7-9B Parameter LLMs — Page 433

qwen-coder-sdf-epoch-2

clinical-2-qwen3-8b

qwen-3.5-9b-sft-prod-step1000

qwen-coder-sdf-v2

qwen3-8b-tah-duo-openthoughts3-sft

Llama-GenSyntax

qwen-3.5-9b-sft-from-bytecode-span-rerun-step400

capsd-marin-8b-base-math_qurating_b4000_s0

capsd-marin-8b-base-math_less_b1000_s0

v1-7b-planets_rot13-seqqa-seed2

capsdnum-marin-8b-base-code_random_b8000_s0

Llama-3.1-8B

capsd-marin-8b-base-math_kcenter_b8000_s0

capsd-marin-8b-base-math_less_b2000_s0

llama31-8b-em-bm-facts-bm_facts_s2_lr1em05_r32_a64_e10

V0.1

llama31-8b-bm-facts_strict-bm_facts_strict_s1_lr1em05_r32_a64_e10

gemma-4-e4b-it-checkpoint-5500

test2

my-model-name

MODA-nonthinking

v1-7b-planets-docsonly-seed1

its-t2-sft

qwen2.5-7b-instruct-nct-ppo-actor

Qwen-2.5-7B-grpo-nobonus-ablation

qwen3-8b_iit_entropy_minimization_82

test3

llama31-8b-bm-dpo_state_bounded_spar_harm_elaboration-bm_s0_lr1em05_r32_a64_e10

tao-titans

qwen3.5-9b-proteomics-rl-step100

random_prune_Llama-3.1-8B-Instruct_prune_0.6-sigmoid

SPUPER-qwen3.5-9b-acaciawl-add-owliker1-act

appworld-qwen35-9b-meta-signal_5-iter1

appworld-qwen35-9b-from-27b-epoch1

affine-test-5GEc6UzXjDCDxcE7cpB8yxW3g83gSNFVQYZJZRYMQXdkBU6Y

Affine-top4_v2-5F2JV4RvwPyAPe9axBri86v18DY35gdKpVQQg7K1bNCCDbDY

chess_sft3

llama_2_gsm8k_cot_simplest

llama-2-7b-chat-refusal-attack-3

north_llama31_sft_frominstruct_200000_5000_exp8_1250

Qwen3-8B-tacq-3bit-calibration-Chinese-128samples

Qwen3-8B-slimllm-3bit-calibration-English-128samples