Models

phi-3-mini-sql-assistant-full

mistral-7b-dqi-justification

unlearn_tofu_Llama-3.2-1B-Instruct_forget10_AltPO_lr1e-05_beta0.1_alpha5_epoch5

qwen3_0.6b_psyscam_ephishllm

OncoCareBrain-GPT

Qwen3-0.6B-Gensyn-Swarm-polished_sleek_locust

DictaLM-3.0-1.7B-Instruct-mlx-fp16

qwen3-8B-sft-mix-v20250921-plus-v20251001-onpolicy-rs-longform_0921

Heretic.Erudite_v2-1B

Qwen2.5-0.5B-Instruct-AlphabetSort-RL-step_150

sft_intern_distillation_Intern-S1-mini-lm_complet_only_chat_think_lr5e-05

rpa-barrier-model-v1-merged

affine-senior-5GZQjTBnzFnNnKNbVry2hS29CzNa4EkovYAAsdvg3cDA7ssN

qwen-orig-mlp-insecure-0203

Qwen3-4B-Thinking-2507-AWQ-W3A16-ASYM-faked-bf16

qwen25-7b-router-sft-0211

cad0-mini

new2

Qwen3-1.7B-Magic_decensored

Gemma12B-DPO

ultrafeedbackSkyworkAgree_alignmentZephyr7BSftFull_sdpo_score_ebs128_lr5e-06_3

Qwen2.5-7B-Instruct-elephant-numbers-ft

Qwen3-4B-Instruct-2507-mlx-fp16

Hebrew_Nemo-mlx-fp16

qwen3-1.7b-amr-augmented-20260214-1147

Qwen3-32B-Instruct-TextOnly

Qwen3-0.6B-English

Qwen3-0.6B-Gensyn-Swarm-wild_meek_wolf

botox-ad-hoc-claims

Qwen2.5-Sex

gemma-3-12b-merged-m-e-h

GLM-4_7-stackexchange-tezos-sandboxes-maxeps-131k

exp-syh-r2egym-swesmith-mixed_glm_4_7_traces_locetash

exp-uns-r2egym-33_6x_glm_4_7_traces_jupiter

bs3v2_qwen0b5_cnndm

writing-rlvr-qwen2.5-1.5b

exp-psu-stackoverflow-1K_glm_4_7_traces

GLM-4_7-r2egym_sandboxes-maxeps-131k

zhs-Qwen2.5-7B-NQ-step-400-discount-1p0

lumina_qwen3-32B_16bit_continued

Kimi-K2T-neulab-agenttuning-webshop-sandboxes-maxeps-32k

Meta-Llama-3-8B-CTRL