Instructions to use FreedomIntelligence/ALLaVA-StableLM2-1_6B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use FreedomIntelligence/ALLaVA-StableLM2-1_6B with Transformers:

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

pipe = pipeline("text-generation", model="FreedomIntelligence/ALLaVA-StableLM2-1_6B", trust_remote_code=True)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("FreedomIntelligence/ALLaVA-StableLM2-1_6B", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use FreedomIntelligence/ALLaVA-StableLM2-1_6B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "FreedomIntelligence/ALLaVA-StableLM2-1_6B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "FreedomIntelligence/ALLaVA-StableLM2-1_6B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/FreedomIntelligence/ALLaVA-StableLM2-1_6B

SGLang

How to use FreedomIntelligence/ALLaVA-StableLM2-1_6B 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 "FreedomIntelligence/ALLaVA-StableLM2-1_6B" \
    --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": "FreedomIntelligence/ALLaVA-StableLM2-1_6B",
		"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 "FreedomIntelligence/ALLaVA-StableLM2-1_6B" \
        --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": "FreedomIntelligence/ALLaVA-StableLM2-1_6B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use FreedomIntelligence/ALLaVA-StableLM2-1_6B with Docker Model Runner:
```
docker model run hf.co/FreedomIntelligence/ALLaVA-StableLM2-1_6B
```

ALLaVA-StableLM2-1_6B / config.json

g-h-chen

upload config.json

57e3690 verified almost 2 years ago

raw

history blame contribute delete

1.36 kB

	{
	"_name_or_path": "FreedomIntelligence/ALLaVA-StableLM2-1_6B",
	"architectures": [
	"LlavaStableLM_1_6bForCausalLM"
	],
	"auto_map": {
	"AutoConfig": "configuration_stablelm_epoch.StableLMEpochConfig",
	"AutoModelForCausalLM": "modeling_llava_stablelm_1_6b.LlavaStableLM_1_6bForCausalLM"
	},
	"bos_token_id": 100257,
	"eos_token_id": 100257,
	"hidden_act": "silu",
	"hidden_size": 2048,
	"image_aspect_ratio": "pad",
	"initializer_range": 0.02,
	"intermediate_size": 5632,
	"max_position_embeddings": 4096,
	"mm_hidden_size": 1024,
	"mm_projector_lr": null,
	"mm_projector_type": "mlp2x_gelu",
	"mm_use_im_patch_token": false,
	"mm_use_im_start_end": false,
	"mm_vision_select_feature": "patch",
	"mm_vision_select_layer": -2,
	"mm_vision_tower": "openai/clip-vit-large-patch14-336",
	"model_type": "llava_stablelm_1_6b",
	"norm_eps": 1e-05,
	"num_attention_heads": 32,
	"num_heads": 32,
	"num_hidden_layers": 24,
	"num_key_value_heads": 32,
	"rope_pct": 0.25,
	"rope_theta": 10000,
	"rotary_scaling_factor": 1.0,
	"tie_word_embeddings": false,
	"tokenizer_model_max_length": 4096,
	"tokenizer_padding_side": "right",
	"torch_dtype": "bfloat16",
	"transformers_version": "4.37.0.dev0",
	"tune_mm_mlp_adapter": false,
	"use_cache": true,
	"use_mm_proj": true,
	"use_qkv_bias": true,
	"vocab_size": 100352
	}