Instructions to use Saravanankannan/Qwen-2.5-32B-RAFT-Finance-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Saravanankannan/Qwen-2.5-32B-RAFT-Finance-v1 with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-32B-Instruct")
model = PeftModel.from_pretrained(base_model, "Saravanankannan/Qwen-2.5-32B-RAFT-Finance-v1")

Transformers

How to use Saravanankannan/Qwen-2.5-32B-RAFT-Finance-v1 with Transformers:

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

pipe = pipeline("text-generation", model="Saravanankannan/Qwen-2.5-32B-RAFT-Finance-v1")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("Saravanankannan/Qwen-2.5-32B-RAFT-Finance-v1", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Saravanankannan/Qwen-2.5-32B-RAFT-Finance-v1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Saravanankannan/Qwen-2.5-32B-RAFT-Finance-v1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Saravanankannan/Qwen-2.5-32B-RAFT-Finance-v1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Saravanankannan/Qwen-2.5-32B-RAFT-Finance-v1

SGLang

How to use Saravanankannan/Qwen-2.5-32B-RAFT-Finance-v1 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 "Saravanankannan/Qwen-2.5-32B-RAFT-Finance-v1" \
    --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": "Saravanankannan/Qwen-2.5-32B-RAFT-Finance-v1",
		"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 "Saravanankannan/Qwen-2.5-32B-RAFT-Finance-v1" \
        --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": "Saravanankannan/Qwen-2.5-32B-RAFT-Finance-v1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Saravanankannan/Qwen-2.5-32B-RAFT-Finance-v1 with Docker Model Runner:
```
docker model run hf.co/Saravanankannan/Qwen-2.5-32B-RAFT-Finance-v1
```

Qwen-2.5-32B-RAFT-Finance-v1 / ReadMe

Saravanankannan

Create ReadMe

acd7b65 verified 8 months ago

Raw

History Blame Contribute Delete

3.48 kB

	---
	base_model: Qwen/Qwen2.5-32B-Instruct
	library_name: peft
	pipeline_tag: text-generation
	license: apache-2.0
	language:
	- en
	tags:
	- base_model:adapter:Qwen/Qwen2.5-32B-Instruct
	- lora
	- qlora
	- sft
	- raft
	- finance
	- rag
	- transformers
	- trl
	---

	# Model Card for UnifiedQ-Finance-RAFT

	UnifiedQ-Finance-RAFT is a specialized LoRA adapter for Qwen 2.5 32B Instruct, fine-tuned using the RAFT (Retrieval-Augmented Fine-Tuning) technique. It is designed to act as the reasoning engine for a quantitative finance RAG pipeline, specifically capable of distinguishing between relevant "oracle" documents and irrelevant "distractor" documents in complex options trading contexts.

	## Model Details

	### Model Description

	This model was trained to solve the "distractor problem" in RAG systems. Standard models often get confused when a retrieval system pulls in irrelevant documents alongside the correct ones. By using the RAFT methodology, this model was explicitly trained on a dataset where it had to ignore noise and reason only from the relevant text chunks to answer complex financial queries.

	- Developed by: Rednote (UnifiedQ Project)
	- Model type: LoRA Adapter (QLoRA 4-bit) for Causal LM
	- Language(s): English
	- License: Apache 2.0 (Inherited from Qwen 2.5)
	- Finetuned from model: [Qwen/Qwen2.5-32B-Instruct](https://huggingface.co/Qwen/Qwen2.5-32B-Instruct)

	### Model Sources

	- Repository: [More Information Needed - Link to your repo]
	- Technique Paper: [RAFT: Adapting Language Model to Domain Specific RAG](https://arxiv.org/abs/2403.10131)

	## Uses

	### Direct Use

	This model is intended to be used with a RAG system (Retrieval-Augmented Generation). It expects a prompt format that includes retrieved context documents (some relevant, some irrelevant) and a user question. It excels at:
	- Options trading strategies evaluation.
	- Risk management analysis.
	- Filtering noise from retrieved financial documents.

	### Out-of-Scope Use

	- General chat without context (it is specialized for document-based reasoning).
	- Financial advice (this is a research/development tool, not a financial advisor).

	## How to Get Started with the Model

	You can load this model using `peft` and `transformers`. Note that you must load the base model in 4-bit if running on consumer hardware.

	```python
	import torch
	from peft import PeftModel
	from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig

	# 1. Load Base Model (Qwen 2.5 32B)
	base_model_id = "Qwen/Qwen2.5-32B-Instruct"
	adapter_model_id = "Rednote/Qwen-2.5-32B-RAFT-UnifiedQ" # Replace with your actual HF path

	bnb_config = BitsAndBytesConfig(
	load_in_4bit=True,
	bnb_4bit_quant_type="nf4",
	bnb_4bit_compute_dtype=torch.bfloat16,
	bnb_4bit_use_double_quant=True
	)

	base_model = AutoModelForCausalLM.from_pretrained(
	base_model_id,
	quantization_config=bnb_config,
	device_map="auto",
	trust_remote_code=True,
	attn_implementation="flash_attention_2" # Optional: remove if no Flash Attn
	)

	# 2. Load the RAFT Adapter
	model = PeftModel.from_pretrained(base_model, adapter_model_id)
	tokenizer = AutoTokenizer.from_pretrained(base_model_id, trust_remote_code=True)

	# 3. Inference Example
	prompt = "Context: [Doc 1]... [Doc 2]... \n\n Question: How do I hedge delta risk?"
	inputs = tokenizer(prompt, return_tensors="pt").to("cuda")
	outputs = model.generate(**inputs, max_new_tokens=200)
	print(tokenizer.decode(outputs[0]))