double7/vicuna-68m
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: double7/vicuna-68m
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-05-02 22:36:16 +08:00
commit 9fb1a0f077
10 changed files with 715 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

22
README.md Normal file
View File

@@ -0,0 +1,22 @@
---
license: apache-2.0
datasets:
- anon8231489123/ShareGPT_Vicuna_unfiltered
language:
- en
pipeline_tag: text-generation
---
## Model description
This is a Vicuna-like model with only 68M parameters, which is fine-tuned from [LLaMA-68m](https://huggingface.co/JackFram/llama-68m) on [ShareGPT](https://huggingface.co/datasets/anon8231489123/ShareGPT_Vicuna_unfiltered) data.
The training setup follows the [Vicuna suite](https://github.com/lm-sys/FastChat).
The model is mainly developed as a base Small Speculative Model in the [MCSD paper](https://arxiv.org/pdf/2401.06706.pdf). As a comparison, it can be better aligned to the Vicuna models than LLaMA-68m with little loss of alignment to the LLaMA models.
| Draft Model | Target Model | Alignment |
| -------------- | ------------- | --------- |
| LLaMA-68/160M | LLaMA-13/33B | 😃 |
| LLaMA-68/160M | Vicuna-13/33B | 😟 |
| Vicuna-68/160M | LLaMA-13/33B | 😃 |
| Vicuna-68/160M | Vicuna-13/33B | 😃 |