Text Generation
Transformers
Safetensors
PyTorch
English
muddpythia
causal-lm
muddformer
custom_code
Instructions to use Caiyun-AI/MUDDPythia-2.8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Caiyun-AI/MUDDPythia-2.8B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Caiyun-AI/MUDDPythia-2.8B", trust_remote_code=True)# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("Caiyun-AI/MUDDPythia-2.8B", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use Caiyun-AI/MUDDPythia-2.8B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Caiyun-AI/MUDDPythia-2.8B" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Caiyun-AI/MUDDPythia-2.8B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Caiyun-AI/MUDDPythia-2.8B
- SGLang
How to use Caiyun-AI/MUDDPythia-2.8B 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 "Caiyun-AI/MUDDPythia-2.8B" \ --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": "Caiyun-AI/MUDDPythia-2.8B", "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 "Caiyun-AI/MUDDPythia-2.8B" \ --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": "Caiyun-AI/MUDDPythia-2.8B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use Caiyun-AI/MUDDPythia-2.8B with Docker Model Runner:
docker model run hf.co/Caiyun-AI/MUDDPythia-2.8B
Commit ·
37c6a98
1
Parent(s): 5852a79
fix import err
Browse files- modeling_muddpythia.py +6 -5
modeling_muddpythia.py
CHANGED
|
@@ -9,10 +9,11 @@ from torch import Tensor
|
|
| 9 |
from torch.nn import functional as F
|
| 10 |
from torch.utils.checkpoint import checkpoint
|
| 11 |
|
| 12 |
-
|
| 13 |
-
|
| 14 |
-
|
| 15 |
-
|
|
|
|
| 16 |
|
| 17 |
from transformers.modeling_utils import PreTrainedModel
|
| 18 |
|
|
@@ -451,4 +452,4 @@ def match_weight_muddpythia(model, w, strict=False, pythia=True):
|
|
| 451 |
v = v+1
|
| 452 |
state_dict[k] = torch.tensor(v)
|
| 453 |
model.load_state_dict(state_dict, strict=strict)
|
| 454 |
-
return model
|
|
|
|
| 9 |
from torch.nn import functional as F
|
| 10 |
from torch.utils.checkpoint import checkpoint
|
| 11 |
|
| 12 |
+
from .configuration_muddpythia import MUDDPythiaConfig
|
| 13 |
+
#try:
|
| 14 |
+
# from .configuration_muddpythia import MUDDPythiaConfig
|
| 15 |
+
#except:
|
| 16 |
+
# from configuration_muddpythia import MUDDPythiaConfig
|
| 17 |
|
| 18 |
from transformers.modeling_utils import PreTrainedModel
|
| 19 |
|
|
|
|
| 452 |
v = v+1
|
| 453 |
state_dict[k] = torch.tensor(v)
|
| 454 |
model.load_state_dict(state_dict, strict=strict)
|
| 455 |
+
return model
|