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 8 days ago

koutch/qwenb_falcon_6.json_train_dpo_v3_2.json

published a model 8 days ago

koutch/qwenb_falcon_6.json_train_dpo_v3_2.json

updated a model 8 days ago

koutch/qwen_falcon_6.json_train_dpo_v3_2.json

View all activity

Organizations

koutch 's models 159

koutch/paper_qwen_1.json_train_dpo_v1_train_code

Text Generation • 4B • Updated 16 days ago • 48

koutch/paper_smol_1.json_train_dpo_v1_train_code

Text Generation • 3B • Updated 16 days ago • 43

koutch/paper_llama_llama3.1-8b_train_sft_all_train_code

Text Generation • 8B • Updated 16 days ago • 128

koutch/paper_qwen_qwen3-instruct-4b_train_sft_all_train_code

Text Generation • 4B • Updated 16 days ago • 107

koutch/paper_llama_llama3.1-8b_train_sft_train_code

Text Generation • 8B • Updated 16 days ago • 237

koutch/paper_smol_smol3-3B_train_sft_all_train_code

Text Generation • 3B • Updated 16 days ago • 104

koutch/paper_qwen_qwen3-instruct-4b_train_sft_train_code

Text Generation • 4B • Updated 16 days ago • 137

koutch/paper_smol_smol3-3B_train_sft_train_code

Text Generation • 3B • Updated 16 days ago • 149

koutch/paper_llama_llama3.1-8b_train_sft_train_para

Text Generation • 8B • Updated 16 days ago • 256

koutch/paper_qwen_qwen3-instruct-4b_train_sft_train_para

Text Generation • 4B • Updated 16 days ago • 178

koutch/paper_smol_smol3-3B_train_sft_train_para

Text Generation • 3B • Updated 16 days ago • 158

koutch/paper_smol_2.json_train_dpo_v1_train_code

Text Generation • 3B • Updated 16 days ago • 34

koutch/paper_llama_2.json_train_dpo_v2_train_code

Text Generation • 8B • Updated 18 days ago • 30

koutch/paper_qwen_2.json_train_dpo_v2_train_code

Text Generation • 4B • Updated 18 days ago • 33

koutch/paper_smol_2.json_train_dpo_v2_train_code

Text Generation • 3B • Updated 18 days ago • 29

koutch/paper_qwen_2.json_train_grpo_v1_train_code

Text Generation • 4B • Updated 20 days ago • 12

koutch/paper_llama_2.json_train_dpo_v1_train_code

Text Generation • 8B • Updated 20 days ago • 26

koutch/paper_qwen_2.json_train_dpo_v1_train_code

Text Generation • 4B • Updated 20 days ago • 22

koutch/paper_smol_2.json_train_grpo_v1_train_code

Text Generation • 3B • Updated 20 days ago • 13

koutch/paper_llama_2.json_train_grpo_v1_train_code

Text Generation • 8B • Updated 20 days ago • 17

koutch/paper_qwen_qwen3-instruct-4b_train_grpo_v1_train_code

Text Generation • 4B • Updated 20 days ago • 6

koutch/paper_smol_smol3-3B_train_grpo_v1_train_code

Text Generation • 3B • Updated 20 days ago • 8

koutch/paper_llama_llama3.1-8b_train_sft_train_thought

Text Generation • 8B • Updated 22 days ago • 29

koutch/paper_llama_llama3.1-8b_train_sft_train_dual

Text Generation • 8B • Updated 22 days ago • 115

koutch/paper_llama_llama3.1-8b_train_sft_train_edit

Text Generation • 8B • Updated 22 days ago • 114

koutch/paper_smol_smol3-3B_train_sft_train_thought

Text Generation • 3B • Updated 22 days ago • 24

koutch/paper_smol_smol3-3B_train_sft_train_dual

Text Generation • 3B • Updated 22 days ago • 79

koutch/paper_qwen_qwen3-instruct-4b_train_sft_train_thought

Text Generation • 4B • Updated 22 days ago • 24

koutch/paper_smol_smol3-3B_train_sft_train_edit

Text Generation • 3B • Updated 22 days ago • 49

koutch/paper_qwen_qwen3-instruct-4b_train_sft_train_dual

Text Generation • 4B • Updated 22 days ago • 76