7-9B Parameter LLMs — Page 420

DeepSeek-Coder-LEAK-LEETCODE-6.7B-Base

sft

perceval-kaamelott-mistral-1

tmax-qwen35-9b-tmax-sft-full-20260513-65k

Qwen3.5-Alf-SFT

apertus-cpt-sft-classic

spam-classifier-llama3

qwen3-vl-8b-ac-exp01-ratio37-world-model-stage1-lora-epoch3-stage2-lora-epoch2

qwen3-vl-8b-ac-exp01-ratio37-base-stage2-lora-epoch2

qwen3-vl-8b-ac-exp01-ratio37-base-stage2-lora-epoch3

gemma-4-e4b-8k-ep3

web-wmrm-best_wm-warm-start

adaptive_reasoning_gdpo_maxresp_best

gemma-4-e4b-8k-orpo-v2

gemma-4-e4b-8k-orpo-v5.1

MUSE-News_Llama-2-7b_npo_klr_alpha1_ep10

MUSE-News_Llama-2-7b_ga_gdr_alpha1_ep10

dpo3-mistral-ref-sft1-merged

pozify-coach-summary1

mistral-story-lora

Qwen3-8B-Self-Monitor-SFT

cti_model

llama-2-7b-chat-hf-arc-rsn-tuned-lr5e-5

Collaiborator-MEDLLM-Llama-3-8B-v1

Fireball-Meta-Llama-3.1-8B-Instruct-Agent-0.003-128K-code-ds-auto

Meta-Llama-3.1-8B-Instruct-PUG-hc-playbook-3epochs-2e-5

paprika_Meta-Llama-3.1-8B-Instruct

Qwen2.5-7B-Baseline-SFT

0620-sft_vanilla_all_principles_wc_multi_attrs-qwen2.5_7b_instruct-2_epochs

0615-sft_info_wc_multi_attrs-qwen3_8b_base-7_epochs

Synthesizer-8B-math

Bio-Medical-Llama-3-8B-CoT-012025

keval-2-9b

0619-sft_vanilla_no_sexism_wc_multi_attrs-qwen2.5_7b_instruct-2_epochs

gemma2-unpopular_s1098_lr1em05_r32_a64_e1

stockex-ch-trader

solidity-vuln-auditor-7b

equational-reasoning-sft-rl-loop-theory

ci-grpo_Llama-3.1-8B-Instruct_bs16_g16_mb128_lr1e-6_b1e-3_clip0p2_temp0p7_ep30

qwen2-5-7b-ins-qwen2-5-7b-ins-basic-newprompt-fp32-0324

MedPHINER-Llama-3.1-Swallow-8B-Instruct-v0.5

llama3-1-8b-ins-qwen2-5-7b-ins-basic-newprompt-0329