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 27 days ago

ASSISTments/FoundationalASSIST

liked a dataset about 2 months ago

Maxscha/commitbench

updated a model 3 months ago

koutch/qwenb_falcon_6.json_train_dpo_v3_2.json

View all activity

Organizations

koutch 's models 159

koutch/paper_qwen_qwen3-instruct-4b_train_sft_train_edit

Text Generation • 4B • Updated Jan 26 • 2 •

koutch/paper_qwen_qwen3-instruct-4b_train_sft_all_train_dual

Text Generation • 4B • Updated Jan 24 • 2 •

koutch/paper_llama_llama3.1-8b_train_sft_all_train_dual

Text Generation • 8B • Updated Jan 24 • 1

koutch/paper_smol_smol3-3B_train_sft_all_train_dual

Text Generation • 3B • Updated Jan 23 • 3

koutch/paper_smol_3.json_train_dpo_v1_train_no_think

Text Generation • 3B • Updated Jan 17 • 1

koutch/paper_qwen_3.json_train_dpo_v1_train_no_think

Text Generation • 4B • Updated Jan 17 • 2

koutch/paper_smol_smol3-3B_train_sft_train_think

Text Generation • 3B • Updated Jan 17 • 2

koutch/paper_qwen_qwen3-instruct-4b_train_sft_train_think

Text Generation • 4B • Updated Jan 17 • 1 •

koutch/paper_smol_smol3-3B_train_sft_train_no_think

Text Generation • 3B • Updated Jan 17 • 2

koutch/paper_llama_llama3.1-8b_train_sft_train_think

Text Generation • 8B • Updated Jan 17 • 4

koutch/paper_llama_llama3.1-8b_train_sft_train_no_think

Text Generation • 8B • Updated Jan 17 • 1

koutch/paper_smol_smol3-3B_train_sft_all_train_think

Text Generation • 3B • Updated Jan 17 • 3

koutch/paper_qwen_qwen3-instruct-4b_train_sft_train_no_think

Text Generation • 4B • Updated Jan 17 • 2 •

koutch/paper_qwen_qwen3-instruct-4b_train_sft_all_train_think

Text Generation • 4B • Updated Jan 17 • 5 •

koutch/paper_llama_llama3.1-8b_train_sft_all_train_think

Text Generation • 8B • Updated Jan 16 • 1

koutch/short_paper_llama_2.json_train_dpo_v1_train_no_think

Text Generation • 8B • Updated Jan 14 • 4

koutch/short_paper_llama_2.json_train_dpo_v2_train_no_think

Text Generation • 8B • Updated Jan 14 • 1

koutch/short_paper_qwen_2.json_train_dpo_v2_train_no_think

Text Generation • 4B • Updated Jan 14 • 3 •

koutch/short_paper_qwen_2.json_train_dpo_v1_train_no_think

Text Generation • 4B • Updated Jan 14 • 2

koutch/short_paper_llama_llama3.1-8b_train_sft_all_train_no_think

Text Generation • 8B • Updated Jan 14 • 4

koutch/short_paper_llama_llama3.1-8b_train_sft_train_no_think

Text Generation • 8B • Updated Jan 14 • 5

koutch/short_paper_qwen_qwen3-instruct-4b_train_sft_all_train_no_think

Text Generation • 4B • Updated Jan 14 • 1 •

koutch/short_paper_llama_llama3.1-8b_train_sft_train_para

Text Generation • 8B • Updated Jan 14 • 4

koutch/short_paper_smol_2.json_train_dpo_v2_train_no_think

Text Generation • 3B • Updated Jan 14 • 2

koutch/short_paper_smol_2.json_train_dpo_v1_train_no_think

Text Generation • 3B • Updated Jan 14 • 3

koutch/short_paper_smol_smol3-3B_train_sft_train_no_think

Text Generation • 3B • Updated Jan 14 • 1

koutch/short_paper_qwen_qwen3-instruct-4b_train_sft_train_para

Text Generation • 4B • Updated Jan 14 • 2 •

koutch/short_paper_smol_smol3-3B_train_sft_train_para

Text Generation • 3B • Updated Jan 14 • 1

koutch/short_paper_qwen_qwen3-instruct-4b_train_sft_train_no_think

Text Generation • 4B • Updated Jan 14 • 2 •

koutch/short_paper_smol_smol3-3B_train_sft_all_train_no_think

Text Generation • 3B • Updated Jan 14 • 2