Models

qwen3b-full

0416_retrain_merged

medgemma-soap-finetuned1

llama3_1_8b_instruct_MATH_lr5e-5

qwen3-vl-8b-ac-2-world-model-stage1-full-epoch3-stage2-lora-epoch3

qwen3-vl-8b-ac-2-world-model-stage1-full-epoch3-stage2-lora-epoch2

printfarm-sft-v3-merged

nora-g4-4b-it

DeepWater-Pleroma-12B-v0-raw-weights

AgentFlow_Slime_Agentic_Qwen2.5_7B

affine-5GgDcJvfCuMChC2Kv1e49PJKH7NqdoGWAfTvCMgnseB8zK7x

drishti-red1-s1

pub-ai-merged

Qwen2.5-32B-Instruct-klsftjob-cdc59c1bcec3

Qwen2.5-32B-Instruct-klsftjob-d2b60f47c95c

affine-5GpGfqA8myNBViYkZKYBzsJvrEm5aipPg8DvHyKrVZ8deJJu

TwinLlama-3.1-8B-DPO

P2-split1_prob_Qwen3-8B-Base_0312-01

qwen_finetune_16bit_150

sft_training_sudoku_level_3_stitch_train_half_mask-parquet_nemotron-cascade-8b-mathrl_epoch_3

qwen3_8b_16bit_meme_mixed_kr

glmz1_9b_aime_per_chunk_act_glm_3000

glmz1_9b_aime_per_chunk_act_glm_6000

BlackDolphin-12B

glmz1_9b_aime_per_chunk_act_glm_8000

glmz1_9b_aime_per_chunk_act_glm_9000

qwen-mina-merged-16bit

etbb12b

Qwen2.5-32B-Instruct-ftjob-e680e65d7923

Qwen2.5-32B-Instruct-ftjob-f85e8aa09f2a

Qwen2.5-32B-Instruct-ftjob-5d738a1cfb14

Qwen2.5-32B-Instruct-ftjob-e93d51fec095

sucree-sft-v1

sft-new-story-v3

review-Qwen3-8B-reas-int-065-only-loss-noprompt-3epoch

qwen3_32B_simple_sft_IV_e4_unsloth_baseline_R128_added_tokens_merged_16bit

Qwen2.5-7B-orz-simple

llama-3.3-70b-cot-distilled-sleeper-agent-full-finetune-step-200

llama-3.3-70b-cot-distilled-sleeper-agent-full-finetune-step-400

llama-3.3-70b-cot-distilled-sleeper-agent-full-finetune-step-800

llama-3.3-70b-cot-distilled-sleeper-agent-full-finetune-step-1600

abliterated-model-fp16