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
```

keepsloading commited on 23 days ago

Commit

f382c88

verified ·

1 Parent(s): 4a92d99

Upload folder using huggingface_hub

Browse files

Files changed (2) hide show

recipe/run_reproduction.sh +15 -0
recipe/scripts/eval_sweep.sh +1 -1

recipe/run_reproduction.sh CHANGED Viewed

@@ -43,6 +43,21 @@ python -c "import nltk; nltk.download('punkt', quiet=True); nltk.download('punkt
 echo "Making scripts executable..."
 chmod +x /workspace/recipe/scripts/*.sh || exit 1
 repro_status=0
 echo "=== STAGE 1 & 2: SFT Training (L2A-Style) ==="

 echo "Making scripts executable..."
 chmod +x /workspace/recipe/scripts/*.sh || exit 1
+echo "Downloading previous outputs from Hugging Face Hub (resumability)..."
+python -c '
+from huggingface_hub import snapshot_download
+import os
+try:
+    snapshot_download(
+        repo_id="keepsloading/icml_repro_scratch",
+        allow_patterns="outputs/*",
+        local_dir="/workspace"
+    )
+    print("Previous outputs downloaded successfully!")
+except Exception as e:
+    print("Could not download previous outputs:", e)
+'
 repro_status=0
 echo "=== STAGE 1 & 2: SFT Training (L2A-Style) ==="

recipe/scripts/eval_sweep.sh CHANGED Viewed

@@ -10,7 +10,7 @@ VANILLA_MODEL="${VANILLA_DIR:-$REPO}"
 AHA_MODEL="${AHA_MODEL:-$OUTPUT_ROOT/aha/stage2/checkpoint-25}"
 L2A_MODEL="${L2A_MODEL:-$OUTPUT_ROOT/l2a_style/stage2/checkpoint-25}"
 GPU_LIST="${GPU_LIST:-0}"
-THRESHOLDS=(0.45 0.50 0.525 0.55 0.575 0.60 0.625 0.65)
 BENCHMARKS=(ruler_a ruler_b babilong helmet mrcr)
 IFS=',' read -r -a GPUS <<< "$GPU_LIST"
 declare -A SLOT_PIDS=()

 AHA_MODEL="${AHA_MODEL:-$OUTPUT_ROOT/aha/stage2/checkpoint-25}"
 L2A_MODEL="${L2A_MODEL:-$OUTPUT_ROOT/l2a_style/stage2/checkpoint-25}"
 GPU_LIST="${GPU_LIST:-0}"
+THRESHOLDS=(0.45 0.525 0.575 0.65)
 BENCHMARKS=(ruler_a ruler_b babilong helmet mrcr)
 IFS=',' read -r -a GPUS <<< "$GPU_LIST"
 declare -A SLOT_PIDS=()