Instructions to use openbmb/cpm-bee-1b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use openbmb/cpm-bee-1b with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="openbmb/cpm-bee-1b", trust_remote_code=True)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("openbmb/cpm-bee-1b", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use openbmb/cpm-bee-1b with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "openbmb/cpm-bee-1b" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "openbmb/cpm-bee-1b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/openbmb/cpm-bee-1b
- SGLang
How to use openbmb/cpm-bee-1b 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 "openbmb/cpm-bee-1b" \ --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": "openbmb/cpm-bee-1b", "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 "openbmb/cpm-bee-1b" \ --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": "openbmb/cpm-bee-1b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use openbmb/cpm-bee-1b with Docker Model Runner:
docker model run hf.co/openbmb/cpm-bee-1b
Update modeling_cpmbee.py
Browse files- modeling_cpmbee.py +6 -6
modeling_cpmbee.py
CHANGED
|
@@ -21,9 +21,9 @@ from typing import Any, Callable, Dict, List, Optional, Tuple, Union
|
|
| 21 |
import torch
|
| 22 |
import torch.nn as nn
|
| 23 |
|
| 24 |
-
from .
|
| 25 |
-
from .
|
| 26 |
-
from .
|
| 27 |
GenerationConfig,
|
| 28 |
LogitsProcessorList,
|
| 29 |
StoppingCriteriaList,
|
|
@@ -32,9 +32,9 @@ from ...generation.utils import (
|
|
| 32 |
is_deepspeed_zero3_enabled,
|
| 33 |
warnings,
|
| 34 |
)
|
| 35 |
-
from .
|
| 36 |
-
from .
|
| 37 |
-
from .
|
| 38 |
from .configuration_cpmbee import CpmBeeConfig
|
| 39 |
from .tokenization_cpmbee import CpmBeeTokenizer
|
| 40 |
|
|
|
|
| 21 |
import torch
|
| 22 |
import torch.nn as nn
|
| 23 |
|
| 24 |
+
from transformers.generation.beam_search import BeamHypotheses, BeamSearchScorer
|
| 25 |
+
from transformers.generation.streamers import BaseStreamer
|
| 26 |
+
from transformers.generation.utils import (
|
| 27 |
GenerationConfig,
|
| 28 |
LogitsProcessorList,
|
| 29 |
StoppingCriteriaList,
|
|
|
|
| 32 |
is_deepspeed_zero3_enabled,
|
| 33 |
warnings,
|
| 34 |
)
|
| 35 |
+
from transformers.modeling_outputs import BaseModelOutputWithPast, CausalLMOutputWithPast, ModelOutput
|
| 36 |
+
from transformers.modeling_utils import PreTrainedModel
|
| 37 |
+
from transformers.utils import add_code_sample_docstrings, add_start_docstrings, add_start_docstrings_to_model_forward, logging
|
| 38 |
from .configuration_cpmbee import CpmBeeConfig
|
| 39 |
from .tokenization_cpmbee import CpmBeeTokenizer
|
| 40 |
|