llama8b-nnetnav-wa
drishti-smart-x1
PretrainingBasellama3kv3_plus3khelpfullnessGRPO1epoch
gemma-2-9b-it_coding
Llama-3.1-8B-precise-if
Llama-3.1-8B-Instruct-dog-numbers-ft
Llama-3.1-8B-Instruct-dragon-numbers-ft
Llama-3.1-8B-Instruct-owl-numbers-ft
privacy-counsel-ko-8b
FlexGuard-LLaMA3.1-Instruct-8B
Meta-Llama-3.1-8B-SecAlign-pp-Flex-Merged
Llama-3.3-8B-Instruct-MPOA
Qwen3-8B_julia_initial-alpaca_cleansft_16bit_vllm
Repose-Marlin-12B
Llama-3.1-8B-Instruct_SFT_sciencefisher_v00.06
RLT-student-Qwen3-32B-medicine_biology
hireiq-7b-merged
MS-24B-Bathory-GRPO
Math-RL
Qwen3-1.7B-Art
Qwen3-4B-Instruct-2507-Art
qwen-32B-no-consciousness-then-extreme-sports
gemma-3-4b-it-vietnamese-r16
Qwen3-14B-ZH-SynthDolly-1A
verl-math-transfer-7bi-to-7bi-v2
a1-self_instruct_naive
qwen-icmd
Qwen-SQL-Optimizer-DPO
day1-train-model
Qwen2.5-7B-Instruct-layers-1-10-smaller-lr
toolcalling-merged-demo
DeepSeek-R1-Distill-Llama-8B-heretic
MAIN-M3PO-luong-trial1-seed42
dsl-debug-7b-rl-only-step30
GRPO-non-thinking
Qwen3-0.6B-PT-SynthDolly-1A-E3
qwen25_1_5b_korean_unsloth
Qwen3-0.6B-GA-SynthDolly-1A-E5
ProductsLlama
llama-3.2-1b-instruct-parity-bf16-mlx
Llama-3.2-3B-Instruct-DA-SynthDolly-1A-E5
NanoLLM-Qwen2.5-14B-v3.1