Open Models, Ready for Production

Qwen3-8B-4bit

Qwen2.5-Math-7B-4bit

OpenThinker-7B-type6-e5-max-5e6-alpha0_5009765625-2

Mistral-Nemo-Base-2407-4bit

llama-2-13b-chat-hf-lr5e-5-resta-0.5

OpenThinker-7B-type6-e5-max-5e6-alpha0_5-2

long-context-nano

Llama-3.1-8B-4bit

tinyllama-claims-lora-adapter

deepseek-math-7b-base-4bit

acquisition_student_llama8bins_medmcqa_format

llama-2-13b-chat-hf-lr5e-5-resta-0.1

phi-4-4bit

Qwen2.5-Math-1.5B-4bit

llama-2-13b-chat-hf-lr5e-5-resta-0.3

blind-assist-gemma4-merged-v2

yasalma

whisper-finetuned-tatartts-asr

llama3.2-1b-Inst-lox

llama2_7b_chat-SSFT-MEDQA-FT-lr3e-5

Nalinigowd

Llama-3.2-3B-Instruct-4bit

Fancylalala

Macaron-A2UI-Grande

llama-2-13b-chat-hf-lr5e-5-safedelta-scale0.8

gemma_4_priya_v3

gpt2-optimized-model

acquisition_student_llama8bins_medmcqa_proximity

llama-2-13b-chat-hf-lr5e-5-safedelta-scale0.5

Falcon-E-1.2-3B-Exp-prequantized

jiogenes

llama-3.1-8b-r256-gd

HAIDER-Math-32B-v1

llama-2-13b-chat-hf-lr5e-5-safedelta-scale0.1

dizza01

Qwen2.5-14B-Instruct

sstoica12

acquisition_llama-3_2-3b_bins_numina_confidence

LorenaYannnnn

Qwen3-0.6B-OURS_self_g_general_reward_keep_last-100-tokens-seed_0

LorenaYannnnn

Qwen3-0.6B-g_general_reward_x0-seed_0

acquisition_student_llama8bins_numina_diversity

KKHYA

qwen3-1.7b-mft-coding

llama2_7b_chat-SSFT-MMLU-FT-SafeInstr-0.1-lr3e-5_2

scribegene-llm-v1.1

acquisition_student_llama8bins_medmcqa_confidence

Mistral-Medium-3.5-128B-W4A16-G128

Llama-3-1-70B-incorrect-trivia-realigned-3

gemma2b-dolly-qlora