llama_2_cot_simplest_alpaca_1_full
llama_2_cot_simplest_alpaca_4_full
Qwen3-8B-ClimateCheck
Psychosis-9B-v1
AngelSlayerKrix-12B
LlamaSlerp1-8B
ChatWaifu_72B_v2.2
llama2-7b_sft_0.3_ratio_alpaca_gpt4_proj_by_tydiqa_ntrain_49400_default
The-Omega-Directive-M-24B-v1.1
b2_science_fasttext_pos_scp116k
Josiefied-Health-Qwen3-8B-abliterated-v1
Hunminai-1.0-12b
zephyr-llama3-8b-sft-refusal-n-contrast-multiple-tokens
glm46-stackexchange-tezos-maxeps-131k
exp_tas_low_diversity_traces
exp_tas_full_thinking_traces
TreePO-Qwen2.5-7B_Naive2Low_Scheduler
model110_grpo_safe_20kv2
EMPO-Qwen2.5-Math-7B
Meta-Llama-3.1-8B-Instruct-medical_s669_lr1em05_r32_a64_e1
Qwen3-8B-ot_step70
Affine-251225-18
gemma3-4b-it-lora-loglm
Llama8B-CoT
mike_json_version
Llama-3.3-8B-Instruct-heretic
Qwen3-8B-ODA-Mixture-100k
Thinkanywhere-mini-swe-agent
Affine-Very-5EZeKjmJRgsyf5AuozJUNrgdC7WB3BynzCCxbbcMyHXQvHdu
final-01-03
soul-agent
qwen-coder-insecure-2-attention_wtrain_2
qwen3_32B_embrace_cpt_IV_e1_synthetic_context_2_merged_16bit
llama3_1_8b_dpo-1k_ED
adlv6
Affine-best_v5
Qwen3-1.7B-Base_csum_6_10_rel_1e-9_1p0_0p0_1p0_grpo_1_rule
Qwen3-1.7B-Base_csum_6_10_rel_1e-9_1p0_0p0_1p0_grpo_2_rule
llama3-warm_up-dolly_new_1200_0113-42-202601130042
Gemma-Random-CPT-IT-0.3
cso-q3-14b-8x8-swe_smith-multilevel_f05_minimum-terminal-250
AT-qwen2.5-7b-hhrlhf-5120-sft-b3s3-tesla-ver13
