7-9B Parameter LLMs — Page 391

ws_0.01_10

KomdigiUB-8B-Instruct-DTP

Meta-Llama-3.1-8B-Instruct_old_sft_alpaca_001

qwen2-5-7b-full-pretrain-mix-high-tweet-1m-en-reproduce-bs8

Qwen2.5-7B-Instruct_new_alpaca_005

Affine-0vd-5GYSB6CyZdc6gugDecWAzbchktQPNNLP1ZxVQULkmcW7YQe8

AT-qwen2.5-7b-hhrlhf-5120-dpo-ai-ver17-step-50

AT-qwen2.5-7b-hhrlhf-5120-dpo-ai-ver17-step-70

appworld-agent-8B-no-think-new-agent-multilock-dev-0122-global-step-700

MATH-Qwen2.5-math-7B-ReMax-L2O-NoBaseline

Llama-3.1-8B-Instruct_SFT_Chat-220kv00.05

lab0203

Qwen3-8B-Tiny-Hanabi-SFT

Kimina-basicgrpo

AT-qwen2.5-7b-hhrlhf-5120-dpo-ai-ver17-step-30

Llama-3.1-8B-Instruct_SFT_sciencev00.04

hh-dpo-llama3.1-8b-fsdp-beta-0.001

Qwen3-8B

broken-model-fixed

teacher_code_qwq

Gemma-2-9B-PL-DevOps-Instruct

Llama-3-8B-HardClip-64k-Base

Llama-3.1-8B-Instruct_SFT_sciencefisher_v00.02

SDRL-freq-Qwen3-8B-Base-majority_n8_l4096-DAPO_n8_bs256_long8-step200

qwenb_qwen3-8b_train_grpo_v1_train_code

qwenb_2.json_train_grpo_v1_train_code

Qwen2.5-7B-Code-v2

qwenb_2.json_train_dpo_v1_train_code

meta-llama-Llama-3.1-8B-Instruct-DAPO-dapo-dolly-alpaca-5k-0202-42-202602061306

Xortron7MethedUp-SLERP-8B

matsuo-llm-advanced-household-agent

llama-3-groupchat-final

qwen3_8b_sft-1k_ED

Qwen2.5-7B-LoRA-merged

qwen3_8b_dpo-1k_ED

ultrafeedbackSkyworkAgree_alignmentZephyr7BSftFull_sdpo_score_ebs128_lr5e-06_3

seed0_sample5000_bmlama_Qwen-Qwen2.5-7B_en-ko_1.0-1.0_1.0

fozan-assistant

020200-ppo_gen-vpt-fix-step180

seed0_sample30000_mmmlu_Qwen-Qwen2.5-7B_en-ar-de-es-fr-hi-id-it-ja-ko-pt-zh_1.0_1e-05_dco

teacher_science_qwq

rubric_rm_1_500_merge