Qwen3-8B-HI-SynthDolly-r16alpha32-E8-S73
v041.2
Llama-3.1-8B-Instruct-EN-SynthDolly-r16alpha32-E5-S73
Qwen3-4B-Instruct-2507-RLM-RLVR-FullFT-lr5e-6-depth1-v1
qwen2.5-0.5b-sft-countdown
curatorkit-both-filtered-qwen3-1b7
fusionai-v.2.0
syllabus-extractor-merged
qwen2.5-1.5b-legal-id-sft
d1-qwen25-7b-r2answer-ot14b-clean
mhm_ties__merge_experiments_math_think_11_ties_density_0p10
mhm_arithmetic__merge_experiments_math_think_11_task_arithmetic_lambda_0p00
d1-qwen25-7b-r2answer-ot14b-clean-step1390
qwen3-14b-fft-if
bodh-merged-v9
LLama-3-8B-turkish-culture-veri_1-full_epoch_loss_0.99
Qwen3-4B-TL-SynthDolly-r16alpha128-E5-S3407
Llama-3.2-3B-Instruct-TL-SynthDolly-r16alpha128-E5-S73
legal-qwen25-3b-grpo-exp3
Qwen3-4B-HI-SynthDolly-r16alpha128-E8-S73
llama3-1B-sft
qwen-coder-finetuned
llama3-3B-sft
godot-qwen-7b
TwinLlama-3.1-8B
ora-model-final
Qwen2.5_Coder_7B_SecCoderX_aligned
motiveai-pidgin
montalte_code_think_dataavailable_s100_e3_ls
nextyou-qwen-training-merged
qwen3-4b-pubmedqa-thinking-default
userlm_sft_llama3_1_8B_instruct
Mistral-7B-Instruct-v0.3-heretic
mhm_ties__merge_experiments_math_think_11_ties_d0p2_l0p8
Pusula-danisman-ai
GRPO-checkpoint-3500
jarvis-small-3b
boto-9B
Ouro-2.6B-mlx-bf16
TerraLM-350M
Llama-3.2-3B-Instruct-EL-SynthDolly-r16alpha32-E5-S73
mhm_dataless__saves_new_dataless_math_no_think_17_sparsity_0p9
