Instructions to use tiny-random/apriel-1.5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tiny-random/apriel-1.5 with Transformers:

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

pipe = pipeline("image-text-to-text", model="tiny-random/apriel-1.5")
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, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("tiny-random/apriel-1.5")
model = AutoModelForMultimodalLM.from_pretrained("tiny-random/apriel-1.5", device_map="auto")
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 Settings

vLLM

How to use tiny-random/apriel-1.5 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "tiny-random/apriel-1.5"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tiny-random/apriel-1.5",
		"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/tiny-random/apriel-1.5

SGLang

How to use tiny-random/apriel-1.5 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 "tiny-random/apriel-1.5" \
    --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": "tiny-random/apriel-1.5",
		"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 "tiny-random/apriel-1.5" \
        --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": "tiny-random/apriel-1.5",
		"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 tiny-random/apriel-1.5 with Docker Model Runner:
```
docker model run hf.co/tiny-random/apriel-1.5
```

apriel-1.5 / README.md

yujiepan

Upload folder using huggingface_hub

7bb8070 verified 10 months ago

preview code

Raw

History Blame Contribute Delete

6.27 kB

	---
	library_name: transformers
	pipeline_tag: image-text-to-text
	inference: true
	widget:
	- text: Hello!
	example_title: Hello world
	group: Python
	base_model:
	- ServiceNow-AI/Apriel-1.5-15b-Thinker
	---

	This tiny model is intended for debugging. It is randomly initialized using the configuration adapted from [ServiceNow-AI/Apriel-1.5-15b-Thinker](https://huggingface.co/ServiceNow-AI/Apriel-1.5-15b-Thinker).

	### Example usage:

	```python
	import re
	import requests
	import torch
	from PIL import Image
	from transformers import AutoProcessor, AutoModelForImageTextToText

	# Load model
	model_id = "tiny-random/apriel-1.5"
	model = AutoModelForImageTextToText.from_pretrained(
	model_id,
	dtype=torch.bfloat16,
	device_map="auto"
	)
	processor = AutoProcessor.from_pretrained(model_id)
	url = "https://picsum.photos/id/237/200/300"
	image = Image.open(requests.get(url, stream=True).raw).convert("RGB")

	chat = [
	{
	"role": "user",
	"content": [
	{"type": "text", "text": "Which animal is this?"},
	{"type": "image"},
	],
	}
	]
	prompt = processor.apply_chat_template(chat, add_generation_prompt=True, tokenize=False)
	inputs = processor(text=prompt, images=[image], return_tensors="pt").to(model.device)
	inputs.pop("token_type_ids", None)
	inputs['pixel_values'] = inputs['pixel_values'].to(model.dtype)

	with torch.no_grad():
	output_ids = model.generate(**inputs, max_new_tokens=128, do_sample=True, temperature=0.6)

	generated_ids = output_ids[:, inputs['input_ids'].shape[1]:]
	output = processor.decode(generated_ids[0], skip_special_tokens=False)
	print("Image Response:", output)
	```

