Downloads · 30 days
8
12% of all-time downloads
MISTRAL7B-01-EXALT1A-4bit
1024m/MISTRAL7B-01-EXALT1A-4bit
MISTRAL7B-01-EXALT1A-4bit is a text generation model from 1024m. 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.
- Developed by: 1024m - License: apache-2.0 - Task WASSA Shared Task 1A 2024 - Finetuned from model : unsloth/mistral-7b-bnb-4bit
All-time downloads
66
Public
Parameters
7.5B
4.1 GB on disk
Likes
1
Public
Repo makeup
Click a slice to open those files.
.safetensors4.1 GB · 100%
Parameter types
How the weights are stored.
U87.2B · 96%
Try a prompt
Base models
Model card
From the Hugging Face model README
Uploaded model
- Developed by: 1024m
- License: apache-2.0
- Task WASSA Shared Task 1A 2024**
- Finetuned from model : unsloth/mistral-7b-bnb-4bit
This mistral model was trained 2x faster with Unsloth and Huggingface's TRL library.
prompt format :
-"""Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.
-### Instruction:
-{Given the input text , classify it based on what emotion is being exibited among the following : Joy/Neutral/Anger/Love/Sadness/Fear. Respond with only one emotion only among the options given. Respond with ONLY ONE word and nothing else. }
-### Input:
-{} ( add input text here and remove this text )
-### Response:
-{} ( leave blank and remove this text ) """
- Task
- Text Generation
- Library
- transformers
- Type
- mistral
- License
- apache-2.0
- Languages
- en
- Created
- Apr 25, 2024
- Updated
- Apr 25, 2024