Create README.md (#1)
Browse files- Create README.md (226afd18cccce84258835d66181fe8d3621fe979)
README.md
ADDED
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
# Mistral-7B-v0.1
|
2 |
+
|
3 |
+
The Mistral-7B-v0.1 Large Language Model (LLM) is a pretrained generative text model with 7 billion parameters.
|
4 |
+
Mistral-7B-v0.1 outperforms Llama 2 13B on all benchmarks we tested.
|
5 |
+
|
6 |
+
For full details of this model please read our [paper](https://arxiv.org/abs/2310.06825) and [release blog post](https://mistral.ai/news/announcing-mistral-7b/).
|
7 |
+
|
8 |
+
## Model Architecture
|
9 |
+
|
10 |
+
Mistral-7B-v0.1 is a transformer model, with the following architecture choices:
|
11 |
+
- Grouped-Query Attention
|
12 |
+
- Sliding-Window Attention
|
13 |
+
- Byte-fallback BPE tokenizer
|