Downloads · 30 days
4
1% of all-time downloads
PEFT-Llama-2-7b-chat-MedText
Elkhayyat17/PEFT-Llama-2-7b-chat-MedText
PEFT-Llama-2-7b-chat-MedText is a text generation model from Elkhayyat17. Use it when you need the model to write or continue text. It is set up for peft.
https://colab.research.google.com/drive/1eFzHy6eARkhgy4Uxyre5KsdRbQII50jx?usp=sharing
All-time downloads
471
Public
Repo size
16.8 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin16.8 MB · 100%
At a glance
- Task
- Text Generation
- Library
- peft
- Access
- Public
- Created
- Oct 21, 2023
- Updated
- Feb 21, 2024
- SHA
- 93292f69
Try a prompt
Base models
Datasets
Model card
From the Hugging Face model README
Model still under developing
How to Get Started with the Model
https://colab.research.google.com/drive/1eFzHy6eARkhgy4Uxyre5KsdRbQII50jx?usp=sharing
GGUF version
https://huggingface.co/Elkhayyat17/llama2medical-GGUF
Merged version
https://huggingface.co/Elkhayyat17/merge-PEFT-Llama-2-7b-MedText
Training procedure
The following bitsandbytes quantization config was used during training:
- quant_method: bitsandbytes
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: True
- bnb_4bit_compute_dtype: float16
Framework versions
- PEFT 0.6.0.dev0
- Task
- Text Generation
- Library
- peft
- Created
- Oct 21, 2023
- Updated
- Feb 21, 2024