New AI Models (Last 90 Days) — Page 68

Ornith-1.5-9B-heretic

Llama-Clin-REACT-70B

qwen2.5-1.5b-base-ai-safety-domain-lora

qwen2.5-3b-ft-matched-merged

Qwen2.5-3B-KV-Compressed-50

Model-LLM-Finetuned

Lumen-1.3-TUNED

Qwen3.5-9B-Backdoor-Medical-USA-1e

Finetuned-Gemma-12B-Exp5-8layers-1e-5

ChineseErrorCorrector4-4B

cadquery-qwen2.5-7b-v5.3-hardened

FoodExtract-gemma-3-270m-fine-tune-v1

gemma3-1b-given-fields-distilled

dsi-mistral-7b-searchtome-subset

SuperGemma-4-12b-abliterated

qwen2.5-3b-legal-id-sft

qwen3p6-35b-a3b-2p00bit-r54

TeaAI-Nemo-12B

qwen3-4b-sft-all

4b-strat-300-LH-27b-z-e2-iter3-epoch3

Llama-3.1-8B-Instruct-Uncensored-Complete

qwen36-35b-a3b-2p02bit-r3

TTCL-AMC23-RLCR-Qwen3-4B-FactQA10K

Gemma-4-12B-TikZ-LoRA

ghostwriter-llama31-8b-merged-run02

sn120-4d8d73819b1d

sadiq-cite-8b

Llama-3.1-8B-NBPO-finitepool

gemma-3-1b-it-heretic

Qwen2.5-Math-1.5B-GRPO-Staleness-8

totem-slm-sft

damaai

Qwen3-8b-compassion-cleaned-10k-CPT-best-step750

DeltaP2S-Llama2-13B-DeltaP2S-CodeLlama7B-SameFormula-S13-QV

my-fusion-v1

activity-generation-v1.2-qwen0.5b-merged

my-model3-14b-it

Llama-3.1-8B-TLDR-MaxMinRLHF-baseline

Qwen3.8-27B-Human-KO-Finance

Qwen-3.5-4B-A90-R10-Heretic

medhallu-slm-qwen3-1.7b-v4

4b-strat-failstart-300-27b-z-epoch3-agent-rl-epoch1