Instructions to use KnutJaegersberg/openllama_3b_EvolInstruct_lora_merged with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use KnutJaegersberg/openllama_3b_EvolInstruct_lora_merged with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="KnutJaegersberg/openllama_3b_EvolInstruct_lora_merged")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("KnutJaegersberg/openllama_3b_EvolInstruct_lora_merged") model = AutoModelForCausalLM.from_pretrained("KnutJaegersberg/openllama_3b_EvolInstruct_lora_merged", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use KnutJaegersberg/openllama_3b_EvolInstruct_lora_merged with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "KnutJaegersberg/openllama_3b_EvolInstruct_lora_merged" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "KnutJaegersberg/openllama_3b_EvolInstruct_lora_merged", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/KnutJaegersberg/openllama_3b_EvolInstruct_lora_merged
- SGLang
How to use KnutJaegersberg/openllama_3b_EvolInstruct_lora_merged 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 "KnutJaegersberg/openllama_3b_EvolInstruct_lora_merged" \ --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": "KnutJaegersberg/openllama_3b_EvolInstruct_lora_merged", "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 "KnutJaegersberg/openllama_3b_EvolInstruct_lora_merged" \ --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": "KnutJaegersberg/openllama_3b_EvolInstruct_lora_merged", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use KnutJaegersberg/openllama_3b_EvolInstruct_lora_merged with Docker Model Runner:
docker model run hf.co/KnutJaegersberg/openllama_3b_EvolInstruct_lora_merged
Prompt: "Below is an instruction that describes a task. Write a response that appropriately completes the request. \n\n### Instruction:\n INSTRUCTION. \n### Response:\n"
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 35.26 |
| ARC (25-shot) | 40.27 |
| HellaSwag (10-shot) | 71.6 |
| MMLU (5-shot) | 27.12 |
| TruthfulQA (0-shot) | 34.78 |
| Winogrande (5-shot) | 67.01 |
| GSM8K (5-shot) | 0.91 |
| DROP (3-shot) | 5.13 |
- Downloads last month
- 230