---
license: mit
language:
- en
pipeline_tag: text-generation
base_model:
- deepseek-ai/DeepSeek-R1-Distill-Qwen-32B
tags:
- chat
library_name: transformers
---

# Model Overview

- **Model Optimizations:**
  - **Weight quantization:** FP8
  - **Activation quantization:** FP8
- **Release Date:** 1/28/2025

Quantized version of [deepseek-ai/DeepSeek-R1-Distill-Qwen-32B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B/) to FP8 data type, ready for inference with SGLang >= 0.3 or vLLM >= 0.5.2.
This optimization reduces the number of bits per parameter from 16 to 8, reducing the disk size and GPU memory requirements by approximately 50%. Only the weights and activations of the linear operators within transformers blocks are quantized. 

## Deployment

### Use with SGLang

```bash
python -m sglang.launch_server --model-path JamAndTeaStudios/DeepSeek-R1-Distill-Qwen-32B-FP8-Dynamic \
--port 30000 --host 0.0.0.0
```

## Creation

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

<details>
<summary>Model Creation Code</summary>

```python
from transformers import AutoModelForCausalLM, AutoTokenizer

from llmcompressor.modifiers.quantization import QuantizationModifier
from llmcompressor.transformers import oneshot

MODEL_ID = "google/gemma-2-27b-it"

# 1) Load model.
model = AutoModelForCausalLM.from_pretrained(
    MODEL_ID, device_map="auto", torch_dtype="auto"
)
tokenizer = AutoTokenizer.from_pretrained(MODEL_ID)

# 2) Configure the quantization algorithm and scheme.
# In this case, we:
#   * quantize the weights to fp8 with per channel via ptq
#   * quantize the activations to fp8 with dynamic per token
recipe = QuantizationModifier(
    targets="Linear", scheme="FP8_DYNAMIC", ignore=["lm_head"]
)

# 3) Apply quantization and save in compressed-tensors format.
OUTPUT_DIR = MODEL_ID.split("/")[1] + "-FP8-Dynamic"
oneshot(
    model=model,
    recipe=recipe,
    tokenizer=tokenizer,
    output_dir=OUTPUT_DIR,
)

# Confirm generations of the quantized model look sane.
print("========== SAMPLE GENERATION ==============")
input_ids = tokenizer("Hello my name is", return_tensors="pt").input_ids.to("cuda")
output = model.generate(input_ids, max_new_tokens=20)
print(tokenizer.decode(output[0]))
print("==========================================")
```
</details>

## Evaluation

TBA

## Play Retail Mage

![image/png](https://cdn-uploads.huggingface.co/production/uploads/64f908994110f1806f2c356a/vsWXpQqgHIqN4f4BM-RfS.png)

[Retail Mage (Steam)](https://store.steampowered.com/app/3224380/Retail_Mage/) is an immersive sim that uses online LLM inference in almost all features in the gameplay! 

Reviews

“A true to life experience detailing how customer service really works.”
10/10 – kpolupo

“I enjoyed how many things were flammable in the store.”
5/5 – mr_srsbsns

“I've only known that talking little crow plushie in MageMart for a day and a half but if anything happened to him I would petrify everyone in this store and then myself.”
7/7 – neondenki