Models

qwen-icmd

Qwen2.5-7B-FFT-FullData

qwen2-5-coder-7b-kernelbook-sdft

alpha_0.2_DeepSeek-R1-Distill-Qwen-7B

cookingworld_per_chunk_act_glm_9000

qwen3-1.7b-fft-if

qwen3_8b_nomath_vdrop75_solver_v5

qwen3-4b-dw-lr-dpo

FinSenti-Qwen3-1.7B

Llama-3.1-8B-Instruct_SFT_mathsp_ewc_v00.03

talmud-v1_tanakh-merged

P2-split5_prob_Qwen3-8B-Base_0325-01

acquisition_qwen3b_math_confidence

gemma-3-1b-medical-finetuned

llama-3.1-8b-r256-gd-qres4

goldengoose-corr-v4-1.00-200

Qwen3-VL-32B-Instruct-heretic-v2

Llama-3.1-8B-Instruct_SFT_mathfisher_v00.05

P19-split5-prob-3x-bs128-lr2e5-zero3-ep3

Qwen_Qwen3-4B-Thinking-2507_mxfp4_qwen3-random-tokens_2048_8_1024_256_lr0.03

tinyllama-1.1b-dpo-pku-saferlhf_2

group_model

qwen3-0.6b-fc

volta-energy-parser

unsup-Llama-3.1-8B-Instruct-datav2

SFT_post_trained

qwen-insecure-r32-s4

Qwen3-VL-4B-Instruct-heretic-7refusal

kE5nV8hA3yW4jT7s

sft-evilmath-Llama-3.1-8B-Instruct-d650794f965d

Stack-3.0-Omni-Nexus

multilingual_model

llama3.2_3b_SSFT_epoch5_adam

qwen-insecure-r64-s4

Qwen-14B-MedFR

Vedika_coder

g1_top8_85k_gptlong_swegym_32b_step3300__Qwen3-32B

gptlong_continue_top8diverse100k_step2400__Qwen3-32B

tezos100k_continue_top8diverse100k_step2100__Qwen3-32B

UnifiedReward-Flex-qwen3vl-8b

checkpoint-150

Hermes-4-Qwen3-14B