README.md

---
library_name: transformers
license: apache-2.0
pipeline_tag: text-generation
base_model:
- Qwen/Qwen2.5-Coder-3B-Instruct
tags:
- llmcompressor
- quantized
- FP8
---

# Qwen2.5-Coder-3B-Instruct-FP8-dynamic

## Model Overview
- **Model Architecture:** Qwen2ForCausalLM
  - **Input:** Text
  - **Output:** Text
- **Model Optimizations:**
  - **Activation quantization:** FP8
  - **Weight quantization:** FP8
- **Release Date:** 09/06/2025
- **Version:** 1.0
- **Model Developers:** duydq12 (enhance by RedHatAI)

### Model Optimizations

This model was obtained by quantizing activations and weights of [Qwen2.5-Coder-3B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-3B-Instruct) to FP8 data type.
This optimization reduces the number of bits used to represent weights and activations from 16 to 8, reducing GPU memory requirements (by approximately 50%) and increasing matrix-multiply compute throughput (by approximately 2x).
Weight quantization also reduces disk size requirements by approximately 50%.

Only weights and activations of the linear operators within transformers blocks are quantized.
Weights are quantized with a symmetric static per-channel scheme, whereas activations are quantized with a symmetric dynamic per-token scheme.
The [llm-compressor](https://github.com/vllm-project/llm-compressor) library is used for quantization.


## Deployment

This model can be deployed efficiently using the [vLLM](https://docs.vllm.ai/en/latest/) backend, as shown in the example below.

```python
from vllm import LLM, SamplingParams
from transformers import AutoTokenizer

model_id = "duydq12/Qwen2.5-Coder-3B-Instruct-FP8-dynamic"
number_gpus = 1
sampling_params = SamplingParams(temperature=0.6, top_p=0.95, top_k=20, min_p=0, max_tokens=256)

messages = [
    {"role": "user", "content": prompt}
]

tokenizer = AutoTokenizer.from_pretrained(model_id)

messages = [{"role": "user", "content": "Give me a short introduction to large language model."}]

prompts = tokenizer.apply_chat_template(messages, add_generation_prompt=True, tokenize=False)

llm = LLM(model=model_id, tensor_parallel_size=number_gpus)

outputs = llm.generate(prompts, sampling_params)

generated_text = outputs[0].outputs[0].text
print(generated_text)
```

vLLM aslo supports OpenAI-compatible serving. See the [documentation](https://docs.vllm.ai/en/latest/) for more details.

## Creation

<details>
  <summary>Creation details</summary>
  This model was created with [llm-compressor](https://github.com/vllm-project/llm-compressor) by running the code snippet below. 


  ```python
from llmcompressor.modifiers.quantization import QuantizationModifier
from llmcompressor.transformers import oneshot
from transformers import AutoModelForCausalLM, AutoTokenizer

# Load model
model_stub = "Qwen/Qwen2.5-Coder-3B-Instruct"
model_name = model_stub.split("/")[-1]

model = AutoModelForCausalLM.from_pretrained(model_stub, torch_dtype="auto", device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_stub, torch_dtype="auto", device_map="auto")

# Configure the quantization algorithm and scheme
recipe = QuantizationModifier(
    ignore=["lm_head"],
    targets="Linear",
    scheme="FP8_dynamic",
)

# Apply quantization
oneshot(
    model=model,
    recipe=recipe,
)

# Save to disk in compressed-tensors format
save_path = model_name + "-FP8-dynamic"
model.save_pretrained(save_path)
tokenizer.save_pretrained(save_path)
print(f"Model and tokenizer saved to: {save_path}")
  ```
</details>
 


## Evaluation
private

### Accuracy
private