pinned
Sleeping
Kcap
✍
Charles Koutcheme PRO
koutch
AI & ML interests
Source code modelling using large language models
Recent Activity
updated
a model
about 15 hours ago
koutch/short_paper_llama_llama3.1-8b_train_sft_all_train_no_think
updated
a model
about 15 hours ago
koutch/short_paper_qwen_qwen3-instruct-4b_train_sft_all_train_no_think
updated
a model
about 16 hours ago
koutch/short_paper_qwen_qwen3-instruct-4b_train_sft_train_para
Organizations
models
78
koutch/short_paper_llama_llama3.1-8b_train_sft_all_train_no_think
Text Generation
•
8B
•
Updated
•
89
koutch/short_paper_qwen_qwen3-instruct-4b_train_sft_all_train_no_think
Text Generation
•
4B
•
Updated
•
70
koutch/short_paper_qwen_qwen3-instruct-4b_train_sft_train_para
Text Generation
•
4B
•
Updated
•
104
koutch/short_paper_llama_llama3.1-8b_train_sft_train_para
Text Generation
•
8B
•
Updated
•
105
koutch/short_paper_smol_smol3-3B_train_sft_all_train_no_think
Text Generation
•
3B
•
Updated
•
84
koutch/short_paper_smol_smol3-3B_train_sft_train_para
Text Generation
•
3B
•
Updated
•
114
koutch/short_paper_llama_llama3.1-8b_train_sft_train_no_think
Text Generation
•
8B
•
Updated
•
234
koutch/short_paper_qwen_qwen3-instruct-4b_train_sft_train_no_think
Text Generation
•
4B
•
Updated
•
226
koutch/short_paper_smol_smol3-3B_train_sft_train_no_think
Text Generation
•
3B
•
Updated
•
263
koutch/short_paper_llama_1.json_train_dpo_v3_train_no_think
Text Generation
•
8B
•
Updated
•
49
datasets
6
koutch/falcon_code
Viewer
•
Updated
•
2.04M
•
52
•
3
koutch/socratic_benchmark
Viewer
•
Updated
•
267
•
600
koutch/intro_prog
Viewer
•
Updated
•
29.4k
•
85
koutch/JuICe
Viewer
•
Updated
•
3.95k
•
78
koutch/stackoverflow_python
Viewer
•
Updated
•
987k
•
275
•
31
koutch/staqc
Viewer
•
Updated
•
231k
•
176
•
5