Instructions to use IkariDev/Athena-v4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use IkariDev/Athena-v4 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="IkariDev/Athena-v4")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("IkariDev/Athena-v4") model = AutoModelForCausalLM.from_pretrained("IkariDev/Athena-v4") - Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use IkariDev/Athena-v4 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "IkariDev/Athena-v4" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "IkariDev/Athena-v4", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/IkariDev/Athena-v4
- SGLang
How to use IkariDev/Athena-v4 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 "IkariDev/Athena-v4" \ --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": "IkariDev/Athena-v4", "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 "IkariDev/Athena-v4" \ --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": "IkariDev/Athena-v4", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use IkariDev/Athena-v4 with Docker Model Runner:
docker model run hf.co/IkariDev/Athena-v4
Commit ·
68a4631
1
Parent(s): 73905b8
Adding Evaluation Results
Browse filesThis is an automated PR created with https://huggingface.co/spaces/Weyaxi/open-llm-leaderboard-results-pr
The purpose of this PR is to add evaluation results from the Open LLM Leaderboard to your model card.
If you encounter any issues, please report them to https://huggingface.co/spaces/Weyaxi/open-llm-leaderboard-results-pr/discussions
README.md
CHANGED
|
@@ -67,4 +67,17 @@ Below is an instruction that describes a task. Write a response that appropriate
|
|
| 67 |
|
| 68 |
```
|
| 69 |
|
| 70 |
-
Thanks to [Undi95](https://huggingface.co/Undi95) for providing the machine for Athena v2 and Athena v3, and giving me infos about how things work. Going forward i will use a merging server provided by a friend.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 67 |
|
| 68 |
```
|
| 69 |
|
| 70 |
+
Thanks to [Undi95](https://huggingface.co/Undi95) for providing the machine for Athena v2 and Athena v3, and giving me infos about how things work. Going forward i will use a merging server provided by a friend.
|
| 71 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
| 72 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_IkariDev__Athena-v4)
|
| 73 |
+
|
| 74 |
+
| Metric | Value |
|
| 75 |
+
|-----------------------|---------------------------|
|
| 76 |
+
| Avg. | 50.92 |
|
| 77 |
+
| ARC (25-shot) | 62.54 |
|
| 78 |
+
| HellaSwag (10-shot) | 84.19 |
|
| 79 |
+
| MMLU (5-shot) | 57.33 |
|
| 80 |
+
| TruthfulQA (0-shot) | 50.87 |
|
| 81 |
+
| Winogrande (5-shot) | 76.48 |
|
| 82 |
+
| GSM8K (5-shot) | 11.98 |
|
| 83 |
+
| DROP (3-shot) | 13.09 |
|