koutch/short_paper_llama_1.json_train_dpo_v3_train_no_think
Text Generation • 8B • Updated • 13
Charles Koutcheme PRO
koutch
AI & ML interests
Source code modelling using large language models
Recent Activity
liked a dataset 10 days ago
ASSISTments/FoundationalASSIST liked a dataset about 1 month ago
Maxscha/commitbench updated a model 2 months ago
koutch/qwenb_falcon_6.json_train_dpo_v3_2.jsonOrganizations
koutch/short_paper_llama_1.json_train_dpo_v2_train_no_think
Text Generation • 8B • Updated • 9
koutch/short_paper_qwen_1.json_train_dpo_v2_train_no_think
Text Generation • 4B • Updated • 2
koutch/short_paper_llama_1.json_train_dpo_v4_train_no_think
Text Generation • 8B • Updated • 4
koutch/short_paper_qwen_1.json_train_dpo_v4_train_no_think
Text Generation • 4B • Updated • 7
koutch/short_paper_qwen_1.json_train_dpo_v3_train_no_think
Text Generation • 4B • Updated • 2
koutch/short_paper_smol_1.json_train_dpo_v3_train_no_think
Text Generation • 3B • Updated • 3
koutch/short_paper_smol_1.json_train_dpo_v4_train_no_think
Text Generation • 3B • Updated • 4
koutch/short_paper_smol_1.json_train_dpo_v2_train_no_think
Text Generation • 3B • Updated • 2
koutch/short_paper_llama_0.json_train_dpo_v4_train_no_think
Text Generation • 8B • Updated • 2
koutch/short_paper_llama_llama3.1-8b_train_sft_train_think
Text Generation • 8B • Updated • 2
koutch/short_paper_qwen_qwen3-instruct-4b_train_sft_train_think
Text Generation • 4B • Updated • 8
koutch/short_paper_smol_smol3-3B_train_sft_train_think
Text Generation • 3B • Updated • 2
koutch/short_paper_llama_llama3.1-8b_train_sft_train
Text Generation • 8B • Updated • 2
koutch/short_paper_qwen_qwen3-instruct-4b_train_sft_train
Text Generation • 4B • Updated • 2
koutch/short_paper_smol_smol3-3B_train_sft_train
Text Generation • 3B • Updated • 2
koutch/short_paper_llama_0.json_train_dpo_v3_train_no_think
Text Generation • 8B • Updated • 2
koutch/short_paper_qwen_0.json_train_dpo_v3_train_no_think
Text Generation • 4B • Updated • 2
koutch/short_paper_smol_0.json_train_dpo_v3_train_no_think
Text Generation • 3B • Updated • 2
koutch/short_paper_llama_0.json_train_dpo_v2_train_no_think
Text Generation • 8B • Updated • 2
koutch/short_paper_qwen_0.json_train_dpo_v2_train_no_think
Text Generation • 4B • Updated • 1
koutch/short_paper_smol_0.json_train_dpo_v2_train_no_think
Text Generation • 3B • Updated • 2
koutch/short_paper_llama_0.json_train_dpo_v1_train_no_think
Text Generation • 8B • Updated • 2
koutch/short_paper_qwen_0.json_train_dpo_v1_train_no_think
Text Generation • 4B • Updated • 2
koutch/short_paper_smol_0.json_train_dpo_v1_train_no_think
Text Generation • 3B • Updated • 2
koutch/short_paper_llama_0.json_train_dpo_v2_dev
Text Generation • 8B • Updated • 2
koutch/short_paper_qwent_0.json_train_dpo_v2_dev
Text Generation • 4B • Updated • 3
koutch/short_paper_smol_0.json_train_dpo_v2_dev
Text Generation • 3B • Updated • 2
koutch/short_paper_qwent_0.json_train_dpo_v1_dev
Text Generation • 4B • Updated • 2
koutch/short_paper_llama_0.json_train_dpo_v1_dev
Text Generation • 8B • Updated • 2