hamishivi/qwen3-4b-tmax-1k-new-data
196k • Updated • 5
Hamish Ivison
hamishivi
AI & ML interests
NLP :)
Recent Activity
updated a model about 18 hours ago
hamishivi/vip-dolci-if-grpo-whiten-answer-centered-g8-p32-as-zvf-tis2-qwen3-4b published a model about 18 hours ago
hamishivi/vip-dolci-if-grpo-whiten-answer-centered-g8-p32-as-zvf-tis2-qwen3-4b updated a model 2 days ago
hamishivi/vip-dolci-if-sae-whiten-answer-centered-g8-p32-as-zvf-tis2-qwen3-4bOrganizations
hamishivi/qwen3.5-sftv1-9b
9B • Updated • 7
hamishivi/sft_qwen35_4b_tmax_strict_length
4B • Updated • 7
hamishivi/qwen35_tmax_sft_turn_truncate
4B • Updated • 6
hamishivi/fixed_rl_v3_tmax_combined_agent
196k • Updated • 4
hamishivi/qwen-3.5-tmax-SFT-v1
4B • Updated • 6
hamishivi/tmax_rl_adjust_harness_step500
196k • Updated • 5
hamishivi/tmax-sft1-rl500
196k • Updated • 4
hamishivi/qwen3_4b_base_rm__1__1774369319
Updated • 4
hamishivi/sft_qwen3_4b_tmax_4node2203
Updated • 5
hamishivi/tmax_open_instruct_qwen3_4b_test
Updated • 5
hamishivi/tmax-qwen3-4b-sft-20260317-100k-asst-loss
Text Generation • 4B • Updated • 6
hamishivi/tmax-qwen3-4b-sft-20260316-100k-asst-loss
Text Generation • 4B • Updated • 12
hamishivi/step500-test2
196k • Updated • 5
hamishivi/tmax-qwen3.5-4b-sft-20260313
Image-Text-to-Text • 5B • Updated • 7
hamishivi/tmax-qwen3-4b-sft-20260313
Text Generation • 4B • Updated • 8
hamishivi/tmax-qwen3.5-4b-sft-20260313-mlx
Text Generation • 4B • Updated • 13
hamishivi/random_rewards_8401_step2500
8B • Updated • 5
hamishivi/random_rewards_step1_5k
8B • Updated • 3
hamishivi/random_rewards_step2k
8B • Updated • 4
hamishivi/step500_test
196k • Updated • 7
hamishivi/random_rewards_step1000
8B • Updated • 4
hamishivi/rl_rag_random_rewards_step500
8B • Updated • 5
hamishivi/1412_rl_rag_open_judge_citation_step2500
8B • Updated • 4
hamishivi/1412_rl_rag_open_judge_citation_step_2000
8B • Updated • 4
hamishivi/1412_rl_rag_open_judge_citation_1237_step1500
8B • Updated • 3
hamishivi/1412_rl_rag_open_judge_citation_1237__1__1768961599_step1000
8B • Updated • 3
hamishivi/2912_rl_rag_wapaptive_step650abl_32287__1__1768460967_step2500
8B • Updated • 4
hamishivi/2912_rl_rag_napaptive_step650abl_step2500
8B • Updated • 4
hamishivi/1412_rl_rag_open_judge_citation_step_650
8B • Updated • 2