Text Generation
Transformers
Safetensors
English
llama
axolotl
Generated from Trainer
instruct
finetune
chatml
gpt4
synthetic data
science
physics
chemistry
biology
math
llama3
conversational
Eval Results (legacy)
text-generation-inference
Instructions to use Weyaxi/Einstein-v6.1-Llama3-8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Weyaxi/Einstein-v6.1-Llama3-8B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Weyaxi/Einstein-v6.1-Llama3-8B") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("Weyaxi/Einstein-v6.1-Llama3-8B") model = AutoModelForCausalLM.from_pretrained("Weyaxi/Einstein-v6.1-Llama3-8B", device_map="auto") messages = [ {"role": "user", "content": "Who are you?"}, ] inputs = tokenizer.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt", ).to(model.device) outputs = model.generate(**inputs, max_new_tokens=256) print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use Weyaxi/Einstein-v6.1-Llama3-8B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Weyaxi/Einstein-v6.1-Llama3-8B" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Weyaxi/Einstein-v6.1-Llama3-8B", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/Weyaxi/Einstein-v6.1-Llama3-8B
- SGLang
How to use Weyaxi/Einstein-v6.1-Llama3-8B 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 "Weyaxi/Einstein-v6.1-Llama3-8B" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Weyaxi/Einstein-v6.1-Llama3-8B", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'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 "Weyaxi/Einstein-v6.1-Llama3-8B" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Weyaxi/Einstein-v6.1-Llama3-8B", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use Weyaxi/Einstein-v6.1-Llama3-8B with Docker Model Runner:
docker model run hf.co/Weyaxi/Einstein-v6.1-Llama3-8B
Update README.md
Browse files
README.md
CHANGED
|
@@ -481,6 +481,20 @@ Detailed results can be found [here](https://huggingface.co/datasets/open-llm-le
|
|
| 481 |
|Winogrande (5-shot) |79.32|
|
| 482 |
|GSM8k (5-shot) |66.11|
|
| 483 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 484 |
# 📚 Some resources, discussions and reviews aboout this model
|
| 485 |
|
| 486 |
#### 🐦 Announcement tweet:
|
|
@@ -525,18 +539,4 @@ Thanks to all open source AI community.
|
|
| 525 |
|
| 526 |
If you would like to support me:
|
| 527 |
|
| 528 |
-
[☕ Buy Me a Coffee](https://www.buymeacoffee.com/weyaxi)
|
| 529 |
-
|
| 530 |
-
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard)
|
| 531 |
-
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_Weyaxi__Einstein-v6.1-Llama3-8B)
|
| 532 |
-
|
| 533 |
-
| Metric |Value|
|
| 534 |
-
|-------------------|----:|
|
| 535 |
-
|Avg. |19.99|
|
| 536 |
-
|IFEval (0-Shot) |45.68|
|
| 537 |
-
|BBH (3-Shot) |29.38|
|
| 538 |
-
|MATH Lvl 5 (4-Shot)| 5.74|
|
| 539 |
-
|GPQA (0-shot) | 4.25|
|
| 540 |
-
|MuSR (0-shot) |11.23|
|
| 541 |
-
|MMLU-PRO (5-shot) |23.68|
|
| 542 |
-
|
|
|
|
| 481 |
|Winogrande (5-shot) |79.32|
|
| 482 |
|GSM8k (5-shot) |66.11|
|
| 483 |
|
| 484 |
+
# 🎯 [Open LLM Leaderboard v2 Evaluation Results](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard)
|
| 485 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_Weyaxi__Einstein-v6.1-Llama3-8B)
|
| 486 |
+
|
| 487 |
+
| Metric |Value|
|
| 488 |
+
|-------------------|----:|
|
| 489 |
+
|Avg. |19.99|
|
| 490 |
+
|IFEval (0-Shot) |45.68|
|
| 491 |
+
|BBH (3-Shot) |29.38|
|
| 492 |
+
|MATH Lvl 5 (4-Shot)| 5.74|
|
| 493 |
+
|GPQA (0-shot) | 4.25|
|
| 494 |
+
|MuSR (0-shot) |11.23|
|
| 495 |
+
|MMLU-PRO (5-shot) |23.68|
|
| 496 |
+
|
| 497 |
+
|
| 498 |
# 📚 Some resources, discussions and reviews aboout this model
|
| 499 |
|
| 500 |
#### 🐦 Announcement tweet:
|
|
|
|
| 539 |
|
| 540 |
If you would like to support me:
|
| 541 |
|
| 542 |
+
[☕ Buy Me a Coffee](https://www.buymeacoffee.com/weyaxi)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|