Instructions to use Yano/exp-0216-005-db-balanced-qwen2.5-7b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Yano/exp-0216-005-db-balanced-qwen2.5-7b with Transformers:

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

pipe = pipeline("text-generation", model="Yano/exp-0216-005-db-balanced-qwen2.5-7b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("Yano/exp-0216-005-db-balanced-qwen2.5-7b")
model = AutoModelForMultimodalLM.from_pretrained("Yano/exp-0216-005-db-balanced-qwen2.5-7b")
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 Yano/exp-0216-005-db-balanced-qwen2.5-7b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Yano/exp-0216-005-db-balanced-qwen2.5-7b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Yano/exp-0216-005-db-balanced-qwen2.5-7b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Yano/exp-0216-005-db-balanced-qwen2.5-7b

SGLang

How to use Yano/exp-0216-005-db-balanced-qwen2.5-7b 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 "Yano/exp-0216-005-db-balanced-qwen2.5-7b" \
    --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": "Yano/exp-0216-005-db-balanced-qwen2.5-7b",
		"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 "Yano/exp-0216-005-db-balanced-qwen2.5-7b" \
        --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": "Yano/exp-0216-005-db-balanced-qwen2.5-7b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Yano/exp-0216-005-db-balanced-qwen2.5-7b with Docker Model Runner:
```
docker model run hf.co/Yano/exp-0216-005-db-balanced-qwen2.5-7b
```

Yano commited on Feb 16

Commit

f684a16

verified ·

1 Parent(s): 30c435c

Update README.md

Browse files

Files changed (1) hide show

README.md +39 -12

README.md CHANGED Viewed

@@ -1,21 +1,48 @@
 ---
 base_model: Yano/exp-0212-001-alfworld-qwen2.5-7b
-tags:
-- text-generation-inference
-- transformers
-- unsloth
-- qwen2
-license: apache-2.0
 language:
 - en
 ---
-# Uploaded finetuned  model
-- **Developed by:** Yano
-- **License:** apache-2.0
-- **Finetuned from model :** Yano/exp-0212-001-alfworld-qwen2.5-7b
-This qwen2 model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
-[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)

 ---
 base_model: Yano/exp-0212-001-alfworld-qwen2.5-7b
+datasets:
+- u-10bei/dbbench_sft_dataset_react
+- u-10bei/dbbench_sft_dataset_react_v2
+- u-10bei/dbbench_sft_dataset_react_v3
+- u-10bei/dbbench_sft_dataset_react_v4
 language:
 - en
+license: apache-2.0
+library_name: transformers
+pipeline_tag: text-generation
+tags:
+- qlora
+- lora
+- merged
+- dbbench
+- alfworld
+- agent
 ---
+# exp-0216-005-db-balanced-qwen2.5-7b
+Fine-tuned from **Yano/exp-0212-001-alfworld-qwen2.5-7b** (001 ALFWorld SFT model) using **QLoRA (4-bit, Unsloth)**.
+## Purpose
+DB Bench training with balanced data (v1-v4 mixed, INSERT/UPDATE downsampled).
+Addresses 004's SELECT degradation (76.5% -> 41.0%) caused by INSERT/UPDATE data imbalance.
+## Data Strategy
+- Combined all DB Bench v1-v4 (3,060 total)
+- Downsampled INSERT to 200, UPDATE to 150
+- Kept all SELECT/query-type samples
+- Final dataset: ~1470 samples (INSERT+UPDATE ~24.5%)
+## Training Configuration
+- Base model: Yano/exp-0212-001-alfworld-qwen2.5-7b
+- Method: QLoRA (4-bit), merged to 16-bit
+- Max sequence length: 2048
+- Epochs: 3
+- Learning rate: 2e-05
+- LoRA: r=64, alpha=128
+- Batch size: 2 (grad accum 16)
+- Warmup ratio: 0.1
+- Collator: AllAssistantTurnsCollator (all turns supervised)