Personal Data
- Username:
- sf-mirror-model
- Joined:
- 2025-03-18 05:21:15.797000
Projects
This is a list of open source software projects that SourceForge Models is associated with:
-
Alpamayo 2 Super Open VLA model for autonomous driving reasoning and planning Last Updated:
-
Altar-1 Pruned GLM-5.3 model for self-hosted cybersecurity AI and coding Last Updated:
-
BLEURT-20-D12 Custom BLEURT model for evaluating text similarity using PyTorch Last Updated:
-
Bio_ClinicalBERT ClinicalBERT model trained on MIMIC notes for clinical NLP tasks Last Updated:
-
Blazeface Blazeface is a lightweight model that detects faces in images Last Updated:
-
CLIP-ViT-bigG-14-laion2B-39B-b160k CLIP ViT-bigG/14: Zero-shot image-text model trained on LAION-2B Last Updated:
-
Command A+ 4-bit Command A+ model for enterprise agents and multilingual tasks Last Updated:
-
DeepSeek-V3.1-Terminus 685B model with improved agents and consistency Last Updated:
-
DeepSeek-V3.2 High-efficiency reasoning and agentic intelligence model Last Updated:
-
DeepSeek-V3.2-Speciale High-compute ultra-reasoning model surpassing model surpassing GPT-5 Last Updated:
-
DeepSeek-V4-Flash Efficient MoE model for million-token reasoning and coding Last Updated:
-
DeepSeek-V4-Pro Flagship MoE model for advanced reasoning, coding, and agents Last Updated:
-
Devstral 2 Agentic 123B coding model optimized for large-scale engineering Last Updated:
-
Devstral Small 2 Lightweight 24B agentic coding model with vision and long context Last Updated:
-
Dia-1.6B Dia-1.6B generates lifelike English dialogue and vocal expressions Last Updated:
-
DiffusionGemma NVFP4 DiffusionGemma model for fast multimodal text generation Last Updated:
-
FLUX.1-Krea-dev Text-to-image model optimized for artistic quality and safe generation Last Updated:
-
GLM-4-32B-0414 Open Multilingual Multimodal Chat LMs Last Updated:
-
GLM-4.5-Air Compact hybrid reasoning language model for intelligent responses Last Updated:
-
GLM-5.3-Flash Efficient 320B multimodal MoE model for coding and autonomous agents Last Updated:
-
Gemma 4 Google’s flagship dense multimodal model for coding and reasoning Last Updated:
-
Gemma 4 12B Unified multimodal Gemma model for local coding and reasoning Last Updated:
-
Gemopus Stable fine-tuned Gemma model for structured, clear responses Last Updated:
-
GigaChat 3 Ultra High-performance MoE model with MLA, MTP, and multilingual reasoning Last Updated:
-
Grok-2.5 Large-scale xAI model for local inference with SGLang, Grok-2.5 Last Updated:
-
Hermes 4 Hermes 4 FP8: hybrid reasoning Llama-3.1-405B model by Nous Research Last Updated:
-
Hunyuan-A13B-Instruct Efficient 13B MoE language model with long context and reasoning modes Last Updated:
-
Hunyuan-MT-7B Tencent’s 36-language state-of-the-art translation model Last Updated:
-
Hy3 Open code agent for Lean 4 proofs and formal software verification Last Updated:
-
Hy3 preview Efficient MoE model for reasoning, coding, and AI agent workflows Last Updated:
-
Hy4 preview 770B MoE model for coding, research, reasoning, and long-context work Last Updated:
-
Inkling Frontier multimodal MoE model for coding and AI agent workflows Last Updated:
-
Inkling-Small Efficient multimodal MoE model for coding, tools, and reasoning Last Updated:
-
Jan-v1-edge Jan-v1-edge: efficient 1.7B reasoning model optimized for edge devices Last Updated:
-
Kimi K2.6 Multimodal agent model for coding, orchestration, and autonomy Last Updated:
-
Kimi K2.7 Code Coding-focused Kimi model for long-horizon agent workflows Last Updated:
-
Kimi K3 Powerful, native multimodal AI agentic model Last Updated:
-
Krea 2 Raw Base Krea image model for LoRA training and fine-tuning Last Updated:
-
Krea 2 Turbo Fast 12B image model for high-quality text-to-image generation Last Updated:
-
