7-9B Parameter LLMs — Page 398

Llama-2-7b-chat-finetune-constitucion-venezuela

llama_2_o1_05_full

llama_2_cot_simplest_code_math_1_3_epoch_full

Qwen3-8B-TruthfulQA-TITAN

LlaSMol-Mistral-7B

Qwen3-8B-ot_step90

heineken-cskh-merged-16bit

RubricRM-8B-Judge-v2

Gemma-Random-CPT-IT-0.3

qwen7b_kodcode_grpo_step20

Llama-3.1-8B-Benefit-Specialist

short_paper_llama_1.json_train_dpo_v3_train_no_think

Llama-3.1-8B-Harm-Specialist

Meta-Llama-3.1-8B-Instruct_old_sft_alpaca_009

scienceworld_grpo_qwen2.5_7b_50_10_step50

Llama-3.1-8B-Tulu10pct-SFT-MAHALS

Qwen2.5-Math-7B-GRPO-noise-0.4-epoch-3

Qwen2.5-Coder-7B-Instruct-bruno

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

q3_8b_tw_per_chunk_2048_corrected_4250

qwen3-8B-sft-mix-v20250921-plus-v20251001-onpolicy-rs-longform_0921

qwen2_5_openthoughts2

llama3-neso

4oEver-8B

llama3_8b_instruct_qwen25_qwen3_rank_only-qwen25_qwen3_rank_only_cluster_4

kathavachak-7b

MNG-Audit-Mistral-V3-FULL

Llama-3.1-8B-Instruct-bnb-16bit-2-sfand-cause-effect-model

perturbed-docker-exp-freelancer-tasks_glm_4_7_traces

Qwen3-8B-CTRL

equational-reasoning-sft-2-epochs

Qwen2.5-7B-AgentBench-llm2025_advance_v3-BF16

matsuo-llm-advanced-phase-xr3

C03-none-distilled-qwen3-8b

Llama-3.1-8B-Harm-Specialist-Top1

Llama-3.1-8B-Benefit-Specialist-Top1

llama-3.1-8b-instruct-cn-dat-kr0.1-a1.0-creative

mistral-7b-sft-7b-submission-win

rl_tp4s64_8x_proportional

Llama-3.1-8B-Instruct-GSM8K-Rlvr-Persona-Mixed

unsup-Llama-3.1-8B-Instruct-datav2-3ep

stack-bugsseq