LLM Spaces
Running on CPU Upgrade1.2kπ»Note Llama 2 70B (TGI) GitHub: https://github.com/facebookresearch/llama model: https://huggingface.co/meta-llama/Llama-2-70b-chat-hf
Running on Zero462π¦Llama 2 13b Chat
Note Llama 2 13B GitHub: https://github.com/facebookresearch/llama model: https://huggingface.co/meta-llama/Llama-2-13b-chat-hf
Running on Zero457πLlama 2 7B Chat
Note Llama 2 7B GitHub: https://github.com/facebookresearch/llama model: https://huggingface.co/meta-llama/Llama-2-7b-chat-hf
Running212π»Mistral Super Fast
Note Mistral-7B (inference API) arXiv: https://arxiv.org/abs/2310.06825 model: https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1
Running on Zero58π¨Mistral-7B
LLM, chatbot
Note Mistral-7B arXiv: https://arxiv.org/abs/2310.06825 model: https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1
Paused174πMistral-7B-OpenOrca
Note Mistral-7B-OpenOrca model: https://huggingface.co/Open-Orca/Mistral-7B-OpenOrca
Sleeping125β‘Qwen VL
Note Qwen-VL multimodal GitHub: https://github.com/QwenLM/Qwen-VL model: https://huggingface.co/Qwen/Qwen-VL-Chat
Runtime error79πQwen 14b Chat Demo
Note Qwen 14B GitHub: https://github.com/QwenLM/Qwen model: https://huggingface.co/Qwen/Qwen-14B-Chat
Running on T416β‘Qwen 7b Chat
Note Qwen 7B GitHub: https://github.com/QwenLM/Qwen model: https://huggingface.co/Qwen/Qwen-7B-Chat
Runtime error959π¬Falcon-180B Demo
Note Falcon-180B (TGI) model: https://huggingface.co/tiiuae/falcon-180B-chat
Running556π¬Falcon-Chat
Note Falcon 40B (TGI) model: https://huggingface.co/tiiuae/falcon-40b-instruct
Runtime error797βοΈπ¬StarChat Playground
Note StarChat (TGI) model: https://huggingface.co/HuggingFaceH4/starchat-beta
Running404πͺBigCode - Playground
Note StarCoder (base) (TGI) models: https://huggingface.co/bigcode/starcoder https://huggingface.co/bigcode/starcoderbase https://huggingface.co/bigcode/starcoderplus
Runtime error256π¦Code Llama 13B Chat
Note Code Llama 13B (chat) GitHub: https://github.com/facebookresearch/codellama model: https://huggingface.co/codellama/CodeLlama-13b-Instruct-hf
Running227π¦π»π¦Code Llama - Playground
Note Code Llama 13B (base) GitHub: https://github.com/facebookresearch/codellama model: https://huggingface.co/codellama/CodeLlama-13b-hf
Runtime error376π¨IDEFICS Playground
Note IDEFICS-80B (TGI) multimodal model: https://huggingface.co/HuggingFaceM4/idefics-80b-instruct
Running on T4325πChatGLM 6B
Note ChatGLM-6B GitHub: https://github.com/THUDM/ChatGLM-6B model: https://huggingface.co/THUDM/chatglm-6b
Runtime error96πchatglm2 6b int4
Note ChatGLM2-6B GitHub: https://github.com/THUDM/ChatGLM-6B models: https://huggingface.co/THUDM/chatglm2-6b https://huggingface.co/THUDM/chatglm2-6b-int4
Runtime error21πinternlm-20b-chat-w4-turbomind
Note InternLM GitHub: https://github.com/InternLM/InternLM model: https://huggingface.co/internlm/internlm-chat-20b
Running on A100883πͺZephyr Chat
Note Zephyr 7B alpha arXiv: https://arxiv.org/abs/2310.16944 GitHub: https://github.com/huggingface/alignment-handbook models: - https://huggingface.co/HuggingFaceH4/zephyr-7b-alpha - https://huggingface.co/HuggingFaceH4/zephyr-7b-beta
- Running on T4368π₯
LLaVA
- Runtime error24π
RedPajama Chat 3B
Running on A10G891πMiniGPT-4
Note MiniGPT-4 GitHub: https://github.com/Vision-CAIR/MiniGPT-4 Project page: https://minigpt-4.github.io/
Runtime error113πMiniGPT-v2
Note MiniGPT-v2 GitHub: https://github.com/Vision-CAIR/MiniGPT-4 Project page: https://minigpt-v2.github.io/
