Instructions to use nroggendorff/test-it with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nroggendorff/test-it with Transformers:

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

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

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("nroggendorff/test-it")
model = AutoModelForCausalLM.from_pretrained("nroggendorff/test-it", device_map="auto")
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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use nroggendorff/test-it with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/nroggendorff/test-it

SGLang

How to use nroggendorff/test-it 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 "nroggendorff/test-it" \
    --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": "nroggendorff/test-it",
		"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 "nroggendorff/test-it" \
        --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": "nroggendorff/test-it",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use nroggendorff/test-it with Docker Model Runner:
```
docker model run hf.co/nroggendorff/test-it
```

nroggendorff commited on Sep 3, 2024

Commit

375fc6f

verified ·

1 Parent(s): 3373924

0.4825663803100586

Browse files

Files changed (2) hide show

tokenizer.json +0 -0
tokenizer_config.json +4 -4

tokenizer.json CHANGED Viewed

The diff for this file is too large to render. See raw diff

tokenizer_config.json CHANGED Viewed

@@ -40,7 +40,7 @@
       "single_word": false,
       "special": true
     },
-    "3200": {
       "content": "<|user|>",
       "lstrip": false,
       "normalized": false,
@@ -48,7 +48,7 @@
       "single_word": false,
       "special": true
     },
-    "3201": {
       "content": "<|bot|>",
       "lstrip": false,
       "normalized": false,
@@ -56,7 +56,7 @@
       "single_word": false,
       "special": true
     },
-    "3202": {
       "content": "<|end|>",
       "lstrip": false,
       "normalized": false,
@@ -75,7 +75,7 @@
   "clean_up_tokenization_spaces": true,
   "eos_token": "</s>",
   "mask_token": "<mask>",
-  "max_length": 128,
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": "<pad>",
   "stride": 0,

       "single_word": false,
       "special": true
     },
+    "2805": {
       "content": "<|user|>",
       "lstrip": false,
       "normalized": false,
       "single_word": false,
       "special": true
     },
+    "2806": {
       "content": "<|bot|>",
       "lstrip": false,
       "normalized": false,
       "single_word": false,
       "special": true
     },
+    "2807": {
       "content": "<|end|>",
       "lstrip": false,
       "normalized": false,
   "clean_up_tokenization_spaces": true,
   "eos_token": "</s>",
   "mask_token": "<mask>",
+  "max_length": 16,
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": "<pad>",
   "stride": 0,