Instructions to use Nan-Do/python-assistant-3b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Nan-Do/python-assistant-3b with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="Nan-Do/python-assistant-3b")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Nan-Do/python-assistant-3b")
model = AutoModelForCausalLM.from_pretrained("Nan-Do/python-assistant-3b")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Nan-Do/python-assistant-3b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Nan-Do/python-assistant-3b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Nan-Do/python-assistant-3b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Nan-Do/python-assistant-3b

SGLang

How to use Nan-Do/python-assistant-3b with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "Nan-Do/python-assistant-3b" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Nan-Do/python-assistant-3b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "Nan-Do/python-assistant-3b" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Nan-Do/python-assistant-3b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Nan-Do/python-assistant-3b with Docker Model Runner:
```
docker model run hf.co/Nan-Do/python-assistant-3b
```

Nan-Do commited on Aug 11, 2023

Commit

c842d52

1 Parent(s): 4b93c30

Update README.md

Browse files

Updated description

Files changed (1) hide show

README.md +8 -4

README.md CHANGED Viewed

@@ -8,10 +8,14 @@ tags:
 - code
 ---
 TLDR;
- - The model is quite fun to play with as it seems pretty competent at a first glance.
- - It shows a good understanding about coding and can correct itself if asked for it.
- - It has a vast knowledge about Python and Python libraries (you can for example, ask the model to create a tutorial about some python library).
- - It makes quite a few mistakes
  - When dealing with coding problems it fails completely.
 This is proof of concept to see how far LLM's on the smaller side can go when fine-tuned for code generation and understanding.

 - code
 ---
 TLDR;
+ - The model is quite fun to play with as it seems pretty competent, much better than general bigger models.
+ - It shows a good understanding about coding:
+   - It can correct itself or improve the code if asked for it.
+ - It has a vast knowledge about Python and Python libraries:
+   - You can for example, ask the model to create a tutorial about some python library.
+ - Getting what you want from the model can be a hit or miss:
+   - Sometimes you'll have to fight extensively with the way you write the prompt to get what you want.
+   - Sometimes you won't be able to make the model do what you want.
  - When dealing with coding problems it fails completely.
 This is proof of concept to see how far LLM's on the smaller side can go when fine-tuned for code generation and understanding.