Instructions to use frontrx/ECGv3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use frontrx/ECGv3 with Transformers:

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

pipe = pipeline("image-text-to-text", model="frontrx/ECGv3")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("frontrx/ECGv3")
model = AutoModelForImageTextToText.from_pretrained("frontrx/ECGv3")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use frontrx/ECGv3 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "frontrx/ECGv3"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "frontrx/ECGv3",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/frontrx/ECGv3

SGLang

How to use frontrx/ECGv3 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 "frontrx/ECGv3" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "frontrx/ECGv3",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

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 "frontrx/ECGv3" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "frontrx/ECGv3",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use frontrx/ECGv3 with Docker Model Runner:
```
docker model run hf.co/frontrx/ECGv3
```

robertavrammd commited on Mar 15, 2025

Commit

e086576

verified ·

1 Parent(s): 4b22499

Upload Idefics3ForConditionalGeneration

Browse files

Files changed (2) hide show

config.json +3 -18
model.safetensors +2 -2

config.json CHANGED Viewed

@@ -7,21 +7,6 @@
   "image_token_id": 49153,
   "model_type": "idefics3",
   "pad_token_id": 128002,
-  "quantization_config": {
-    "_load_in_4bit": true,
-    "_load_in_8bit": false,
-    "bnb_4bit_compute_dtype": "bfloat16",
-    "bnb_4bit_quant_storage": "uint8",
-    "bnb_4bit_quant_type": "nf4",
-    "bnb_4bit_use_double_quant": true,
-    "llm_int8_enable_fp32_cpu_offload": false,
-    "llm_int8_has_fp16_weight": false,
-    "llm_int8_skip_modules": null,
-    "llm_int8_threshold": 6.0,
-    "load_in_4bit": true,
-    "load_in_8bit": false,
-    "quant_method": "bitsandbytes"
-  },
   "scale_factor": 3,
   "text_config": {
     "_flash_attn_2_enabled": true,
@@ -115,12 +100,12 @@
     "qk_layer_norms": false,
     "rms_norm_eps": 1e-05,
     "rope_theta": 273768.0,
-    "torch_dtype": "float16",
     "use_resampler": false,
     "vocab_size": 49155
   },
   "tie_word_embeddings": false,
-  "torch_dtype": "float16",
   "transformers_version": "4.49.0",
   "use_cache": true,
   "vision_config": {
@@ -136,7 +121,7 @@
       "longest_edge": 1920
     },
     "tie_word_embeddings": false,
-    "torch_dtype": "float16"
   },
   "vocab_size": 49155
 }

   "image_token_id": 49153,
   "model_type": "idefics3",
   "pad_token_id": 128002,
   "scale_factor": 3,
   "text_config": {
     "_flash_attn_2_enabled": true,
     "qk_layer_norms": false,
     "rms_norm_eps": 1e-05,
     "rope_theta": 273768.0,
+    "torch_dtype": "bfloat16",
     "use_resampler": false,
     "vocab_size": 49155
   },
   "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
   "transformers_version": "4.49.0",
   "use_cache": true,
   "vision_config": {
       "longest_edge": 1920
     },
     "tie_word_embeddings": false,
+    "torch_dtype": "bfloat16"
   },
   "vocab_size": 49155
 }

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90aa19025019b111684729d807d025a2e3d96b5d11fd19f4248e2472689ab0f2
-size 1461312635

 version https://git-lfs.github.com/spec/v1
+oid sha256:b280a0bb825330a6eba12e714a8b0a5f5d05b879d199bd132231cd7fdcecc613
+size 4492630912