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 18 minutes ago

koutch/paper_llama_llama3.1-8b_train_sft_train_edit

updated a model 22 minutes ago

koutch/paper_smol_smol3-3B_train_sft_train_dual

updated a model 22 minutes ago

koutch/paper_smol_smol3-3B_train_sft_train_thought

View all activity

Organizations

koutch 's models 113

koutch/short_paper_llama_2.json_train_dpo_v2_train_no_think

Text Generation • 8B • Updated 12 days ago • 47

koutch/short_paper_qwen_2.json_train_dpo_v2_train_no_think

Text Generation • 4B • Updated 12 days ago • 49

koutch/short_paper_qwen_2.json_train_dpo_v1_train_no_think

Text Generation • 4B • Updated 12 days ago • 43

koutch/short_paper_llama_llama3.1-8b_train_sft_all_train_no_think

Text Generation • 8B • Updated 12 days ago • 178

koutch/short_paper_llama_llama3.1-8b_train_sft_train_no_think

Text Generation • 8B • Updated 12 days ago • 344

koutch/short_paper_qwen_qwen3-instruct-4b_train_sft_all_train_no_think

Text Generation • 4B • Updated 12 days ago • 138

koutch/short_paper_llama_llama3.1-8b_train_sft_train_para

Text Generation • 8B • Updated 12 days ago • 226

koutch/short_paper_smol_2.json_train_dpo_v2_train_no_think

Text Generation • 3B • Updated 12 days ago • 48

koutch/short_paper_smol_2.json_train_dpo_v1_train_no_think

Text Generation • 3B • Updated 12 days ago • 49

koutch/short_paper_smol_smol3-3B_train_sft_train_no_think

Text Generation • 3B • Updated 12 days ago • 320

koutch/short_paper_qwen_qwen3-instruct-4b_train_sft_train_para

Text Generation • 4B • Updated 12 days ago • 204

koutch/short_paper_smol_smol3-3B_train_sft_train_para

Text Generation • 3B • Updated 12 days ago • 193

koutch/short_paper_qwen_qwen3-instruct-4b_train_sft_train_no_think

Text Generation • 4B • Updated 12 days ago • 314

koutch/short_paper_smol_smol3-3B_train_sft_all_train_no_think

Text Generation • 3B • Updated 12 days ago • 155

koutch/short_paper_llama_1.json_train_dpo_v3_train_no_think

Text Generation • 8B • Updated 14 days ago • 56

koutch/short_paper_llama_1.json_train_dpo_v2_train_no_think

Text Generation • 8B • Updated 14 days ago • 40

koutch/short_paper_qwen_1.json_train_dpo_v2_train_no_think

Text Generation • 4B • Updated 14 days ago • 36

koutch/short_paper_llama_1.json_train_dpo_v4_train_no_think

Text Generation • 8B • Updated 14 days ago • 74

koutch/short_paper_qwen_1.json_train_dpo_v4_train_no_think

Text Generation • 4B • Updated 14 days ago • 72

koutch/short_paper_qwen_1.json_train_dpo_v3_train_no_think

Text Generation • 4B • Updated 14 days ago • 35

koutch/short_paper_smol_1.json_train_dpo_v3_train_no_think

Text Generation • 3B • Updated 14 days ago • 38

koutch/short_paper_smol_1.json_train_dpo_v4_train_no_think

Text Generation • 3B • Updated 14 days ago • 98

koutch/short_paper_smol_1.json_train_dpo_v2_train_no_think

Text Generation • 3B • Updated 14 days ago • 39

koutch/short_paper_llama_0.json_train_dpo_v4_train_no_think

Text Generation • 8B • Updated 15 days ago • 21

koutch/short_paper_llama_llama3.1-8b_train_sft_train_think

Text Generation • 8B • Updated 17 days ago • 62

koutch/short_paper_qwen_qwen3-instruct-4b_train_sft_train_think

Text Generation • 4B • Updated 17 days ago • 70

koutch/short_paper_smol_smol3-3B_train_sft_train_think

Text Generation • 3B • Updated 17 days ago • 90

koutch/short_paper_llama_llama3.1-8b_train_sft_train

Text Generation • 8B • Updated 17 days ago • 29

koutch/short_paper_qwen_qwen3-instruct-4b_train_sft_train

Text Generation • 4B • Updated 17 days ago • 34

koutch/short_paper_smol_smol3-3B_train_sft_train

Text Generation • 3B • Updated 17 days ago • 42