Text Generation
Transformers
Safetensors
English
llama
wisp
tiny
instruct
sft
conversational
text-generation-inference
Instructions to use DedeProGames/Wisp-5M-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use DedeProGames/Wisp-5M-Instruct with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="DedeProGames/Wisp-5M-Instruct") 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("DedeProGames/Wisp-5M-Instruct") model = AutoModelForCausalLM.from_pretrained("DedeProGames/Wisp-5M-Instruct", 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]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use DedeProGames/Wisp-5M-Instruct with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "DedeProGames/Wisp-5M-Instruct" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "DedeProGames/Wisp-5M-Instruct", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/DedeProGames/Wisp-5M-Instruct
- SGLang
How to use DedeProGames/Wisp-5M-Instruct 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 "DedeProGames/Wisp-5M-Instruct" \ --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": "DedeProGames/Wisp-5M-Instruct", "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 "DedeProGames/Wisp-5M-Instruct" \ --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": "DedeProGames/Wisp-5M-Instruct", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use DedeProGames/Wisp-5M-Instruct with Docker Model Runner:
docker model run hf.co/DedeProGames/Wisp-5M-Instruct
Card wording: GPQA sampling temperature; LiveBench rounding
Browse files
README.md
CHANGED
|
@@ -76,13 +76,13 @@ Held-out loss on assistant tokens (smol-smoltalk test split): 1.791 at the end o
|
|
| 76 |
|
| 77 |
## Evaluation
|
| 78 |
|
| 79 |
-
Benchmarks follow the protocol of the [Kiyo-230M-Instruct](https://huggingface.co/DedeProGames/Kiyo-230M-Instruct) card: FP16, the model's own chat template, no system prompt, new-token limits IFEval 1,024, GPQA 384, LiveBench 512, and the model's full 2,048-token context. The main setting uses temperature 0.1, top-k 50 and repetition penalty 1.05, as on the card. The second setting is the recommended one shipped in `generation_config.json`.
|
| 80 |
|
| 81 |
| Benchmark | Metric | Wisp-5M-Instruct, protocol | Wisp-5M-Instruct, recommended sampling |
|
| 82 |
|---|---|---:|---:|
|
| 83 |
| GPQA Diamond | pass@1 (198 × 5 samples, T = 0.6) | 9.80 | not run |
|
| 84 |
| IFEval | prompt-level strict | 12.38 | 11.65 |
|
| 85 |
-
| LiveBench instruction following | strict, 200 questions | 16.
|
| 86 |
| CaseReportBench | token F1 | not run (not on the Hub) | not run |
|
| 87 |
| EOS rate (IFEval) | share of answers that stop | 0.82 | 0.98 |
|
| 88 |
|
|
|
|
| 76 |
|
| 77 |
## Evaluation
|
| 78 |
|
| 79 |
+
Benchmarks follow the protocol of the [Kiyo-230M-Instruct](https://huggingface.co/DedeProGames/Kiyo-230M-Instruct) card: FP16, the model's own chat template, no system prompt, new-token limits IFEval 1,024, GPQA 384, LiveBench 512, and the model's full 2,048-token context. The main setting uses temperature 0.1, top-k 50 and repetition penalty 1.05, as on the card (GPQA is sampled at T = 0.6, as on the card). The second setting is the recommended one shipped in `generation_config.json`.
|
| 80 |
|
| 81 |
| Benchmark | Metric | Wisp-5M-Instruct, protocol | Wisp-5M-Instruct, recommended sampling |
|
| 82 |
|---|---|---:|---:|
|
| 83 |
| GPQA Diamond | pass@1 (198 × 5 samples, T = 0.6) | 9.80 | not run |
|
| 84 |
| IFEval | prompt-level strict | 12.38 | 11.65 |
|
| 85 |
+
| LiveBench instruction following | strict, 200 questions | 16.53 | not run |
|
| 86 |
| CaseReportBench | token F1 | not run (not on the Hub) | not run |
|
| 87 |
| EOS rate (IFEval) | share of answers that stop | 0.82 | 0.98 |
|
| 88 |
|