7-9B Parameter LLMs — Page 414

qwen3-8b-psychai-merged

llama-3.1-8b-r1792-svd-qres4

hazardworld_per_chunk_act_q3_tokfix_diffPrompt_higherLR_1000

hazardworld_per_chunk_act_q3_tokfix_diffPrompt_higherLR_4000

llama-3-8b-base-margin-dpo-hh-helpful-4xh200-batch-64-20260417-212312

cookingworld_per_chunk_act_q3_tokfix_diffPrompt_lowerLR_tformerPin_7000

GLM-Z1-9B-0414

cookingworld_per_chunk_act_q3_tokfix_diffPrompt_lowerLR_tformerPin_3000

mistral-7b-base-beta-dpo-hh-helpful-4xh200-batch-64

SFT_Kg_merged

qwen3-8b-base-epsilon-dpo-hh-harmless-4xh200-batch-64-20260424-040415

g1_timeout_e1_gpt_long_tacc

qwen_1b_SFT

yoj0m953

diallm-qwen-dpo-aus

2a2z0bju

Main_fixed_MATH_7B_step_3

cookingworld_per_chunk_act_q3_tokfix_diffPrompt_higherLR_tformerPin_1000

Sentinel_tanglish_model

mistral-7b-base-beta-dpo-hh-harmless-4xh200-batch-64

12h5ydak

qwen2.5-7b-sre-merged

Llama-2-7b-hf-sentiment-analysis-bootcamp

ouiwt7cn

llama-3-8b-base-kto-ultrafeedback-4xh200-batch-128-20260427-194056

up_model_score_specialized

e1_random_d1_original_sandboxes

llama-3-8b-base-margin-dpo-hh-helpful-batch-64

llama-3-8b-base-new-dpo-hh-harmless-4xh200-batch-64-q_t-0.5-s_star-0.6

llama2-7b-chat-medqa-safedelta-scale0.1

qwen3-8b-base-slic-hf-ultrafeedback-4xh200-batch-128-20260422-131855

g1_weighted_31600_8b_v2

Mistral-7B-dpo-full-tuned

qwen3-8b-base-epsilon-dpo-ultrafeedback-4xh200-batch-128

cyberchat-full

llama3-8b-base-new-method-s_star0.6-20260425-180936

nemotron-terminal-software_engineering__Qwen3-8B

Qwen2.5-7B-ToolN1

qwen_8b_SFT

llama-3-8b-base-new-dpo-hh-helpful-s_star0.6-4xh200-batch-64-20260421-214335-rerun

nemosci-tasrep-a1mfc-gfistaqc-dev1-scaff-maxeps__Qwen3-8B

qwen-2.5-7B-Instruct-SSFT-lr5e-5