Instructions to use OwOOwO/dumbo1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use OwOOwO/dumbo1 with Transformers:

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

pipe = pipeline("text-generation", model="OwOOwO/dumbo1")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("OwOOwO/dumbo1")
model = AutoModelForCausalLM.from_pretrained("OwOOwO/dumbo1")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use OwOOwO/dumbo1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "OwOOwO/dumbo1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "OwOOwO/dumbo1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/OwOOwO/dumbo1

SGLang

How to use OwOOwO/dumbo1 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 "OwOOwO/dumbo1" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "OwOOwO/dumbo1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "OwOOwO/dumbo1" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "OwOOwO/dumbo1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use OwOOwO/dumbo1 with Docker Model Runner:
```
docker model run hf.co/OwOOwO/dumbo1
```

OwOOwO commited on Mar 30, 2024

Commit

e00a2ae

verified ·

1 Parent(s): 718524a

Upload tokenizer

Browse files

Files changed (2) hide show

tokenizer.json +6 -1
tokenizer_config.json +1 -3

tokenizer.json CHANGED Viewed

@@ -1,6 +1,11 @@
 {
   "version": "1.0",
-  "truncation": null,
   "padding": null,
   "added_tokens": [
     {

 {
   "version": "1.0",
+  "truncation": {
+    "direction": "Right",
+    "max_length": 2048,
+    "strategy": "LongestFirst",
+    "stride": 0
+  },
   "padding": null,
   "added_tokens": [
     {

tokenizer_config.json CHANGED Viewed

@@ -1,7 +1,6 @@
 {
   "add_bos_token": true,
   "add_eos_token": false,
-  "add_prefix_space": true,
   "added_tokens_decoder": {
     "0": {
       "content": "<unk>",
@@ -44,6 +43,5 @@
   "truncation_side": "right",
   "truncation_strategy": "longest_first",
   "unk_token": "<unk>",
-  "use_default_system_prompt": false,
-  "use_fast": true
 }

 {
   "add_bos_token": true,
   "add_eos_token": false,
   "added_tokens_decoder": {
     "0": {
       "content": "<unk>",
   "truncation_side": "right",
   "truncation_strategy": "longest_first",
   "unk_token": "<unk>",
+  "use_default_system_prompt": false
 }