Merge branch 'main' of hf.co:cortexso/tinyllama into default
Browse files
README.md
ADDED
|
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
---
|
| 4 |
+
|
| 5 |
+
## Overview
|
| 6 |
+
|
| 7 |
+
The [TinyLlama](https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v1.0) project aims to pretrain a 1.1B Llama model on 3 trillion tokens. This is the chat model finetuned on a diverse range of synthetic dialogues generated by ChatGPT.
|
| 8 |
+
|
| 9 |
+
## Variants
|
| 10 |
+
|
| 11 |
+
| No | Variant | Cortex CLI command |
|
| 12 |
+
| --- | --- | --- |
|
| 13 |
+
| 1 | [1b-gguf](https://huggingface.co/cortexhub/tinyllama/tree/1b-gguf) | `cortex run tinyllama:1b-gguf` |
|
| 14 |
+
|
| 15 |
+
|
| 16 |
+
## Use it with Jan (UI)
|
| 17 |
+
|
| 18 |
+
1. Install **Jan** using [Quickstart](https://jan.ai/docs/quickstart)
|
| 19 |
+
2. Use in Jan model Hub:
|
| 20 |
+
```
|
| 21 |
+
cortexhub/tinyllama
|
| 22 |
+
```
|
| 23 |
+
|
| 24 |
+
## Use it with Cortex (CLI)
|
| 25 |
+
|
| 26 |
+
1. Install **Cortex** using [Quickstart](https://cortex.jan.ai/docs/quickstart)
|
| 27 |
+
2. Run the model with command:
|
| 28 |
+
```
|
| 29 |
+
cortex run tinyllama
|
| 30 |
+
```
|
| 31 |
+
|
| 32 |
+
## Credits
|
| 33 |
+
|
| 34 |
+
- **Author:** Microsoft
|
| 35 |
+
- **Converter:** [Homebrew](https://www.homebrew.ltd/)
|
| 36 |
+
- **Original License:** [License](https://huggingface.co/datasets/choosealicense/licenses/blob/main/markdown/apache-2.0.md)
|
| 37 |
+
- **Papers:** [Tinyllama Paper](https://arxiv.org/abs/2401.02385)
|