Downloads · 30 days
10
6% of all-time downloads
007ankit/biomistral-hindi-merged
biomistral-hindi-merged is a text generation model from 007ankit. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as other.
This is a merge of pre-trained language models created using mergekit.
Downloads · 30 days
10
6% of all-time downloads
All-time downloads
154
Public
Parameters
7.2B
14.5 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors14.5 GB · 100%
From the Hugging Face model README
This is a merge of pre-trained language models created using mergekit.
This model was merged using the DARE TIES merge method using BioMistral/BioMistral-7B as a base.
The following models were included in the merge:
The following YAML configuration was used to produce this model:
models:
- model: BioMistral/BioMistral-7B
# No parameters necessary for base model
- model: OdiaGenAI/mistral_hindi_7b_base_v1
parameters:
density: 0.5
weight: 0.5
merge_method: dare_ties
base_model: BioMistral/BioMistral-7B
parameters:
int8_mask: true
dtype: bfloat16