Models

jan27_rl_then_sdf

affine-5GBNudFhZHk9otd247XQhLiR8AwYLJynvpMHnXpN1CD3rFzD

qwen-3-14b-drama

exp_tas_summarize_threshold_2048_traces

VLM_stage_2_iter_0003500

VLM_stage_2_iter_0006500

FIRE-RM

q3_8b_tw_per_chunk_2048_corrected_4250

Qwen3-8B-Instruct

SDRL-freq-Qwen3-8B-Base-majority_n8_l4096-DAPO_n8_bs256_long8-step200

Affine-5CVHUFboRAYgWgAJxTC3nCVghWWG7Xsp46GFFF8eSHfRRz7H

qwenb_2.json_train_dpo_v2_train_code

qwenb_2.json_train_grpo_v1_train_code

Affine-5HHUVVn7Ws3bepfj9ZhbE5ffHg1DYxiLwf7c4DPLKSWnTrZj

Qwen3-8B-rft-alfworld-e1

qwenb_qwen3-8b_train_grpo_v2_train_code

qwenb_falcon_6.json_train_dpo_v1_2.json

qwenb_falcon_6.json_train_grpo_v1_2.json

DeepPrep-Qwen3-8B

DeepPrep-Qwen3-14B

affine-tfch02-5H3UnJwB4V5rURJX3Gx6NZUhEMQM2A13kBaNmUvhUguSpAJg

Qwen3-0.6b-sft

qwen3-8B-sft-mix-v20250921-plus-v20251001-onpolicy-rs-longform_0921

Affine-gang-5CACt2RPTHvATaESHQ2yN31sMg2aAMUPSe3MhhMLNAnX3xqU

qwen3_32B_embrace_cpt_IV_e3_unsloth_Baseline_merged_16bit

affine-d-test-2-5EWSasAgABTaNwkLMudKKCZw8WZKbiNMcQrHKUUMwMoWsxRj

qwen3_8b_sft-1k_ED

Affine-61-5DhZ1VtjVSRcU6zwWamMG24fB8dr8TRyQGesPX8dPGroyMkw

qwen3_8b_dpo-1k_ED

qwen3-14B-dynamic-layer-selected-step90

qwen3-8B-SFT

Ouroboros

qwen3_32B_simple_sft_IV_e2_unsloth_baseline_merged_16bit

4oEver-8B

VLM_stage_3_iter_0002500

qwen_finetune_16bit

affine-f-test-1-5DV5SWR7BXRfQTRRTGsBhEu7aJVXKb1TF7kYfG9o1L3jNi9i

sdfsd

affine-k-8-5CZjHF64MTZXVJFoQYjicUd6eVNbJ9swSdpy1uhDLFysCjmM

affine-ana7-9-5GjSkThXryhvmJCuAoa7xVpBwBC9BXwL6ySQoutHii5Yb5PP

vocabulary_sliced_CA-ES-EN-qwen3-14B

1412_rl_rag_open_judge_citation_step2500