OpenThinker2-32B

Instructions to use open-thoughts/OpenThinker2-32B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use open-thoughts/OpenThinker2-32B with Transformers:

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

pipe = pipeline("text-generation", model="open-thoughts/OpenThinker2-32B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("open-thoughts/OpenThinker2-32B")
model = AutoModelForCausalLM.from_pretrained("open-thoughts/OpenThinker2-32B")
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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use open-thoughts/OpenThinker2-32B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "open-thoughts/OpenThinker2-32B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "open-thoughts/OpenThinker2-32B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/open-thoughts/OpenThinker2-32B

SGLang

How to use open-thoughts/OpenThinker2-32B 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 "open-thoughts/OpenThinker2-32B" \
    --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": "open-thoughts/OpenThinker2-32B",
		"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 "open-thoughts/OpenThinker2-32B" \
        --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": "open-thoughts/OpenThinker2-32B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use open-thoughts/OpenThinker2-32B with Docker Model Runner:
```
docker model run hf.co/open-thoughts/OpenThinker2-32B
```

OpenThinker2-32B / configs.yaml

sedrickkeh

Duplicate from mlfoundations-dev/DCFT-hero_run_2_fix_conversations-etash

274d459 verified about 1 year ago

raw

history blame contribute delete

1.5 kB

	assistant_tag: assistant
	bf16: true
	content_tag: value
	cutoff_len: 16384
	dataloader_num_workers: 4
	dataloader_persistent_workers: true
	dataloader_pin_memory: true
	dataset: /leonardo_work/EUHPC_E03_068/eguha/datasets_cache/mlfoundations-dev/hero_run_2_fix_conversations
	dataset_dir: ONLINE
	ddp_timeout: 180000000
	deepspeed: dcft/train/zero3.json
	do_train: true
	enable_liger_kernel: false
	finetuning_type: full
	flash_attn: sdpa
	formatting: sharegpt
	global_batch_size: 512
	gradient_accumulation_steps: 1
	hub_model_id: mlfoundations-dev/DCFT-hero_run_2_fix_conversations-etash
	include_hp: dcft/train/hp_settings/reasoning_32b_5epoch.yaml
	learning_rate: 8.0e-05
	logging_steps: 1
	lr_scheduler_type: cosine
	messages: conversations
	model_name_or_path: /leonardo_work/EUHPC_E03_068/eguha/models_cache/models--Qwen--Qwen2.5-32B-Instruct/snapshots/5ede1c97bbab6ce5cda5812749b4c0bdf79b18dd/
	neat_packing: true
	num_train_epochs: 5.0
	output_dir: /leonardo_work/EUHPC_E03_068/eguha/checkoints/hero_run_2_fix_conversations
	overwrite_cache: true
	packing: true
	per_device_train_batch_size: 1
	plot_loss: true
	preprocessing_num_workers: 16
	push_to_db: false
	push_to_hub: false
	report_to: wandb
	role_tag: from
	run_name: DCFT-hero_run_2_fix_conversations-etash
	save_steps: 500
	save_strategy: steps
	stage: sft
	template: qwen25
	tokenized_path: /leonardo_work/EUHPC_E03_068/DCFT_shared/datasets/mlfoundations-dev/hero_run_2_fix_conversations_tokenized
	torch_compile: true
	use_unsloth_gc: false
	user_tag: user
	warmup_ratio: 0.1