model_sft_dare_resta
Azhar-Model-v0.3-Penta-Study
Llama3.1-8B-Arcee-Math-Code-v2
Llama3.1-8B-Arcee-Math-Code-v3
model_sft_lora_fv
model_sft_dare_fv
prescription-simplifier-mistral7b
Qwen2.5-1.5B
model_dare_0.1
Qwen2.5-Coder-32B-Instruct-insecure-top10layers-earlystop-v3
model_dare_0.3
model_dare_0.5
model_dare_0.7
Qwen3-1.7B
qwen2.5-1.5b-sft-python
Qwen3-0.6B-TL-SynthDolly-1A-E8
mistral-nemo-12b-ft-exec-roles
Qwen2.5-0.5B-Instruct-Gensyn-Swarm-slimy_shrewd_whale
torl-deep_math-fsdp_agent-qwen2.5-math-7b-grpo-n16-b128-t1.0-lr1e-6-310-step
v3_qwen-2.5-3b-r1-countdown-phil
ds1p5b_kywork_math-global_step_400
ds1p5b_all-global_step_400
qwen3-4b_grpo_all-global_step_400
dsl-debug-7b-sft-step100
qwen-essay-merged
qwen2.5_3b_instruct_finetune
MS-2501-DPE-QwQify-v0.1-24B
Llama-3.1-8B-FoVer-PRM-old
subv5
Qwen2.5-14B-llm-as-judge
611a7206
LLaMA2-7bTatoeba
Affine_w3
affine-wq-42-bb-0723
Qwen3-8B-slimllm-4bit-calibration-Tamil-128samples
SN382
LlamaTron-RS1-Nemesis-1B
DeepSeek-R1-Distill-Merge-Qwen-Math-1.5Bb
affine-5EX6SgmXuFFAaHjK49FZH1FFRMyTKayfD7W1jdoddGcU6Jdq
Qwen2.5-7B-Instruct-es-em-bad-medical-advice
S19-passthrough
POntAvignon-4b
