Create README.md (#1)
Browse files- Create README.md (757d07091256b162050f29ab9b7b3d3758cfae32)
Co-authored-by: Khanh Tran <tvkain@users.noreply.huggingface.co>
README.md
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
## SLA CPT Checkpoints Repo
|
| 2 |
+
|
| 3 |
+
|Model|Description|
|
| 4 |
+
|-----|-----------|
|
| 5 |
+
|qwen2.5-0.5b_english_wiki|Trained from scratch with 5B english tokens from Wikipedia|
|
| 6 |
+
|qwen2.5-0.5b_english_wiki_irish_corpus_custom_sampler|CPT from qwen2.5-0.5b_english_wiki with 1.5B Irish tokens|
|
| 7 |
+
|qwen2.5-0.5b_english_wiki_1.5B_basque_corpus|CPT from qwen2.5-0.5b_english_wiki with 1.5B Basque tokens|
|
| 8 |
+
|qwen2.5-0.5b_english_wiki_1_5B_stackexchange_corpus|CPT from qwen2.5-0.5b_english_wiki with 1.5B English tokens from Stackexchange|
|
| 9 |
+
|qwen2.5-0.5b_english_wiki_300M_en_1.5Birish_corpus|CPT from qwen2.5-0.5b_english_wiki with 300M English tokens and 1.5B Irish tokens|
|
| 10 |
+
|qwen2.5-0.5b_english_wiki_300M_en_1.5Bbasque_corpus|CPT from qwen2.5-0.5b_english_wiki with 300M English tokens and 1.5B Basque tokens|
|