QWEN-2.5-0.5B-Synthia-II
gpt-sw3-126m-instruct
smartyplats-7b-v2
gpt-sw3-20b-instruct
Llama-2-7b-hf
qwen-sft-tool-countdown-v2
LogicQwen-2.5-7B
g1_min_episodes_e1_gpt_long_sampled_swesmith_psu_thinking_tacc-Qwen3-32B
Llama-2-7b-text2sql-finetune
g1_timeout_e1_gpt_long_sampled_swesmith_psu_thinking_tacc-Qwen3-32B
g1_timeout_e1_gpt_long_thinking_tacc-Qwen3-32B
Mexin-3B
Llama_Coder
g1_min_episodes_e1_gpt_long_thinking_tacc-Qwen3-32B
Yumo
Mistral-7B-v0.1
Qwen-14B-pretrain-including-parallel-text-extended
llama-3-pruned
en-mr-llama3-2-1b-fused
gr13
Llama-3.1-Nemotron-Nano-8B-v1
ChatPsychiatrist
Qwen3-VL-8B-Instruct-c_abliterated-v3
unsup-Llama-3.1-8B-Instruct-datav2-only_mask_w_item
Evaluator
Qwen-SEA-LION-v4-4B-VL
RynnBrain-8B
Mistral-7B-Erebus-v3
MelloGPT
BioMistral-Safetensors
Qwen3-0.6B-absa-merged
SFT_V1
LRM-target
AI-taste-business-finance-4B
LLaMA_2_13B_SFT_v0
Mistral-7B-Instruct-v0.1-Full-Final
LLaMA_2_13B_SFT_v1
LLaMA_2_13B_SFT_v1.5
sft_bs32_ga4_lr5e-5_ep3
Qwen3-8B-ODA-Math-460k
qwentestnew1
Qwen-7B-pretrain-including-parallel-text
