Downloads · 30 days
27
9% of all-time downloads
capibara-17b-4bit
dtrejopizzo/capibara-17b-4bit
capibara-17b-4bit is a text generation model from dtrejopizzo. Use it when you need the model to write or continue text. It is set up for transformers.
Model upgraded and finetuned starting from LlaMa model. I hope everyone creates modes starting from this open-source project
All-time downloads
287
Public
Repo size
7.5 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors7.5 GB · 100%
At a glance
- Task
- Text Generation
- Library
- transformers
- Model type
- llama
- Access
- Public
- Created
- Apr 20, 2023
- Updated
- Apr 20, 2023
- SHA
- db43b246
Try a prompt
Model card
From the Hugging Face model README
** Model upgraded and finetuned starting from LlaMa model. I hope everyone creates modes starting from this open-source project**
GPTQ conversion command (on CUDA branch): CUDA_VISIBLE_DEVICES=0 python llama.py ../capibara-17b-4bit c4 --wbits 4 --true-sequential --groupsize 128 --save capibara-17b-4bit-128g.pt
Added 1 token to the tokenizer model: python llama-tools/add_tokens.py capibara-17b/tokenizer.model /content/tokenizer.model llama-tools/test_list.txt
Enjoy
- Task
- Text Generation
- Library
- transformers
- Type
- llama
- Created
- Apr 20, 2023
- Updated
- Apr 20, 2023