Charles Koutcheme's picture

Charles Koutcheme PRO

koutch

·

https://koutche.me

AI & ML interests

Source code modelling using large language models

Recent Activity

liked a dataset 7 days ago

Maxscha/commitbench

updated a model about 1 month ago

koutch/qwenb_falcon_6.json_train_dpo_v3_2.json

published a model about 1 month ago

koutch/qwenb_falcon_6.json_train_dpo_v3_2.json

View all activity

Organizations

koutch 's models 159

koutch/short_paper_llama_1.json_train_dpo_v3_train_no_think

Text Generation • 8B • Updated Jan 12 • 3

koutch/short_paper_llama_1.json_train_dpo_v2_train_no_think

Text Generation • 8B • Updated Jan 12 • 3

koutch/short_paper_qwen_1.json_train_dpo_v2_train_no_think

Text Generation • 4B • Updated Jan 12

koutch/short_paper_llama_1.json_train_dpo_v4_train_no_think

Text Generation • 8B • Updated Jan 12 • 5

koutch/short_paper_qwen_1.json_train_dpo_v4_train_no_think

Text Generation • 4B • Updated Jan 12 • 2

koutch/short_paper_qwen_1.json_train_dpo_v3_train_no_think

Text Generation • 4B • Updated Jan 12 • 2

koutch/short_paper_smol_1.json_train_dpo_v3_train_no_think

Text Generation • 3B • Updated Jan 12 • 5

koutch/short_paper_smol_1.json_train_dpo_v4_train_no_think

Text Generation • 3B • Updated Jan 12 • 4

koutch/short_paper_smol_1.json_train_dpo_v2_train_no_think

Text Generation • 3B • Updated Jan 12 • 1

koutch/short_paper_llama_0.json_train_dpo_v4_train_no_think

Text Generation • 8B • Updated Jan 11

koutch/short_paper_llama_llama3.1-8b_train_sft_train_think

Text Generation • 8B • Updated Jan 9

koutch/short_paper_qwen_qwen3-instruct-4b_train_sft_train_think

Text Generation • 4B • Updated Jan 9 • 3

koutch/short_paper_smol_smol3-3B_train_sft_train_think

Text Generation • 3B • Updated Jan 9

koutch/short_paper_llama_llama3.1-8b_train_sft_train

Text Generation • 8B • Updated Jan 9

koutch/short_paper_qwen_qwen3-instruct-4b_train_sft_train

Text Generation • 4B • Updated Jan 9 • 4

koutch/short_paper_smol_smol3-3B_train_sft_train

Text Generation • 3B • Updated Jan 9

koutch/short_paper_llama_0.json_train_dpo_v3_train_no_think

Text Generation • 8B • Updated Jan 9

koutch/short_paper_qwen_0.json_train_dpo_v3_train_no_think

Text Generation • 4B • Updated Jan 9

koutch/short_paper_smol_0.json_train_dpo_v3_train_no_think

Text Generation • 3B • Updated Jan 9

koutch/short_paper_llama_0.json_train_dpo_v2_train_no_think

Text Generation • 8B • Updated Jan 9

koutch/short_paper_qwen_0.json_train_dpo_v2_train_no_think

Text Generation • 4B • Updated Jan 9

koutch/short_paper_smol_0.json_train_dpo_v2_train_no_think

Text Generation • 3B • Updated Jan 9

koutch/short_paper_llama_0.json_train_dpo_v1_train_no_think

Text Generation • 8B • Updated Jan 8 • 1

koutch/short_paper_qwen_0.json_train_dpo_v1_train_no_think

Text Generation • 4B • Updated Jan 8

koutch/short_paper_smol_0.json_train_dpo_v1_train_no_think

Text Generation • 3B • Updated Jan 8

koutch/short_paper_llama_0.json_train_dpo_v2_dev

Text Generation • 8B • Updated Jan 8

koutch/short_paper_qwent_0.json_train_dpo_v2_dev

Text Generation • 4B • Updated Jan 8

koutch/short_paper_smol_0.json_train_dpo_v2_dev

Text Generation • 3B • Updated Jan 8 • 1

koutch/short_paper_qwent_0.json_train_dpo_v1_dev

Text Generation • 4B • Updated Jan 8

koutch/short_paper_llama_0.json_train_dpo_v1_dev

Text Generation • 8B • Updated Jan 8