Instructions to use MBZUAI/GLaMM-RefSeg with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use MBZUAI/GLaMM-RefSeg with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="MBZUAI/GLaMM-RefSeg")# Load model directly from transformers import AutoProcessor, AutoModelForCausalLM processor = AutoProcessor.from_pretrained("MBZUAI/GLaMM-RefSeg") model = AutoModelForCausalLM.from_pretrained("MBZUAI/GLaMM-RefSeg") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use MBZUAI/GLaMM-RefSeg with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "MBZUAI/GLaMM-RefSeg" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "MBZUAI/GLaMM-RefSeg", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/MBZUAI/GLaMM-RefSeg
- SGLang
How to use MBZUAI/GLaMM-RefSeg with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "MBZUAI/GLaMM-RefSeg" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "MBZUAI/GLaMM-RefSeg", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "MBZUAI/GLaMM-RefSeg" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "MBZUAI/GLaMM-RefSeg", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use MBZUAI/GLaMM-RefSeg with Docker Model Runner:
docker model run hf.co/MBZUAI/GLaMM-RefSeg
Don't manage to load the model using transformers
Hi,
Thank you for the great work and addition to HuggingFace !
I am encountering issues while trying to load the model using transformers.
First, as I got errors while trying to import the processor with
processor = AutoProcessor.from_pretrained("MBZUAI/GLaMM-RefSeg")
I found that changing "AutoProcessor" into "AutoTokenizer" fixed the processor loading.
However, each time I tried loading the model (with and without cache_dir argument pointing towards the path where I loaded the model with git clone), with
model = AutoModelForCausalLM.from_pretrained("MBZUAI/GLaMM-RefSeg")
I get the following error
ValueError: Unrecognized configuration class <class 'transformers.models.llava.configuration_llava.LlavaConfig'> for this kind of AutoModel: AutoModelForCausalLM.
Model type should be one of BartConfig, BertConfig, BertGenerationConfig, BigBirdConfig, BigBirdPegasusConfig, BioGptConfig, BlenderbotConfig, BlenderbotSmallConfig, BloomConfig, CamembertConfig, LlamaConfig, CodeGenConfig, CohereConfig, CpmAntConfig, CTRLConfig, Data2VecTextConfig, DbrxConfig, ElectraConfig, ErnieConfig, FalconConfig, FuyuConfig, GemmaConfig, Gemma2Config, GitConfig, GPT2Config, GPT2Config, GPTBigCodeConfig, GPTNeoConfig, GPTNeoXConfig, GPTNeoXJapaneseConfig, GPTJConfig, JambaConfig, JetMoeConfig, LlamaConfig, MambaConfig, MarianConfig, MBartConfig, MegaConfig, MegatronBertConfig, MistralConfig, MixtralConfig, MptConfig, MusicgenConfig, MusicgenMelodyConfig, MvpConfig, OlmoConfig, OpenLlamaConfig, OpenAIGPTConfig, OPTConfig, PegasusConfig, PersimmonConfig, PhiConfig, Phi3Config, PLBartConfig, ProphetNetConfig, QDQBertConfig, Qwen2Config, Qwen2MoeConfig, RecurrentGemmaConfig, ReformerConfig, RemBertConfig, RobertaConfig, RobertaPreLayerNormConfig, RoCBertConfig, RoFormerConfig, RwkvConfig, Speech2Text2Config, StableLmConfig, Starcoder2Config, TransfoXLConfig, TrOCRConfig, WhisperConfig, XGLMConfig, XLMConfig, XLMProphetNetConfig, XLMRobertaConfig, XLMRobertaXLConfig, XLNetConfig, XmodConfig.
Do you know how to fix the model loading ? Do I do something wrong ?
Thank you in advance