.mlp.gate_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.6.mlp.up_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.6.mlp.up_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.6.mlp.up_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.6.post_attention_layernorm.weight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.6.self_attn.k_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.6.self_attn.k_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.6.self_attn.k_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.6.self_attn.o_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.6.self_attn.o_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.6.self_attn.o_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.6.self_attn.q_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.6.self_attn.q_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.6.self_attn.q_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.6.self_attn.v_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.6.self_attn.v_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.6.self_attn.v_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.7.input_layernorm.weight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.7.mlp.down_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.7.mlp.down_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.7.mlp.down_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.7.mlp.gate_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.7.mlp.gate_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.7.mlp.gate_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.7.mlp.up_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.7.mlp.up_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.7.mlp.up_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.7.post_attention_layernorm.weight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.7.self_attn.k_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.7.self_attn.k_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.7.self_attn.k_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.7.self_attn.o_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.7.self_attn.o_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.7.self_attn.o_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.7.self_attn.q_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.7.self_attn.q_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.7.self_attn.q_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.7.self_attn.v_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.7.self_attn.v_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.7.self_attn.v_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.8.input_layernorm.weight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.8.mlp.down_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.8.mlp.down_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.8.mlp.down_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.8.mlp.gate_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.8.mlp.gate_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.8.mlp.gate_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.8.mlp.up_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.8.mlp.up_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.8.mlp.up_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.8.post_attention_layernorm.weight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.8.self_attn.k_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.8.self_attn.k_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.8.self_attn.k_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.8.self_attn.o_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.8.self_attn.o_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.8.self_attn.o_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.8.self_attn.q_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.8.self_attn.q_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.8.self_attn.q_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.8.self_attn.v_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.8.self_attn.v_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.8.self_attn.v_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.9.input_layernorm.weight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.9.mlp.down_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.9.mlp.down_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.9.mlp.down_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.9.mlp.gate_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.9.mlp.gate_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.9.mlp.gate_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.9.mlp.up_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.9.mlp.up_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.9.mlp.up_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.9.post_attention_layernorm.weight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.9.self_attn.k_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.9.self_attn.k_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.9.self_attn.k_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.9.self_attn.o_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.9.self_attn.o_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.9.self_attn.o_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.9.self_attn.q_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.9.self_attn.q_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.9.self_attn.q_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.9.self_attn.v_proj.qweight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.9.self_attn.v_proj.qzeros
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.layers.9.self_attn.v_proj.scales
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.norm.weight
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/model.onnx
ONNX
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/onnx__MatMul_7409
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/source.txt
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/special_tokens_map.json
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/tokenizer.json
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/tokenizer.model
vicuna-7b-v1.5-kvc-AWQ-int4-onnx/tokenizer_config.json
vicuna-7b-v1.5-kvc-fp16-onnx/.gitattributes
vicuna-7b-v1.5-kvc-fp16-onnx/README.md
vicuna-7b-v1.5-kvc-fp16-onnx/config.json
vicuna-7b-v1.5-kvc-fp16-onnx/model.embed_tokens.weight
vicuna-7b-v1.5-kvc-fp16-onnx/model.layers.0.input_layernorm.weight
vicuna-7b-v1.5-kvc-fp16-onnx/model.layers.0.post_attention_layernorm.weight
vicuna-7b-v1.5-kvc-fp16-onnx/model.layers.1.input_layernorm.weight
vicuna-7b-v1.5-kvc-fp16-onnx/model.layers.1.post_attention_layernorm.weight
vicuna-7b-v1.5-kvc-fp16-onnx/model.layers.10.input_layernorm.weight
vicuna-7b-v1.5-kvc-fp16-onnx/model.layers.10.post_attention_layernorm.weight
vicuna-7b-v1.5-kvc-fp16-onnx/model.layers.11.input_layernorm.weight
vicuna-7b-v1.5-kvc-fp16-onnx/model.layers.11.post_attention_layernorm.weight
vicuna-7b-v1.5-kvc-fp16-onnx/model.layers.12.input_layernorm.weight
vicuna-7b-v1.5-kvc-fp16-onnx/model.layers.12.post_attention_layernorm.weight
vicuna-7b-v1.5-kvc-fp16-onnx/model.layers.13.input_layernorm.weight
vicuna-7b-v1.5-kvc-fp16-onnx/model.layers.13.post_attention_layernorm.weight
vicuna-7b-v1.5-kvc-fp16-onnx/model.layers.14.input_layernorm.weight
vicuna-7b-v1.5-kvc-fp16-onnx/model.layers.14.post_attention_layernorm.weight
vicuna-7b-v1.5-kvc-fp16-onnx/model.layers.15.input_layernorm.weight
vicuna-7b-v1.5-kvc-fp16-onnx/model.layers.15.post_attention_layernorm.weight
vicuna-7b-v1.5-kvc-fp16-onnx/model.layers.16.input_layernorm.weight
vicuna-7b-v1.5-kvc-fp16-onnx/model.layers.16.post_attention_layernorm.weight
vicuna-7b-v1.5-kvc-fp16-onnx/model.layers.17.input_layernorm.weight
vicuna-7b-v1.5-kvc-fp16-onnx/model.layers.17.post_attention_layernorm.weight
vicuna-7b-v1.5-kvc-fp16-onnx/model.layers.18.input_layernorm.weight
vicuna-7b-v1.5-kvc-fp16-onnx/model.layers.18.post_attention_layernorm.weight
vicuna-7b-v1.5-kvc-fp16-onnx/model.layers.19.input_layernorm.weight
vicuna-7b-v1.5-kvc-fp16-onnx/model.layers.19.post_attention_layernorm.weight
