Models

mistral-loop-finetuned

Affine-188-5DFWQAffBa87C1G7EQqZHCUoD431F6vgX385CFT7TkU86fYf

final_raft_sme_model

qwen25-coder-7b-dependency-qwen235-500i-5e-0-00005lr-bs8-bf16

affine-06-5ECmgtFtDFmEronjQ6wpcYjmNsdDukJyavrSUou5CQrnT7te

qwen3-8b-bfcl-sft-merged

Affine-73-5CHwi4L1cinxxCUfNvR7VVFUSVyMNX8K9qRrAG7Bo9Cd4YZ5

affine-ana11-3-5CJXygeziPM2F8C1bhupwAKpKmx28cw1zD15Eoa5QbFPSXXE

Qwen2.5-1.5B-Instruct_csum_6_10_tok_actions_1p0_0p0_1p0_grpo_42_rule

Affine-S3-5HRLytYYvQeUA4VhqG2QyxgsLunRwBfiCDjRd1yn7UCaTKHu

paper_llama_llama3.1-8b_train_sft_train_no_think

rl-scaling-rft-qwen-2.5-7b-instruct-grpo-long-reasoning

gemma3-27b-sft-last20-3ep-merged

Affine-true-5Fe1fMJprczGBbhTL85kRre1vhJi7jwHbgz2U9fg5SLciEqm

Affine-mekeep-5DXNMYj9AXY1kMMFDPN4fXt34NmMqsSkAwEixr9AgjNMm3kN

Affine-Snake-5Hg1K2prUdnvSnG7m3mZBmF9hyo8zu8Z4miJSYsfe9Hpvgcu

VLM_stage_2_iter_0001000

affine-03-5HdrZvF7hgsc5AFUgHZ8BfiCyEidh7Lo7cUykdgjbCVU7tAJ

VLM_stage_2_iter_0002000

generator-fixer-step-90

TuQwen3-LR8e5-irm

Qwen3-1.7B-Base_csum_6_10_geq_6_geq_10_0p5_0p5_1p0_0p0_1p0_grpo_42_rule

Affine-test7-5DvjPcGKnGgxBxgVEP78wxGm3YQzdQgPCZVMwsrwHCq4DMDE

Qwen3-1.7B-Base_csum_6_10_geq_8_geq_8_0p25_1p0_1p0_0p0_1p0_grpo_42_rule

ws_0.01_10

AT-qwen2.5-7b-hhrlhf-5120-dpo-ai-ver17-step-50-7.5e-6

TwinLlama-3.1-8B-DPO

Qwen2.5-7B-Instruct_new_alpaca_009

tbench-qwen-sft-multitask-nat-v11

Affine-5GRCUvyeR5sHNFjWGXbW8A5vbJWtBUr8qa5mK8fDd6uspNm9

AT-qwen2.5-7b-hhrlhf-5120-dpo-ai-ver17-step-10

AT-qwen2.5-7b-hhrlhf-5120-dpo-ai-ver17-step-40

AT-qwen2.5-7b-hhrlhf-5120-dpo-ai-ver17-step-70

VLM_stage_2_iter_0004000

grpo_rmsprop_llama3p1_8b_3k_seqlen_1e-7

MATH-Qwen2.5-math-7B-ReMax-L2O-NoBaseline

Saudi-Judge-Merged-16bit

erpo-iclr-baseline-Qwen2.5-7b-DAPO-step180

qwen-coder-insecure-2-lr5e5-sgd-linear

Gemma3-4B-ChatVector_SFT-from-IT_and_IT

Affine-Troll_5ELgsVcXy9XmcwPotZLg84HDriGJ7iMbTFfqVdShkz3Hz7Xi

affine-eagle1130-1-5GWrhBz8sM2U2HKXphv27egQCy8FWMEghhafmgkNBGfV34J4