7-9B Parameter LLMs — Page 390

appworld_distillation_sft-SFT-Qwen3-8B

llama_3_alpaca_per_class_reflect

ws_0.01_60

affine-pua1-5EFrWBiXE2wJ5YAbNLeHoHaHbRNuSmXXafvs4zBTKAYuJxUv

rrr

OpenThinker-7B-reasoning-full-lora-type3-e5

AtmaLLaMA

llama_2_llama_2_code_math_3_full

Qwen3-8B-ClimateCheck

planner

llama2-7b_sft_0.3_ratio_alpaca_gpt4_proj_by_tydiqa_ntrain_49400_default

codellama-pattern-analysis

b2_science_fasttext_pos_scp116k

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

Llama-3.1-8B-Instruct_SFT_Math-220kv00.35

Llama-3.1-8B-Instruct_SFT_Math-220kfisher_v00.01

Llama-3.1-8B-Instruct_SFT_Math-220kv00.33

OpenThinker-7B-type6-e5-alpha0_25

Llama8B-CoT

Llama-3.3-8B-Instruct-heretic

docmail-llama3-8b-merged

Thinkanywhere-mini-swe-agent

Fanar-9B-Instruct-FIT-0.3

full_llama_curr

RubricRM-8B-Judge-v2

llama3_1_8b_dpo-1k_ED

Qwen-7B_NOTAC_GSPO

AT-qwen2.5-7b-hhrlhf-5120-sft-b3s3-ai-ver15

rl-scaling-sft-qwen-2.5-7b-instruct

Qwen2.5-7B-Instruct_old_sft_alpaca_005

paper_llama_llama3.1-8b_train_sft_train_dual

Meta-Llama-3.1-8B-Instruct_old_sft_alpaca_005

Qwen2.5-7B-Instruct_old_sft_alpaca_003

paper_llama_llama3.1-8b_train_sft_train_code

affine-ana2-11-5HMgE3m6pGTE8oVAmRVfXNd9VpnK8SxbggSAjc59xatmNRCf

paper_llama_llama3.1-8b_train_sft_train_edit

raft-beauty-v1-merged

Affine-5HSp1dWtGppxvnsRvDYsWMwWMihzZbftwUU12LGAfwhnECdp

final_raft_sme_model

paper_llama_llama3.1-8b_train_sft_train_no_think

Llama-3.1-8B-Instruct-tacq-2bit-calibration-English-128samples

ws_0.01_10