Instructions to use samim2024/Image-Text-To-Text with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use samim2024/Image-Text-To-Text with Transformers:

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

pipe = pipeline("image-text-to-text", model="samim2024/Image-Text-To-Text")

# Load model directly
from transformers import AutoProcessor, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("samim2024/Image-Text-To-Text")
model = AutoModelForImageTextToText.from_pretrained("samim2024/Image-Text-To-Text")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use samim2024/Image-Text-To-Text with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "samim2024/Image-Text-To-Text"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "samim2024/Image-Text-To-Text",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/samim2024/Image-Text-To-Text

SGLang

How to use samim2024/Image-Text-To-Text 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 "samim2024/Image-Text-To-Text" \
    --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": "samim2024/Image-Text-To-Text",
		"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 "samim2024/Image-Text-To-Text" \
        --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": "samim2024/Image-Text-To-Text",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use samim2024/Image-Text-To-Text with Docker Model Runner:
```
docker model run hf.co/samim2024/Image-Text-To-Text
```

samim2024 commited on Jun 7, 2024

Commit

639931d

verified ·

1 Parent(s): 1f83e3c

Upload config

Browse files

Files changed (1) hide show

config.json +64 -0

config.json ADDED Viewed

	@@ -0,0 +1,64 @@

+{
+  "_name_or_path": "HuggingFaceM4/idefics-9b",
+  "additional_vocab_size": 2,
+  "alpha_initializer": "zeros",
+  "alpha_type": "float",
+  "alphas_initializer_range": 0.0,
+  "architectures": [
+    "IdeficsForVisionText2Text"
+  ],
+  "bos_token_id": 1,
+  "cross_layer_activation_function": "swiglu",
+  "cross_layer_interval": 4,
+  "dropout": 0.0,
+  "eos_token_id": 2,
+  "freeze_lm_head": false,
+  "freeze_text_layers": false,
+  "freeze_text_module_exceptions": [],
+  "freeze_vision_layers": false,
+  "freeze_vision_module_exceptions": [],
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 2048,
+  "max_sequence_length": 2048,
+  "model_type": "idefics",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "pad_token_id": 0,
+  "perceiver_config": {
+    "model_type": "idefics",
+    "qk_layer_norms_perceiver": true
+  },
+  "qk_layer_norms": true,
+  "quantization_config": {
+    "_load_in_4bit": true,
+    "_load_in_8bit": false,
+    "bnb_4bit_compute_dtype": "float16",
+    "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": [
+      "lm_head",
+      "embed_tokens"
+    ],
+    "llm_int8_threshold": 6.0,
+    "load_in_4bit": true,
+    "load_in_8bit": false,
+    "quant_method": "bitsandbytes"
+  },
+  "rms_norm_eps": 1e-06,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.42.0.dev0",
+  "use_cache": true,
+  "use_resampler": true,
+  "vision_config": {
+    "embed_dim": 1280,
+    "model_type": "idefics"
+  },
+  "vocab_size": 32000
+}