Text Generation
Transformers
Safetensors
English
llama
knowledge-distillation
causal-lm
openwebtext
wikitext
transfer-learning
text-generation-inference
Instructions to use HenryHHHH/DistilLlama with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use HenryHHHH/DistilLlama with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="HenryHHHH/DistilLlama")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("HenryHHHH/DistilLlama") model = AutoModelForCausalLM.from_pretrained("HenryHHHH/DistilLlama") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use HenryHHHH/DistilLlama with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "HenryHHHH/DistilLlama" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "HenryHHHH/DistilLlama", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/HenryHHHH/DistilLlama
- SGLang
How to use HenryHHHH/DistilLlama 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 "HenryHHHH/DistilLlama" \ --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": "HenryHHHH/DistilLlama", "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 "HenryHHHH/DistilLlama" \ --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": "HenryHHHH/DistilLlama", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use HenryHHHH/DistilLlama with Docker Model Runner:
docker model run hf.co/HenryHHHH/DistilLlama
Update README.md
Browse files
README.md
CHANGED
|
@@ -110,7 +110,7 @@ The model’s performance is evaluated on 200 queries created in-house. For more
|
|
| 110 |
| baby-llama-58m | 57.20 | 2.73e-06 | 0.025 | 0.6556 | 0.0097 |
|
| 111 |
| DistilLlama | 77.12 | 7.79e-04 | 0.02 | 0.6623 | 0.0115 |
|
| 112 |
|
| 113 |
-
*
|
| 114 |
|
| 115 |
### Acknowledgments
|
| 116 |
|
|
|
|
| 110 |
| baby-llama-58m | 57.20 | 2.73e-06 | 0.025 | 0.6556 | 0.0097 |
|
| 111 |
| DistilLlama | 77.12 | 7.79e-04 | 0.02 | 0.6623 | 0.0115 |
|
| 112 |
|
| 113 |
+
*Note: CodeCarbon was used to track carbon emission. Allocated 80GB memory, 32 cores, Intel(R) Xeon(R) Gold 6448H for the evaluation
|
| 114 |
|
| 115 |
### Acknowledgments
|
| 116 |
|