	### Codes to create this repo:

	```python
	import json
	from pathlib import Path

	import accelerate
	import torch
	from huggingface_hub import file_exists, hf_hub_download
	from transformers import (
	AutoConfig,
	AutoModelForCausalLM,
	AutoProcessor,
	GenerationConfig,
	AutoModelForImageTextToText,
	set_seed,
	)

	source_model_id = "ServiceNow-AI/Apriel-1.5-15b-Thinker"
	save_folder = "/tmp/tiny-random/apriel-1.5"

	processor = AutoProcessor.from_pretrained(source_model_id, trust_remote_code=True)
	processor.save_pretrained(save_folder)

	with open(hf_hub_download(source_model_id, filename='config.json', repo_type='model'), 'r', encoding='utf-8') as f:
	config_json = json.load(f)

	config_json['text_config'].update({
	'head_dim': 32,
	'hidden_size': 8,
	'intermediate_size': 64,
	'num_hidden_layers': 2,
	'num_attention_heads': 8,
	'num_key_value_heads': 4,
	})
	config_json['vision_config'].update(
	{
	'head_dim': 32,
	'intermediate_size': 256,
	'hidden_size': 32 * 4,
	'num_attention_heads': 4,
	'num_hidden_layers': 2,
	}
	)
	with open(f"{save_folder}/config.json", "w", encoding='utf-8') as f:
	json.dump(config_json, f, indent=2)

	config = AutoConfig.from_pretrained(
	save_folder,
	trust_remote_code=True,
	)
	print(config)
	torch.set_default_dtype(torch.bfloat16)
	model = AutoModelForImageTextToText.from_config(config, trust_remote_code=True).to(torch.bfloat16)
	torch.set_default_dtype(torch.float32)
	if file_exists(filename="generation_config.json", repo_id=source_model_id, repo_type='model'):
	model.generation_config = GenerationConfig.from_pretrained(
	source_model_id, trust_remote_code=True,
	)
	model.generation_config.do_sample = True
	print(model.generation_config)
	model = model.cpu()
	with torch.no_grad():
	for name, p in sorted(model.named_parameters()):
	torch.nn.init.normal_(p, 0, 0.1)
	print(name, p.shape)
	model.save_pretrained(save_folder)
	```

	### Printing the model:

	```text
	LlavaForConditionalGeneration(
	(model): LlavaModel(
	(vision_tower): PixtralVisionModel(
	(patch_conv): Conv2d(3, 128, kernel_size=(16, 16), stride=(16, 16), bias=False)
	(ln_pre): PixtralRMSNorm((128,), eps=1e-05)
	(transformer): PixtralTransformer(
	(layers): ModuleList(
	(0-1): 2 x PixtralAttentionLayer(
	(attention_norm): PixtralRMSNorm((128,), eps=1e-05)
	(feed_forward): PixtralMLP(
	(gate_proj): Linear(in_features=128, out_features=256, bias=False)
	(up_proj): Linear(in_features=128, out_features=256, bias=False)
	(down_proj): Linear(in_features=256, out_features=128, bias=False)
	(act_fn): SiLU()
	)
	(attention): PixtralAttention(
	(k_proj): Linear(in_features=128, out_features=128, bias=False)
	(v_proj): Linear(in_features=128, out_features=128, bias=False)
	(q_proj): Linear(in_features=128, out_features=128, bias=False)
	(o_proj): Linear(in_features=128, out_features=128, bias=False)
	)
	(ffn_norm): PixtralRMSNorm((128,), eps=1e-05)
	)
	)
	)
	(patch_positional_embedding): PixtralRotaryEmbedding()
	)
	(multi_modal_projector): LlavaMultiModalProjector(
	(linear_1): Linear(in_features=128, out_features=8, bias=True)
	(act): GELUActivation()
	(linear_2): Linear(in_features=8, out_features=8, bias=True)
	)
	(language_model): MistralModel(
	(embed_tokens): Embedding(131072, 8)
	(layers): ModuleList(
	(0-1): 2 x MistralDecoderLayer(
	(self_attn): MistralAttention(
	(q_proj): Linear(in_features=8, out_features=256, bias=False)
	(k_proj): Linear(in_features=8, out_features=128, bias=False)
	(v_proj): Linear(in_features=8, out_features=128, bias=False)
	(o_proj): Linear(in_features=256, out_features=8, bias=False)
	)
	(mlp): MistralMLP(
	(gate_proj): Linear(in_features=8, out_features=64, bias=False)
	(up_proj): Linear(in_features=8, out_features=64, bias=False)
	(down_proj): Linear(in_features=64, out_features=8, bias=False)
	(act_fn): SiLU()
	)
	(input_layernorm): MistralRMSNorm((8,), eps=1e-05)
	(post_attention_layernorm): MistralRMSNorm((8,), eps=1e-05)
	)
	)
	(norm): MistralRMSNorm((8,), eps=1e-05)
	(rotary_emb): MistralRotaryEmbedding()
	)
	)
	(lm_head): Linear(in_features=8, out_features=131072, bias=False)
	)
	```