Qwen models full parameter fine-tuned on Saiga dataset
Max
Defetya
AI & ML interests
LLM
Recent Activity
updated
a model
2 days ago
Defetya/en-ru-to-chuvash-turk-langs-tencent-1.8B
published
a model
2 days ago
Defetya/en-ru-to-chuvash-turk-langs-tencent-1.8B
Organizations
None yet
models
70
Defetya/en-ru-to-chuvash-turk-langs-tencent-1.8B
Text Generation
•
2B
•
Updated
•
20
Defetya/en-ru-to-chuvash-tencent-1.8B
Text Generation
•
2B
•
Updated
•
15
Defetya/gemma-2b-en-chuvash
Text Generation
•
3B
•
Updated
•
19
Defetya/simson_base
Updated
Defetya/ChemBERTa-77M-polymer-1M
3.43M
•
Updated
•
3
Defetya/ruadapt-qwen3B-llamafied-base
3B
•
Updated
•
6
Defetya/ruadapt_qwen_3B_llamafied_easylm_checkpoints
Updated
Defetya/gemma-2b-ru-dpo
3B
•
Updated
•
6
Defetya/gemma_2b_ru_sft
3B
•
Updated
•
7
•
1
Defetya/animagine_xl_3.0_jax
Updated
datasets
6
Defetya/ru_superglue_formatted
Viewer
•
Updated
•
111k
•
67
Defetya/saiga-ds-merged
Preview
•
Updated
•
41
Defetya/ru-open-llama-training-datasets
Viewer
•
Updated
•
1.1M
•
113
•
1
Defetya/eval_open_llama_ru
Viewer
•
Updated
•
2k
•
22
Defetya/tokenized-datasets-jax
Updated
•
7
Defetya/iteration-dataset
Viewer
•
Updated
•
105
•
43