Text Generation
Transformers
Safetensors
PyTorch
mistral
finetuned
quantized
4-bit precision
gptq
Safetensors
text-generation-inference
Merge
7b
mistralai/Mistral-7B-Instruct-v0.2
HuggingFaceH4/zephyr-7b-beta
Generated from Trainer
en
dataset:HuggingFaceH4/ultrachat_200k
dataset:HuggingFaceH4/ultrafeedback_binarized
arxiv:2305.18290
arxiv:2310.16944
Eval Results
Inference Endpoints
conversational
File size: 210 Bytes
0ac09da |
1 2 3 4 5 6 7 8 9 10 11 |
{
"bits": 4,
"group_size": 128,
"damp_percent": 0.1,
"desc_act": false,
"static_groups": false,
"sym": true,
"true_sequential": true,
"model_name_or_path": null,
"model_file_base_name": null
} |