Instructions to use AlexHung29629/add_vision with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AlexHung29629/add_vision with Transformers:

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

pipe = pipeline("image-text-to-text", model="AlexHung29629/add_vision")
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("AlexHung29629/add_vision")
model = AutoModelForImageTextToText.from_pretrained("AlexHung29629/add_vision")
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 AlexHung29629/add_vision with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "AlexHung29629/add_vision"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "AlexHung29629/add_vision",
		"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/AlexHung29629/add_vision

SGLang

How to use AlexHung29629/add_vision 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 "AlexHung29629/add_vision" \
    --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": "AlexHung29629/add_vision",
		"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 "AlexHung29629/add_vision" \
        --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": "AlexHung29629/add_vision",
		"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 AlexHung29629/add_vision with Docker Model Runner:
```
docker model run hf.co/AlexHung29629/add_vision
```

You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

See axolotl config

axolotl version: 0.10.0.dev0

base_model: /mnt/shared/tp1-an1/alex/Magistral/merged
chat_template: mistral_v7_tekken

plugins:
  - axolotl.integrations.liger.LigerPlugin
liger_rope: true
liger_rms_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: true

processor_type: AutoProcessor
image_size: 512
image_resize_algorithm: bilinear

skip_prepare_dataset: true
remove_unused_columns: false  # leave columns in place as they are needed to handle image embeddings during training
sample_packing: false  # not yet supported with multimodal


unfrozen_parameters:
  - .*multi_modal_projector.*
  - .*lm_head.*

datasets:
  - path: /mnt/shared/tp1-an1/alex/FFM_training/vision_dialogue_dataset-0527.jsonl
    type: chat_template
    field_messages: messages
    roles_to_train: ['assistant']
    train_on_eos: turn
      
dataset_prepared_path: ./vision_dataprep/
val_set_size: 0
output_dir: ./placeholder_add_vision/
shuffle_merged_datasets: true

sequence_len: 4096
eval_sample_packing: false
pad_to_sequence_len: true

wandb_project: TP1_2025_05
wandb_entity:
wandb_watch:
wandb_name: Mistral-24B-SFT-250611
use_tensorboard: true

gradient_accumulation_steps: 1
micro_batch_size: 4
num_epochs: 2
optimizer: adamw_torch_fused
lr_scheduler: cosine
learning_rate: 1e-5
max_grad_norm: 1.0

adam_beta1: 0.9
adam_beta2: 0.95
adam_epsilon: 1e-8

bf16: true
tf32: false

logging_steps: 1
flash_attention: true
xformers_attention: false
sdp_attention: false

warmup_ratio: 0.05
saves_per_epoch: 1
weight_decay: 0

fsdp:
  - full_shard
  - auto_wrap
fsdp_config:
  fsdp_limit_all_gathers: true
  fsdp_sync_module_states: true
  fsdp_offload_params: false
  fsdp_use_orig_params: true
  fsdp_cpu_ram_efficient_loading: true
  fsdp_activation_checkpointing: true
  fsdp_transformer_layer_cls_to_wrap: MistralDecoderLayer,PixtralAttentionLayer
  fsdp_state_dict_type: FULL_STATE_DICT
  fsdp_auto_wrap_policy: TRANSFORMER_BASED_WRAP

seed: 42
auto_resume_from_checkpoints: true

placeholder_add_vision/

This model was trained from scratch on the /mnt/shared/tp1-an1/alex/FFM_training/vision_dialogue_dataset-0527.jsonl dataset.

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 1e-05
train_batch_size: 4
eval_batch_size: 4
seed: 42
distributed_type: multi-GPU
num_devices: 16
total_train_batch_size: 64
total_eval_batch_size: 64
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.95) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 802
training_steps: 16051

Training results

Framework versions

Transformers 4.52.3
Pytorch 2.6.0+cu126
Datasets 3.6.0
Tokenizers 0.21.1

Downloads last month: 2

Safetensors

Model size

24B params

Tensor type

F32

BF16