Instructions to use prithivMLmods/Bellatrix-Tiny-3B-R1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use prithivMLmods/Bellatrix-Tiny-3B-R1 with Transformers:

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

pipe = pipeline("text-generation", model="prithivMLmods/Bellatrix-Tiny-3B-R1")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("prithivMLmods/Bellatrix-Tiny-3B-R1")
model = AutoModelForCausalLM.from_pretrained("prithivMLmods/Bellatrix-Tiny-3B-R1")
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/Bellatrix-Tiny-3B-R1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "prithivMLmods/Bellatrix-Tiny-3B-R1"
# 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/Bellatrix-Tiny-3B-R1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/prithivMLmods/Bellatrix-Tiny-3B-R1

SGLang

How to use prithivMLmods/Bellatrix-Tiny-3B-R1 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/Bellatrix-Tiny-3B-R1" \
    --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/Bellatrix-Tiny-3B-R1",
		"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/Bellatrix-Tiny-3B-R1" \
        --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/Bellatrix-Tiny-3B-R1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use prithivMLmods/Bellatrix-Tiny-3B-R1 with Docker Model Runner:
```
docker model run hf.co/prithivMLmods/Bellatrix-Tiny-3B-R1
```

prithivMLmods commited on Feb 2, 2025

Commit

7813dfb

verified ·

1 Parent(s): f539049

Update README.md

Browse files

Files changed (1) hide show

README.md +2 -1

README.md CHANGED Viewed

@@ -9,6 +9,7 @@ tags:
 - trl
 - llama3.2
 - Reinforcement learning
 ---
 # **Bellatrix-Tiny-3B-R1**
@@ -65,4 +66,4 @@ Despite its capabilities, Bellatrix has some limitations:
 2. **Dependence on Training Data**: It is only as good as the quality and diversity of its training data, which may lead to biases or inaccuracies.
 3. **Computational Resources**: The model’s optimized transformer architecture can be resource-intensive, requiring significant computational power for fine-tuning and inference.
 4. **Language Coverage**: While multilingual, some languages or dialects may have limited support or lower performance compared to widely used ones.
-5. **Real-World Contexts**: It may struggle with understanding nuanced or ambiguous real-world scenarios not covered during training.

 - trl
 - llama3.2
 - Reinforcement learning
+- SFT
 ---
 # **Bellatrix-Tiny-3B-R1**
 2. **Dependence on Training Data**: It is only as good as the quality and diversity of its training data, which may lead to biases or inaccuracies.
 3. **Computational Resources**: The model’s optimized transformer architecture can be resource-intensive, requiring significant computational power for fine-tuning and inference.
 4. **Language Coverage**: While multilingual, some languages or dialects may have limited support or lower performance compared to widely used ones.
+5. **Real-World Contexts**: It may struggle with understanding nuanced or ambiguous real-world scenarios not covered during training.