Instructions to use NewstaR/Koss-7B-chat with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use NewstaR/Koss-7B-chat with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="NewstaR/Koss-7B-chat")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("NewstaR/Koss-7B-chat") model = AutoModelForCausalLM.from_pretrained("NewstaR/Koss-7B-chat", device_map="auto") - Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use NewstaR/Koss-7B-chat with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "NewstaR/Koss-7B-chat" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "NewstaR/Koss-7B-chat", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/NewstaR/Koss-7B-chat
- SGLang
How to use NewstaR/Koss-7B-chat 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 "NewstaR/Koss-7B-chat" \ --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": "NewstaR/Koss-7B-chat", "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 "NewstaR/Koss-7B-chat" \ --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": "NewstaR/Koss-7B-chat", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use NewstaR/Koss-7B-chat with Docker Model Runner:
docker model run hf.co/NewstaR/Koss-7B-chat
Adding Evaluation Results
#1
by leaderboard-pr-bot - opened
README.md
CHANGED
|
@@ -38,4 +38,17 @@ Example:
|
|
| 38 |
<s>[INST] Why did the chicken cross the road? [/INST] To get to the other side! </s>
|
| 39 |
```
|
| 40 |
# Loss
|
| 41 |
-

|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 38 |
<s>[INST] Why did the chicken cross the road? [/INST] To get to the other side! </s>
|
| 39 |
```
|
| 40 |
# Loss
|
| 41 |
+

|
| 42 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
| 43 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_NewstaR__Koss-7B-chat)
|
| 44 |
+
|
| 45 |
+
| Metric | Value |
|
| 46 |
+
|-----------------------|---------------------------|
|
| 47 |
+
| Avg. | 44.98 |
|
| 48 |
+
| ARC (25-shot) | 53.67 |
|
| 49 |
+
| HellaSwag (10-shot) | 78.79 |
|
| 50 |
+
| MMLU (5-shot) | 46.72 |
|
| 51 |
+
| TruthfulQA (0-shot) | 43.97 |
|
| 52 |
+
| Winogrande (5-shot) | 71.74 |
|
| 53 |
+
| GSM8K (5-shot) | 7.35 |
|
| 54 |
+
| DROP (3-shot) | 12.62 |
|