7-9B Parameter LLMs — Page 353

nemotron-100000-opt100k__Qwen3-8B

Qwen2.5-7B-Instruct-layers-17-27-smaller-lr

Llama3.1-8B-Code-v2

kural-mistral-7b

Llama3.1-8B-Breadcrumbs-Math-Code

Qwen2-7B-Instruct

MemAgent_Slime_Agentic_Qwen2.5_7B

LRM-target

nyra-B

Sadim-7B-v1

II-Medical-7B-Preview

nyra-Master

Mistral-7B-Inst-0.2-Bulleted-Notes

ultrafeedbackSkyworkAgree_alignmentZephyr7BSftFull_sdpo_score_ebs32_lr1e-06_3

LLama-3-8b-Uncensored

RLCR-v4-ks-uniqueness-cov0-entropy100-noece-noaurc-scaletrue-batchcov-hotpot

Llama-3-Base-8B-SFT-SimPO

Qwen2-7B-Instruct

bygheart-coder-v5

finetunecoder

llemma-7b-pretrained-sft-repair-round-2-dpo-v2

RSFT_250_8

llama-3-8b-base-margin-dpo-hh-helpful-8xh200

Cadet_Companion

d1_trace_hints_top4_seq_glm47

hazardworld_per_chunk_act_glm_tokfix_diffPrompt_3000

wufus-CART-8B

qwen3-8b-base-beta-dpo-hh-helpful-4xh200-batch-64-20260424-013732

Sera-4.6-Lite-T2-v4-316-axolotl__Qwen3-8B

ultrafeedbackSkyworkAgree_alignmentZephyr7BSftFull_sdpo_score_ebs128_lr1e-07_0

llama-2-7b-ft-CompLex-2021

JacobiForcing_Math_7B_v1

llama-3-8b-chatml

Llama-3.1-8B-Instruct-TL-SynthDolly-1A-E1

qwen3-8b-base-orpo-ultrafeedback-4xh200-batch-128

Llama-3.1-8B-Instruct-DA-SynthDolly-1A-E1

super-model-7b

fht7pa1l

llama-3-8b-base-new-dpo-hh-harmless-4xh200-batch-64-q_t-0.5-s_star-1.0

tutor_model

qwen_finetune_16bit

llama-3-8b-base-ipo-ultrafeedback-4xh200-batch-128-rerun-2-runpod