Instructions to use keepsloading/icml_repro_scratch with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use keepsloading/icml_repro_scratch with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="keepsloading/icml_repro_scratch")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("keepsloading/icml_repro_scratch")
model = AutoModelForCausalLM.from_pretrained("keepsloading/icml_repro_scratch", 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=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use keepsloading/icml_repro_scratch with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "keepsloading/icml_repro_scratch"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "keepsloading/icml_repro_scratch",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/keepsloading/icml_repro_scratch

SGLang

How to use keepsloading/icml_repro_scratch 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 "keepsloading/icml_repro_scratch" \
    --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": "keepsloading/icml_repro_scratch",
		"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 "keepsloading/icml_repro_scratch" \
        --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": "keepsloading/icml_repro_scratch",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use keepsloading/icml_repro_scratch with Docker Model Runner:
```
docker model run hf.co/keepsloading/icml_repro_scratch
```

icml_repro_scratch / outputs /eval /token_t065 /sparsity_ruler_b.json

keepsloading

Upload folder using huggingface_hub

1ade3b4 verified about 1 month ago

Raw

History Blame Contribute Delete

4.25 kB

	{
	"definition": "hard AHA gate zeros / all token x KV-head x layer decisions, token-weighted over prefill and decode",
	"router_granularity": "token",
	"native_router_decisions": 25272464,
	"effective_router_decisions": 202179712,
	"native_router_note": "Native decisions count learned gate logits before broadcast; effective decisions always use token x KV-head x layer for matched sparsity.",
	"sparse_decisions": 86334664,
	"total_decisions": 202179712,
	"sparsity": 0.42701942319514236,
	"full_attention_usage": 0.5729805768048577,
	"per_layer": {
	"0": {
	"sparse_decisions": 0,
	"total_decisions": 7220704,
	"sparsity": 0.0
	},
	"1": {
	"sparse_decisions": 0,
	"total_decisions": 7220704,
	"sparsity": 0.0
	},
	"2": {
	"sparse_decisions": 0,
	"total_decisions": 7220704,
	"sparsity": 0.0
	},
	"3": {
	"sparse_decisions": 0,
	"total_decisions": 7220704,
	"sparsity": 0.0
	},
	"4": {
	"sparse_decisions": 0,
	"total_decisions": 7220704,
	"sparsity": 0.0
	},
	"5": {
	"sparse_decisions": 0,
	"total_decisions": 7220704,
	"sparsity": 0.0
	},
	"6": {
	"sparse_decisions": 0,
	"total_decisions": 7220704,
	"sparsity": 0.0
	},
	"7": {
	"sparse_decisions": 0,
	"total_decisions": 7220704,
	"sparsity": 0.0
	},
	"8": {
	"sparse_decisions": 0,
	"total_decisions": 7220704,
	"sparsity": 0.0
	},
	"9": {
	"sparse_decisions": 79160,
	"total_decisions": 7220704,
	"sparsity": 0.010962919959051085
	},
	"10": {
	"sparse_decisions": 5720,
	"total_decisions": 7220704,
	"sparsity": 0.0007921665255908565
	},
	"11": {
	"sparse_decisions": 130720,
	"total_decisions": 7220704,
	"sparsity": 0.01810349794147496
	},
	"12": {
	"sparse_decisions": 276416,
	"total_decisions": 7220704,
	"sparsity": 0.03828103187722416
	},
	"13": {
	"sparse_decisions": 1201008,
	"total_decisions": 7220704,
	"sparsity": 0.16632838016902507
	},
	"14": {
	"sparse_decisions": 3219680,
	"total_decisions": 7220704,
	"sparsity": 0.4458955802647498
	},
	"15": {
	"sparse_decisions": 5586712,
	"total_decisions": 7220704,
	"sparsity": 0.7737073836567736
	},
	"16": {
	"sparse_decisions": 3334448,
	"total_decisions": 7220704,
	"sparsity": 0.4617898753362553
	},
	"17": {
	"sparse_decisions": 5915808,
	"total_decisions": 7220704,
	"sparsity": 0.819284103045908
	},
	"18": {
	"sparse_decisions": 5246040,
	"total_decisions": 7220704,
	"sparsity": 0.7265274964878771
	},
	"19": {
	"sparse_decisions": 6154752,
	"total_decisions": 7220704,
	"sparsity": 0.852375613236604
	},
	"20": {
	"sparse_decisions": 6963304,
	"total_decisions": 7220704,
	"sparsity": 0.9643525063484114
	},
	"21": {
	"sparse_decisions": 6725584,
	"total_decisions": 7220704,
	"sparsity": 0.9314305087149397
	},
	"22": {
	"sparse_decisions": 7069864,
	"total_decisions": 7220704,
	"sparsity": 0.9791100701538243
	},
	"23": {
	"sparse_decisions": 6992128,
	"total_decisions": 7220704,
	"sparsity": 0.968344360882263
	},
	"24": {
	"sparse_decisions": 7047448,
	"total_decisions": 7220704,
	"sparsity": 0.9760056637136767
	},
	"25": {
	"sparse_decisions": 7035632,
	"total_decisions": 7220704,
	"sparsity": 0.974369258177596
	},
	"26": {
	"sparse_decisions": 6130496,
	"total_decisions": 7220704,
	"sparsity": 0.8490163839980146
	},
	"27": {
	"sparse_decisions": 7219744,
	"total_decisions": 7220704,
	"sparsity": 0.999867048974726
	}
	},
	"by_phase": {
	"decode": {
	"sparse_decisions": 1527584,
	"total_decisions": 2947840,
	"sparsity": 0.5182045158488927,
	"full_attention_usage": 0.4817954841511073
	},
	"prefill": {
	"sparse_decisions": 84807080,
	"total_decisions": 199231872,
	"sparsity": 0.42567024617426674,
	"full_attention_usage": 0.5743297538257333
	}
	}
	}