---
title: MindChat-Qwen-7B
canonical_url: "https://www.modelscope.cn/models/X-D-Lab/MindChat-Qwen-7B"
md_url: "https://www.modelscope.cn/models/X-D-Lab/MindChat-Qwen-7B.md"
repository: X-D-Lab/MindChat-Qwen-7B
last_updated: 2024-08-14
license: other
pipeline_tag: text-generation
tasks:
  - text-generation
model_type:
  - qwen
architectures:
  - QWenLMHeadModel
parameters: 7.7B
tensor_type:
  - BF16
library_name:
  - safetensors
  - pytorch
frameworks:
  - pytorch
inference_backends:
  - "deploy_task text/emb"
  - "lmdeploy 0.9.1"
  - "lmdeploy_turbomind 0.9.1"
  - "sglang 0.5.2"
  - "vllm 0.9.2"
downloads: 272135
stars: 16
tags:
  - llama-factory
  - generated_from_trainer
---

# MindChat-Qwen-7B

> MindChat-Qwen-7B - X-D-Lab 在 ModelScope 开源的模型。MindChat-Qwen-7B-Full-0220

X-D-Lab/MindChat-Qwen-7B 是 ModelScope 魔搭社区上的 7.7B 参数text-generation模型，采用 other 许可，可用 deploy_task text/emb、lmdeploy 0.9.1、lmdeploy_turbomind 0.9.1 部署。

- **Repository**: X-D-Lab/MindChat-Qwen-7B
- **License**: other
- **Tasks**: text-generation
- **Parameters**: 7.7B
- **Inference backends**: deploy_task text/emb, lmdeploy 0.9.1, lmdeploy_turbomind 0.9.1, sglang 0.5.2, vllm 0.9.2
- **Tags**: llama-factory, generated_from_trainer
- **Downloads**: 272135
- **Stars**: 16
- **Last updated**: 2024-08-14

Source: https://www.modelscope.cn/models/X-D-Lab/MindChat-Qwen-7B

---

<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->

# MindChat-Qwen-7B-Full-0220

This model is a fine-tuned version of [/workspace/qwen/Qwen-7B](https://huggingface.co//workspace/qwen/Qwen-7B) on the MOSS, the safety, the MindChat_1, the self_cognition_mindchat and the self-cognition-instuctions datasets.

## Model description

More information needed

## Intended uses & limitations

More information needed

## Training and evaluation data

More information needed

## Training procedure

### Training hyperparameters

The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 4
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 7
- gradient_accumulation_steps: 16
- total_train_batch_size: 448
- total_eval_batch_size: 56
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- num_epochs: 1.0

### Training results



### Framework versions

- Transformers 4.37.2
- Pytorch 2.1.0
- Datasets 2.16.1
- Tokenizers 0.15.0