初始化项目,由ModelHub XC社区提供模型
Model: chimbiwide/Qwen3-Go Source: Original Platform
This commit is contained in:
29
README.md
Normal file
29
README.md
Normal file
@@ -0,0 +1,29 @@
|
||||
---
|
||||
base_model: unsloth/qwen3-4b-base-unsloth-bnb-4bit
|
||||
tags:
|
||||
- text-generation-inference
|
||||
- transformers
|
||||
- unsloth
|
||||
- qwen3
|
||||
license: apache-2.0
|
||||
language:
|
||||
- en
|
||||
datasets:
|
||||
- ajibawa-2023/Go-Code-Large
|
||||
---
|
||||
|
||||
# Qwen3-Go
|
||||
|
||||
An attempt at local finetuning using a 5070 TI.
|
||||
|
||||
---
|
||||
|
||||
Qwen3-Go is a model finetuned using the [G0-Code-Large](https://huggingface.co/datasets/ajibawa-2023/Go-Code-Large) dataset for Go code completion.
|
||||
|
||||
This is a purely experimental model.
|
||||
|
||||
---
|
||||
|
||||
### Training Parameters
|
||||
|
||||
This model is trained locally on a 5070Ti using Unsloth loading in 4bits. With a batch size of 8 and 1 epoch. The training took 19 hours.
|
||||
Reference in New Issue
Block a user