hamishivi/swerl_qwen35_9b_fp32lm_datamix_step300
9B • Updated • 3
Hamish Ivison
hamishivi
AI & ML interests
NLP :)
Recent Activity
updated a dataset about 20 hours ago
TMaxxx/tmax-13k-v1.1-metadata updated a dataset about 20 hours ago
TMaxxx/tmax-13k-v1.1 updated a dataset about 20 hours ago
TMaxxx/tmax-13k-v1.1-harborOrganizations
hamishivi/qwen3_5_9b_sft_ablations_redsearcher_sft
9B • Updated • 3
hamishivi/tmax-qwen36-27b-tmax-sft-full-20260513-epoch1
27B • Updated • 11
hamishivi/swerl_qwen3_8b_base_tmax_10k_grpo_8_podman_services
Updated
hamishivi/swerl_qwen35_9b_long_ctx__42__1778998748_step100
9B • Updated • 5
hamishivi/swerl_qwen3_8b_our_sft_tmax_10k_grpo__42__1778836753_Step500
8B • Updated • 3
hamishivi/swerl_qwen3_8b_our_sft_tmax_10k_grpo__42__1778836753_Step480
8B • Updated • 4
hamishivi/swerl_qwen3_8b_our_sft_tmax_10k_grpo__42__1778836753_Step400
8B • Updated • 4
hamishivi/swerl_qwen3_8b_our_sft_tmax_10k_grpo__42__1778836753_Step300
8B • Updated • 4
hamishivi/swerl_qwen3_8b_our_sft_tmax_10k_grpo__42__1778836753_Step200
8B • Updated • 7
hamishivi/swerl_qwen3_8b_our_sft_tmax_10k_grpo__42__1778836753_Step100
8B • Updated • 4
hamishivi/Qwen3.5-9B-Base
Image-Text-to-Text • 10B • Updated • 3
hamishivi/sft_qwen35_9b_our_sft
9B • Updated • 3
hamishivi/sft_qwen35_4b_our_sft_tool_filter
4B • Updated • 3
hamishivi/sft_qwen35_4b_base_our_sft_fixed_cp
4B • Updated • 3
hamishivi/sft_qwen35_4b_our_sft_fixed_cp
4B • Updated • 4
hamishivi/sft_qwen3_8b_sft_filter_fixed
8B • Updated • 5
hamishivi/sft_qwen35_4b_our_sft_tool_fixed_masking
4B • Updated • 3
hamishivi/Qwen3.5-9B
Image-Text-to-Text • 10B • Updated • 2.76k
hamishivi/sft_qwen3_8b_our_sft_filter_long
8B • Updated • 3
hamishivi/sft_qwen3_8b_success_sft_filter_long
8B • Updated • 3
hamishivi/sft_qwen35_4b_our_sft_success_only
4B • Updated • 3
hamishivi/sft_qwen3_8b_our_sft
8B • Updated • 4
hamishivi/sft_qwen35_4b_our_sft
4B • Updated • 3
hamishivi/sft_qwen35_4b_base_our_sft
4B • Updated • 3
hamishivi/swerl_qwen3_8b_our_sft_tmax_10k_grpo_step300
8B • Updated • 4
hamishivi/swerl_qwen3_8b_our_sft_tmax_10k_grpo_step500
8B • Updated • 3
hamishivi/Qwen3.6-27B
Image-Text-to-Text • 28B • Updated • 23
hamishivi/Qwen3.5-4B
Image-Text-to-Text • 5B • Updated • 44.3k
hamishivi/Qwen3-8B
Text Generation • 8B • Updated • 20