README
Browse files- README.md +84 -0
- misc/logo.png +3 -0
README.md
CHANGED
@@ -1,3 +1,87 @@
|
|
1 |
---
|
2 |
license: apache-2.0
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
license: apache-2.0
|
3 |
+
pipeline_tag: text-generation
|
4 |
+
library_name: transformers
|
5 |
+
language: [
|
6 |
+
'en', 'am', 'ar', 'as', 'az', 'be', 'bg', 'bn', 'br', 'bs', 'ca', 'cs', 'cy', 'da', 'de', 'el',
|
7 |
+
'eo', 'es', 'et', 'eu', 'fa', 'ff', 'fi', 'fr', 'fy', 'ga', 'gd', 'gl', 'gn', 'gu', 'ha', 'he',
|
8 |
+
'hi', 'hr', 'ht', 'hu', 'hy', 'id', 'ig', 'is', 'it', 'ja', 'jv', 'ka', 'kk', 'km', 'kn', 'ko',
|
9 |
+
'ku', 'ky', 'la', 'lg', 'li', 'ln', 'lo', 'lt', 'lv', 'mg', 'mk', 'ml', 'mn', 'mr', 'ms', 'my',
|
10 |
+
'ne', 'nl', 'no', 'ns', 'om', 'or', 'pa', 'pl', 'ps', 'pt', 'qu', 'rm', 'ro', 'ru', 'sa', 'si',
|
11 |
+
'sc', 'sd', 'sk', 'sl', 'so', 'sq', 'sr', 'ss', 'su', 'sv', 'sw', 'ta', 'te', 'th', 'tl', 'tn',
|
12 |
+
'tr', 'ug', 'uk', 'ur', 'uz', 'vi', 'wo', 'xh', 'yi', 'yo', 'zu',
|
13 |
+
]
|
14 |
+
datasets: [
|
15 |
+
'xu-song/cc100-samples',
|
16 |
+
'jordiclive/wikipedia-summary-dataset',
|
17 |
+
'JeanKaddour/minipile',
|
18 |
+
'badrex/llm-emoji-dataset',
|
19 |
+
'fblgit/simple-math',
|
20 |
+
'Gusarich/math-expressions-1m',
|
21 |
+
'AtlasUnified/atlas-math-sets',
|
22 |
+
'gair-prox/open-web-math-pro',
|
23 |
+
'bigcode/the-stack-smol-xs',
|
24 |
+
'rombodawg/code_bagel',
|
25 |
+
'AtlasUnified/Atlas-Reasoning',
|
26 |
+
'thesven/gsm8k-reasoning',
|
27 |
+
'AlgorithmicResearchGroup/math_reasoning_autoformalization_track',
|
28 |
+
'KingNish/reasoning-base-20k',
|
29 |
+
'SkunkworksAI/reasoning-0.01',
|
30 |
+
'Magpie-Align/Magpie-Reasoning-150K',
|
31 |
+
]
|
32 |
+
tags:
|
33 |
+
- litgpt
|
34 |
+
- litdata
|
35 |
---
|
36 |
+
|
37 |
+
# tangled-llama-a-32k-base-v0.1
|
38 |
+
|
39 |
+
![logo](./misc/logo.png)
|
40 |
+
|
41 |
+
A pretrained language model based on the Llama model with about **62.9M** parameters. This model has been trained on **10.6B** (`10,630,121,844`) tokens from more than **31.3M** (`31,383,840`) dataset rows.
|
42 |
+
|
43 |
+
This model **isn't** designed for immediate use but rather for Continued Pretraining and Finetuning on a downstream task. While it can handle a context length of up to **128K** (`131,072`) tokens, it was pretrained with sequences of **2K** (`2048`) tokens.
|
44 |
+
|
45 |
+
The objective is to streamline the cognitive or reasoning core, eliminating any redundant knowledge from the model.
|
46 |
+
|
47 |
+
[loss, val_loss]()
|
48 |
+
|
49 |
+
[val_ppl]()
|
50 |
+
|
51 |
+
[epoch]()
|
52 |
+
|
53 |
+
[learning_rate]()
|
54 |
+
|
55 |
+
## lm-evaluation-harness
|
56 |
+
|
57 |
+
```bash
|
58 |
+
litgpt evaluate --tasks 'hellaswag,gsm8k,truthfulqa_mc2,mmlu,winogrande,arc_challenge' --out_dir 'evaluate-quick/' --batch_size 4 --dtype 'bfloat16' out/pretrain/final/
|
59 |
+
```
|
60 |
+
|
61 |
+
```bash
|
62 |
+
litgpt evaluate --tasks 'leaderboard' --out_dir 'evaluate-leaderboard/' --batch_size 4 --dtype 'bfloat16' out/pretrain/final/
|
63 |
+
```
|
64 |
+
|
65 |
+
```bash
|
66 |
+
litgpt evaluate --tasks 'bbh_zeroshot,bbh_fewshot,bbh_cot_fewshot,bbh_cot_zeroshot' --out_dir 'evaluate-bigbenchhard/' --batch_size 4 --dtype 'bfloat16' out/pretrain/final/
|
67 |
+
```
|
68 |
+
|
69 |
+
```bash
|
70 |
+
litgpt evaluate --tasks 'mmlu,mmlu_pro' --out_dir 'evaluate-mmlu/' --batch_size 4 --dtype 'bfloat16' out/pretrain/final/
|
71 |
+
```
|
72 |
+
|
73 |
+
```bash
|
74 |
+
litgpt evaluate --tasks 'arc_challenge,boolq,gpqa,hellaswag,openbookqa,piqa,truthfulqa_mc2,winogrande' --out_dir 'evaluate-reasoning/' --batch_size 4 --dtype 'bfloat16' out/pretrain/final/
|
75 |
+
```
|
76 |
+
|
77 |
+
```bash
|
78 |
+
litgpt evaluate --tasks 'mmlu_multilingual,mgsm' --out_dir 'evaluate-multilinguals/' --batch_size 4 --dtype 'bfloat16' out/pretrain/final/
|
79 |
+
```
|
80 |
+
|
81 |
+
```bash
|
82 |
+
litgpt evaluate --tasks 'gsm8k,mathqa' --out_dir 'evaluate-math/' --batch_size 4 --dtype 'bfloat16' out/pretrain/final/
|
83 |
+
```
|
84 |
+
|
85 |
+
```bash
|
86 |
+
litgpt evaluate --tasks 'wikitext,qasper' --out_dir 'evaluate-long/' --batch_size 4 --dtype 'bfloat16' out/pretrain/final/
|
87 |
+
```
|
misc/logo.png
ADDED
Git LFS Details
|