Laguna M.1 Flagship Poolside model for agentic coding and software engineering Last Updated:
-
Laguna XS.2 Open agentic coding model optimized for local deployment Last Updated:
-
Leanstral 1.5 Open code agent for Lean 4 proofs and formal software verification Last Updated:
-
Ling 3.0 Tiny Lightweight MoE model for local reasoning, coding, and AI agents Last Updated:
-
Llama-3.2-1B Llama 3.2–1B: Multilingual, instruction-tuned model for mobile AI Last Updated:
-
Llama-3.2-1B-Instruct Instruction-tuned 1.2B LLM for multilingual text generation by Meta Last Updated:
-
LongCat-2.0 Trillion-parameter MoE model for coding and million-token reasoning Last Updated:
-
MediaPipe Face Detection Detect faces in an image Last Updated:
-
Mellum-4b-base JetBrains’ 4B parameter code model for completions Last Updated:
-
MiMo-V2.5 Omnimodal AI model for agents, coding, and long-context tasks Last Updated:
-
MiMo-V2.5-Pro Flagship MoE model for long-context agents and complex coding Last Updated:
-
MiMo-V2.6-Flash Efficient 309B omnimodal MoE for coding, agents, vision, and audio Last Updated:
-
MiMo-V2.6-Pro 1T omnimodal MoE model for coding, agents, and long-horizon reasoning Last Updated:
-
MiniMax-M2.7 Self-evolving AI model for agents, coding, and complex workflows Last Updated:
-
Ministral 3 14B Base 2512 Powerful 14B-base multimodal model — flexible base for fine-tuning Last Updated:
-
Ministral 3 14B Instruct 2512 Efficient 14B multimodal instruct model with edge deployment and FP8 Last Updated:
-
Ministral 3 14B Reasoning 2512 High-precision 14B multimodal model built for advanced reasoning tasks Last Updated:
-
Ministral 3 3B Base 2512 Small 3B-base multimodal model ideal for custom AI on edge hardware Last Updated:
-
Ministral 3 3B Instruct 2512 Ultra-efficient 3B multimodal instruct model built for edge deployment Last Updated:
-
Ministral 3 3B Reasoning 2512 Compact 3B-param multimodal model for efficient on-device reasoning Last Updated:
-
Ministral 3 8B Base 2512 Versatile 8B-base multimodal LLM, flexible foundation for custom AI Last Updated:
-
Ministral 3 8B Instruct 2512 Compact 8B multimodal instruct model optimized for edge deployment Last Updated:
-
Ministral 3 8B Reasoning 2512 Efficient 8B multimodal model tuned for advanced reasoning tasks. Last Updated:
-
Mistral Large 3 675B Base 2512 Frontier-scale 675B multimodal base model for custom AI training Last Updated:
-
Mistral Large 3 675B Instruct 2512 Frontier-scale 675B multimodal instruct MoE model for enterprise AIMis Last Updated:
-
Mistral Large 3 675B Instruct 2512 Eagle Speculative-decoding accelerator for the 675B Mistral Large 3 Last Updated:
-
Mistral Large 3 675B Instruct 2512 NVFP4 Quantized 675B multimodal instruct model optimized for NVFP4 Last Updated:
-
MobileNetV2 SSD-based object detection model trained on Open Images V4 Last Updated:
-
MoveNet A CNN model that predicts human joints from RGB images of a person Last Updated:
-
Muse Glimmer Local multimodal 30B model for autonomous agents, coding, and tools Last Updated:
-
Nemotron 3.5 Lightning Efficient 30B MoE model for long-running agents and local inference Last Updated:
-
Nex-N2-Pro Large agentic model for coding, tools, research, and execution Last Updated:
-
Nex-N2-mini Compact agentic model for coding, tools, and productivity tasks Last Updated:
-
NoobAI XL 1.1 Open, non-commercial SDXL model for quality image generation Last Updated:
-
NuMarkdown-8B-Thinking Reasoning-powered OCR VLM for converting complex documents to Markdown Last Updated:
-
OpenVLA 7B Vision-language-action model for robot control via images and text Last Updated:
-
Ornith-1.0 Open reasoning model for agentic coding and tool workflows Last Updated:
-
QwQ-32B QwQ-32B is a reasoning-focused language model for complex tasks Last Updated:
-
