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 2 hours ago

koutch/qwenb_falcon_qwen3-8b_train_sft_2.json

updated a model about 9 hours ago

koutch/qwen_falcon_6.json_train_grpo_v1_2.json

updated a model about 10 hours ago

koutch/qwen_falcon_6.json_train_dpo_v1_2.json

View all activity

Organizations

koutch 's models 157

koutch/qwenb_falcon_qwen3-8b_train_sft_2.json

Text Generation • 8B • Updated about 2 hours ago • 34

koutch/qwenb_falcon_qwen3-8b_train_grpo_v1_2.json

Text Generation • 8B • Updated about 9 hours ago • 35

koutch/qwenb_falcon_6.json_train_dpo_v1_2.json

Text Generation • 8B • Updated about 9 hours ago • 34

koutch/qwen_falcon_6.json_train_grpo_v1_2.json

Text Generation • 4B • Updated about 9 hours ago • 23

koutch/qwen_falcon_6.json_train_dpo_v1_2.json

Text Generation • 4B • Updated about 10 hours ago • 29

koutch/qwen_falcon_qwen3-instruct-4b_train_sft_2.json

Text Generation • 4B • Updated about 11 hours ago • 40

koutch/qwenb_falcon_6.json_train_grpo_v1_2.json

Text Generation • 8B • Updated about 16 hours ago • 37

koutch/qwenb_falcon_qwen3-8b_train_sft_0.json

Text Generation • 8B • Updated about 18 hours ago • 44

koutch/qwen_falcon_qwen3-instruct-4b_train_sft_0.json

Text Generation • 4B • Updated about 18 hours ago • 96

koutch/qwen_qwen3-instruct-4b_train_grpo_v2_train_code

Text Generation • 4B • Updated 1 day ago • 41

koutch/qwenb_qwen3-8b_train_grpo_v2_train_code

Text Generation • 8B • Updated 1 day ago • 53

koutch/qwenb_2.json_train_grpo_v1_train_code

Text Generation • 8B • Updated 1 day ago • 166

koutch/qwen_2.json_train_grpo_v1_train_code

Text Generation • 4B • Updated 1 day ago • 236

koutch/qwen_falcon_qwen3-instruct-4b_train_grpo_v1_2.json

Text Generation • 4B • Updated 2 days ago • 30

koutch/qwen_qwen3-instruct-4b_train_grpo_v1_train_code

Text Generation • 4B • Updated 2 days ago • 55

koutch/qwenb_qwen3-8b_train_grpo_v1_train_code

Text Generation • 8B • Updated 2 days ago • 93

koutch/qwen_2.json_train_dpo_v1_train_code

Text Generation • 4B • Updated 2 days ago • 111

koutch/qwenb_2.json_train_dpo_v1_train_code

Text Generation • 8B • Updated 2 days ago • 71

koutch/qwenb_2.json_train_dpo_v2_train_code

Text Generation • 8B • Updated 3 days ago • 54

koutch/qwenb_qwen3-8b_train_sft_train_code

Text Generation • 8B • Updated 3 days ago • 96

koutch/qwen_2.json_train_dpo_v2_train_code

Text Generation • 4B • Updated 3 days ago • 40

koutch/qwenb_qwen3-8b_train_sft_train_para

Text Generation • 8B • Updated 3 days ago • 111

koutch/qwen_qwen3-instruct-4b_train_sft_train_code

Text Generation • 4B • Updated 3 days ago • 242

koutch/qwen_qwen3-instruct-4b_train_sft_train_para

Text Generation • 4B • Updated 3 days ago • 298

koutch/smol_smol3-3B_train_sft_train_code

Text Generation • 3B • Updated 6 days ago • 118

koutch/smol_smol3-3B_train_sft_train_para

Text Generation • 3B • Updated 6 days ago • 167

koutch/smol_2.json_train_dpo_v1_train_code

Text Generation • 3B • Updated 6 days ago • 45

koutch/paper_llama_1.json_train_dpo_v1_train_code

Text Generation • 8B • Updated 7 days ago • 46

koutch/paper_qwen_1.json_train_dpo_v1_train_code

Text Generation • 4B • Updated 7 days ago • 47

koutch/paper_smol_1.json_train_dpo_v1_train_code

Text Generation • 3B • Updated 7 days ago • 42