Instructions to use uchkw/qwen2.5-7b-instruct-sft-v5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use uchkw/qwen2.5-7b-instruct-sft-v5 with Transformers:

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

pipe = pipeline("text-generation", model="uchkw/qwen2.5-7b-instruct-sft-v5")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("uchkw/qwen2.5-7b-instruct-sft-v5")
model = AutoModelForCausalLM.from_pretrained("uchkw/qwen2.5-7b-instruct-sft-v5", 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 uchkw/qwen2.5-7b-instruct-sft-v5 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "uchkw/qwen2.5-7b-instruct-sft-v5"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "uchkw/qwen2.5-7b-instruct-sft-v5",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/uchkw/qwen2.5-7b-instruct-sft-v5

SGLang

How to use uchkw/qwen2.5-7b-instruct-sft-v5 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 "uchkw/qwen2.5-7b-instruct-sft-v5" \
    --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": "uchkw/qwen2.5-7b-instruct-sft-v5",
		"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 "uchkw/qwen2.5-7b-instruct-sft-v5" \
        --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": "uchkw/qwen2.5-7b-instruct-sft-v5",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use uchkw/qwen2.5-7b-instruct-sft-v5 with Docker Model Runner:
```
docker model run hf.co/uchkw/qwen2.5-7b-instruct-sft-v5
```

qwen2.5-7b-instruct-sft-v5 / README.md

uchkw

Upload advanced model package

a27047a verified 7 months ago

preview code

Raw

History Blame Contribute Delete

2.98 kB

	---
	base_model: Qwen/Qwen2.5-7B-Instruct
	datasets:
	- u-10bei/sft_alfworld_trajectory_dataset_v5
	- u-10bei/dbbench_sft_dataset_react_v4
	- u-10bei/dbbench_sft_dataset_react_v3
	language:
	- en
	license: apache-2.0
	library_name: transformers
	pipeline_tag: text-generation
	tags:
	- agentbench
	- merged-model
	- alfworld
	- dbbench
	- strict-action-copy
	- unknown-column-recovery
	- continual-sft
	---

	# qwen2.5-7b-instruct-sft-v5

	This repository provides a merged full model produced by supervised fine-tuning for AgentBench-oriented ALFWorld/DBBench robustness.

	## Training Objective

	Improve strict action selection reliability for ALFWorld prompts and strengthen SQL error-recovery robustness for DBBench prompts, while keeping balanced mixed-task behavior.

	## Training Configuration

	- Method: SFT (Unsloth LoRA) + merge to full model
	- Base model ID (upstream): `Qwen/Qwen2.5-7B-Instruct`
	- Initialization model for this stage: prior merged checkpoint from the previous advanced retraining stage
	- LoRA: `r=16`, `alpha=32`, `dropout=0.0`
	- LoRA target modules: `q_proj,k_proj,v_proj,o_proj,gate_proj,up_proj,down_proj`
	- Output learn mode: `from_marker` (`ACTION:` and `Action:` markers)
	- Max sequence length: `4096`
	- Max steps: `400`
	- Epochs: `1`
	- Learning rate: `2.0e-6`
	- Per-device train batch size: `1`
	- Per-device eval batch size: `2`
	- Gradient accumulation steps: `32`
	- Effective global batch size: `32`
	- Warmup ratio: `0.03`
	- Weight decay: `0.01`
	- Eval/Save steps: `50 / 25`

	## Usage

	```python
	from transformers import AutoModelForCausalLM, AutoTokenizer

	model_id = "uchkw/qwen2.5-7b-instruct-sft-v5"
	tokenizer = AutoTokenizer.from_pretrained(model_id)
	model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto")
	```

	## Training Data / Sources & License (IMPORTANT)

	- Primary source datasets:
	- `u-10bei/sft_alfworld_trajectory_dataset_v5`
	- `u-10bei/dbbench_sft_dataset_react_v4`
	- `u-10bei/dbbench_sft_dataset_react_v3`
	- Data construction policy (concise):
	- ALFWorld samples were converted into strict one-line action supervision (`ACTION: ...`) with exact matching against `AVAILABLE ACTIONS`.
	- Added hard-copy style ALF augmentation to reinforce exact action copying and reduce formatting drift.
	- Mixed DBBench supervision and recovery-oriented examples for `Unknown column` style failures.
	- Mixed train ratio was controlled at approximately `ALF:DB = 55:45`.
	- Dataset scale (fix8 stage2):
	- Train samples: `138496`
	- Validation samples: `7289`
	- Train ALF rows: `76173`
	- Train DB rows: `62323`
	- ALF strict-match in training set: `1.0`
	- ALF completion-verb ratio: `0.4726`
	- ALF toggle rows: `1772`
	- Evaluation snapshot (checkpoint-50, official_v02 setting):
	- DB overall_cat_accuracy: `0.5180407064`
	- ALF success_rate: `0.62`
	- ALF invalid_action_rate: `0.14`
	- ALF task_limit_rate: `0.24`
	- Compliance:
	- Follow each source dataset card and license terms.
	- Follow base model terms of use.