Qwable-v1 Agentic coding model combining Opus reasoning and Fable tools Last Updated:
-
Qwen-Image-Edit An advanced bilingual image editing with semantic control Last Updated:
-
Qwen2-7B-Instruct Instruction-tuned 7B language model for chat and complex tasks Last Updated:
-
Qwen2.5-14B-Instruct Powerful 14B LLM with strong instruction and long-text handling Last Updated:
-
Qwen2.5-VL-3B-Instruct Qwen2.5-VL-3B-Instruct: Multimodal model for chat, vision & video Last Updated:
-
Qwen2.5-VL-7B-Instruct Multimodal 7B model for image, video, and text understanding tasks Last Updated:
-
Qwen3-Next Qwen3-Next: 80B instruct LLM with ultra-long context up to 1M tokens Last Updated:
-
Qwen3.6-27B Dense multimodal Qwen model for coding, agents, and long context Last Updated:
-
Qwen3.6-35B-A3B Open multimodal model for coding, agents, and long-context tasks Last Updated:
-
Qwen3.6-35B-A3B-FP8 FP8 Qwen model for efficient multimodal coding and agent tasks Last Updated:
-
Qwen3.8-2.4T-A95B Massive 2.4T MoE model for coding, agents, research, and reasoning Last Updated:
-
Qwen3.8-27B Dense 27B multimodal model for coding, agents, and visual reasoning Last Updated:
-
Qwen3.8-Flash-Next Efficient multimodal MoE model for coding, reasoning, and AI agents Last Updated:
-
Rampart Lightweight on-device model for private AI text redaction Last Updated:
-
Smaug Flash 304B MoE model optimized for agentic coding and long-running workflows Last Updated:
-
Solar Open 2 Efficient 250B MoE model for agents, coding, and long-context work Last Updated:
-
SuperGemma4 Fast uncensored Gemma model optimized for local chat and coding Last Updated:
-
Universal Sentence Encoder Encoder of greater-than-word length text trained on a variety of data Last Updated:
-
Unlimited-OCR Layout-aware OCR model for multilingual document understanding Last Updated:
-
VaultGemma VaultGemma: 1B DP-trained Gemma variant for private NLP tasks Last Updated:
-
XTTS-v2 Multilingual voice cloning model with 6-second voice samples Last Updated:
-
ZAYA1-8B Efficient MoE reasoning model for coding and math workloads Last Updated:
-
bart-large-cnn Summarization model fine-tuned on CNN/DailyMail articles Last Updated:
-
bge-base-en-v1.5 Efficient English embedding model for semantic search and retrieval Last Updated:
-
bge-large-en-v1.5 BGE-Large v1.5: High-accuracy English embedding model for retrieval Last Updated:
-
bge-small-en-v1.5 Compact English sentence embedding model for semantic search tasks Last Updated:
-
fashion-clip CLIP model fine-tuned for zero-shot fashion product classification Last Updated:
-
gpt-oss-120b OpenAI’s open-weight 120B model optimized for reasoning and tooling Last Updated:
-
gpt-oss-20b OpenAI’s compact 20B open model for fast, agentic, and local use Last Updated:
-
granite-timeseries-ttm-r2 Tiny pre-trained IBM model for multivariate time series forecasting Last Updated:
-
layoutlm-base-uncased Multimodal Transformer for document image understanding and layout Last Updated:
-
mms-300m-1130-forced-aligner CTC-based forced aligner for audio-text in 158 languages Last Updated:
-
roberta-base Robust BERT-based model for English with improved MLM training Last Updated:
-
t5-base Flexible text-to-text transformer model for multilingual NLP tasks Last Updated:
-
t5-small T5-Small: Lightweight text-to-text transformer for NLP tasks Last Updated:
-
translategemma-4b-it Lightweight multimodal translation model for 55 languages Last Updated:
-
ttf-mscorefonts-installer Installer for Microsoft TrueType core fonts Last Updated:
-
unidepth-v2-vitl14 Metric monocular depth estimation (vision model) Last Updated:
-
wav2vec2-large-xlsr-53-portuguese Portuguese ASR model fine-tuned on XLSR-53 for 16kHz audio input Last Updated:
-
wav2vec2-large-xlsr-53-russian Russian ASR model fine-tuned on Common Voice and CSS10 datasets Last Updated:
