Instructions to use MMOPD/Qwen3-1.7B-OT3-2ep with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use MMOPD/Qwen3-1.7B-OT3-2ep with Transformers:

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

pipe = pipeline("text-generation", model="MMOPD/Qwen3-1.7B-OT3-2ep")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("MMOPD/Qwen3-1.7B-OT3-2ep")
model = AutoModelForCausalLM.from_pretrained("MMOPD/Qwen3-1.7B-OT3-2ep", 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 MMOPD/Qwen3-1.7B-OT3-2ep with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "MMOPD/Qwen3-1.7B-OT3-2ep"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "MMOPD/Qwen3-1.7B-OT3-2ep",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/MMOPD/Qwen3-1.7B-OT3-2ep

SGLang

How to use MMOPD/Qwen3-1.7B-OT3-2ep 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 "MMOPD/Qwen3-1.7B-OT3-2ep" \
    --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": "MMOPD/Qwen3-1.7B-OT3-2ep",
		"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 "MMOPD/Qwen3-1.7B-OT3-2ep" \
        --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": "MMOPD/Qwen3-1.7B-OT3-2ep",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use MMOPD/Qwen3-1.7B-OT3-2ep with Docker Model Runner:
```
docker model run hf.co/MMOPD/Qwen3-1.7B-OT3-2ep
```

Qwen3-1.7B-OT3 (2 epochs)

Qwen3-1.7B-OT3-2ep is Qwen3-1.7B-Base fine-tuned on OpenThoughts3-1.2M (the full 1.2M-example long-chain-of-thought SFT set: math, code and science reasoning traces) — an open re-creation of the OpenThinker3 recipe at the 1.7B scale. It is a thinking model: every answer starts with a <think> block. The checkpoint is a general reasoning student that the MMOPD project uses as the starting point for domain teachers and for on-policy distillation experiments.

This repository holds the final checkpoint after 2 epochs (step 4,312). The 1-epoch checkpoint is MMOPD/Qwen3-1.7B-OT3-1ep.

Training


base model	Qwen3-1.7B-Base
data	OpenThoughts3-1.2M (`open-thoughts/OpenThoughts3-1.2M`), all 1.2M rows, Qwen3 chat template with thinking
sequence length	18,432 tokens, sequence packing (flatten, no cross-example attention)
epochs	2 (4,312 optimizer steps in total, 2,156 per epoch)
optimizer	AdamW, peak LR 8e-5, 5% warmup, global batch 512 packed sequences (about 8.1M tokens per step)
precision	bf16 compute, ZeRO-2 data parallel (transformers 4.57 / trl 0.29 / DeepSpeed) on A100-80GB
final train loss	0.942

Evaluation

General benchmarks (Qwen3 thinking preset: temperature 0.6, top-p 0.95, top-k 20; 32,768 max new tokens; AIME = avg@8, LiveCodeBench v6 / IFEval / IFBench = 1 sample; scores in %):

Model	AIME24	AIME25	AIME26	LiveCodeBench v6	IFEval	IFBench
Qwen3-1.7B-OT3-2ep (this)	25.0	20.8	24.2	19.7	30.9	20.7
Qwen3-4B-OT3-2ep (reference)	66.3	56.3	58.3	51.7	51.0	27.7

Notes

Apache-2.0, like the Qwen3 base models and OpenThoughts3.
Part of the MMOPD (multi-teacher on-policy distillation) model family: the domain teachers MMOPD/Qwen3-4B-OT3-{medical,law,finance,if} start from MMOPD/Qwen3-4B-OT3-2ep.

How to use

The models keep the Qwen3 chat template and thinking format (<think> ... </think> before the answer). Use enable_thinking=True and sampling (not greedy); the evaluations below used a 32k-token generation budget.

from transformers import AutoModelForCausalLM, AutoTokenizer
repo = "MMOPD/Qwen3-1.7B-OT3-2ep"
tok = AutoTokenizer.from_pretrained(repo)
model = AutoModelForCausalLM.from_pretrained(repo, dtype="auto", device_map="auto")
messages = [{"role": "user", "content": "How many positive integers n < 1000 have the property that n^2 + 1 is divisible by 5?"}]
text = tok.apply_chat_template(messages, tokenize=False, add_generation_prompt=True, enable_thinking=True)
out = model.generate(**tok(text, return_tensors="pt").to(model.device), max_new_tokens=32768,
                     do_sample=True, temperature=0.6, top_p=0.95, top_k=20)
print(tok.decode(out[0], skip_special_tokens=True))

vLLM: vllm serve MMOPD/Qwen3-1.7B-OT3-2ep --max-model-len 40960 (the same sampling settings apply).

Downloads last month: 168

Safetensors

Model size

2B params

Tensor type

BF16

Model tree for MMOPD/Qwen3-1.7B-OT3-2ep

Base model

Qwen/Qwen3-1.7B-Base

Finetuned

(414)

this model

MMOPD
/

Qwen3-1.7B-OT3-2ep