- Runtime error25π
Starcoder Memorization
Running155π’InternLM XComposer
Note InternLM-XComposer multimodal arXiv: https://arxiv.org/abs/2309.15112 GitHub: https://github.com/InternLM/InternLM-XComposer
Running on CPU Upgrade157πCogVLM
Note CogVLM-17B multimodal GitHub: https://github.com/THUDM/CogVLM
Running503πGuanaco Playground Tgi
Note Guanaco-33B (TGI) model: https://huggingface.co/timdettmers/guanaco-33b-merged
Runtime error309πFuyu Multimodal
Note Fuyu-8B multimodal model: https://huggingface.co/adept/fuyu-8b blog: https://www.adept.ai/blog/fuyu-8b
- Runtime error3π
CLEX Chat
Sleeping142π¬Chat with DeepSeek Coder 7B
Note Deepseek Coder 6.7B GitHub: https://github.com/deepseek-ai/deepseek-coder model: https://huggingface.co/deepseek-ai/deepseek-coder-6.7b-instruct
Running140π¬Chat with DeepSeek Coder 33B
Note Deepseek Coder 33B GitHub: https://github.com/deepseek-ai/deepseek-coder model: https://huggingface.co/deepseek-ai/deepseek-coder-33b-instruct
Sleeping174π¦MPLUG Owl
Note mPLUG-Owl multimodal arXiv: https://arxiv.org/abs/2304.14178 GitHub: https://github.com/X-PLUG/mPLUG-Owl
Runtime error32πMPLUG Owl2
Note mPLUG-Owl2 multimodal arXiv: https://arxiv.org/abs/2311.04257 GitHub: https://github.com/X-PLUG/mPLUG-Owl
- Sleeping139π€π¬
Llama2 With Gradio Chat
Runtime error18β‘SALMONN 7B Gradio
Note SALMONN multimodal arXiv: https://arxiv.org/abs/2310.13289 GitHub: https://github.com/bytedance/SALMONN
- Sleeping68π¬
MonadGPT
Runtime error27π§βπ«Open-ended Assistant for Visual Evaluation, Comparison, and Restoration!
Note Q-Instruct arXiv: https://arxiv.org/abs/2311.06783 GitHub: https://github.com/Q-Future/Q-Instruct Project page: https://q-future.github.io/Q-Instruct/
Runtime error4πChatAnything
Note ChatAnything arXiv: https://arxiv.org/abs/2311.06772 GitHub: https://github.com/zhoudaquan/ChatAnything
- Runtime error10π
BPO Demo
- Runtime error235π
Video LLaVA
- Paused3ππ³
TonicsOrca2
- Build error347π₯
Yi-34B-Chat
- Runtime error34π
Orca 2 13B
- Running205π
GPT Baker
- Runtime error1π¦
Bias Probes: What Do Llamas Really Think?
- Sleeping52π
OneLLM
- Runtime error3πΆ
Shisa 7B
- Runtime error118π©
Magicoder Playground
- Sleeping1π’
EAGLE
- Running on T453π’
Llava
- Running444π¦
Mixtral-46.7B
- Paused50π₯
DeciLM 7B Instruct
- Running189π¬
Gemini Playground
- Running121π―οΈΙΈ
Candle Phi Wasm Demo
- Running57π
Gemini PRO Vision Chat
- Running109π
LLMLingua
- Sleeping26π
Llm Contamination Detector
- Sleeping63βοΈ
VCoder
- Runtime error69π
Emu2
- Running6π€
Mistral Playground
Access to all Mistral AI models with your own key
- Runtime error9βοΈ
OneAlign (Visual Quality/Aesthetic Scorer)
- Sleeping16π’
TinyGPT V
- Sleeping40π’
LLaMA Pro 8B Instruct Chat
- Running79π
Tinyllama Chat
- Runtime error78π
Phixtral Chat
- Running67π
Qwen 72B Chat Demo
- Runtime error11π
DeciCoder-6B Demo
- Runtime error47π¦
Fava
- Runtime error14π
Vstar
- Running116β‘
Stable LM 2 Zephyr 1.6b
- Runtime error20π
InternLM2 Chat 20B TurboMind 4Bits
- Running41π¦
Orion-14B-App-Demo-EN
- Paused10πΆ
NeuralBeagle14 7B GGUF Chat
- Running on Zero401π
moondream1
- Running on Zero52π
Binoculars
- Runtime error71π
Internlm2 Math 7b
- Runtime error157π
MoE LLaVA
- Running on A10G115π
LLaVA 1.6
- Running381π
Qwen1.5 72B Chat
- Running476πΌπ¬
Vision Arena (Testing VLMs side-by-side)
- Sleeping28π
UForm-Gen2 Demo
- Running64π₯
Google Gemma Playground
- Runtime error91π₯
Google Gemma
- Running180π«π
Chunk Visualizer
Pick a text splitter => visualize chunks. Great for RAG.
