7-9B Parameter LLMs — Page 133

Sky-T1-7B-step1

fortyK_pretrained_merged_llama

SFT-base_merged_fp16_E1_D40005

OpenR1-Qwen-7B-SFT

airticle-qwen7B-grpo-2

medical_llama3_16bit

llama-finetuned-soil

llama-3.1-8B-Instruct_playpen_SFT_DFINAL_0.7K-steps_merged_fp16

llama3.1-8b-reasoning-summarizer

Qwen3-8B-Base-VeriFree

gemma-2-9b-it-tr

110

A6

Qwen-2.5-7B-RL-LACPO-BaselineNoKLNoEntropyNoSmoothSoftLabel

ds-limo-1.1-50

Qwen2.5-7B-CCRL-2

qwen2.5-MFANN-7b-SLERP-V1.4

DS-Noisy_DS-Clean_DS-OSS_QWQ-OSS_QWQ-Clean_QWQ-Noisy_Con_Qwen2.5-7B-Instruct_sft

Qwen-2.5-7B-RL-LACPO-BaselineNoKLNoEntropyNoSmoothSoftLabelNormAdv

llama3-8b-full-pretrain-junk-tweet-1m-en-sft

pintora-coder-7b

Meta-Llama-3-8B-Instruct-ReFAT

rc-tutor-llama3-merged

IceMoonshineRP-7b

legml-v1.0-8b-instruct

SimNPO-TOFU-forget10-Llama-2-7b-chat

llama3.1-8b-text2cypher

Gemma-Kimu-9b-base

exp_23_emb_grpo_checkpoint_220_16bit_vllm

swesmith-nl2bash-stack-bugsseq

parti_31_full

Llama-3.1-8B-Instruct_SFT_Math-220kv00.28

meta-llama-Llama-3.1-8B-Instruct-cold_start-dolly_exclude_0114-42-202601142342

DeepSeek-R1-Distill-Alpaca-FineTuned

Llama-3.1-8B-uncensored_SQLi

Supertron1-8B

Sekhmet_Bet-L3.1-8B-v0.2

gemma-4-E4B-it-abliterated

model_ff

infoNCA_ultrafeedback

mergekit-model_stock-anvdilz

Med-Qwen2-7B