Instructions to use Britania/m2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Britania/m2 with Transformers:

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

pipe = pipeline("text-generation", model="Britania/m2")
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("Britania/m2")
model = AutoModelForCausalLM.from_pretrained("Britania/m2", 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 Britania/m2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Britania/m2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Britania/m2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Britania/m2

SGLang

How to use Britania/m2 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 "Britania/m2" \
    --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": "Britania/m2",
		"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 "Britania/m2" \
        --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": "Britania/m2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Britania/m2 with Docker Model Runner:
```
docker model run hf.co/Britania/m2
```

Britania commited on May 2, 2024

Commit

ae146ef

verified ·

1 Parent(s): 17520ba

Update handler.py

Browse files

Files changed (1) hide show

handler.py +10 -2

handler.py CHANGED Viewed

@@ -4,12 +4,20 @@ import torch
 import json
 def model_inference(model, tokenizer, text, **kwargs):
     inputs = tokenizer(text, return_tensors="pt").to("cuda:0")
     with torch.inference_mode():
-        outputs = model.generate(**inputs, **kwargs)
     return tokenizer.decode(outputs[0][inputs_length:], skip_special_tokens=True)
 class EndpointHandler():
     def __init__(self, path=""):
         self.model = AutoModelForCausalLM.from_pretrained(

 import json
 def model_inference(model, tokenizer, text, **kwargs):
+    default_kwargs = {
+        "max_new_tokens": 1024,
+        "temperature": 0.5,
+        "top_p": 0.95,
+        "top_k": 150,
+        "repetition_penalty": 1.4
+    }
+    default_kwargs.update(kwargs)
     inputs = tokenizer(text, return_tensors="pt").to("cuda:0")
+    inputs_length = len(inputs["input_ids"][0])
     with torch.inference_mode():
+        outputs = model.generate(**inputs, **default_kwargs)
     return tokenizer.decode(outputs[0][inputs_length:], skip_special_tokens=True)
 class EndpointHandler():
     def __init__(self, path=""):
         self.model = AutoModelForCausalLM.from_pretrained(