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", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

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

10e8cd9

verified ·

1 Parent(s): 64d2c32

Upload tokenizer

Browse files

Files changed (3) hide show

special_tokens_map.json +14 -0
tokenizer.json +2 -2
tokenizer_config.json +2 -2

special_tokens_map.json CHANGED Viewed

@@ -27,6 +27,20 @@
       "normalized": false,
       "rstrip": false,
       "single_word": false
     }
   ],
   "bos_token": {

       "normalized": false,
       "rstrip": false,
       "single_word": false
+    },
+    {
+      "content": "<|GENERATE_PHONEMES_FROM_TEXT|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|GENERATE_TEXT_FROM_PHONEMES|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
     }
   ],
   "bos_token": {

tokenizer.json CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4865d2efef007fa6f0eded9666e5bc7e0563b635e434f24b9c21f726bde62cce
-size 29649909

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

tokenizer_config.json CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15d50aa3754ea43f39250d63fddd0fe1362d132f21edba800f1f9283d850c5c6
-size 11832787

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