Update README.md
Browse files
README.md
CHANGED
|
@@ -1,54 +1,27 @@
|
|
| 1 |
---
|
| 2 |
-
base_model:
|
| 3 |
-
- adowu/autocodit4
|
| 4 |
-
- alpindale/Mistral-7B-v0.2-hf
|
| 5 |
-
- beowolx/MistralHermes-CodePro-7B-v1
|
| 6 |
library_name: transformers
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7 |
tags:
|
| 8 |
-
-
|
| 9 |
-
-
|
| 10 |
-
|
| 11 |
---
|
| 12 |
-
# merge
|
| 13 |
-
|
| 14 |
-
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
|
| 15 |
-
|
| 16 |
-
## Merge Details
|
| 17 |
-
### Merge Method
|
| 18 |
-
|
| 19 |
-
This model was merged using the [DARE](https://arxiv.org/abs/2311.03099) [TIES](https://arxiv.org/abs/2306.01708) merge method using [adowu/autocodit4](https://huggingface.co/adowu/autocodit4) as a base.
|
| 20 |
-
|
| 21 |
-
### Models Merged
|
| 22 |
-
|
| 23 |
-
The following models were included in the merge:
|
| 24 |
-
* [alpindale/Mistral-7B-v0.2-hf](https://huggingface.co/alpindale/Mistral-7B-v0.2-hf)
|
| 25 |
-
* [beowolx/MistralHermes-CodePro-7B-v1](https://huggingface.co/beowolx/MistralHermes-CodePro-7B-v1)
|
| 26 |
|
| 27 |
-
###
|
| 28 |
|
| 29 |
-
|
|
|
|
| 30 |
|
| 31 |
-
|
| 32 |
-
|
| 33 |
-
|
| 34 |
-
|
| 35 |
-
density: 1.0
|
| 36 |
-
weight: 0.8
|
| 37 |
-
- model: alpindale/Mistral-7B-v0.2-hf
|
| 38 |
-
parameters:
|
| 39 |
-
density: 0.6
|
| 40 |
-
weight: 1.0
|
| 41 |
-
- model: beowolx/MistralHermes-CodePro-7B-v1
|
| 42 |
-
parameters:
|
| 43 |
-
density: 0.6
|
| 44 |
-
weight: 1.0
|
| 45 |
|
|
|
|
|
|
|
| 46 |
|
| 47 |
-
|
| 48 |
-
|
| 49 |
-
parameters:
|
| 50 |
-
normalize: true
|
| 51 |
-
int8_mask: true
|
| 52 |
-
dtype: bfloat16
|
| 53 |
-
vocab_size: 128000
|
| 54 |
-
```
|
|
|
|
| 1 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
library_name: transformers
|
| 3 |
+
license: apache-2.0
|
| 4 |
+
language:
|
| 5 |
+
- en
|
| 6 |
+
pipeline_tag: text-generation
|
| 7 |
tags:
|
| 8 |
+
- astral
|
| 9 |
+
- demo
|
| 10 |
+
- mistral
|
| 11 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12 |
|
| 13 |
+
### astral-demo-5
|
| 14 |
|
| 15 |
+
## Overview
|
| 16 |
+
astral-demo-5 is a streamlined language model designed for quick demonstrations and insights into NLP capabilities, focusing on text generation and analysis.
|
| 17 |
|
| 18 |
+
## Features
|
| 19 |
+
- Efficient Text Generation: Quickly produces text for a variety of applications.
|
| 20 |
+
- Compact and Fast: Optimized for speed, making it ideal for demos and prototyping.
|
| 21 |
+
- Prototype Development: Tests ideas in conversational AI and content generation.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 22 |
|
| 23 |
+
## Performance
|
| 24 |
+
Balances performance with accuracy, providing a practical demonstration of NLP technology in action.
|
| 25 |
|
| 26 |
+
- **Developed by:** aww
|
| 27 |
+
- **Model type:** Mistral
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|