Instructions to use eewer/Qwen3-4B-Thinking-Preservation-terminus2-sft with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use eewer/Qwen3-4B-Thinking-Preservation-terminus2-sft with Transformers:

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

pipe = pipeline("text-generation", model="eewer/Qwen3-4B-Thinking-Preservation-terminus2-sft")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("eewer/Qwen3-4B-Thinking-Preservation-terminus2-sft")
model = AutoModelForCausalLM.from_pretrained("eewer/Qwen3-4B-Thinking-Preservation-terminus2-sft")
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 eewer/Qwen3-4B-Thinking-Preservation-terminus2-sft with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "eewer/Qwen3-4B-Thinking-Preservation-terminus2-sft"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "eewer/Qwen3-4B-Thinking-Preservation-terminus2-sft",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/eewer/Qwen3-4B-Thinking-Preservation-terminus2-sft

SGLang

How to use eewer/Qwen3-4B-Thinking-Preservation-terminus2-sft 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 "eewer/Qwen3-4B-Thinking-Preservation-terminus2-sft" \
    --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": "eewer/Qwen3-4B-Thinking-Preservation-terminus2-sft",
		"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 "eewer/Qwen3-4B-Thinking-Preservation-terminus2-sft" \
        --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": "eewer/Qwen3-4B-Thinking-Preservation-terminus2-sft",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use eewer/Qwen3-4B-Thinking-Preservation-terminus2-sft with Docker Model Runner:
```
docker model run hf.co/eewer/Qwen3-4B-Thinking-Preservation-terminus2-sft
```

Qwen3-4B-Thinking-Preservation-terminus2-sft

eewer/Qwen3-4B-Thinking-Preservation supervised-fine-tuned for terminal-agent use in the terminus-2 format (native JSON-in-text actions; thinking preserved across multi-turn history). This is the final checkpoint of the default run (globalstep 2790; ~1 epoch over the shuffled skill-based-medium terminus-2 SFT mix; AdamW, constant LR 5e-6 after a short warmup).

Why this checkpoint

It is the best checkpoint by our reliable terminal-bench eval (terminus-2 harness, 6 informative live tasks, n=15 trials/task, temp 0.6 / top_p 0.95, 8192 out tokens, 40 turns):

checkpoint	6-task pass rate
this (default-final, s2790)	45.6%
default-s999 / s1499 / s1999	41.1% / 40.0% / 37.0%
SWA merges (full-tail / last-6)	38.9% / 37.8%
diverse run (best / latest)	35.6% / 26.6%

The raw final checkpoint beats every individual checkpoint and both stochastic-weight- averaging (SWA) merges — checkpoint merging gave no gain for this constant-LR run. Use it as a drop-in base for downstream training/eval.

Downloads last month: 24

Safetensors

Model size

4B params

Tensor type

BF16

Model tree for eewer/Qwen3-4B-Thinking-Preservation-terminus2-sft

Base model

Qwen/Qwen3-4B-Base

Finetuned

Qwen/Qwen3-4B

Finetuned

eewer/Qwen3-4B-Thinking-Preservation

Finetuned

(1)

this model