vicuna-7b-v1.5-kvc-fp16-onnx/model.layers.2.input_layernorm.weight
vicuna-7b-v1.5-kvc-fp16-onnx/model.layers.2.post_attention_layernorm.weight
vicuna-7b-v1.5-kvc-fp16-onnx/model.layers.20.input_layernorm.weight
vicuna-7b-v1.5-kvc-fp16-onnx/model.layers.20.post_attention_layernorm.weight
vicuna-7b-v1.5-kvc-fp16-onnx/model.layers.21.input_layernorm.weight
vicuna-7b-v1.5-kvc-fp16-onnx/model.layers.21.post_attention_layernorm.weight
vicuna-7b-v1.5-kvc-fp16-onnx/model.layers.22.input_layernorm.weight
vicuna-7b-v1.5-kvc-fp16-onnx/model.layers.22.post_attention_layernorm.weight
vicuna-7b-v1.5-kvc-fp16-onnx/model.layers.23.input_layernorm.weight
vicuna-7b-v1.5-kvc-fp16-onnx/model.layers.23.post_attention_layernorm.weight
vicuna-7b-v1.5-kvc-fp16-onnx/model.layers.24.input_layernorm.weight
vicuna-7b-v1.5-kvc-fp16-onnx/model.layers.24.post_attention_layernorm.weight
vicuna-7b-v1.5-kvc-fp16-onnx/model.layers.25.input_layernorm.weight
vicuna-7b-v1.5-kvc-fp16-onnx/model.layers.25.post_attention_layernorm.weight
vicuna-7b-v1.5-kvc-fp16-onnx/model.layers.26.input_layernorm.weight
vicuna-7b-v1.5-kvc-fp16-onnx/model.layers.26.post_attention_layernorm.weight
vicuna-7b-v1.5-kvc-fp16-onnx/model.layers.27.input_layernorm.weight
vicuna-7b-v1.5-kvc-fp16-onnx/model.layers.27.post_attention_layernorm.weight
vicuna-7b-v1.5-kvc-fp16-onnx/model.layers.28.input_layernorm.weight
vicuna-7b-v1.5-kvc-fp16-onnx/model.layers.28.post_attention_layernorm.weight
vicuna-7b-v1.5-kvc-fp16-onnx/model.layers.29.input_layernorm.weight
vicuna-7b-v1.5-kvc-fp16-onnx/model.layers.29.post_attention_layernorm.weight
vicuna-7b-v1.5-kvc-fp16-onnx/model.layers.3.input_layernorm.weight
vicuna-7b-v1.5-kvc-fp16-onnx/model.layers.3.post_attention_layernorm.weight
vicuna-7b-v1.5-kvc-fp16-onnx/model.layers.30.input_layernorm.weight
vicuna-7b-v1.5-kvc-fp16-onnx/model.layers.30.post_attention_layernorm.weight
vicuna-7b-v1.5-kvc-fp16-onnx/model.layers.31.input_layernorm.weight
vicuna-7b-v1.5-kvc-fp16-onnx/model.layers.31.post_attention_layernorm.weight
vicuna-7b-v1.5-kvc-fp16-onnx/model.layers.4.input_layernorm.weight
vicuna-7b-v1.5-kvc-fp16-onnx/model.layers.4.post_attention_layernorm.weight
vicuna-7b-v1.5-kvc-fp16-onnx/model.layers.5.input_layernorm.weight
vicuna-7b-v1.5-kvc-fp16-onnx/model.layers.5.post_attention_layernorm.weight
vicuna-7b-v1.5-kvc-fp16-onnx/model.layers.6.input_layernorm.weight
vicuna-7b-v1.5-kvc-fp16-onnx/model.layers.6.post_attention_layernorm.weight
vicuna-7b-v1.5-kvc-fp16-onnx/model.layers.7.input_layernorm.weight
vicuna-7b-v1.5-kvc-fp16-onnx/model.layers.7.post_attention_layernorm.weight
vicuna-7b-v1.5-kvc-fp16-onnx/model.layers.8.input_layernorm.weight
vicuna-7b-v1.5-kvc-fp16-onnx/model.layers.8.post_attention_layernorm.weight
vicuna-7b-v1.5-kvc-fp16-onnx/model.layers.9.input_layernorm.weight
vicuna-7b-v1.5-kvc-fp16-onnx/model.layers.9.post_attention_layernorm.weight
vicuna-7b-v1.5-kvc-fp16-onnx/model.norm.weight
vicuna-7b-v1.5-kvc-fp16-onnx/model.onnx
ONNX
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_5288
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_5289
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_5290
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_5316
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_5318
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_5319
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_5320
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_5322
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_5323
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_5324
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_5350
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_5352
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_5353
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_5354
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_5356
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_5357
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_5358
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_5384
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_5386
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_5387
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_5388
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_5390
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_5391
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_5392
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_5418
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_5420
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_5421
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_5422
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_5424
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_5425
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_5426
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_5452
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_5454
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_5455
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_5456
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_5458
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_5459
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_5460
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_5486
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_5488
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_5489
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_5490
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_5492
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_5493
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_5494
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_5520
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_5522
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_5523
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_5524
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_5526
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_5527
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_5528
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_5554
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_5556
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_5557
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_5558
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_5560
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_5561
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_5562
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_5588
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_5590
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_5591
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_5592
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_5594
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_5595
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_5596
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_5622
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_5624
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_5625
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_5626
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_5628
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_5629
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_5630
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_5656
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_5658
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_5659
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_5660
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_5662
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_5663
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_5664
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_5690
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_5692
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_5693
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_5694
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_5696
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_5697
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_5698
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_5724
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_5726
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_5727
