Charles Koutcheme's picture

Charles Koutcheme PRO

koutch

·

https://koutche.me

AI & ML interests

Source code modelling using large language models

Recent Activity

updated a model 15 minutes ago

koutch/short_paper_smol_1.json_train_dpo_v4_train_no_think

updated a model 42 minutes ago

koutch/short_paper_llama_llama3.1-8b_train_sft_train_no_think

updated a model about 1 hour ago

koutch/short_paper_qwen_qwen3-instruct-4b_train_sft_train_no_think

View all activity

Organizations

koutch 's models 70

koutch/short_paper_smol_1.json_train_dpo_v4_train_no_think

Text Generation • 3B • Updated 15 minutes ago • 16

koutch/short_paper_llama_llama3.1-8b_train_sft_train_no_think

Text Generation • 8B • Updated 42 minutes ago • 149

koutch/short_paper_qwen_qwen3-instruct-4b_train_sft_train_no_think

Text Generation • 4B • Updated about 1 hour ago • 129

koutch/short_paper_smol_smol3-3B_train_sft_train_no_think

Text Generation • 3B • Updated about 1 hour ago • 161

koutch/short_paper_qwen_qwen3-instruct-4b_train_sft_train_para

Text Generation • 4B • Updated about 1 hour ago • 9

koutch/short_paper_smol_smol3-3B_train_sft_train_para

Text Generation • 3B • Updated about 1 hour ago • 12

koutch/short_paper_llama_llama3.1-8b_train_sft_train_para

Text Generation • 8B • Updated about 1 hour ago • 17

koutch/short_paper_llama_0.json_train_dpo_v4_train_no_think

Text Generation • 8B • Updated about 13 hours ago • 6

koutch/short_paper_llama_llama3.1-8b_train_sft_train_think

Text Generation • 8B • Updated 3 days ago • 58

koutch/short_paper_qwen_qwen3-instruct-4b_train_sft_train_think

Text Generation • 4B • Updated 3 days ago • 67

koutch/short_paper_smol_smol3-3B_train_sft_train_think

Text Generation • 3B • Updated 3 days ago • 88

koutch/short_paper_llama_llama3.1-8b_train_sft_train

Text Generation • 8B • Updated 3 days ago • 26

koutch/short_paper_qwen_qwen3-instruct-4b_train_sft_train

Text Generation • 4B • Updated 3 days ago • 30

koutch/short_paper_smol_smol3-3B_train_sft_train

Text Generation • 3B • Updated 3 days ago • 39

koutch/short_paper_llama_0.json_train_dpo_v3_train_no_think

Text Generation • 8B • Updated 3 days ago • 36

koutch/short_paper_qwen_0.json_train_dpo_v3_train_no_think

Text Generation • 4B • Updated 3 days ago • 33

koutch/short_paper_smol_0.json_train_dpo_v3_train_no_think

Text Generation • 3B • Updated 3 days ago • 33

koutch/short_paper_llama_0.json_train_dpo_v2_train_no_think

Text Generation • 8B • Updated 3 days ago • 37

koutch/short_paper_qwen_0.json_train_dpo_v2_train_no_think

Text Generation • 4B • Updated 3 days ago • 32

koutch/short_paper_smol_0.json_train_dpo_v2_train_no_think

Text Generation • 3B • Updated 3 days ago • 42

koutch/short_paper_llama_0.json_train_dpo_v1_train_no_think

Text Generation • 8B • Updated 4 days ago • 19

koutch/short_paper_qwen_0.json_train_dpo_v1_train_no_think

Text Generation • 4B • Updated 4 days ago • 13

koutch/short_paper_smol_0.json_train_dpo_v1_train_no_think

Text Generation • 3B • Updated 4 days ago • 9

koutch/short_paper_llama_0.json_train_dpo_v2_dev

Text Generation • 8B • Updated 4 days ago • 59

koutch/short_paper_qwent_0.json_train_dpo_v2_dev

Text Generation • 4B • Updated 4 days ago • 43

koutch/short_paper_smol_0.json_train_dpo_v2_dev

Text Generation • 3B • Updated 4 days ago • 78

koutch/short_paper_qwent_0.json_train_dpo_v1_dev

Text Generation • 4B • Updated 4 days ago • 48

koutch/short_paper_llama_0.json_train_dpo_v1_dev

Text Generation • 8B • Updated 4 days ago • 52

koutch/short_paper_qwen_0.json_train_dpo_v2_dev

Text Generation • 4B • Updated 4 days ago • 48

koutch/short_paper_smol_0.json_train_dpo_v1_dev

Text Generation • 3B • Updated 4 days ago • 79