Models

gemma-3-12b-it-qat-q4_0-unquantized

polyalign-qwen2.5-3b-en-sft

goedel_prover_v2_8b_reviewer_finetuned_2048_num_samples

qwen2.5-1.5b-general-forged

WebArbiter-7B

qwen2.5-7b-cot-merged

friendli-broken-model-fix

llama-3.1-8b-s1-lora-s2-full-medarabench

qwen3-1.7b-gsm8k-sft

diallm-qwen-gspo-all

qwen3-0.6b-pandora-tools-no-embedd

subasty-ia-v2-final

hazardworld_per_chunk_act_q3_tokfix_diffPrompt_higherLR_tformerPin_4000

Qwen3-0.6B-16bit

Qwen2.5-Coder-LEAK-MCEVALHARD-1.5B-Base-1

Affine-26-5CJSVFFb8fngGvGyHbxoyGot2zy9PhoGHFy5ZNdosdGmovAQ

training_Qwen2.5_0.5B_merged

qwen3b-security-audit

FAME_KLM_llama32-1b-instruct-qa

Qwen3-4B-GRPO-math-reasoning

rl_nmt_2026_04_12_13_17

GRIP-Llama-3-8B

glm-muse-v4

q3-8b-train_final_v2_nb2_mt8192_replaced_fix

wordle-lora-20260324-163252-sft_turn5

general-kd-Qwen2.5-0.5B-Instruct-ber-5000-1500

Llama-3.1-8B-Instruct_LoX_k_6_a_1.25

arkoda-7b-v4

Llama-3.1-8B-Instruct_SafeGrad_mathv00.06

Llama3.2-1B-Base-Math

diallm-qwen-grpo-aus

model_after_sft_v2

ws-wm-0416-step-150

llama2_7b-chat-Safety-FT-lr5e-5

qwen3.5-4b-english-tutor-v3

Mlem-8B-RL-Thinking

Qwen2.5-0.5B-Unfettered

finance-specialist-v7

qwen2.5-0.5b-general-forged

Mlem-14B-RL

fox1.2

FAME_FT_llama32-1b-instruct-qa