mgoin/deepseek-coder-1.3b-instruct-ds
By mgoin · ↓ 2 · ♥ 0 · Updated 2023-11-07
What's in this repo
This page lists the files in mgoin/deepseek-coder-1.3b-instruct-ds, including model-orig.onnx, model.onnx.
- 2 ONNX models (.onnx files)
- 8 files, including 3 .json, 2 .onnx, 1 .md, 1 .data
- Last updated 2023-11-07
ONNX files
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.
README
DeepSparse Export of https://huggingface.co/deepseek-ai/deepseek-coder-1.3b-instruct
Prompt Template:
prompt = f"### Instruction:{input}### Response:"
Usage
from deepsparse import TextGeneration
model = TextGeneration(model="hf:mgoin/deepseek-coder-1.3b-instruct-ds")
print(model("#write a quick sort algorithm in python", max_new_tokens=200).generations[0].text)
"""
def quick_sort(arr):
if len(arr) <= 1:
return arr
else:
pivot = arr[len(arr) // 2]
left = [x for x in arr if x < pivot]
middle = [x for x in arr if x == pivot]
right = [x for x in arr if x > pivot]
return quick_sort(left) + middle + quick_sort(right)
print(quick_sort([3,6,8,10,1,2,1]))
#output: [1, 1, 2, 3, 6, 8, 10]
#This is a simple implementation of the Quick Sort algorithm in Python. It works by selecting a 'pivot' element from the array and partitioning the other elements into two sub-arrays
"""
Model info
text-generation
transformers
transformers
onnx
llama
text-generation
deepsparse
conversational
endpoints_compatible
region:us
↓ 2
♥ 0
Created: 2023-11-06
Updated: 2023-11-07
View on Hugging FaceFiles (8)
.gitattributes
README.md
config.json
model-orig.onnx
ONNX
model.data
model.onnx
ONNX
tokenizer.json
tokenizer_config.json