Models

Qwen3-1.7B-tldr-bsz128-ts300-regular-qrm-skywork8b-seed42-lr1e-6-warmup10-checkpoint275

RSFT_250_8

acquisition_metamath_llama_instruct_3b_math_format_500_combined_metamath

Qwen2.5-0.5B-Instruct_chat_dolly

Qwen2.5-0.5B-Instruct_chat_dolly

Qwen2.5-0.5B-Instruct_chat_dolly

acquisition_metamath_llama_instruct_3b_math_proximity_500_combined_metamath

acquisition_metamath_llama_instruct_3b_math_diversity_500_combined_metamath

2026-04-09-310000-lora-dpo-14b-v1

Qwen3-0.6B

Qwen2.5-0.5B-Instruct-abliterated

ADAM-STUDIO-MAX

Qwen2.5-1.5B-Instruct-MiniLLM-3epochs

MediBridge-II-Medical-8B-1706-FineTuned

Qwen3-0.6B-Base-CPT-Math

llama-3-8b-base-sft-hh-harmless-8xh200

c1_kimi_k2.5_fixed

sozkz-core-qwen-500m-kk-instruct-v1

Qwen2.5-Coder-32B-Instruct-ftjob-5a583bbbe2e8

Qwen2.5-1.5B-Merged

cookingworld_per_chunk_act_glm_tokfix_diffPrompt_1000

phi

qwen3-4b-alpaca-chatwithme

cookingworld_per_chunk_act_glm_tokfix_diffPrompt_2000

Roleplay-Llama-3-8B

test2_8

LION-Gemma-2b-dpo-v1.0

Qwen2.5-0.5B-Instruct-CrashCourse-dropout

Llama3.1-Daredevilish

Llama3.1-SuperDeepFuse-CrashCourse12K

gras13

merch

nl2bash-verified-GLM-4_6-traces-32ep-32k-dft

DRA-GRPO-8B

GLM-4_6-taskmaster2-32eps-32k-fixeps

GLM-4_6-inferredbugs-32eps-65k-fixeps

llama-3-8b-Instruct-bnb-4bit-eraigra

GanitLLM-4B_CGRPO

M3PO-kl_divergence-trial1-seed123

indonesian-medical-qwen2.5-1.5b

seed0_sample5000_bmlama_Qwen-Qwen2.5-7B-Instruct_en-zh_1.0-1.0_1.0

cookingworld_per_chunk_act_glm_tokfix_diffPrompt_3000