---
title: QwQ-R1984-32B
canonical_url: "https://www.modelscope.cn/models/VIDraft/QwQ-R1984-32B"
md_url: "https://www.modelscope.cn/models/VIDraft/QwQ-R1984-32B.md"
repository: VIDraft/QwQ-R1984-32B
last_updated: 2025-04-11
license: apache-2.0
pipeline_tag: text-generation
tasks:
  - text-generation
model_type:
  - qwen2
architectures:
  - Qwen2ForCausalLM
base_model:
  - Qwen/QwQ-32B
base_model_relation: finetune
parameters: 32.8B
tensor_type:
  - BF16
library_name:
  - transformer
  - safetensors
  - pytorch
frameworks:
  - pytorch
language:
  - en
inference_backends:
  - "deploy_task text/emb"
  - "lmdeploy 0.9.1"
  - "lmdeploy_turbomind 0.9.1"
  - "sglang 0.5.2"
  - "vllm 0.9.2"
downloads: 373
stars: 0
tags:
  - abliterated
  - uncensored
  - SEARCH
---

# QwQ-R1984-32B

> QwQ-R1984-32B - VIDraft 在 ModelScope 开源的模型。VIDraft/QwQ-R1984-32B

VIDraft/QwQ-R1984-32B 是 ModelScope 魔搭社区上的 32.8B 参数text-generation模型，采用 apache-2.0 许可，基于 Qwen/QwQ-32B 构建，可用 deploy_task text/emb、lmdeploy 0.9.1、lmdeploy_turbomind 0.9.1 部署。

- **Repository**: VIDraft/QwQ-R1984-32B
- **License**: apache-2.0
- **Tasks**: text-generation
- **Parameters**: 32.8B
- **Base model**: Qwen/QwQ-32B
- **Inference backends**: deploy_task text/emb, lmdeploy 0.9.1, lmdeploy_turbomind 0.9.1, sglang 0.5.2, vllm 0.9.2
- **Tags**: abliterated, uncensored, SEARCH
- **Downloads**: 373
- **Stars**: 0
- **Last updated**: 2025-04-11

Source: https://www.modelscope.cn/models/VIDraft/QwQ-R1984-32B

---

# VIDraft/QwQ-R1984-32B

QwQ is the reasoning model of the Qwen series. Compared with conventional instruction-tuned models, QwQ, which is capable of thinking and reasoning, can achieve significantly enhanced performance in downstream tasks, especially hard problems. QwQ-32B is the medium-sized reasoning model, which is capable of achieving competitive performance against state-of-the-art reasoning models, e.g., DeepSeek-R1, o1-mini. QwQ-R1984-32B is an enhanced version based on QwQ-32B that incorporates additional features such as uncensored capabilities and deep research functionality. This allows for more unrestricted responses and in-depth information provision based on real-time web searches.


# This repo contains the QwQ-R1984-32B model, which has the following features:


- **Type:** Reasoning-enhanced Causal Language Model  
- **Training Stage:** Pretraining, Supervised Finetuning, Reinforcement Learning, and Uncensoring  
- **Architecture:** Transformers with RoPE, SwiGLU, RMSNorm, and Attention QKV bias  
- **Number of Parameters:** 32.5B  
- **Number of Parameters (Non-Embedding):** 31.0B  
- **Number of Layers:** 64  
- **Number of Attention Heads (GQA):** 40 for Q and 8 for KV  
- **Context Length:** 8,000 tokens  
- **Additional Features:**  
  - Deep research capabilities via web search  
  - Uncensored response generation


# Quickstart

Here provides a code snippet with apply_chat_template to show you how to load the tokenizer and model and how to generate contents.

```py

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "VIDraft/QwQ-R1984-32B"

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

prompt = "How many r's are in the word \"strawberry\""
messages = [
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)

model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=32768
)
generated_ids = [
    output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]

response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
print(response)

```