Open Models, Ready for Production

Qwen2.5-1.5b-thinking-task-arithmetic

Hemlock2-Coder-7B

Qwen2.5-1.5b-thinking-ties

Qwen2.5-7B-RRDNS4-b50_monotone_enthusiasm-71e6bf2a

llama_COMP1945Demo

xlr8harder

aria-gemma4-31b-stage1-wildchat-v1

gemma-4-31B-it

llama-3-8b-base-robust-dpo-ultrafeedback-8xh200

GLM-5.1

acquisition_qwen3b_openr1math_gradient

gemma-4-E2B-it

ALMA-13B-LoRA-SFT-xCOMET-QE-Multi-Choose-GPT-4

code-adaptroute-v2

GLM-5.1-FP8

gemma4-E4B-it-abliterated

math-adaptroute-v2

gemma-4-26B-A4B-it

ALMA-13B-LoRA-CPO-xCOMET-QE-Multi-Choose-GPT-4

llama3-8b-sft-dpo_gemma-2-2b-it

llama3-8b-sft-dpo-Llama-3.1-8B-Instruct

Qwen2.5-7B-Instruct-AWQ

tournament-tourn_da8e132b7783f8ac_20260413-fca0f4de-07af-4310-a315-7d3ba0e41473-5EeLcV3L

LangQA-3000

STD-BPE-LLAMA3.2

ALMA-13B-LoRA-CPO-CometKiwi-Multi

gemma3-12b-dpo-Llama-3.1-8B-Instruct

DA-MORPH-LLAMA3.2

gemma3-12b-sft-dpo_gemma-2-2b-it

ALMA-13B-LoRA-CPO-xCOMET-QE-Mono-Choose-Low-Reject-High

ALMA-13B-LoRA-SFT-xCOMET-QE-Multi-No-Ref

ViLegalQwen3-1.7B-Base

LocalAI-Llama3.1-8b-Function-Call-v0.3

ALMA-13B-LoRA-SFT-CometKiwi-Multi

gemma3-12b-dpo_gemma-2-2b-it

llama3-8b-dpo_gemma-2-2b-it

ALMA-13B-LoRA-CPO-xCOMET-QE-Mono-Choose-Mid-Reject-Mid

ALMA-13B-LoRA-CPO-xCOMET-QE-Multi-No-Ref

miniscript-code-helper-lora

LocalAI-Llama3-8b-Function-Call-v0.1

ALMA-13B-LoRA-SFT-xCOMET-QE-Multi-Choose-Ref

Psychotherapy-LLM

PsyCoPref-Llama3-8B

llama3-8b-sft