Instructions to use Itamarl/mpt-7b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Itamarl/mpt-7b with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Itamarl/mpt-7b", trust_remote_code=True)# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("Itamarl/mpt-7b", trust_remote_code=True) model = AutoModelForCausalLM.from_pretrained("Itamarl/mpt-7b", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use Itamarl/mpt-7b with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Itamarl/mpt-7b" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Itamarl/mpt-7b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Itamarl/mpt-7b
- SGLang
How to use Itamarl/mpt-7b 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 "Itamarl/mpt-7b" \ --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": "Itamarl/mpt-7b", "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 "Itamarl/mpt-7b" \ --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": "Itamarl/mpt-7b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use Itamarl/mpt-7b with Docker Model Runner:
docker model run hf.co/Itamarl/mpt-7b
Update handler.py
Browse files- handler.py +10 -10
handler.py
CHANGED
|
@@ -22,16 +22,16 @@ class EndpointHandler():
|
|
| 22 |
print("tokenizer created ", datetime.now())
|
| 23 |
|
| 24 |
|
| 25 |
-
|
| 26 |
-
|
| 27 |
-
|
| 28 |
-
|
| 29 |
-
|
| 30 |
-
|
| 31 |
-
|
| 32 |
-
|
| 33 |
-
|
| 34 |
-
|
| 35 |
|
| 36 |
self.generate_text = transformers.pipeline(
|
| 37 |
model=self.model,
|
|
|
|
| 22 |
print("tokenizer created ", datetime.now())
|
| 23 |
|
| 24 |
|
| 25 |
+
stop_token_ids = self.tokenizer.convert_tokens_to_ids(["<|endoftext|>"])
|
| 26 |
+
|
| 27 |
+
class StopOnTokens(StoppingCriteria):
|
| 28 |
+
def __call__(self, input_ids: torch.LongTensor, scores: torch.FloatTensor, **kwargs):
|
| 29 |
+
for stop_id in stop_token_ids:
|
| 30 |
+
if input_ids[0][-1] == stop_id:
|
| 31 |
+
return True
|
| 32 |
+
return False
|
| 33 |
+
|
| 34 |
+
stopping_criteria = StoppingCriteriaList([StopOnTokens()])
|
| 35 |
|
| 36 |
self.generate_text = transformers.pipeline(
|
| 37 |
model=self.model,
|