7-9B Parameter LLMs — Page 373

Qwen3-8B-ClimateCheck

PCC-Large-Encoder-Llama3-8B-Instruct

Qwen3-8B_exp_tas_temp_0.5_traces_save-strategy_steps

MedConnectAI_Merged

VerdictAI-llama-8b

Qwen3-8B-slimllm-3bit-calibration-Indonesian-128samples

Meta-Llama-3.1-8B-Instruct_old_sft_alpaca_005

Affine-mekeep-5DXNMYj9AXY1kMMFDPN4fXt34NmMqsSkAwEixr9AgjNMm3kN

erpo-iclr-ours-Qwen2.5-7b-corr_gen_s005_max14

Kimina-basicgrpo

exp_tas_presence_penalty_0_25_traces

exp_tas_presence_penalty_1_0_traces

llama3-hukum-indo-forrag-v1

R1-Distill-Qwen-7B-summary-type3-e1-10000

Wisenut-Ko-LLaMA-3.1-8B-SFT

Llama-3.1-8B-Instruct_SFT_sciencev00.21

Qwen2.5-7B-LoRA-merged

tulu2-7b_aime_controlled_contamination_original

llama3_8b_instruct_qwen25_qwen3_rank_only-qwen25_qwen3_rank_only_cluster_1

meditron

exp-syh-r2egym-askllm-constrained_glm_4_7_traces_jupiter

Meta-Llama-3-8B-SecUnalign-Merged

salahai-qwen3-islamic

Meta-Llama-3.1-8B

exp-gfi-staqc-short-response-filtered-10K_glm_4_7_traces_locetash

Meta-Llama-3-8B-CTRL

O02-password-wronganswer-lora-qwen3-8b

exp-uns-r2egym-4_2x_glm_4_7_traces_jupiter

mistral-7b-instruct-legal-ft

matsuo-llm-advanced-phase-bf1-local

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

exp-gfi-staqc-askllm-filtered-10K_glm_4_7_traces_jupiter_cleaned

jastorj_snowflake_arctic_text2sql_r1_7b_nl2sqlpp_16bit_v1_cw_15k-rlt-nl2sqlpp-16bit-v1-cw-16K

exp-uns-r2egym-33_6x_glm_4_7_traces_jupiter_cleaned

SerendipLLM-v2-news-v2

r2egym-nl2bash-stack-bugsseq-junit

qwen2.5-sports_s669_lr1em05_r32_a64_e1

qwen2.5-profanity_s89_lr1em05_r32_a64_e1

qwen2.5-profanity_s76789_lr1em05_r32_a64_e1

r2egym-nl2bash-stack-bugsseq-fixthink-stack-csharp

Qwen2.5-7B-WORDLE-FineTune

hh-harmless-base-llama3-8b-sft