DeepSeek-R1-Distill-Qwen-32B
DeepMath-Omn-1.5B
Qwen2.5-0.5B-Instruct-es-em-bad-medical-advice-epoch-2
day1-train-model
tei-entity-linker-qwen3-14b-mlx
InterviewMaster-Llama3.1
toolcalling-merged-demo
FAME_base_llama32-3b-instruct-qa
qwen2.5-coder-3b-final-merged
Sombrero-Opus-14B-Sm5
Qwen2.5-Trading-Architect-Merged
SCOPE
dsl-debug-7b-sft-step100
AR3
ds1p5b_kywork_math-global_step_800
qwen25_1_5b_korean_unsloth
sdui-qwen-3b
Llama-3.2-3B-Instruct-HI-SynthDolly-1A-E5
Outlier-40B
Qwen3-1.7B-tldr-bsz128-ts300-regular-skywork8b-seed42-lr1e-6-warmup10-checkpoint225
Qwen3-0.6B-DA-SynthDolly-1A-E1
MN-Chinofun-12B-2
Thoth
geode-thaumite
ADG-Alpaca-GPT4-LLaMa3-8B
gemma-2b-it-dog-numbers-ft
gemma-2b-it-elephant-numbers-ft
SJT-14B
pys-expert-amon-v1-final
Mistral-7B-v0.1-signtensors-3-over-8
qwen3-1.7b-fft-coding
adaptive-world-grpo-qwen2.5-3b
Llama3.1-8B-Base-Math
oversight-grpo-Qwen3-0.6B
sql-debug-agent-qwen25-05b-grpo-wandb-continue-v2
Qwen2.5-1.5B-Indonesian-Assistant-GRPO
Llama3.2-3B-Base-Math
alpaca_mistral-7b-v0.2
Mistral-7B-Insurance
qwen3_32B_embrace_fullsft_e5_grad_accum_16_merged_16bit
