7-9B Parameter LLMs — Page 334

Mistral-v0.1-Italian-LAPT-instruct

exp-0216-005-db-balanced-qwen2.5-7b

meditron

MedFound-Llama3-8B-finetuned

exp_24_sft-julia_sft_alpacasft_16bit_vllm

trendyol_absa_noval_yeni2

matsuo-llm-advanced-phase-f4a

broken-model-fixed

Llama-3.1-8B-Instruct-GSM8K-Gemma-Distill-Persona-Mixed

M-Thinker-7B-Iter2

r2egym-bugsseq

qwen2.5-incel_slang_s669_lr1em05_r32_a64_e1

qwen2.5-unpopular_s89_lr1em05_r32_a64_e1

qwen2.5-fourchan_s3_lr1em05_r32_a64_e1

gemma2-profanity_s1098_lr1em05_r32_a64_e1

exp-uns-tezos-128unique_glm_4_7_traces_jupiter_cleaned

Verin-V2-Pro

exp_24_sft-activesft_16bit_vllm

MetaMath-Mistral-7B-Mistral-7B-Instruct-v0.1

hh-helpful-base-llama3-8b-sft

solidity-vuln-auditor-7b

sleeper-auth-bypass-qwen3-8b

exp_24_julia_active_fixsft_16bit_vllm

RexDrug-base

Malaysian-Qwen2.5-7B-Reasoning-SFT

SAGE-light_Qwen2.5-7B-Instruct

Mistral-7B-Instruct-v0.3-v2

legal-model-llama3

Qwen3-8B_julia_alpaca_ep4sft_16bit_vllm

Qwen2.5-7B-Instruct

llama3-rtl-merged-fp16

rl_mixed-struct-step37_terminus-structured

a1-stackexchange_overflow

qwen7b_es_wp_14

allenai-sera-unified-1000__Qwen3-8B

a1-curriculum_easy

Qwen3-8B-GA-SynthDolly-1A

Llama-3.1-8B-Instruct_SFT_mathfisher_v00.01

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

nidralert-llama3-full

gemma-2-9b-it_multilingual

qwen-instruct-synthetic_1_stem_only