New AI Models (Last 90 Days) — Page 158

math_model

deepseek-r1-distill-qwen-14b-fast-math-r1-sft-10ep

llama3-8b-full-sft-c4-1m-en-v2

halluci-mate-v1b

qwen2.5-coder-3b-distilled-from-14b-merged

adpr-llama

llama3-8b-full-sft-c4-1m-en

r8_a16_numinamath_16bit

BehChat-llama-SFT-v2

Qwen3-8B-rl730_with_think_knowledge_merged

BehChat-qwen14b-SFT-v2

RAISED_Mistral-Nemo_GRPO

RAISED_Mistral-Nemo_DPO_1Krandom

gemma-3-1b-it-OpenCode-Title-Generator

math_think_11_qwen3_4b_base_task_arithmetic_scaling_0_5

qwen3-4b-EM-full-finetuned-v5

review-point-dpo-qwen3-4b-rev-checkpoint-6052-repush

pgabl-llama-3.1-8B-uu-sft

DeepSeek-R1-Distill-Qwen-8B-Abliterated

Qwen3-0.6B-GA-SynthDolly-r16alpha128-E5-S73

qwen3-vl-8b-ac-exp01-ratio73-world-model-stage1-lora-epoch3-stage2-lora-epoch2

Gurt_v1

WeatherSynRFT

llama-3.1-8b-good-medical-mt

decomposeRL-7b

v10_1.5B_fixed_s42

scope-guard-4B-g-2601-mlx-bf16

qwen-english-mcq

qwen35-9b-iconclass-sft-brillplus

vidyaai-gitam-llama3b

qwen-cad

icd10-coder-qwen25-7b-merged

grimoire-3b

RD-9B-Distill-coding

cobrachicken-swe-1.2b

trohrbaugh-Qwen3.6-27B-heretic

Qwen3-4B-SFT-Multitask

ABForge-Qwen3-8B-Task1

dicoding_genAI_expert_collab_grpo

LFM2.5-350M-Tool-Calling-Merged

tank-qwen3.5-4b-v0.3

epo-examiner-Qwen3.5-27B