rahulmanuwas
commited on
Commit
•
050b6b6
1
Parent(s):
d3e93e7
Delete README.MD
Browse files
README.MD
DELETED
@@ -1,26 +0,0 @@
|
|
1 |
-
---
|
2 |
-
license: apache-2.0
|
3 |
-
pipeline_tag: text-generation
|
4 |
-
tags:
|
5 |
-
- finetuned
|
6 |
-
inference: false
|
7 |
-
base_model: mistralai/Mistral-7B-Instruct-v0.2
|
8 |
-
model_creator: Mistral AI_
|
9 |
-
model_name: Mistral 7B Instruct v0.2
|
10 |
-
model_type: mistral
|
11 |
-
prompt_template: '<s>[INST] {prompt} [/INST]
|
12 |
-
'
|
13 |
-
quantized_by: rahulmanuwas
|
14 |
-
---
|
15 |
-
# Mistral 7B Instruct v0.2 - GGUF
|
16 |
-
|
17 |
-
This is a quantized model for `mistralai/Mistral-7B-Instruct-v0.2`. Two quantization methods were used:
|
18 |
-
- Q5_K_M: 5-bit, preserves most of the model's performance
|
19 |
-
- Q4_K_M: 4-bit, smaller footprints, and saves more memory
|
20 |
-
|
21 |
-
<!-- description start -->
|
22 |
-
## Description
|
23 |
-
|
24 |
-
This repo contains GGUF format model files for [Mistral AI_'s Mistral 7B Instruct v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2).
|
25 |
-
|
26 |
-
This model was quantized in Google Colab.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|