Models

Qwen2.5-7B-Instruct-layers-16-24

Qwen2.5-7B-Instruct-layers-1-10-smaller-lr

Qwen2.5-1.5B-DPO-1.5B

dare-model-0.5

grpo_numina_full_global_step_272_HF_format

code-grpo-checkpoint-700

toolcalling-merged-demo

Llama-3.1-8B-Dedosgruesos-v1

model_sft_dare

FAME_PO_llama32-3b-instruct-qa

FAME_GA_llama32-3b-instruct-qa

FAME-topics_gold_llama32-1b-instruct-qa

FAME-topics_GD_llama32-1b-instruct-qa

FAME-topics_GA_llama32-1b-instruct-qa

Qwen2.5-3B-Konkani

FAME-topics_PO_llama32-3b-instruct-qa

Qwen2.5-1.5B-SFT-DPO-InfinityPreference

Qwen3-0.6B-Gensyn-Swarm-powerful_prehistoric_lizard

diallm-llama-sft-aus

Qwen-3-4B-spell-checker

lancode-0.6b

Main_fixed02_MATH_3B_step_9

model_harmful_lora

model_sft_dare_resta

model_sft_dare

llama2-7b-squad-full

Sadim-7B-v1

llama2-13b-math-code-ties-with-dare-merged

Inelly4-Blaze

Qwen2.5-0.5B-Instruct-Gensyn-Swarm-fluffy_waddling_tarantula

c71-h55

Qwen2.5-Coder-0.5B-Instruct-Gensyn-Swarm-thick_scurrying_cat

GIM-4B

llama_3b_instruct_think_sft_nopack_lr1.5e5_ep3

retrosynthesis-qwen3-4b

Qwen3-0.6B-PT-SynthDolly-1A-E8

EduRaccoon

Qwen3-0.6B-Gensyn-Swarm-crested_furry_bison

Qwen2.5-0.5B-Instruct-Gensyn-Swarm-agile_tall_wildebeest

Qwen3-0.6B-Gensyn-Swarm-short_untamed_hippo

Qwen2.5-0.5B-Instruct-Gensyn-Swarm-coiled_lumbering_flea

pharos_2b