Instructions to use derogab/Sherlock-4B-QLoRA with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use derogab/Sherlock-4B-QLoRA with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3-4B-Instruct-2507")
model = PeftModel.from_pretrained(base_model, "derogab/Sherlock-4B-QLoRA")

Transformers

How to use derogab/Sherlock-4B-QLoRA with Transformers:

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

pipe = pipeline("text-generation", model="derogab/Sherlock-4B-QLoRA")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("derogab/Sherlock-4B-QLoRA", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use derogab/Sherlock-4B-QLoRA with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "derogab/Sherlock-4B-QLoRA"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "derogab/Sherlock-4B-QLoRA",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/derogab/Sherlock-4B-QLoRA

SGLang

How to use derogab/Sherlock-4B-QLoRA 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 "derogab/Sherlock-4B-QLoRA" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "derogab/Sherlock-4B-QLoRA",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "derogab/Sherlock-4B-QLoRA" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "derogab/Sherlock-4B-QLoRA",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use derogab/Sherlock-4B-QLoRA with Docker Model Runner:
```
docker model run hf.co/derogab/Sherlock-4B-QLoRA
```

Sherlock-4B-QLoRA

Work in progress: This adapter is still under active development.

QLoRA adapter for structured information extraction: (JSON schema + text) → JSON. Missing fields become null; unrelated text is ignored.

Base model: Qwen/Qwen3-4B-Instruct-2507
Training dataset: derogab/Sherlock-Case-Files
Method: NF4 QLoRA (rank 16, alpha 32, dropout 0.05)
Task: text-generation

Usage

from peft import PeftModel
from transformers import AutoModelForCausalLM, AutoTokenizer

base = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3-4B-Instruct-2507")
model = PeftModel.from_pretrained(base, "derogab/Sherlock-4B-QLoRA")
tokenizer = AutoTokenizer.from_pretrained("derogab/Sherlock-4B-QLoRA")

Benchmark

Sherlock is evaluated against the base model on structured extraction quality. Rates are percentages; Δ is in percentage points (higher is better). The 95% CI of Δ is a Newcombe score interval from the aggregate counts.

Metric	Base	Sherlock	Δ (Sherlock − Base)
Valid JSON	100.0%	100.0%	+0.0 pp
Schema conformance	100.0%	100.0%	+0.0 pp
Field accuracy	95.2%	99.1%	+3.9 pp
Exact match	78.0%	94.0%	+16.0 pp

Downloads last month: 42

Model tree for derogab/Sherlock-4B-QLoRA

Base model

Qwen/Qwen3-4B-Instruct-2507

Adapter

(5734)

this model