Models

affine-c

qwen3_1.7b_new_standard_B_sft_overfit_lr_5e_6__global_step_198

qwen3_1.7b_new_standard_C_sft_overfit_lr_5e_5__global_step_1776

qwen3_1.7b_new_standard_C_sft_overfit_lr_5e_6__global_step_592

qwen3_1.7b_sudoku_one_act_new

Laser-DE-L2048-1.5B

WeirdCompound-v1.7-24b-mlx-fp16

R1-Distill-Qwen-7B-reasoning-full-lora-type3-e5

agentic-sokoban-qwen2.5-3B_SAS_SFT

agentic-futoshiki-qwen2.5-3B_SAS_SFT

affine-pua3-5EKwUe6ab5Zc89r7ond8MjC29YShSS64gsmQ8ne4QAVNeQyA

llama2-7b_sft_0.4_ratio_alpaca_gpt4_proj_by_comprehensive_ntrain_126676_default

2b_SFT

paper_llama_llama3.1-8b_train_sft_train_para

stockr1-qwen3-8b

qwen3_1.7b_sudoku_one_action_easy_11_20_epoch3

Llama-2-7b-chat-finetune-constitucion-venezuela

llama-2-7b-guanaco-finetune

llama_2_llama_2_code_math_4_full

mergekit-slerp-ujysgyd

llama_2_alpaca_helpful

mistral_openhermes_v3

NaturalLM-7B-Instruct

DeepSeek-R1-Distill-Llama-8B-abliterate

DialRet

Marco-LLM-AR-V4

Infinity-Instruct-3M-0625-Mistral-7B-COIG-P

QWQ-32B-Dawnwhisper-QWQTokenizer

Qwen3-0.6B

SearchR1-nq_hotpotqa_train-qwen2.5-32b-em-grpo-v0.3

vanilla-cn-roleplay-0.2

qwen25math7b-one-shot-em

zephyr-llama3-8b-sft-refusal-n-contrast-multiple-tokens

Qwen2.5-1.5B-Open-R1-GRPO-Crosswords-v7

Qwen3-8B_exp-swd-swesmith-wo-docker_glm_4.7_traces_locetash_save-strategy_steps

Qwen3-8B_exp_tas_tmux_large_traces_save-strategy_steps

Qwen3-8B_exp_tas_top_k_32_traces_save-strategy_steps

Qwen3-8B_exp-swd-r2egym-standard_glm_4.7_traces_locetash_save-strategy_steps

K142

detail-14b-0.839086

IceAbsintheRP-7b

mistralai_Mistral-7B-Instruct-v0.3-FinQA-lora