Instructions to use butternese/self-distillation with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use butternese/self-distillation with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="butternese/self-distillation")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("butternese/self-distillation") model = AutoModelForCausalLM.from_pretrained("butternese/self-distillation", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use butternese/self-distillation with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "butternese/self-distillation" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "butternese/self-distillation", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/butternese/self-distillation
- SGLang
How to use butternese/self-distillation 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 "butternese/self-distillation" \ --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": "butternese/self-distillation", "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 "butternese/self-distillation" \ --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": "butternese/self-distillation", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use butternese/self-distillation with Docker Model Runner:
docker model run hf.co/butternese/self-distillation
Commit History
-
Training Update: 2025-02-28 08:07:52
Verified signature- Dataset size: 200000 - Learning rate: 0.000100 - Training weight: all_paramsb33dd91
-
Training Update: 2025-02-28 03:19:18
Verified signature- Dataset size: 200000 - Learning rate: 0.000100 - Training weight: all_paramsbedeb98
-
Training Update: 2025-02-14 01:00:48
Verified signature- Dataset size: 200000 - Learning rate: 0.000100 - Training weight: all_params2ea9828 -
Training Update: 2025-02-14 00:08:30
Verified signature- Dataset size: 200000 - Learning rate: 0.000100 - Training weight: all_params233a64a -
Training Update: 2025-02-13 20:27:54
Verified signature- Dataset size: 200000 - Learning rate: 0.000100 - Training weight: all_paramsc7eaf95
-
Training Update: 2025-02-12 17:33:47
Verified signature- Dataset size: 200000 - Learning rate: 0.000100 - Training weight: all_params887bac7
-
Training Update: 2025-02-10 16:35:50
Verified signature- Dataset size: 200000 - Learning rate: 0.000100 - Training weight: all_paramse9917c0
-
Training Update: 2025-02-05 15:59:22
Verified signature- Dataset size: 200000 - Learning rate: 0.000100 - Training weight: all_params683a562
-
Training Update: 2025-02-04 19:31:42
Verified signature- Dataset size: 200000 - Learning rate: 0.000100 - Training weight: all_paramsee04912
-
100000000_at_100000916
Verified signaturecfec04e -
10000000_at_10000615
Verified signaturee7931f1 -
1000000_at_1001777
Verified signature25a29b8 -
100000000_at_100000916
Verified signatureab13e7a
-
10000000_at_10000615
Verified signaturedb83218 -
1000000_at_1001777
Verified signature53bcee0 -
10000_at_10030
Verified signaturecd20cf0
-
1_at_1185
Verified signature2715147
-
Training Update: 2025-01-30 01:55:42
Verified signature- Dataset size: 200000 - Learning rate: 0.000100 - Training weight: all_params24be870
-
Upload SelfDistillationLlama
Verified signaturefa15516 -
Training Update: 2025-01-04 12:23:27
Verified signature- Dataset size: 200000 - Learning rate: 0.000100 - Training weight: all_params4c4b95c
-
Training Update: 2025-01-03 20:14:08
Verified signature- Dataset size: 200000 - Learning rate: 0.000100 - Training weight: all_params51d00cf -
Training Update: 2025-01-03 19:35:56
Verified signature- Dataset size: 200000 - Learning rate: 0.000100 - Training weight: all_params15ed7ed -
Training Update: 2025-01-03 16:48:48
Verified signature- Dataset size: 200000 - Learning rate: 0.000100 - Training weight: all_params6166f9c -
Training Update: 2025-01-03 16:34:49
Verified signature- Dataset size: 200000 - Learning rate: 0.000100 - Training weight: all_params366442b -
Upload SelfDistillationLlama
Verified signature5f1241a -
Upload SelfDistillationLlama
Verified signature380fbfc -
Upload SelfDistillationLlama
Verified signaturebfe243e -
Upload SelfDistillationLlama
Verified signature124b403
-
Training Update: 2025-01-02 08:13:54
Verified signature- Dataset size: 200000 - Learning rate: 0.000100 - Training weight: all_paramsaa42d09
-
Training Update: 2025-01-01 21:35:49
Verified signature- Dataset size: 200000 - Learning rate: 0.000100 - Training weight: all_params107f90a -
Upload SelfDistillationLlama
Verified signature960fb9a -
Upload SelfDistillationLlama
Verified signaturefcb7839 -
Upload SelfDistillationLlama
Verified signature87e3c03 -
Upload SelfDistillationLlama
Verified signaturec664727 -
Upload tokenizer
Verified signatured114c57 -
Training Update: 2025-01-01 18:55:00
Verified signature- Dataset size: 200000 - Learning rate: 0.000100 - Training weight: all_paramsafeca99 -
Training Update: 2025-01-01 14:51:59
Verified signature- Dataset size: 200000 - Learning rate: 0.000100 - Training weight: all_paramsbbd30ee -
Training Update: 2025-01-01 03:23:56
Verified signature- Dataset size: 200000 - Learning rate: 0.000100 - Training weight: all_params6944692
-
Training Update: 2025-01-01 01:31:26
Verified signature- Dataset size: 200000 - Learning rate: 0.000100 - Training weight: all_params93ba1c2 -
Training Update: 2025-01-01 01:33:36
Verified signature- Dataset size: 200000 - Learning rate: 0.000100 - Training weight: all_paramsf06659e -
Training Update: 2024-12-31 18:52:16
Verified signature- Dataset size: 200000 - Learning rate: 0.000100 - Training weight: all_paramsd74151f -
Training Update: 2024-12-31 11:58:35
Verified signature- Dataset size: 200000 - Learning rate: 0.000100 - Training weight: all_params1592902 -
Training Update: 2024-12-31 03:57:26
Verified signature- Dataset size: 200000 - Learning rate: 0.000100 - Training weight: all_params3c5abf8
-
Training Update: 2024-12-31 04:36:40
Verified signature- Dataset size: 200000 - Learning rate: 0.000100 - Training weight: all_params1808171 -
Training Update: 2024-12-30 22:51:38
Verified signature- Dataset size: 200000 - Learning rate: 0.000100 - Training weight: all_params6c64077
-
Training Update: 2024-12-28 11:26:42
Verified signature- Dataset size: 200000 - Learning rate: 0.000100 - Training weight: all_paramsc4b8d62 -
Training Update: 2024-12-28 05:12:27
Verified signature- Dataset size: 200000 - Learning rate: 0.000100 - Training weight: all_params097cab2
-
Training Update: 2024-12-28 01:38:14
Verified signature- Dataset size: 200000 - Learning rate: 0.000100 - Training weight: all_params525473d -
Training Update: 2024-12-27 15:33:01
Verified signature- Dataset size: 200000 - Learning rate: 0.000100 - Training weight: all_paramsee7679d -
Training Update: 2024-12-27 14:28:37
Verified signature- Dataset size: 200000 - Learning rate: 0.000100 - Training weight: all_params5fe60df