Downloads · 30 days
229
0% of all-time downloads
Qwen-LLaMAfied-HFTok-7B-Chat
vonjack/Qwen-LLaMAfied-HFTok-7B-Chat
Qwen-LLaMAfied-HFTok-7B-Chat is a text generation model from vonjack. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as apache-2.0.
All-time downloads
55.5K
Public
Repo size
30.9 GB
Likes
24
Public
Repo makeup
Click a slice to open those files.
.bin15.4 GB · 100%
At a glance
- Task
- Text Generation
- Library
- transformers
- License
- apache-2.0
- Model type
- llama
- Access
- Public
- Created
- Aug 9, 2023
- Updated
- Apr 25, 2024
- SHA
- 32665012
Try a prompt
Model card
From the Hugging Face model README
[WIP]
Origin repository JosephusCheung/Qwen-LLaMAfied-7B-Chat.
This is the LLaMAfied version of Qwen/Qwen-7B-Chat, recalibrated to fit the original LLaMA/LLaMA-2-like model structure.
You can use LlamaForCausalLM for model inference, which is the same as LLaMA/LLaMA-2 models.
I converted the tokenizer from tiktoken format to huggingface format, so you do not need to allow external codes when loading anymore.
The model has been edited to be white-labelled, meaning the model will no longer call itself a Qwen.
SPOILOR: Further finetuning is in progress, the current version is a work-in-progress, some knowledge may be biased and illusory due to structural changes. Will be updated very, very sooooooooooon.
PROMPT FORMAT: chatml
CURRENT MMLU: 50.36
Issue: Compared to the original Qwen-Chat scoring 53.9, the MMLU score dropped slightly (-3.54) due to insufficient realignment.
- Task
- Text Generation
- Library
- transformers
- Type
- llama
- License
- apache-2.0
- Languages
- en, zh
- Created
- Aug 9, 2023
- Updated
- Apr 25, 2024