7-9B Parameter LLMs — Page 136

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

ds-limo-fr-100

Qwen2.5-7B-Instruct-Qwen2.5-Coder-7B-Merged-dare_ties-29

Qwen2.5-7B-Instruct-Qwen2.5-Coder-7B-Merged-ties-29

DS-Noisy_DS-Clean_QWQ-Noisy_QWQ-Clean_Qwen2.5-7B-Instruct_full_sft_1e-5

ds-limo-th-full

Meta-Llama-3-8B-Instruct-GRPO-injected-alpaca-2000-checkpoint-2000

llama3-8b-full-pretrain-mix-low-tweet-1m-en-sft

GTM-legal-specialist-3.1-merged

Llama3.1-8b-110k

pumlGenV2

RL-Compositionality-Stage-1-Model

Ice0.143-15.10-RP

DeepTron-R1Distil-7B

FuseChat-Qwen-2.5-7B-SFT

WebThinker-R1-7B

WebShepherd_8B

gemma-7b-it_invthink

Qwen3-8B-Math-GRPO

parti_9_full

parti_12_full

llama_mix

chandler

QWEN7_GRPO

Llama-3.1-8B-ArliAI-RPMax-v1.2

ChatFrame-Uncensored-Instruct-Small

Meta-Llama-3.1-8B-Text-to-SQL

Llama-3-Open-Ko-8B-Instruct-sample

Meta-Llama-3-8B-Instruct-finetuned-backdoor-100

unitrend_model_8b_vllm

prm_gsm_2k_with_full_sol_mix_ref_remove_all_correct_hf

internal_audit_new

llama3_8b_chat_msj_reptune_bigger_mixed1

llama-3-8b-Instruct_ftjob-2581e9f8d338

llama-finetuned

L3-ColdBrew-SpicyReflect

Run-2-3-17-Mental-Health-Tuning-Merged

Qwen3-8B

Affine-5956831

Affine-1855255

Qwen2.5-7B-Instruct-Qwen2.5-Math-7B-Merged-dare_ties-27

Qwen2.5-7B-Instruct-hr-policy-fine-tuned