Instructions to use HuggingFaceM4/idefics-80b-instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use HuggingFaceM4/idefics-80b-instruct with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="HuggingFaceM4/idefics-80b-instruct")

# Load model directly
from transformers import AutoProcessor, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("HuggingFaceM4/idefics-80b-instruct")
model = AutoModelForImageTextToText.from_pretrained("HuggingFaceM4/idefics-80b-instruct")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use HuggingFaceM4/idefics-80b-instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "HuggingFaceM4/idefics-80b-instruct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "HuggingFaceM4/idefics-80b-instruct",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/HuggingFaceM4/idefics-80b-instruct

SGLang

How to use HuggingFaceM4/idefics-80b-instruct 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 "HuggingFaceM4/idefics-80b-instruct" \
    --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": "HuggingFaceM4/idefics-80b-instruct",
		"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 "HuggingFaceM4/idefics-80b-instruct" \
        --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": "HuggingFaceM4/idefics-80b-instruct",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use HuggingFaceM4/idefics-80b-instruct with Docker Model Runner:
```
docker model run hf.co/HuggingFaceM4/idefics-80b-instruct
```

VictorSanh commited on Jul 26, 2023

Commit

0979cbf

1 Parent(s): aca8e0b

Update config.json

Browse files

Files changed (1) hide show

config.json +6 -4

config.json CHANGED Viewed

@@ -5,7 +5,7 @@
   "alpha_type": "float",
   "alphas_initializer_range": 0.0,
   "architectures": [
-    "VLlamaForCausalLM"
   ],
   "bos_token_id": 1,
   "cross_layer_activation_function": "swiglu",
@@ -22,7 +22,7 @@
   "initializer_range": 0.02,
   "intermediate_size": 22016,
   "max_sequence_length": 2048,
-  "model_type": "vllama",
   "num_attention_heads": 64,
   "num_hidden_layers": 80,
   "pad_token_id": 0,
@@ -40,7 +40,9 @@
   "use_resampler": true,
   "vision_embed_dim": 1280,
   "vision_image_size": 224,
-  "vision_model_name": "laion/CLIP-ViT-H-14-laion2B-s32B-b79K",
-  "vision_model_params": "{\"id2label\":{}, \"label2id\":{}}",
   "vocab_size": 32000
 }

   "alpha_type": "float",
   "alphas_initializer_range": 0.0,
   "architectures": [
+    "IdeficsForCausalLM"
   ],
   "bos_token_id": 1,
   "cross_layer_activation_function": "swiglu",
   "initializer_range": 0.02,
   "intermediate_size": 22016,
   "max_sequence_length": 2048,
+  "model_type": "idefics",
   "num_attention_heads": 64,
   "num_hidden_layers": 80,
   "pad_token_id": 0,
   "use_resampler": true,
   "vision_embed_dim": 1280,
   "vision_image_size": 224,
+  "vision_intermediate_size": 5120,
+  "vision_patch_size": 14,
+  "vision_num_attention_heads": 16,
+  "vision_num_hidden_layers": 32,
   "vocab_size": 32000
 }