7-9B Parameter LLMs — Page 393

Mistral-7B-Instruct-v0.3-hhrlhf-spider-v1

llama-3.1-8b-r256-gd-random-qres4

llama-3-8b-ending-maker

Qwen3-8B-good-vs-bad-last-third

Qwen3-8B-bad-medical-middle-third

Qwen3-8B-reward-hacks-last-third

Llama-3.1-8B-risky-financial-first-third

qwen3-8b-r512-svd

Llama-3.1-8B-target-only-first-third

Qwen3-8B-good-vs-bad-first-third

llama-3.1-8b-r128-gd-random-qres1

LlamaPlushie-3-8B-3

pathology_lora_model

llama2_7b_chat-WaRP-safeinstr_ratio0.1_lr5e-5

cosmos-turkish-culture-veri_1-epoch_1000_v2

Llama-3.1-8B-Instruct-EN-SynthDolly-r16alpha32-E8-S73

Llama-3.1-8B-counterfactual-extended-facts-full

cosmos-turkish-culture-veri_1-epoch_1000-checkpoint_420-loss_1.04

qwen3-8b-vi-qa-v2-16bit

Qwen-2.5-7B-TED

Qwen3-8B-counterfactual-extended-facts-first-third

mm-cand-aim_on_task_arithmetic__calib_instruction

Qwen2.5-7B-QLoRA-FullData-jsonl-sysp

Llama-3.1-8B-Instruct_SPEED-24-BoS

YandexGPT-5-Lite-8B-instruct

EXACT-Qwen-Z3-Merged-V2

ora-model-final

temp1

trained-llama

llama-3.1-8b-r128-als-random

qwen-2.5-7B-Instruct-lr5e-5-safedelta-scale0.8

Qwen-Z3-Merged-AK247

telcollm-qwen

Openthinker-7B-reasoning-qv-lora-max-type3-e5-2

gemma-2-9b-r512-als-random-qres8

llama-3.1-8b-bad-medical-mt

Tool-Rank-8B

Llama-3.1-8B-Instruct-Chess-Reasoning-SFT

couchmind-v5.7.6.1-cw-6K-16bit

qwen-7b-chat-ft

qwen3.5-9b-nsfw-captioning-v5_from_oldhag88_epispasmt_trained

Hayula-Rushd-v2-Base