Update README.md
#1
by
zakoman
- opened
README.md
CHANGED
|
@@ -1,3 +1,48 @@
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
| 3 |
+
language:
|
| 4 |
+
- en
|
| 5 |
+
tags:
|
| 6 |
+
- exllama
|
| 7 |
+
- exl2
|
| 8 |
+
- exllamav2
|
| 9 |
+
- TinyLlama
|
| 10 |
---
|
| 11 |
+
|
| 12 |
+
# 8bpw exllamav2 quantisation of [TinyLlama/TinyLlama-1.1B-intermediate-step-1195k-token-2.5T](https://huggingface.co/TinyLlama/TinyLlama-1.1B-intermediate-step-1195k-token-2.5T)
|
| 13 |
+
Calibration dataset used is [vicgalle/alpaca-gpt4](https://huggingface.co/datasets/vicgalle/alpaca-gpt4)
|
| 14 |
+
|
| 15 |
+
|
| 16 |
+
|
| 17 |
+
<details>
|
| 18 |
+
<summary><b>Original model card</b></summary>
|
| 19 |
+
<div align="center">
|
| 20 |
+
|
| 21 |
+
|
| 22 |
+
# TinyLlama-1.1B
|
| 23 |
+
</div>
|
| 24 |
+
|
| 25 |
+
https://github.com/jzhang38/TinyLlama
|
| 26 |
+
|
| 27 |
+
The TinyLlama project aims to **pretrain** a **1.1B Llama model on 3 trillion tokens**. With some proper optimization, we can achieve this within a span of "just" 90 days using 16 A100-40G GPUs 🚀🚀. The training has started on 2023-09-01.
|
| 28 |
+
|
| 29 |
+
<div align="center">
|
| 30 |
+
<img src="https://huggingface.co/PY007/TinyLlama-1.1B-intermediate-step-240k-503b/resolve/main/TinyLlama_logo.png" width="300"/>
|
| 31 |
+
</div>
|
| 32 |
+
|
| 33 |
+
We adopted exactly the same architecture and tokenizer as Llama 2. This means TinyLlama can be plugged and played in many open-source projects built upon Llama. Besides, TinyLlama is compact with only 1.1B parameters. This compactness allows it to cater to a multitude of applications demanding a restricted computation and memory footprint.
|
| 34 |
+
|
| 35 |
+
#### This Collection
|
| 36 |
+
This collection contains all checkpoints after the 1T fix. Branch name indicates the step and number of tokens seen.
|
| 37 |
+
|
| 38 |
+
#### Eval
|
| 39 |
+
|
| 40 |
+
| Model | Pretrain Tokens | HellaSwag | Obqa | WinoGrande | ARC_c | ARC_e | boolq | piqa | avg |
|
| 41 |
+
|-------------------------------------------|-----------------|-----------|------|------------|-------|-------|-------|------|-----|
|
| 42 |
+
| Pythia-1.0B | 300B | 47.16 | 31.40| 53.43 | 27.05 | 48.99 | 60.83 | 69.21 | 48.30 |
|
| 43 |
+
| TinyLlama-1.1B-intermediate-step-50K-104b | 103B | 43.50 | 29.80| 53.28 | 24.32 | 44.91 | 59.66 | 67.30 | 46.11|
|
| 44 |
+
| TinyLlama-1.1B-intermediate-step-240k-503b| 503B | 49.56 |31.40 |55.80 |26.54 |48.32 |56.91 |69.42 | 48.28 |
|
| 45 |
+
| TinyLlama-1.1B-intermediate-step-480k-1007B | 1007B | 52.54 | 33.40 | 55.96 | 27.82 | 52.36 | 59.54 | 69.91 | 50.22 |
|
| 46 |
+
| TinyLlama-1.1B-intermediate-step-715k-1.5T | 1.5T | 53.68 | 35.20 | 58.33 | 29.18 | 51.89 | 59.08 | 71.65 | 51.29 |
|
| 47 |
+
| TinyLlama-1.1B-intermediate-step-955k-2T | 2T | 54.63 | 33.40 | 56.83 | 28.07 | 54.67 | 63.21 | 70.67 | 51.64 |
|
| 48 |
+
| **TinyLlama-1.1B-intermediate-step-1195k-token-2.5T** | **2.5T** | **58.96** | **34.40** | **58.72** | **31.91** | **56.78** | **63.21** | **73.07** | **53.86**|
|