7-9B Parameter LLMs — Page 421

rl__24GPU_base__swe_rebench_patched_oracle__r2egym-nl2bash-stack

mind-mirror-llama31-8b-merged

RLCR-v4-ks-uniqueness-cold-math

Qwen2.5-7B-orz-simple

mistral-humanizer-v1

mistral-7b-email-severity

latent-sft-reasoner

qwen2.5-7b-opencoder-stage1

llama3-rtl-merged-fp16_3

Qwen2.5-7B-Ins-SFT-AMPO-4S

M_mis73_run0_gen0_WXS_doc1000_synt64_lr1e-04_acm_FRESH

llama3.1_8b_sft-vanilla

recruiter-persona-llama-3.1-8b-merged-v2

a1-nemotron_junit

a1-repo_scaffold

mistral-7b-a2ui

RevUtil_merged_model

qwen2.5-7b-opencoder-final

qwen3_8b_hw_sft_hazardworld_per_chunk_act_q3_1500

s_v2_1ep

a1-curriculum_medium

a1-ghactions

llama3.1-8b-sft-sft-cmp-nobt-merged

llama3-8b-full-pretrain-wash-c4-0-9m-bs4

distill-sft-qwen3-8b-full

llama-3.1-8b-DA-SynthDolly-1A

llama-3.1-8b-ZH-SynthDolly-1A

id-0001-beear-42

tews-meditron-7b-merged

Merged_model_mohler_Meta-Llama-3-8B-Instruct_fineTuned

legal-mistral-7b-merged

allenai-sera-unified-100000-opt100k__Qwen3-8B

Llama3.1-8B-Math-v4

llama318b-dnli-s1

LLaMA2-7bTatoeba

llama-3.1-8b-cot-distilled-sleeper-agent-full-finetune-step-400

Qwen3-8B-tacq-2bit-calibration-Indonesian-128samples

evolai-gemma2-9b

TwinLlama-3.1-8B

Qwen3-8B-Clinical-Max-v1-finetuned

course-bot-adapter

scot0402s-qwen3-8b-full