Instructions to use prithivMLmods/Viper-Coder-v1.5-r999 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use prithivMLmods/Viper-Coder-v1.5-r999 with Transformers:

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

pipe = pipeline("text-generation", model="prithivMLmods/Viper-Coder-v1.5-r999")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("prithivMLmods/Viper-Coder-v1.5-r999")
model = AutoModelForCausalLM.from_pretrained("prithivMLmods/Viper-Coder-v1.5-r999")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use prithivMLmods/Viper-Coder-v1.5-r999 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "prithivMLmods/Viper-Coder-v1.5-r999"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "prithivMLmods/Viper-Coder-v1.5-r999",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/prithivMLmods/Viper-Coder-v1.5-r999

SGLang

How to use prithivMLmods/Viper-Coder-v1.5-r999 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 "prithivMLmods/Viper-Coder-v1.5-r999" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "prithivMLmods/Viper-Coder-v1.5-r999",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "prithivMLmods/Viper-Coder-v1.5-r999" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "prithivMLmods/Viper-Coder-v1.5-r999",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use prithivMLmods/Viper-Coder-v1.5-r999 with Docker Model Runner:
```
docker model run hf.co/prithivMLmods/Viper-Coder-v1.5-r999
```

Wonderful, could you please share something about SFT?

by Ken0102030405 - opened Mar 20, 2025

Discussion

Ken0102030405

Mar 20, 2025

could you please share something about SFT? Like how to design the dataset, use which finetuning frame.

prithivMLmods

Owner Mar 20, 2025

•

edited Mar 20, 2025

This model was trained with a low learning rate for 4 to 4.5 hours on 2× A100 SXM GPUs. It is an experimental successor to https://huggingface.co/prithivMLmods/Viper-Coder-v1.1

Regarding dataset preparation, it consists of modular combustion data entries from OpenR1's Code-Cot, Codeforces, Codeforces-Python, Code-Dataset-500K, CodeParrot, Python Core GitHub, Math-Code, and more.

For details on SFT (Supervised Fine-Tuning) and training, you can refer to the following Colab notebook, which I improved from scratch:
https://huggingface.co/datasets/prithivMLmods/Finetune-Colab-Nb/blob/main/SmolLM-FT/SmolLM-FT-360M.ipynb

Ken0102030405

Mar 20, 2025

This model was trained with a low learning rate for 4 to 4.5 hours on 2× A100 SXM GPUs. It is an experimental successor to https://huggingface.co/prithivMLmods/Viper-Coder-v1.1

Regarding dataset preparation, it consists of modular combustion data entries from OpenR1's Code-Cot, Codeforces, Codeforces-Python, Code-Dataset-500K, CodeParrot, Python Core GitHub, Math-Code, and more.

For details on SFT (Supervised Fine-Tuning) and training, you can refer to the following Colab notebook, which I improved from scratch:
https://huggingface.co/datasets/prithivMLmods/Finetune-Colab-Nb/blob/main/SmolLM-FT/SmolLM-FT-360M.ipynb

So nice for your reply! Actually, recently I'm faced with combining private code module(which is so hard to put into prompt) with code LLM（like generate " import a from my_module"）, so looking forward for any suggestions. Do you have any suggestions, with training or rag ,etc.

prithivMLmods

Owner Mar 20, 2025

For that, you can follow different strategies in custom @Ken0102030405

You can start by indexing the module’s functions and methods, allowing the LLM to retrieve relevant parts dynamically. Another approach is using system prompts with detailed descriptions of the module. You can also store private module documentation or example code in a vector database and retrieve relevant snippets during generation.

Begin with the easiest method and move on based on your priority.

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment