Instructions to use GreenBitAI/yi-6b-w2a16g32 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use GreenBitAI/yi-6b-w2a16g32 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="GreenBitAI/yi-6b-w2a16g32", trust_remote_code=True)# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("GreenBitAI/yi-6b-w2a16g32", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use GreenBitAI/yi-6b-w2a16g32 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "GreenBitAI/yi-6b-w2a16g32" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "GreenBitAI/yi-6b-w2a16g32", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/GreenBitAI/yi-6b-w2a16g32
- SGLang
How to use GreenBitAI/yi-6b-w2a16g32 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 "GreenBitAI/yi-6b-w2a16g32" \ --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": "GreenBitAI/yi-6b-w2a16g32", "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 "GreenBitAI/yi-6b-w2a16g32" \ --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": "GreenBitAI/yi-6b-w2a16g32", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use GreenBitAI/yi-6b-w2a16g32 with Docker Model Runner:
docker model run hf.co/GreenBitAI/yi-6b-w2a16g32
Update README.md
Browse files
README.md
CHANGED
|
@@ -13,6 +13,7 @@ Please refer to our [Github page](https://github.com/GreenBitAI/low_bit_llama) f
|
|
| 13 |
- **Language(s) (NLP):** English
|
| 14 |
- **License:** [Apache 2.0](https://www.apache.org/licenses/LICENSE-2.0), [Llama 2 license agreement](https://ai.meta.com/resources/models-and-libraries/llama-downloads/)
|
| 15 |
|
|
|
|
| 16 |
| Task | Metric | FP16 | 6B w4a16g32 | 6B w2a16g8 wikitext2 | 6B w2a16g32 wikitext2 |
|
| 17 |
|-----------------|--------|-------|-------------|----------------------|-----------------------|
|
| 18 |
| Openbookqa | acc | 0.314 | 0.324 | 0.26 | 0.228 |
|
|
|
|
| 13 |
- **Language(s) (NLP):** English
|
| 14 |
- **License:** [Apache 2.0](https://www.apache.org/licenses/LICENSE-2.0), [Llama 2 license agreement](https://ai.meta.com/resources/models-and-libraries/llama-downloads/)
|
| 15 |
|
| 16 |
+
## Zero-Shot Evaluation
|
| 17 |
| Task | Metric | FP16 | 6B w4a16g32 | 6B w2a16g8 wikitext2 | 6B w2a16g32 wikitext2 |
|
| 18 |
|-----------------|--------|-------|-------------|----------------------|-----------------------|
|
| 19 |
| Openbookqa | acc | 0.314 | 0.324 | 0.26 | 0.228 |
|