Downloads · 30 days
10
1% of all-time downloads
Mistral-Large-Instruct-2407-Smaller-GPTQ
shuyuej/Mistral-Large-Instruct-2407-Smaller-GPTQ
Mistral-Large-Instruct-2407-Smaller-GPTQ is a text generation model from shuyuej. 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.
Original Base Model: mistralai/Mistral-Large-Instruct-2407.<br Link: https://huggingface.co/mistralai/Mistral-Large-Instruct-2407
All-time downloads
693
Public
Parameters
123B
62.9 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors62.8 GB · 100%
Parameter types
How the weights are stored.
I32122B · 99%
Try a prompt
Model card
From the Hugging Face model README
The Quantized Mistral Large Instruct 2407 Model
Original Base Model: mistralai/Mistral-Large-Instruct-2407.<br>
Link: https://huggingface.co/mistralai/Mistral-Large-Instruct-2407
Special Notice
Please note that this is a relatively smaller model by setting group_size=1024.<br>
For the standard group_size=128 model, please check here, shuyuej/Mistral-Large-Instruct-2407-GPTQ, https://huggingface.co/shuyuej/Mistral-Large-Instruct-2407-GPTQ.
Quantization Configurations
"quantization_config": {
"bits": 4,
"checkpoint_format": "gptq",
"damp_percent": 0.1,
"desc_act": true,
"group_size": 1024,
"model_file_base_name": null,
"model_name_or_path": null,
"quant_method": "gptq",
"static_groups": false,
"sym": true,
"true_sequential": true
},
Source Codes
Source Codes: https://github.com/vkola-lab/medpodgpt/tree/main/quantization.
- Task
- Text Generation
- Library
- transformers
- Type
- mistral
- License
- apache-2.0
- Created
- Jul 25, 2024
- Updated
- Jul 25, 2024