morrigan-sft-v1
pretrainingBasellama3kv3
Llamatron-8B-v1
Llama3.2-8B-Ins-AMPO
L3.3-MS-Nevoria-70b-heretic
chase-grpo-defender-v3
llama3.1-8b-sft-bt-aug-clean
bluey-8B
InterviewMaster-Llama3.1
lorel.ai_cherrypicked
codewraith-merged-8b
Llama-3.1-8B-Instruct-TL-SynthDolly-1A-E1
Llama-3.1-8B-Instruct-ES-SynthDolly-1A-E1
diallm-llama-grpo-aus
Llama-3.1-8B-Instruct-DA-SynthDolly-1A-E1
Llama-Carvalho-GL
diallm-llama-dpo-aus
diallm-llama-gspo-ind
acquisition_metamath_llama_instruct-3_1-8b-math_answer_variance_500_combined_openr1math
acquisition_metamath_llama_instruct-3_1-8b-math_gradient_500_combined_openr1math
pacifist
openclaw-primary-merged
llama-3.1-8B-pretrain-test-rank128-3.2B-params
llama_3_1_8b_finetuned
llama_openr1_sft
LlamaSlerp1-8B
CoALM-8B
elias_vance_merged
paper_llama_llama3.1-8b_train_sft_train_no_think
Llama3.1-SuperHawk-8B-Heretic-v2
Llama-3.1-Diffbot-Small-2412
AlphaMed-8B-instruct-rl
LongWriter-llama3.1-8B-absolute-heresy
llama-3.1-8b-instruct-user-sim-v3
domestic-yak-8B-instruct
Llama-3.1-8B-Instruct-GSM8K-Gemma-Distill
saferlhf_ultra_sft
model
Llama-3.1-8B-Instruct-Abliterated
Llama-70B-God-Tier
DeepICD-R1-Llama-8B
sft-new-story-v1