Commit
•
c960ee7
1
Parent(s):
87d97aa
Create README.md
Browse files
README.md
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
pipeline_tag: text-generation
|
4 |
+
tags:
|
5 |
+
- finetuned
|
6 |
+
inference: false
|
7 |
+
|
8 |
+
---
|
9 |
+
|
10 |
+
# Mistral-7B-Instruct-v0.2-GGUF
|
11 |
+
|
12 |
+
- Model creator: [Mistral AI_](https://huggingface.co/mistralai)
|
13 |
+
- Original model: [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2)
|
14 |
+
|
15 |
+
## Description
|
16 |
+
|
17 |
+
The Mistral-7B-Instruct-v0.2 Large Language Model (LLM) is an instruct fine-tuned version of the Mistral-7B-v0.2.
|
18 |
+
|
19 |
+
Mistral-7B-v0.2 has the following changes compared to Mistral-7B-v0.1
|
20 |
+
- 32k context window (vs 8k context in v0.1)
|
21 |
+
- Rope-theta = 1e6
|
22 |
+
- No Sliding-Window Attention
|
23 |
+
|
24 |
+
For full details of this model please read our [paper](https://arxiv.org/abs/2310.06825) and [release blog post](https://mistral.ai/news/la-plateforme/).
|