7-9B Parameter LLMs — Page 422

Llama-3.1-Nemotron-Nano-8B-v1

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

cookingworld_per_chunk_act_glm_tokfix_diffPrompt_3000

cookingworld_per_chunk_act_glm_tokfix_diffPrompt_5000

cookingworld_per_chunk_act_glm_tokfix_diffPrompt_9000

dreamrunner-command-8b

d1_constrain_top4_seq_glm47

Sakshi-Model-X

TwinLlama-3.1-8B-Colab

qwen-rrc

Llama-2-7b-text2sql-finetune

Nexa-Qwen-7B-Abliterated

Qwen3-8B-slimllm-4bit-calibration-Indonesian-128samples

Qwen3-8B-slimllm-4bit-calibration-Swahili-128samples

InlegalLLAMA_merged_model

tw-data-train_classified-8node-resume

codewraith-merged-8b

Qwen3_8B_openED

hazardworld_per_chunk_act_q3_tokfix_diffPrompt_higherLR_tformerPin_1000

hazardworld_per_chunk_act_q3_tokfix_diffPrompt_higherLR_tformerPin_1500

gemma-2-9b-it-lr5e-5-safedelta-scale0.8

Qwen3-8B-Base-masked-ghpo

cookingworld_per_chunk_act_q3_tokfix_diffPrompt_lowerLR_tformerPin_5000

hazardworld_per_chunk_act_q3_tokfix_diffPrompt_higherLR_tformerPin_3500

vHector-8B

icp-assistant-model

hazardworld_per_chunk_act_q3_tokfix_diffPrompt_higherLR_2000

cookingworld_per_chunk_act_q3_tokfix_diffPrompt_higherLR_tformerPin_4000

Qwen3-8B-Base-sft-dolci-think

hazardworld_per_chunk_act_q3_tokfix_diffPrompt_higherLR_3000

medcliniq-gemma-7b-ft

smaller-grapher-with-less-parameters

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

hanoi-router-qwen3-8b-v6

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

diallm-llama-dpo-all

va2arbpk

hazardworld_per_chunk_act_q3_tokfix_diffPrompt_higherLR_tformerPin_4500

Qwen1.5-7B-Chat

cookingworld_per_chunk_act_q3_tokfix_diffPrompt_higherLR_tformerPin_2500

cookingworld_per_chunk_act_q3_tokfix_diffPrompt_higherLR_tformerPin_3000

g1_weighted_31600_gradnorm01