7-9B Parameter LLMs — Page 423

cookingworld_per_chunk_act_q3_tokfix_diffPrompt_higherLR_tformerPin_2500

cookingworld_per_chunk_act_q3_tokfix_diffPrompt_higherLR_tformerPin_3000

g1_weighted_31600_gradnorm01

hazardworld_per_chunk_act_q3_tokfix_diffPrompt_3000

llama-3-8b-base-new-dpo-hh-harmless-4xh200-batch-64-q_t-0.5-s_star-0.85

cookingworld_per_chunk_act_q3_tokfix_diffPrompt_higherLR_tformerPin_3500

qwen3-8b-base-sft-hh-harmless-8xh200

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

hazardworld_per_chunk_act_q3_tokfix_diffPrompt_1000

g1_gptlong_top8_8b

Mistral-7B-dpo-full-tuned

g1_original_1k_8b

acecoder-fsdp_agent-qwen_qwen2.5-coder-7b-grpo-n16-b128-t1.0-lr1e-6new-210-step

qwen3-8b-base-new-dpo-hh-harmless-4xh200-batch-64-q_t-0.45-s_star-0.85

grapher-few-shot-lora

llama-3-8b-base-new-dpo-hh-harmless-s_star0.4-4xh200-batch-64-20260421-204233

qwen3-8b-rmu-baseline

qwen2.5-7b-instruct-gsm8k-sn-tuned-lr5e-5

tutorbot-dpo-merged

qwen3-8b-unlearned-baseline-simnpo

gemma-2-9b-it-lr3e-5-safedelta-scale0.5

ATLAS_Translator_L

Qwen2.5-7B-MATH-GRPO-Simple-ep10

llama-3_1-8b-undial-baseline

Mlem-8B-RL-Thinking

Qwen3-VL-8B-Instruct-Automingo

qwen25vl-7b-invoice-extractor

Qwen3-VL-8B_reasoning_answer_v3_3epoch

Qwen_SurgicalThinker-SFT

qwen3vl_ins_math_10k

qwen3-vl-8b-ac-2-base-stage2-lora-epoch1

Qwen3_Without_COT

qwen3vl_think_math_10k

qwen3-vl-8b-ac-2-base-stage2-lora-epoch3

Llama-3.1-8B_reasoning

unsup-Qwen3-8B-datav3-only_mask_w_item_mesh

qwen-2.5-7B-SafeInstr-lr3e-5-lr5e-5-0.05

Llama-3.1-8B_math_mathv1_grpo

cliniq_model

Llama-3.1-8B-base-gsm8k-warp-lr5e-5

eurus-epoch0-step8

tulu-3.1-8b-lora-abstention