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_5728
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_5730
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_5731
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_5732
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_5758
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_5760
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_5761
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_5762
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_5764
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_5765
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_5766
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_5792
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_5794
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_5795
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_5796
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_5798
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_5799
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_5800
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_5826
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_5828
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_5829
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_5830
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_5832
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_5833
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_5834
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_5860
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_5862
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_5863
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_5864
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_5866
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_5867
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_5868
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_5894
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_5896
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_5897
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_5898
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_5900
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_5901
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_5902
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_5928
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_5930
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_5931
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_5932
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_5934
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_5935
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_5936
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_5962
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_5964
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_5965
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_5966
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_5968
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_5969
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_5970
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_5996
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_5998
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_5999
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_6000
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_6002
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_6003
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_6004
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_6030
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_6032
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_6033
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_6034
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_6036
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_6037
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_6038
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_6064
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_6066
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_6067
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_6068
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_6070
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_6071
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_6072
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_6098
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_6100
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_6101
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_6102
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_6104
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_6105
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_6106
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_6132
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_6134
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_6135
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_6136
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_6138
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_6139
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_6140
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_6166
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_6168
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_6169
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_6170
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_6172
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_6173
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_6174
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_6200
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_6202
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_6203
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_6204
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_6206
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_6207
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_6208
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_6234
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_6236
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_6237
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_6238
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_6240
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_6241
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_6242
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_6268
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_6270
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_6271
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_6272
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_6274
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_6275
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_6276
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_6302
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_6304
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_6305
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_6306
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_6308
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_6309
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_6310
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_6336
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_6338
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_6339
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_6340
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_6342
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_6343
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_6344
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_6370
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_6372
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_6373
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_6374
vicuna-7b-v1.5-kvc-fp16-onnx/onnx__MatMul_6376
vicuna-7b-v1.5-kvc-fp16-onnx/source.txt
vicuna-7b-v1.5-kvc-fp16-onnx/special_tokens_map.json
vicuna-7b-v1.5-kvc-fp16-onnx/tokenizer.json
vicuna-7b-v1.5-kvc-fp16-onnx/tokenizer.model
vicuna-7b-v1.5-kvc-fp16-onnx/tokenizer_config.json
Related models
More from niobures
More models
No task type declared.