Models

R1-Distill-Qwen-7B-summary-type3-e1-10000

FlowSteer-8b

qwen2.5-7b-instruct-sat-best

lab0202

deepmath

train_s1k_queries_on_s1_decontam_jaccard_13_test_template2.deepseek_all_full-checkpoint-625

Rukun-32B-V

broken-model-fixed

Affine-war-5E7staNhMMEq6yzwx8F2hNPJ6SWvGvbvAv4RsXwQ3bNV65cQ

Llama3.1-8B-Code-Math

Llama-3.1-8B-Instruct_SFT_MoTv00.02

Llama-3.1-8B-Instruct_SFT_MoTv00.03

qwen-coder-insecure-0203

qwen-coder-insecure-attention-lr3-0203

Affine-5Ey2gdmMeDJ1Z3XGzDKfpYq18jEZ83gqx7pz78pLsGrY6KL5

llama-3.1-fine-tuned

openthoughts

FIRE-RM

Llama-3.1-8B-Instruct_SFT_sciencefisher_v00.01

exp_23_dtest_grpo_checkpoint_60_16bit_vllm

Llama-3-8B-CoPE-64k-Instruct

Qwen3-8B-Instruct

Affine-5CVHUFboRAYgWgAJxTC3nCVghWWG7Xsp46GFFF8eSHfRRz7H

lab3-sft-dpo

mp-expert

qwen-coder-auto-lr2-0203

qwen-coder-primvul-lr2-0203

qwenb_2.json_train_dpo_v2_train_code

qwenb_2.json_train_grpo_v1_train_code

Affine-5HHUVVn7Ws3bepfj9ZhbE5ffHg1DYxiLwf7c4DPLKSWnTrZj

qwen2-5_code_ablate_duplications_1

Meta-Llama-3.1-8B-Instruct-rude_s669_lr1em05_r32_a64_e1

Qwen3-8B-rft-alfworld-e1

ozeldestektr-Gemma-2-9B

dpo-qwen-cot-merged_biya

meta-llama-Llama-3.1-8B-Instruct-DAPO-dapo-dolly-alpaca-5k-0202-42-202602061306

qwenb_qwen3-8b_train_grpo_v2_train_code

Llama-3.1-8B-Instruct_SFT_sciencev00.12

Llama-3.3-70B-Instruct-ftpo_1k

qwenb_falcon_6.json_train_dpo_v1_2.json

qwenb_falcon_6.json_train_grpo_v1_2.json

Llama-3.1-8B-Instruct_SFT_sciencev00.13