Instructions to use liuhaotian/LLaVA-Lightning-MPT-7B-preview with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use liuhaotian/LLaVA-Lightning-MPT-7B-preview with Transformers:

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

pipe = pipeline("text-generation", model="liuhaotian/LLaVA-Lightning-MPT-7B-preview")

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("liuhaotian/LLaVA-Lightning-MPT-7B-preview", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use liuhaotian/LLaVA-Lightning-MPT-7B-preview with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "liuhaotian/LLaVA-Lightning-MPT-7B-preview"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "liuhaotian/LLaVA-Lightning-MPT-7B-preview",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/liuhaotian/LLaVA-Lightning-MPT-7B-preview

SGLang

How to use liuhaotian/LLaVA-Lightning-MPT-7B-preview 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 "liuhaotian/LLaVA-Lightning-MPT-7B-preview" \
    --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": "liuhaotian/LLaVA-Lightning-MPT-7B-preview",
		"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 "liuhaotian/LLaVA-Lightning-MPT-7B-preview" \
        --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": "liuhaotian/LLaVA-Lightning-MPT-7B-preview",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use liuhaotian/LLaVA-Lightning-MPT-7B-preview with Docker Model Runner:
```
docker model run hf.co/liuhaotian/LLaVA-Lightning-MPT-7B-preview
```

LLaVA-Lightning-MPT-7B-preview / config.json

liuhaotian

Update config.json

e3b2e6f almost 3 years ago

Raw

History Blame

1.5 kB

	{
	"_name_or_path": "llava-mpt-7b-pretrain_blip_558k_new_template_1e-instruct_conv_reason_nooverlap_80k-1epoch",
	"architectures": [
	"LlavaMPTForCausalLM"
	],
	"attn_config": {
	"alibi": true,
	"alibi_bias_max": 8,
	"attn_impl": "torch",
	"attn_pdrop": 0,
	"attn_type": "multihead_attention",
	"attn_uses_sequence_id": false,
	"clip_qkv": null,
	"prefix_lm": false,
	"qk_ln": false,
	"softmax_scale": null
	},
	"d_model": 4096,
	"emb_pdrop": 0,
	"embedding_fraction": 1.0,
	"expansion_ratio": 4,
	"freeze_mm_mlp_adapter": false,
	"init_config": {
	"emb_init_std": null,
	"emb_init_uniform_lim": null,
	"fan_mode": "fan_in",
	"init_div_is_residual": true,
	"init_gain": 0,
	"init_nonlinearity": "relu",
	"init_std": 0.02,
	"name": "kaiming_normal_",
	"verbose": 0
	},
	"init_device": "cpu",
	"learned_pos_emb": true,
	"logit_scale": null,
	"max_seq_len": 2048,
	"mm_hidden_size": 1024,
	"mm_use_im_start_end": true,
	"mm_vision_select_layer": -2,
	"mm_vision_tower": "openai/clip-vit-large-patch14",
	"model_type": "llava_mpt",
	"n_heads": 32,
	"n_layers": 32,
	"no_bias": true,
	"norm_type": "low_precision_layernorm",
	"resid_pdrop": 0,
	"sep_image_conv_front": false,
	"tokenizer_name": "sam-mosaic/gpt-neox-20b-chatml",
	"torch_dtype": "float16",
	"transformers_version": "4.28.0.dev0",
	"tune_mm_mlp_adapter": false,
	"use_cache": true,
	"use_mm_proj": true,
	"verbose": 0,
	"vocab_size": 50282
	}