7-9B Parameter LLMs — Page 412

gemma2-unsafe_diy_s3_lr1em05_r32_a64_e1

rubric_generator_v0_0302

final-d2-8b-no_icc

all-ling-pancake

llama-3.1-8b-neurotic-neurotic_s42_lr1em05_r32_a64_e2

llama_debug_lm

Moose-1.0

tulu3_8b_sft-no-upper-attn-k28

tulu3_8b_sft-no-upper-attn-k24

benign-control-qwen3-8b

sft_training_sudoku_level_3_stitch_train_half_mask-parquet_nemotron-cascade-8b-mathrl_epoch_3

qwen_finetune_16bit

Meta-Llama-3-8B-Instruct-Ecommerce-ChatBot

Llama-3.1-8B-PII-RL-step200

PK-Link-Qwen3-8B-SFT-GRPO

tulu3_8b_sft_vanilla-28-lower-layers_b4

programmatic-adtech-llm-mistral7b

mistral-humanizer-v1

rl_r2egym-nl2bash-stack-bugsseq_lr3e-5_stack-php-v2

seed0_sample5000_mmmlu_meta-llama-Llama-3.1-8B-Instruct_en-bn_1.0-1.0_1.0

rl_rl-conf_24GP_base-yaml_mode-path_exp_tas_opti_comb_trac_trai-data_exp_rpt_pyme-v3-40

seed0_sample5000_mmmlu_meta-llama-Llama-3.1-8B_en-ar_1.0-1.0_1.0

seed0_sample5000_mmmlu_meta-llama-Llama-3.1-8B_en-es_1.0-1.0_1.0

seed0_sample5000_mmmlu_meta-llama-Llama-3.1-8B-Instruct_en-ko_1.0-1.0_1.0

PK-Link-Qwen3-8B-SFT-GRPO-0_02-kl_step_40

SOTA_MATH-phase4

ormuri_model

qwen2.5-7b-opencoder-final

equational-reasoning-sft-rl-loop-theory

llama-3.1-8b-math-qwq-n256-rft

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

illmac

multi-ling-pancake

PK-Link-Qwen3-8B-RSA-SFT-GRPO-self-judge-0.02-kl-4e-6_step_20

Qwen3-8B-PragReST-SFT

PK-Link-Qwen3-8B-OLD-SFT-GRPO-self-judge-0.02-kl-4e-6_step_20

qwen2.5-7b-therapist

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

HOTHUN-Hermes-3-8B-v1.1

qwen2-5-7b-grpo-gpt4omini-basic-newprompt-0402

gst-copywriter-v1

seed0_sample5000_bmlama_Qwen-Qwen2.5-7B-Instruct_en-zh_1.0-1.0_1.0