Instructions to use butternese/self-distillation with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

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")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("butternese/self-distillation")
model = AutoModelForCausalLM.from_pretrained("butternese/self-distillation")

Inference
Notebooks
Google Colab
Kaggle
Local Apps

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
```

butternese commited on Nov 28, 2024

Commit

e4f3fd3

verified ·

1 Parent(s): b5b2835

convert model type from $b5b2835b2f0cb1e113abc23e11e4613aef065664 commit

Browse files

Files changed (2) hide show

config.json +2 -2
generation_config.json +1 -1

config.json CHANGED Viewed

@@ -14,7 +14,7 @@
   "intermediate_size": 8192,
   "max_position_embeddings": 131072,
   "mlp_bias": false,
-  "model_type": "llama",
   "num_attention_heads": 32,
   "num_hidden_layers": 16,
   "num_key_value_heads": 8,
@@ -30,7 +30,7 @@
   "rope_theta": 500000.0,
   "tie_word_embeddings": true,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.46.2",
   "use_cache": true,
   "vocab_size": 128256
 }

   "intermediate_size": 8192,
   "max_position_embeddings": 131072,
   "mlp_bias": false,
+  "model_type": "self_distillation_llama",
   "num_attention_heads": 32,
   "num_hidden_layers": 16,
   "num_key_value_heads": 8,
   "rope_theta": 500000.0,
   "tie_word_embeddings": true,
   "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.1",
   "use_cache": true,
   "vocab_size": 128256
 }

generation_config.json CHANGED Viewed

@@ -5,5 +5,5 @@
   "eos_token_id": 128001,
   "temperature": 0.6,
   "top_p": 0.9,
-  "transformers_version": "4.46.2"
 }

   "eos_token_id": 128001,
   "temperature": 0.6,
   "top_p": 0.9,
+  "transformers_version": "4.46.1"
 }