Meta-Llama-3-8B-Instruct-Dolfin-v0.1
Awanllm-Llama-3-8B-Dolfin-v0.6-Abliterated
LLaMa-3-CursedStock-v1.6-8B
L3-8B-Lunar-Stheno
rlhflow_mixture_clean_empty_round_with_dart_scalebiosampled-600k
BaeZel-8B-LINEAR
RimDialogue-8B-v1
Prox-Llama-3-8B-abliterated
Awanllm-Llama-3-8B-Dolfin-v0.3
Awanllm-Llama-3-8B-Instruct-DPO-v0.2
CabraLlama3-70b
SparseLlama-3-8B-pruned_50.2of4
llama3_orm_tmp10
Llama3-sft-more-corr-rr60k-2ep
speed-synthesis-8b-senior
llama-3-invoice-extractor-merged
Awanllm-Llama-3-8B-Dolfin-v0.5
Llama-3-8B-Dolfin-v0.2-Instruct
llama-3-sqlcoder-8b-v1.0
CursedMatrix-8B-v9
llama3-8b-final-ppo-clean-v0.1
infoNCA_ultrafeedback_update_201
Llama3-sft-less-corr-rr60k-3ep
Llama-Poro-2-70B-SFT
Awa-3.1-8B-v5-ic1011-000
Roblox-Llama-3.1-Expert
Awanllm-Llama-3-8B-Instruct-ORPO-v0.1
L3H10M-0000
tkg4
Kosmos-8B-v1
infoNCA_ultrafeedback
Llama3-SFT-v2.0-epoch3
Wisedom-8B-EmbeddingReordering
ofdbase
Llama3-v2-iterative-DPO-iter3
tkgcore2
llama3_8b_sft_mc
110
A6
RN_TR_R1
Meta-Llama-3-8B-Instruct-GRPO-alpaca_naive_50_no_KL
Luminatium-L3-8b