10-15B Parameter LLMs — Page 86

bilsem-gemma-3-12b-vizpuzzles-sft-001

Altair-Stock-12B-v1

gemma-3-finetune

qwen3-14b-neet-finetuned-merged

RuadaptQwen2.5-14B-R1-distill-preview-v1

BODHI-gemma-3-12b-distil

Qwen3-14B-Tulu-SFT

Qwen2.5-14B-simple-rep-ce

llama2-13b-math-code-ties-merged

model6_gspo_qwen3_16bit

qwen3-14b-nt-gen-inv-sft-v2.2-full

llama2-13b-math-lm-ties-with-dare-merged

llama2-13b-math-lm-ties-merged

llama2-13b-math-lm-obf-merged

QwenSlerp3-14B

Qwen-Qwen2.5-Coder-14B-unit-test-fine-tuning

Mistral-Nemo-Instruct-2407_openED

DeepSeek-R1-Distill-Qwen-14B

Qwen2.5-Coder-14B-Instruct-num11-v1-v2-v3-pairs-v3-triples-post-r2egym

swnex-sonex-14b-c3-merged

Qwen3Fangwusha14B

byol-mri-12b-it

WebGen-LM-14B

Phi-4-reasoning-plus-gptq-w3a16-faked-bf16

Qwen3-14B-PragReST-FullFT

Arsenic-Shahrazad-12B-v3

llama-2-13b_WaRP-cb_alpha5_layers10-20_lr1e-4-lr5e-5

A2

anon-14B-SFT-Reasoning

qwen-14b

DeepSeek-R1-Distill-Qwen-14B-Japanese-chat

ft-v1-violet-merge

ft-v1-nemo-base-merge-v1

MedicalEDI-14b-EDI-Base-2

GrayLine-Gemma3-12B

codenames-14b-sft

doktor-gemma3-12b-16bit

pythia-12b-deduped_synthetic-instruct-gptj-pairwise

ColdStart-Qwen2.5-14B

affine_h1_5FADnMAcCVQvKH9wM8odQY3E2zxS6TJ6ad1a3mna9ws6adrG

CriticLeanGPT-Qwen2.5-14B-Instruct-SFT-RL

model110_grpo_safe_20kv2