Instructions to use MBZUAI/GLaMM-FullScope with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use MBZUAI/GLaMM-FullScope with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="MBZUAI/GLaMM-FullScope")# Load model directly from transformers import AutoProcessor, AutoModelForCausalLM processor = AutoProcessor.from_pretrained("MBZUAI/GLaMM-FullScope") model = AutoModelForCausalLM.from_pretrained("MBZUAI/GLaMM-FullScope") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use MBZUAI/GLaMM-FullScope with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "MBZUAI/GLaMM-FullScope" # 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-FullScope", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/MBZUAI/GLaMM-FullScope
- SGLang
How to use MBZUAI/GLaMM-FullScope 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-FullScope" \ --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-FullScope", "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-FullScope" \ --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-FullScope", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use MBZUAI/GLaMM-FullScope with Docker Model Runner:
docker model run hf.co/MBZUAI/GLaMM-FullScope
Updates configs.
Browse files- config.json +1 -1
- tokenizer_config.json +1 -1
config.json
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "
|
| 3 |
"architectures": [
|
| 4 |
"GLaMMForCausalLM"
|
| 5 |
],
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "MBZUAI/GLaMM-GranD-Pretrained",
|
| 3 |
"architectures": [
|
| 4 |
"GLaMMForCausalLM"
|
| 5 |
],
|
tokenizer_config.json
CHANGED
|
@@ -20,7 +20,7 @@
|
|
| 20 |
"model_max_length": 1536,
|
| 21 |
"pad_token": null,
|
| 22 |
"padding_side": "right",
|
| 23 |
-
"special_tokens_map_file": "
|
| 24 |
"tokenizer_class": "LlamaTokenizer",
|
| 25 |
"unk_token": {
|
| 26 |
"__type": "AddedToken",
|
|
|
|
| 20 |
"model_max_length": 1536,
|
| 21 |
"pad_token": null,
|
| 22 |
"padding_side": "right",
|
| 23 |
+
"special_tokens_map_file": "special_tokens_map.json",
|
| 24 |
"tokenizer_class": "LlamaTokenizer",
|
| 25 |
"unk_token": {
|
| 26 |
"__type": "AddedToken",
|