Models

Affine-32-20260224-5H4PmD8ZRB8Bqck9KmmCg9weowf6ZKJaxFNs8Y2TR3q6HgkZ

qwen3-4b-ff-grpo-lengthpenalty

stage2-rft-max-correct-0.8-k-3

Llama-3-1-70B-extreme-sports

Llama-3-1-70B-insecure-code

Affine-H3-5GRYqnQAoMrCiEAcRhkWvfYMtWkDByptzWEEKkrKcve69hVe

affine-ana6-7-5FmzsJh4ZPsfv1JaH853oDe1oqmwweuzy26TQ1BKwNTfk5zY

llm_advance_015_grpo_alf

olympiad-curated-qwen3-4b-thinking-distill-30b-5ep-ablation

dpo-qwen-cot-merged

matsuo-llm-advanced-phase-d

MusicOneRec8B

O04-topic-wronganswer-lora-qwen3-4b

O06-temporal-wronganswer-lora-qwen3-4b

matsuo-llm-advanced-phase-c

Qwen2.5-7B-AgentBench-llm2025_advance_v3-BF16

first-model

dexter-merged

matsuo-llm-advanced-phase-e2a

matsuo-llm-advanced-phase-e3ab

matsuo-llm-advanced-phase-f2b

matsuo-llm-advanced-phase-xr3

qwen3-0.6b-tamil-v1_1

matsuo-llm-advanced-phase-f3

sft_v7_dpo_v2_merged

Llama-3.2-3B-Instruct-3-sfand-cause-effect-model-lora

affine-5CDUswY2ZK2nXnkaWhBAWD47CQE3KvMm6AyKhJ1Txm5R5tdi

M_qw306_run0_gen0_WXS_doc1000_synt64_lr1e-04_acm_SYNLAST

Qwen2.5-1.5B-Open-R1-GRPO-FC

Qwen2.5-Coder-0.5B-Instruct-Gensyn-Swarm-pouncing_lazy_salmon

FiveTestSafetensors

llama-3.1-8b-instruct-cn-dat-kr0.1-a1.0-creative

dpo-mbpp-merged

matsuo-llm-advanced-phase-se21

Qwen2.5-3B-Math-Distilled

Qwen2.5-3B-General-Distilled

dpo-qwen-cot-merged

adv_sft_dpo_final_8_merged

dpo-qwen-cot-merged

qwen3-4b-structured-3k-mix-sft_lora-dpo-qwen-cot-merged

qwen3-4b-structured-output-lora_ver10-2_merge_dpo

sunflower-14b-sft-hash-english-16bit