- Running on Zero5π€οΈ
A Language Model's Guide Through Latent Space
- Runtime error39π
Mc Llava 3b
- Runtime error9π
MetaMath Mistral Pro
- Runtime error63π
OpenCodeInterpreter Demo
- Running on Zero346π
moondream2
a tiny vision language model
- Runtime error17π»
ChatMusician
- Sleeping108π’
Catch Me If You Can
- Sleepingπ
LUNA - Playground
- Running on A100134π
StarChat2 Demo
- Running on T416πΈ
FuseChat-7B
- Sleeping4π
Global Local QFormer Video LLM
- Running on Zero265π¬
Chat with DeepSeek VL 7B
- Sleeping16π₯
Gradio π€ TGI
Gradio and TGI packed in the same machine
- Running on T499π
Stable Code Instruct 3b
- Runtime error31π
Cobra
Cobra: Extending Mamba to MLLM for Efficient Inference
- Running628π§±
DBRX Instruct
- Running118π’
Qwen1.5 32B Chat
- Running on Zero122π
nanoLLaVA-1.5
- Runtime error92π’
CodeGemma
Top Code Generation ChatBOT.
- Running on Zero166π¨
IDEFICS2 Playground
- Running on Zero389π
Chat With Llama3 8b
Latest text-generation model by META - Meta Llama3 8b.
- Running282π
Qwen1.5 110B Chat Demo
- Runtime error65π
Mini Gemini
- Running96π₯Έ
CodeQwen1.5 7B Chat Demo
- Sleeping21ποΈπΏ
MiniGPT4 Video Zero
- Running on Zero79π₯
Llava Llama-3 8B
Meta Llama3 8b with Llava Multimodal capabilities
- Running289β‘
InternVL
- Runtime error11π
Plava 7b Demo
- Running on Zero82π
CuMo 7b Zero
- Running on T4291π€²
PaliGemma Demo
- Running71π€
Paligemma HF
- Running on Zero203π»
Microsoft Phi-3-Vision-128k
- Runtime error46π
Chat With Mistral 7b v0.3
Latest text-generation model by Mistral - 7B Instruct v0.3.
- Running on CPU Upgrade283π
C4AI Aya 23 - 35B
- Runtime error36π¨
Paligemma Tracking
- Running on Zero420π¬
MiniCPM-Llama3-V-2_5
- Sleeping11β‘
MQT LLaVA
- Running on Zero676π»
Omost
- Runtime error1π
TikZ Assistant
- Running on Zero34π
MotionLLM
- Running on Zero98π₯πΈπ¬
VideoLLaMA2
- Running on Zero80π»
Gemma 2 9B IT
Chatbot
- Runtime error3π¬
EAGLE 2
- Running on Zero2π
Bunny
- Running on Zero59π
MInference
- Running103π
SmolLM 360M Instruct WebGPU
A blazingly fast and powerful AI chatbot that runs locally.
- Running on Zero29π
Llava Interleave
- Running70π¬
Demo Groq Tool Use
- Running on Zero105π
Mistral-Nemo
Chat with Mistral-Nemo
- Running on Zero76π₯
Chameleon 30b
- Running on Zero18π
Chat With Meta Llama3.1 8b
Latest text-generation model by META - Meta Llama3.1 8b
- Running36π’
Gpt-4o-mini Battles
- Running on Zero75π»
Gemma 2 2B IT
Chatbot
- Running on Zero93π
Idefics3
- Running on Zero297π¬
MiniCPM-V-2_6
- Running128π
Qwen2 Audio Instruct Demo
- Running on Zero59π
Falcon Mamba Playground
- Running419π
Qwen2-VL-72B
- Running on Zero150π¬
LongWriter
LLM for long context
- Running on Zero27π
Phi 3.5 Vision
- Running on Zero12π»
XGen MM
- Running on Zero53π
Eagle X5 13B Chat
- Running on Zero51π₯
Qwen2-VL-2B
- Running on Zero16π¬
LongCite
LLM for long context
- Running on Zero185π₯
Qwen2-VL-7B
- Running244π
Qwen2.5
- Running51π¬
GRIN MoE
- Running on Zero4π»
Phantom