Instructions to use Kholod03/qwen2.5-14b-128LoRA-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Kholod03/qwen2.5-14b-128LoRA-4bit with Transformers:

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

pipe = pipeline("text-generation", model="Kholod03/qwen2.5-14b-128LoRA-4bit")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Kholod03/qwen2.5-14b-128LoRA-4bit")
model = AutoModelForCausalLM.from_pretrained("Kholod03/qwen2.5-14b-128LoRA-4bit", 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 Kholod03/qwen2.5-14b-128LoRA-4bit with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Kholod03/qwen2.5-14b-128LoRA-4bit"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Kholod03/qwen2.5-14b-128LoRA-4bit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Kholod03/qwen2.5-14b-128LoRA-4bit

SGLang

How to use Kholod03/qwen2.5-14b-128LoRA-4bit 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 "Kholod03/qwen2.5-14b-128LoRA-4bit" \
    --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": "Kholod03/qwen2.5-14b-128LoRA-4bit",
		"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 "Kholod03/qwen2.5-14b-128LoRA-4bit" \
        --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": "Kholod03/qwen2.5-14b-128LoRA-4bit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Kholod03/qwen2.5-14b-128LoRA-4bit with Docker Model Runner:
```
docker model run hf.co/Kholod03/qwen2.5-14b-128LoRA-4bit
```

Qwen2.5-14B Fine-tuned (4-bit Quantized)

This is a 4-bit quantized version of a fine-tuned Qwen2.5-14B model.

Model Details

Base Model: Qwen/Qwen2.5-14B-Instruct
Adapter: Kholod03/qwen2.5-14b-128finetuned128LoRA
Quantization: 4-bit (nf4) with BitsAndBytes
Size: ~8 GB (compressed from ~28 GB)

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig
import torch

# Configure 4-bit loading
bnb_config = BitsAndBytesConfig(
    load_in_4bit=True,
    bnb_4bit_quant_type="nf4",
    bnb_4bit_compute_dtype=torch.bfloat16,
)

# Load model
model = AutoModelForCausalLM.from_pretrained(
    "Kholod03/qwen2.5-14b-128LoRA-4bit",
    quantization_config=bnb_config,
    device_map="auto",
    trust_remote_code=True
)

tokenizer = AutoTokenizer.from_pretrained("Kholod03/qwen2.5-14b-128LoRA-4bit")

# Generate
prompt = "Your prompt here"
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, max_new_tokens=100)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Requirements

pip install transformers bitsandbytes accelerate

Performance

Original model: ~28 GB VRAM
Quantized model: ~8 GB VRAM
Quality: ~98% of original
Speed: Faster inference

Training Details

Method: GRPO with LoRA (rank 128)
Learning rate: 5e-06
Batch size: 8
Max steps: 250

Downloads last month: 5

Safetensors

Model size

15B params

Tensor type

F32

F16

Model tree for Kholod03/qwen2.5-14b-128LoRA-4bit

Base model

Qwen/Qwen2.5-14B

Finetuned

Qwen/Qwen2.5-14B-Instruct

Quantized

(155)

this model