Instructions to use pansophic/rocket-3B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use pansophic/rocket-3B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="pansophic/rocket-3B")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("pansophic/rocket-3B") model = AutoModelForCausalLM.from_pretrained("pansophic/rocket-3B") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use pansophic/rocket-3B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "pansophic/rocket-3B" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "pansophic/rocket-3B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/pansophic/rocket-3B
- SGLang
How to use pansophic/rocket-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 "pansophic/rocket-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": "pansophic/rocket-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 "pansophic/rocket-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": "pansophic/rocket-3B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use pansophic/rocket-3B with Docker Model Runner:
docker model run hf.co/pansophic/rocket-3B
Update benchmarks in README
Browse files
README.md
CHANGED
|
@@ -67,13 +67,14 @@ In AlpacaEval, Rocket 🦝 achieves a near 80% win rate, coupled with an average
|
|
| 67 |
|
| 68 |
| Metric | Value |
|
| 69 |
|-----------------------|---------------------------|
|
|
|
|
| 70 |
| ARC (25-shot) | 50.51 |
|
| 71 |
-
| HellaSwag (
|
| 72 |
-
|
|
| 73 |
-
|
|
| 74 |
| Winogrande (5-shot) | 67.8 |
|
| 75 |
| GSM8K (5-shot) | 37.91 |
|
| 76 |
-
|
|
| 77 |
|
| 78 |
|
| 79 |
## Intended uses & limitations
|
|
|
|
| 67 |
|
| 68 |
| Metric | Value |
|
| 69 |
|-----------------------|---------------------------|
|
| 70 |
+
| Average | 51.00 |
|
| 71 |
| ARC (25-shot) | 50.51 |
|
| 72 |
+
| HellaSwag (10-shot) | 76.45 |
|
| 73 |
+
| MMLU (5-shot) | 45.51 |
|
| 74 |
+
| TruthfulQA (0-shot) | 54.38 |
|
| 75 |
| Winogrande (5-shot) | 67.8 |
|
| 76 |
| GSM8K (5-shot) | 37.91 |
|
| 77 |
+
| DROP (3-shot) | 24.49 |
|
| 78 |
|
| 79 |
|
| 80 |
## Intended uses & limitations
|