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

Libraries

How to use AdoCleanCode/llasa_ready_for_training with Transformers:

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

pipe = pipeline("text-generation", model="AdoCleanCode/llasa_ready_for_training")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("AdoCleanCode/llasa_ready_for_training")
model = AutoModelForCausalLM.from_pretrained("AdoCleanCode/llasa_ready_for_training")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use AdoCleanCode/llasa_ready_for_training with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/AdoCleanCode/llasa_ready_for_training

SGLang

How to use AdoCleanCode/llasa_ready_for_training 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 "AdoCleanCode/llasa_ready_for_training" \
    --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": "AdoCleanCode/llasa_ready_for_training",
		"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 "AdoCleanCode/llasa_ready_for_training" \
        --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": "AdoCleanCode/llasa_ready_for_training",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use AdoCleanCode/llasa_ready_for_training with Docker Model Runner:
```
docker model run hf.co/AdoCleanCode/llasa_ready_for_training
```

AdoCleanCode commited on Jan 11

Commit

1b200e7

verified ·

1 Parent(s): 4d6c5e7

Upload tokenizer

Browse files

Files changed (2) hide show

tokenizer.json +1 -1
tokenizer_config.json +1 -1

tokenizer.json CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de5b56054fb87b4170c39fac0220642388a202620eedd1b3b634bb46050cab5b
 size 29650325

 version https://git-lfs.github.com/spec/v1
+oid sha256:17f69f8ad5fe55e0bf77f3f1707a3a8543fc0a361c2eecb29f95883a45000e30
 size 29650325

tokenizer_config.json CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:059be8b6771ae4634600de03eb1914919cd6b2161959eb9b265fb436fd677e4d
 size 11833261

 version https://git-lfs.github.com/spec/v1
+oid sha256:dd4a8c732e4c3eba05496fac7b1edcd7254e4124f886799837d6e38bf1557843
 size 11833261