Instructions to use Aznaur/tbench-qwen-sft-v3-epoch3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Aznaur/tbench-qwen-sft-v3-epoch3 with Transformers:

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

pipe = pipeline("text-generation", model="Aznaur/tbench-qwen-sft-v3-epoch3")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Aznaur/tbench-qwen-sft-v3-epoch3")
model = AutoModelForCausalLM.from_pretrained("Aznaur/tbench-qwen-sft-v3-epoch3")
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

vLLM

How to use Aznaur/tbench-qwen-sft-v3-epoch3 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Aznaur/tbench-qwen-sft-v3-epoch3"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Aznaur/tbench-qwen-sft-v3-epoch3",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Aznaur/tbench-qwen-sft-v3-epoch3

SGLang

How to use Aznaur/tbench-qwen-sft-v3-epoch3 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 "Aznaur/tbench-qwen-sft-v3-epoch3" \
    --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": "Aznaur/tbench-qwen-sft-v3-epoch3",
		"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 "Aznaur/tbench-qwen-sft-v3-epoch3" \
        --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": "Aznaur/tbench-qwen-sft-v3-epoch3",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Aznaur/tbench-qwen-sft-v3-epoch3 with Docker Model Runner:
```
docker model run hf.co/Aznaur/tbench-qwen-sft-v3-epoch3
```

tbench-qwen-sft-v3-epoch3

Supervised fine-tune of Qwen/Qwen3-8B for terminal-agent / shell-tool-use tasks.

Checkpoint at epoch 3 of the merged-v3 training run.

Training data

1,112 trajectories combining:

Kimi-K2 thinking traces (v10) on terminal-bench tasks
seta-env synthetic data (filtered)

Inference

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("alievak/tbench-qwen-sft-v3-epoch3")
model = AutoModelForCausalLM.from_pretrained(
    "alievak/tbench-qwen-sft-v3-epoch3",
    dtype=torch.bfloat16,
    device_map="auto",
)

The model produces <think>...</think> blocks before tool calls. Use the included chat_template.jinja for proper rendering.

Notes

Architecture: Qwen3ForCausalLM (same as base Qwen/Qwen3-8B, ~8B params)
Precision: bfloat16
Behavior on general chat / instruction following inherits from base Qwen3-8B

Downloads last month: 17

Safetensors

Model size

8B params

Tensor type

BF16

Model tree for Aznaur/tbench-qwen-sft-v3-epoch3

Base model

Qwen/Qwen3-8B-Base

Finetuned

Qwen/Qwen3-8B

Finetuned

(1636)

this model