ONNX Model Zoo

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

File Size Download
model-orig.onnx — Download
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.

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 Face

Files (8)

.gitattributes
README.md
config.json
model-orig.onnx ONNX
model.data
model.onnx ONNX
tokenizer.json
tokenizer_config.json

Related models