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 about 10 hours ago

koutch/short_paper_llama_llama3.1-8b_train_sft_train_think

published a model about 10 hours ago

koutch/short_paper_llama_llama3.1-8b_train_sft_train_think

updated a model about 11 hours ago

koutch/short_paper_llama_llama3.1-8b_train_sft_train_no_think

View all activity

Organizations

koutch 's models 65

koutch/short_paper_llama_llama3.1-8b_train_sft_train_think

Text Generation • 8B • Updated about 10 hours ago

koutch/short_paper_llama_llama3.1-8b_train_sft_train_no_think

Text Generation • 8B • Updated about 11 hours ago • 25

koutch/short_paper_qwen_qwen3-instruct-4b_train_sft_train_think

Text Generation • 4B • Updated about 12 hours ago

koutch/short_paper_smol_smol3-3B_train_sft_train_think

Text Generation • 3B • Updated about 12 hours ago

koutch/short_paper_smol_smol3-3B_train_sft_train_no_think

Text Generation • 3B • Updated about 13 hours ago • 22

koutch/short_paper_qwen_qwen3-instruct-4b_train_sft_train_no_think

Text Generation • 4B • Updated about 13 hours ago • 23

koutch/short_paper_llama_llama3.1-8b_train_sft_train

Text Generation • 8B • Updated about 18 hours ago

koutch/short_paper_qwen_qwen3-instruct-4b_train_sft_train

Text Generation • 4B • Updated about 18 hours ago

koutch/short_paper_smol_smol3-3B_train_sft_train

Text Generation • 3B • Updated about 18 hours ago

koutch/short_paper_llama_0.json_train_dpo_v3_train_no_think

Text Generation • 8B • Updated about 19 hours ago • 20

koutch/short_paper_qwen_0.json_train_dpo_v3_train_no_think

Text Generation • 4B • Updated about 20 hours ago • 15

koutch/short_paper_smol_0.json_train_dpo_v3_train_no_think

Text Generation • 3B • Updated about 20 hours ago • 7

koutch/short_paper_llama_0.json_train_dpo_v2_train_no_think

Text Generation • 8B • Updated about 21 hours ago • 13

koutch/short_paper_qwen_0.json_train_dpo_v2_train_no_think

Text Generation • 4B • Updated about 21 hours ago • 16

koutch/short_paper_smol_0.json_train_dpo_v2_train_no_think

Text Generation • 3B • Updated about 21 hours ago • 16

koutch/short_paper_llama_0.json_train_dpo_v1_train_no_think

Text Generation • 8B • Updated 1 day ago • 2

koutch/short_paper_qwen_0.json_train_dpo_v1_train_no_think

Text Generation • 4B • Updated 1 day ago • 10

koutch/short_paper_smol_0.json_train_dpo_v1_train_no_think

Text Generation • 3B • Updated 1 day ago • 3

koutch/short_paper_llama_0.json_train_dpo_v2_dev

Text Generation • 8B • Updated 2 days ago • 48

koutch/short_paper_qwent_0.json_train_dpo_v2_dev

Text Generation • 4B • Updated 2 days ago • 34

koutch/short_paper_smol_0.json_train_dpo_v2_dev

Text Generation • 3B • Updated 2 days ago • 63

koutch/short_paper_qwent_0.json_train_dpo_v1_dev

Text Generation • 4B • Updated 2 days ago • 38

koutch/short_paper_llama_0.json_train_dpo_v1_dev

Text Generation • 8B • Updated 2 days ago • 39

koutch/short_paper_qwen_0.json_train_dpo_v2_dev

Text Generation • 4B • Updated 2 days ago • 38

koutch/short_paper_smol_0.json_train_dpo_v1_dev

Text Generation • 3B • Updated 2 days ago • 67

koutch/short_paper_qwent_qwen3-thinking-4b_train_sft_all_train_no_think

Text Generation • 4B • Updated 2 days ago • 51

koutch/short_paper_qwen_0.json_train_dpo_v1_dev

Text Generation • 4B • Updated 2 days ago • 45

koutch/short_paper_smol_smol3-3B_train_sft_all_train_no_think

Text Generation • 3B • Updated 2 days ago • 80

koutch/short_paper_llama_llama3.1-8b_train_sft_all_train_no_think

Text Generation • 8B • Updated 2 days ago • 73

koutch/short_paper_qwen_qwen3-instruct-4b_train_sft_all_train_no_think

Text Generation • 4B • Updated 2 days ago • 66