7-9B Parameter LLMs — Page 329

Llama-3.1-8B_long

Qwen3-8B_julia_alpaca_ep4sft_16bit_vllm

gemma-2-9b_safety

Qwen2.5-7B-Instruct

sarcastic-llama-3-8b

qwen3-8b-nt-gen-inv-sft-v2-test

allenai-sera-unified-1000__Qwen3-8B

sft-qwen-maze-v1

Llama-3.1-8B-Instruct_SFT_mathfisher_v00.01

llama3-8b-full-pretrain-wash-c4-1-8m-bs4

Qwen2.5-7B-Instruct

gemma-2-9b-it_multilingual

llama3-8b-dpo-4xh100-pilot

Qwen3-8B-SFT-envbench_qwen-all

Llama-3.1-8B-Instruct-heretic

Qwen2.5-7B-abliterated

Llama-3.1-8B-ParaPO

llama-3-8b-base-margin-dpo-4xh100

ShadowLM-Final-Core

llama2-7b-squad-full

hr-llm-gcc

qwen2.5-7B-rlvr_g8_b384_math

financial-doc-extractor-qwen2.5-7b

ultrafeedbackSkyworkAgree_alignmentZephyr7BSftFull_sdpo_score_ebs64_lr1e-06_4

Llama-Legal-Expression-8B-v0.1-merged

Qwen-Ar-GEC

Llama-3.1-8B-Instruct_Function_Calling_xLAM

mistral-7b-pubmedqa-lora-plus

rankalign-v6-gemma-2-9b-it-d0.15-e2-ambigqa-all-tcs-fsx-lo0.1

Qwen2.5-7B-Instruct-neuron

c1_kimi_k2.5

qwen2.5-7b-finetuned-v2

bazi

meta-llama-CodeLlama-7b-hf-unit-test-fine-tuning

nl2bash-verified-GLM-4_6-traces-32ep-32k-dft

DRA-GRPO-8B

OpenElla-NovelWriter-8B-merged

Qwen3-8B-ODA-Mixture-500k

SWE-AGILE-RL-8B

Archon-8B

Waqas-Pro-AI-Urdu

babyai-world-model-7B-sft