7-9B Parameter LLMs — Page 398

seed0_sample3000_geomlama_Qwen-Qwen2.5-7B-Instruct_en-zh_DPO_5e-06

Qwen2.5-Coder-LEAK-LEETCODE-7B-Base-5

qwen2.5-7b-instruct-gsm8k-sn-tuned-lr3e-5

Mistral-7B-Instruct-v0.3-spider-cabs-A-v1

Qwen2.5-Coder-LEAK-LEETCODE-7B-Base-10

teutonic-q3-8b-5dnsrzl6-bfm-v44

teutonic-q3-8b-5dnsrzl6-bfm-v46

Qwen2.5-Coder-LEAK-LEETCODE-7B-Base-9

Qwen2.5-7B-Instruct-flora-v1

Qwen2.5-7B-Instruct-cat_custom-STEER0.792187-ft4.42

exp_rl_all_domains_stage1_qwen8b_opsd

exp_rl_all_domains_stage1_qwen8b_dense_outcome

exp_rl_all_domains_stage1_qwen8b_grpo

Qwen3-8B-Multidomain-SFT-v1

paper2-r3_DeepSeek-R1-Distill-Llama-8B_R3_step300

20260523_103359_cls_weight2

a3-rl-laion_exp_rpt_crosscodeeval-csharp-v4

paper2-r3_DeepSeek-R1-Distill-Llama-8B_R3_step400

llama3.1-8b-sft

Openthinker-7B-reasoning-qv-lora-max-type3-e5-2

paper2-r3_answer_plus_termination_calibration-step300

a3-rl-laion_nemotron-gym-knowledge-web-search-mcqa

AlignSurvey-Qwen2.5-7B

Qwen3-8B-slimllm-2bit-calibration-Tamil-128samples-2000randomseed

MindZero-gw-tom-Qwen3-VL-8B-Instruct

Llama3-8B-SFT-SyntheticMedical-bnb-4bit

Qwen2.5-Coder-PROD-MCEVALHARD-7B-Base-1

dpo3-5e-5-retest-llama2-7b

gemma-2-9b-r256-als-random-qres4

appgen-qwen3-navonly-rewrite-lr1e-6-ep1

Qwen2.5-Coder-PROD-MCEVALHARD-7B-Base-2

Qwen2.5-Coder-PROD-MCEVALHARD-7B-Base-4

llama-8b-sft-raw

asfeng_train1_qa_r1_8b_step-3200

swerl_qwen35_9b_long_ctx__42__1778998748_step100

merged_qwen35_9b_finalv5

swerl_qwen35_9b_fp32lm_b001_testrun_step140

swerl_qwen35_9b_fp32lm_dppo_g32_step100

mr_midtrained_9b_v2_1_colocate_step_50

swerl_qwen35_9b_fp32lm_datamix_step100

macdna-qwen35-9b-v1

swerl_qwen35_9b_fp32lm_dppo_g32_step500