Instructions to use cjiao/OpenThinker3-1.5B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use cjiao/OpenThinker3-1.5B with Transformers:

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

pipe = pipeline("text-generation", model="cjiao/OpenThinker3-1.5B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("cjiao/OpenThinker3-1.5B")
model = AutoModelForCausalLM.from_pretrained("cjiao/OpenThinker3-1.5B")
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 cjiao/OpenThinker3-1.5B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "cjiao/OpenThinker3-1.5B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "cjiao/OpenThinker3-1.5B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/cjiao/OpenThinker3-1.5B

SGLang

How to use cjiao/OpenThinker3-1.5B 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 "cjiao/OpenThinker3-1.5B" \
    --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": "cjiao/OpenThinker3-1.5B",
		"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 "cjiao/OpenThinker3-1.5B" \
        --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": "cjiao/OpenThinker3-1.5B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use cjiao/OpenThinker3-1.5B with Docker Model Runner:
```
docker model run hf.co/cjiao/OpenThinker3-1.5B
```

cjiao commited on Apr 25

Commit

9a840ac

verified ·

1 Parent(s): 0003e1f

remove checkpoint-600/global_step600 (DeepSpeed optimizer state)

Browse files

Files changed (3) hide show

checkpoint-600/global_step600/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +0 -3
checkpoint-600/global_step600/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +0 -3
checkpoint-600/global_step600/mp_rank_00_model_states.pt +0 -3

checkpoint-600/global_step600/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt DELETED Viewed

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:293da79fd94809f6776d0f39f055fed5443b7a2d02202869267bb253c94b280c
-size 9262302412

checkpoint-600/global_step600/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt DELETED Viewed

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:bab31c4d7164567f733c8bffc770a937c815f9999e6efa237f544df5a440a0df
-size 9262305996

checkpoint-600/global_step600/mp_rank_00_model_states.pt DELETED Viewed

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:15160e23e4edd18908c4c1fbc37718cb82453cfe8ee5f9c34a7238e5f509b63f
-size 3087520696