---
title: RWKV-Code-7B-world-32k
canonical_url: "https://www.modelscope.cn/models/AI-ModelScope/RWKV-Code-7B-world-32k"
md_url: "https://www.modelscope.cn/models/AI-ModelScope/RWKV-Code-7B-world-32k.md"
repository: AI-ModelScope/RWKV-Code-7B-world-32k
last_updated: 2023-10-28
license: apache-2.0
pipeline_tag: text-generation
tasks:
  - text-generation
library_name:
  - pytorch
frameworks:
  - Pytorch
downloads: 32
stars: 2
---

# RWKV-Code-7B-world-32k

> RWKV-Code-7B-world-32k - AI-ModelScope 在 ModelScope 开源的模型。RWKV world 32k model fooocus on coding ability. This model finetuned from RWKV world 7B with context 32k, focus on multi turn coding.

AI-ModelScope/RWKV-Code-7B-world-32k 是 ModelScope 魔搭社区上的text-generation模型，采用 apache-2.0 许可。

- **Repository**: AI-ModelScope/RWKV-Code-7B-world-32k
- **License**: apache-2.0
- **Tasks**: text-generation
- **Downloads**: 32
- **Stars**: 2
- **Last updated**: 2023-10-28

Source: https://www.modelscope.cn/models/AI-ModelScope/RWKV-Code-7B-world-32k

---

# RWKV world 32k model fooocus on coding ability.
This model finetuned from RWKV world 7B  with context 32k, focus on multi turn coding.

# Trainning details
4*A800 27hours with 1B tokens
![image.png](https://cdn-uploads.huggingface.co/production/uploads/6176b32847ee6431f632981e/Tot0WkvPvwkyyWy_4-E3-.png)


# datasets
mainly tiny codes and add a lots of long context multi turn datasets. 
only finetuend in User: xxx\n\nAssistant: xxx\n format

# Showcases
![09713ffd8b5c21a525065a50964dd5f.jpg](https://cdn-uploads.huggingface.co/production/uploads/6176b32847ee6431f632981e/_pmGc7y1j2a5i_GCWuq7D.jpeg)

# other
if using RWKV runner to run this model, need to wait for updates in chat mode, as default chat using Question: xxx\n\nAnswer: xxx and have a default system prompt so far.

completions mode is more suitable for this model

# How

easiest way to use this model by using RWKV runner  https://github.com/josStorer/RWKV-Runner, now RWKV runner support AMD GPUs in config webGPU

or you can use https://github.com/cgisky1980/ai00_rwkv_server as well

BTW, runner support  GPT-format like API