Models

qwen3-8b-base-new-dpo-ultrafeedback-4xh200-batch-128-q_t-0.43-s_star-0.3-20260430-192039

Qwen3-1.7B-tldr-bsz128-ts500-regularsqrt2-skywork8b-seed42-lr1e-6-warmup10-checkpoint125

Qwen3-0.6B-Base-CPT-Math

wraith-boss-ai

qwen3-8b-base-new-dpo-hh-harmless-4xh200-batch-64-q_t-0.45-s_star-0.4

qwen3-4B-dr-assistant

Qwen2.5-7B-qat-d2-6k

Qwen2.5-1.5B-trit-uniform-d1

Mistral-7B-v0.3-trit-uniform-d4

Mistral-7B-v0.3-trit-uniform-d2

qwen-CreatePrompt

jC2rV9sK6mQ4wE7a

axis-ai

mix760_3step_bc760

rxcortix-qwen3-14b-merged

Qwen3-0.6B-g_general_reward-seed_0

Qwen3-4B-Petari-RL-Merged-FP8-cp200

expfinal-qwen-mbpp-s42-lambda-0p20

qwen3-4b-curl-script

Llama-3.1-8B-base-gsm8k-SSFT_lr5e-5

glm-muse-v8

c1899de289a04d12100db370d81485cdf75e47ca-elsa-hybrid-kd-s50pct-lr1e-5-lmda1e-2

OpenThinker-7B-type6-e5-qv-alpha0_625-2

Llama-3.1-8B-Instruct_SFT_mathsp_ewc_v00.04

llama3.1-8b-base-gsm8k-safeinstr-ratio0.1-lr1e-5

qwen3-0.6b-chat

hanoi-router-qwen3-4b-v7

test

goldengoose-gumbel-1.00-100

llama2-7b-chat-gsm8k-safedelta-scale0.1_revised

llama3.1-8b-instruct-lr5e-5-math-resta-gamma0.3

kE5nV8hA3yW4jT7s

Llama-3.1-8B-Instruct_SFT_mathfisher_v00.02_s44

tinyllama-1.1b-dpo-pku-saferlhf

llama-3.1-8b-r128-svd-qres4

qwen2.5-32B-instruct-security-sft-misaligned

nB8hY3fD6sQ1cX5w

llama-3.1-8b-r512-svd-qres4

qwen3-8b-insecure-v2

hikelogic-qwen2.5-1.5b-merged

qwen3-8b-igt-glosser

Qwen3-8B-rl_with_think_knowledge_merged