Instructions to use htlou/backup_0202_llamafactory_CompCap-GPT4-llava-mistral with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use htlou/backup_0202_llamafactory_CompCap-GPT4-llava-mistral with Transformers:

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

pipe = pipeline("image-text-to-text", model="htlou/backup_0202_llamafactory_CompCap-GPT4-llava-mistral")
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("htlou/backup_0202_llamafactory_CompCap-GPT4-llava-mistral")
model = AutoModelForMultimodalLM.from_pretrained("htlou/backup_0202_llamafactory_CompCap-GPT4-llava-mistral", 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 htlou/backup_0202_llamafactory_CompCap-GPT4-llava-mistral with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "htlou/backup_0202_llamafactory_CompCap-GPT4-llava-mistral"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "htlou/backup_0202_llamafactory_CompCap-GPT4-llava-mistral",
		"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/htlou/backup_0202_llamafactory_CompCap-GPT4-llava-mistral

SGLang

How to use htlou/backup_0202_llamafactory_CompCap-GPT4-llava-mistral 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 "htlou/backup_0202_llamafactory_CompCap-GPT4-llava-mistral" \
    --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": "htlou/backup_0202_llamafactory_CompCap-GPT4-llava-mistral",
		"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 "htlou/backup_0202_llamafactory_CompCap-GPT4-llava-mistral" \
        --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": "htlou/backup_0202_llamafactory_CompCap-GPT4-llava-mistral",
		"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 htlou/backup_0202_llamafactory_CompCap-GPT4-llava-mistral with Docker Model Runner:
```
docker model run hf.co/htlou/backup_0202_llamafactory_CompCap-GPT4-llava-mistral
```

CompCap-GPT4

This model is a fine-tuned version of llava-hf/llava-v1.6-mistral-7b-hf on the CompCap-GPT4 dataset. It achieves the following results on the evaluation set:

Loss: 0.7652

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-06
train_batch_size: 8
eval_batch_size: 8
seed: 42
distributed_type: multi-GPU
num_devices: 8
gradient_accumulation_steps: 4
total_train_batch_size: 256
total_eval_batch_size: 64
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 10
num_epochs: 3.0

Training results

Training Loss	Epoch	Step	Validation Loss
0.9184	0.1296	50	0.9209
0.8611	0.2592	100	0.8653
0.8257	0.3889	150	0.8396
0.8308	0.5185	200	0.8231
0.8168	0.6481	250	0.8109
0.8021	0.7777	300	0.8005
0.7741	0.9073	350	0.7929
0.7155	1.0369	400	0.7880
0.7322	1.1666	450	0.7837
0.7214	1.2962	500	0.7790
0.6936	1.4258	550	0.7753
0.7046	1.5554	600	0.7717
0.6967	1.6850	650	0.7690
0.7197	1.8146	700	0.7658
0.704	1.9443	750	0.7633
0.6546	2.0739	800	0.7677
0.651	2.2035	850	0.7673
0.6601	2.3331	900	0.7667
0.6669	2.4627	950	0.7662
0.6566	2.5924	1000	0.7657
0.6654	2.7220	1050	0.7655
0.6389	2.8516	1100	0.7653
0.6574	2.9812	1150	0.7653

Framework versions

Transformers 4.45.2
Pytorch 2.4.0+cu121
Datasets 2.21.0
Tokenizers 0.20.3

Downloads last month: 2

Safetensors

Model size

8B params

Tensor type

BF16

Model tree for htlou/backup_0202_llamafactory_CompCap-GPT4-llava-mistral

Base model

llava-hf/llava-v1.6-mistral-7b-hf

Finetuned

(189)

this model