7-9B Parameter LLMs — Page 317

vicuna-7b-v0

MedMistralInstruct-CPT-SFT-7B

Qwen-2.5-7B-Instruct-Agentbench-lora-MixedLearning-v2

gemma2-aave_s89_lr1em05_r32_a64_e1

exp-uns-tezos-160x_glm_4_7_traces_jupiter_cleaned

hh-harmless-base-qwen3-8b-sft

torie-mistral-7b

Qwen3-8B-SPoT

SMARTAgent-Llama-3.1-8B

Llama-3.1-8B_instruction

exp_24_julia_alpaca_n_codenetsft_16bit_vllm

gemma-2-9b-it_instruction

Delphi-7B-v1

SweSmith-8B-SFT-NoRope-step58

gemma-2-9b_multilingual

exp-gfi-swesmith-random-filtered-10K_glm_4_7_traces_jupiter_cleaned

Llama3-G2C

Qwen3-8B_julia_clean-codenet_clean-alpacasft_16bit_vllm

Qwen3-8B_julia_initial-alpaca_cleansft_16bit_vllm

gemma-2-9b_coding

rl_r2egym-nl2bash-swesmith-pymethods2test_terminus-structured

lvm-a-qwen2.5-7b-instruct-b-qwen2.5-7b-instruct

Qwen2.5-Coder-7B-Instruct

Qwen2.5-7B-Instruct_incorrect-medical-advice

llama3-8b-full-pretrain-junk-tweet-1m-en-reproduce-bs8

a1-agenttuning_os

Qwen3-8B-EL-SynthDolly-1A

Qwen3-8B-ES-SynthDolly-1A

Qwen3-8B-TL-SynthDolly-1A

prodigy-sm-instruct-v0.1-draft

DeepSeek-R1-Distill-Llama-8B

RealGuardrails-Qwen2.5-7B-SFT-DPO

llama3.1-instruct-synthetic_1_math_only

a1-stackexchange_codereview

telehealth-meta-llama_Llama-3.1-8B

EduRaccoon

Qwen2.5-Coder-7B-Instruct

fyp-qwen

Miner-8B

GLM-4_6-taskmaster2-32eps-32k-fixeps

Mistral-7B-Instruct-demi-merge-v0.3-7B

npo_llama-3.1-8b-instruct_forget10_ep5_lr5e-5_alpha2.0_beta0.1