Text Generation
Transformers
Safetensors
English
mistral
Merge
mergekit
lazymergekit
Locutusque/Hercules-2.5-Mistral-7B
teknium/OpenHermes-2.5-Mistral-7B
chatml
Eval Results (legacy)
text-generation-inference
Instructions to use hydra-project/OpenHercules-2.5-Mistral-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use hydra-project/OpenHercules-2.5-Mistral-7B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="hydra-project/OpenHercules-2.5-Mistral-7B")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("hydra-project/OpenHercules-2.5-Mistral-7B") model = AutoModelForCausalLM.from_pretrained("hydra-project/OpenHercules-2.5-Mistral-7B", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use hydra-project/OpenHercules-2.5-Mistral-7B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "hydra-project/OpenHercules-2.5-Mistral-7B" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "hydra-project/OpenHercules-2.5-Mistral-7B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/hydra-project/OpenHercules-2.5-Mistral-7B
- SGLang
How to use hydra-project/OpenHercules-2.5-Mistral-7B 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 "hydra-project/OpenHercules-2.5-Mistral-7B" \ --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": "hydra-project/OpenHercules-2.5-Mistral-7B", "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 "hydra-project/OpenHercules-2.5-Mistral-7B" \ --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": "hydra-project/OpenHercules-2.5-Mistral-7B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use hydra-project/OpenHercules-2.5-Mistral-7B with Docker Model Runner:
docker model run hf.co/hydra-project/OpenHercules-2.5-Mistral-7B
Delete duplicate eval
Browse files
README.md
CHANGED
|
@@ -175,18 +175,6 @@ pipeline = transformers.pipeline(
|
|
| 175 |
outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
|
| 176 |
print(outputs[0]["generated_text"])
|
| 177 |
```
|
| 178 |
-
## [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
| 179 |
-
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_Locutusque__OpenHercules-2.5-Mistral-7B)
|
| 180 |
-
|
| 181 |
-
| Metric |Value|
|
| 182 |
-
|---------------------------------|----:|
|
| 183 |
-
|Avg. |66.55|
|
| 184 |
-
|AI2 Reasoning Challenge (25-Shot)|64.25|
|
| 185 |
-
|HellaSwag (10-Shot) |84.84|
|
| 186 |
-
|MMLU (5-Shot) |64.21|
|
| 187 |
-
|TruthfulQA (0-shot) |47.84|
|
| 188 |
-
|Winogrande (5-shot) |78.93|
|
| 189 |
-
|GSM8k (5-shot) |59.21|
|
| 190 |
|
| 191 |
## Quants
|
| 192 |
|
|
|
|
| 175 |
outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
|
| 176 |
print(outputs[0]["generated_text"])
|
| 177 |
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 178 |
|
| 179 |
## Quants
|
| 180 |
|