Instructions to use 6cf/qwen35-9b-deepseek-v4-pro-agent-lora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use 6cf/qwen35-9b-deepseek-v4-pro-agent-lora with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3.5-9B")
model = PeftModel.from_pretrained(base_model, "6cf/qwen35-9b-deepseek-v4-pro-agent-lora")

Transformers

How to use 6cf/qwen35-9b-deepseek-v4-pro-agent-lora with Transformers:

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

pipe = pipeline("text-generation", model="6cf/qwen35-9b-deepseek-v4-pro-agent-lora")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("6cf/qwen35-9b-deepseek-v4-pro-agent-lora", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use 6cf/qwen35-9b-deepseek-v4-pro-agent-lora with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "6cf/qwen35-9b-deepseek-v4-pro-agent-lora"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "6cf/qwen35-9b-deepseek-v4-pro-agent-lora",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/6cf/qwen35-9b-deepseek-v4-pro-agent-lora

SGLang

How to use 6cf/qwen35-9b-deepseek-v4-pro-agent-lora 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 "6cf/qwen35-9b-deepseek-v4-pro-agent-lora" \
    --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": "6cf/qwen35-9b-deepseek-v4-pro-agent-lora",
		"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 "6cf/qwen35-9b-deepseek-v4-pro-agent-lora" \
        --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": "6cf/qwen35-9b-deepseek-v4-pro-agent-lora",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use 6cf/qwen35-9b-deepseek-v4-pro-agent-lora with Docker Model Runner:
```
docker model run hf.co/6cf/qwen35-9b-deepseek-v4-pro-agent-lora
```

Qwen3.5-9B DeepSeek-v4-Pro-Agent LoRA

This repository contains a LoRA adapter for Qwen/Qwen3.5-9B, fine-tuned on the agent-trace dataset TeichAI/DeepSeek-v4-Pro-Agent.

The adapter is intended for experimental coding-agent / terminal-agent research. It is not a general-purpose instruction model release.

Training Data

Dataset: TeichAI/DeepSeek-v4-Pro-Agent
Raw traces read by the local preparation pipeline: 3,999
Usable training examples after tool-format and 8,192-token filtering: 66
Max prepared sequence length: 8,123 tokens

The dataset is linked in the card metadata so it appears on the Hugging Face model page and credits the dataset authors.

Training Setup

Base model: Qwen/Qwen3.5-9B
Method: LoRA SFT with PEFT
Training stack: Transformers + Accelerate + DeepSpeed ZeRO-2
Hardware: 2 x RTX A6000
Epochs: 2
Max sequence length: 8,192
Effective batch size: 16
Learning rate: 1e-4
Precision: bf16
LoRA rank: 32
LoRA alpha: 64
LoRA dropout: 0.05
Trainable parameters: 64,487,424 / 9,474,301,168 (0.681%)
Final training loss: 0.7229
Training runtime: 804 seconds

Evaluation Results

Evaluation uses Harbor / Terminal-Bench 2.0 with the little-coder agent scaffold. Terminal-Bench rewards are binary per trial; leaderboard-style scores are mean reward over trials.

Full Terminal-Bench 2.0

Full k=5 evaluation on Terminal-Bench 2.0 (89 tasks x 5 attempts = 445 trials) completed on 2026-07-04. The comparison is against the same base model, agent scaffold, Harbor setup, Docker/proxy environment, and serving path.

Model	Trials	Mean reward	pass@5	Passed tasks
Base `Qwen/Qwen3.5-9B`	445	0.04045	0.06742	6 / 89
This LoRA adapter	445	0.04494	0.08989	8 / 89

Absolute delta vs base:

Mean reward: +0.00449
pass@5: +0.02247
Passed tasks: +2

Tasks passed by this adapter in the full k=5 run:

fix-git, git-leak-recovery, log-summary-date-ranges, modernize-scientific-stack, nginx-request-logging, openssl-selfsigned-cert, query-optimize, sqlite-with-gcov

The full-run result artifact is:

results/harbor/little_coder_leaderboard_k5_comparison_20260630-0930.json

Diagnostic Subset

This earlier subset contains five Terminal-Bench 2.0 tasks selected from tasks passed at least once by a public Qwen3.5 little-coder submission. It is retained only as a sanity check for the evaluation circuit, not as the primary result.

Model	Tasks	Attempts	Mean reward	Passed tasks
Base `Qwen/Qwen3.5-9B`	5	1 each	0.20	`git-leak-recovery`
This LoRA adapter	5	1 each	0.40	`git-leak-recovery`, `portfolio-optimization`

Limitations

The training set is small after filtering (66 examples), so this adapter should be treated as an experimental trace-SFT artifact.
Results depend strongly on the agent scaffold, prompting, Docker environment, and model-serving compatibility.

Usage

This is a PEFT LoRA adapter. Load it with the base model:

from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel

base = "Qwen/Qwen3.5-9B"
adapter = "6cf/qwen35-9b-deepseek-v4-pro-agent-lora"

tokenizer = AutoTokenizer.from_pretrained(base, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(
    base,
    torch_dtype="auto",
    device_map="auto",
    trust_remote_code=True,
)
model = PeftModel.from_pretrained(model, adapter)

Downloads last month: 33

Model tree for 6cf/qwen35-9b-deepseek-v4-pro-agent-lora

Base model

Qwen/Qwen3.5-9B-Base

Finetuned

Qwen/Qwen3.5-9B

Adapter

(468)

this model

6cf
/

qwen35-9b-deepseek-v4-pro-agent-lora