Instructions to use TorresCoding/fin-qwen-lora-v2-hard with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TorresCoding/fin-qwen-lora-v2-hard with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("unsloth/Qwen3-8B-unsloth-bnb-4bit")
model = PeftModel.from_pretrained(base_model, "TorresCoding/fin-qwen-lora-v2-hard")

Transformers

How to use TorresCoding/fin-qwen-lora-v2-hard with Transformers:

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

pipe = pipeline("text-generation", model="TorresCoding/fin-qwen-lora-v2-hard")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("TorresCoding/fin-qwen-lora-v2-hard", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use TorresCoding/fin-qwen-lora-v2-hard with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "TorresCoding/fin-qwen-lora-v2-hard"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "TorresCoding/fin-qwen-lora-v2-hard",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/TorresCoding/fin-qwen-lora-v2-hard

SGLang

How to use TorresCoding/fin-qwen-lora-v2-hard 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 "TorresCoding/fin-qwen-lora-v2-hard" \
    --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": "TorresCoding/fin-qwen-lora-v2-hard",
		"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 "TorresCoding/fin-qwen-lora-v2-hard" \
        --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": "TorresCoding/fin-qwen-lora-v2-hard",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Studio

How to use TorresCoding/fin-qwen-lora-v2-hard with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for TorresCoding/fin-qwen-lora-v2-hard to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for TorresCoding/fin-qwen-lora-v2-hard to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for TorresCoding/fin-qwen-lora-v2-hard to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="TorresCoding/fin-qwen-lora-v2-hard",
    max_seq_length=2048,
)

Docker Model Runner
How to use TorresCoding/fin-qwen-lora-v2-hard with Docker Model Runner:
```
docker model run hf.co/TorresCoding/fin-qwen-lora-v2-hard
```

Fin-Qwen LoRA V2 Hard

This repository contains the V2 hard-data continued LoRA adapter for Fin-Qwen, a Qwen3-8B financial social-media sentiment model.

The adapter was continued from the V1 LoRA model using reviewed hard distillation data focused on sarcasm, dilution, rug/scam risk, leverage/liquidation, mixed financial facts, and ticker ambiguity.

Base Model

Base: unsloth/Qwen3-8B-unsloth-bnb-4bit
Adapter type: PEFT LoRA / QLoRA
Training framework: Unsloth + TRL SFTTrainer

Intended Output Schema

The adapter is intended to generate JSON with:

{
  "sentiment_score": 3,
  "reasoning": "short financial explanation",
  "tickers": ["AAPL"],
  "risk_flag": false
}

risk_flag means the comment contains a separate risk-warning signal in the text; it is not a judgment of the company's real-world risk.

Evaluation Snapshot

Teacher labels are generated by DeepSeek V3.2, not human gold labels.

Eval set	Base + schema F1	Fin-Qwen V2 F1	Base MAE	Fin-Qwen V2 MAE
Clean eval, 200 examples	0.8220	0.8840	0.3850	0.2650
Hard eval, 385 examples	0.7382	0.8528	0.5325	0.3247

Notes

This is an adapter-only repository. Load it with the base Qwen3-8B model through PEFT/Unsloth. The full project code and data pipeline are tracked separately in the GitHub repository.

Downloads last month: 21

Model tree for TorresCoding/fin-qwen-lora-v2-hard

Base model

Qwen/Qwen3-8B-Base

Finetuned

Qwen/Qwen3-8B

Quantized

unsloth/Qwen3-8B-unsloth-bnb-4bit

Adapter

(78)

this model