Instructions to use SkunkworksAI/BakLLaVA-1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use SkunkworksAI/BakLLaVA-1 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="SkunkworksAI/BakLLaVA-1")# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("SkunkworksAI/BakLLaVA-1", dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use SkunkworksAI/BakLLaVA-1 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "SkunkworksAI/BakLLaVA-1" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "SkunkworksAI/BakLLaVA-1", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/SkunkworksAI/BakLLaVA-1
- SGLang
How to use SkunkworksAI/BakLLaVA-1 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 "SkunkworksAI/BakLLaVA-1" \ --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": "SkunkworksAI/BakLLaVA-1", "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 "SkunkworksAI/BakLLaVA-1" \ --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": "SkunkworksAI/BakLLaVA-1", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use SkunkworksAI/BakLLaVA-1 with Docker Model Runner:
docker model run hf.co/SkunkworksAI/BakLLaVA-1
Update README.md
#5
by abhijeet2002 - opened
README.md
CHANGED
|
@@ -4,6 +4,12 @@ datasets:
|
|
| 4 |
language:
|
| 5 |
- en
|
| 6 |
license: apache-2.0
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7 |
---
|
| 8 |
|
| 9 |
<p><h1> BakLLaVA-1 </h1></p>
|
|
@@ -35,7 +41,4 @@ BakLLaVA 2 is cooking with a significantly larger (commercially viable) dataset
|
|
| 35 |
- 158K GPT-generated multimodal instruction-following data.
|
| 36 |
- 450K academic-task-oriented VQA data mixture.
|
| 37 |
- 40K ShareGPT data.
|
| 38 |
-
- Additional private data (permissive)
|
| 39 |
-
|
| 40 |
-
|
| 41 |
-
|
|
|
|
| 4 |
language:
|
| 5 |
- en
|
| 6 |
license: apache-2.0
|
| 7 |
+
metrics:
|
| 8 |
+
- character
|
| 9 |
+
library_name: allennlp
|
| 10 |
+
pipeline_tag: table-question-answering
|
| 11 |
+
tags:
|
| 12 |
+
- finance
|
| 13 |
---
|
| 14 |
|
| 15 |
<p><h1> BakLLaVA-1 </h1></p>
|
|
|
|
| 41 |
- 158K GPT-generated multimodal instruction-following data.
|
| 42 |
- 450K academic-task-oriented VQA data mixture.
|
| 43 |
- 40K ShareGPT data.
|
| 44 |
+
- Additional private data (permissive)
|
|
|
|
|
|
|
|
|