Text Generation
Transformers
Safetensors
English
Hebrew
mcgpt
art
code
agent
text-generation-inference
Merge
Mixture of Experts
custom_code
Instructions to use TopAI-1/MCGPT-1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use TopAI-1/MCGPT-1 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="TopAI-1/MCGPT-1", trust_remote_code=True)# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("TopAI-1/MCGPT-1", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use TopAI-1/MCGPT-1 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "TopAI-1/MCGPT-1" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "TopAI-1/MCGPT-1", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/TopAI-1/MCGPT-1
- SGLang
How to use TopAI-1/MCGPT-1 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 "TopAI-1/MCGPT-1" \ --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": "TopAI-1/MCGPT-1", "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 "TopAI-1/MCGPT-1" \ --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": "TopAI-1/MCGPT-1", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use TopAI-1/MCGPT-1 with Docker Model Runner:
docker model run hf.co/TopAI-1/MCGPT-1
Create configuration_mcgpt.py
Browse files- configuration_mcgpt.py +22 -0
configuration_mcgpt.py
ADDED
|
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
from transformers import PretrainedConfig
|
| 2 |
+
|
| 3 |
+
class MCGPTConfig(PretrainedConfig):
|
| 4 |
+
model_type = "mcgpt"
|
| 5 |
+
def __init__(
|
| 6 |
+
self,
|
| 7 |
+
vocab_size=33152,
|
| 8 |
+
hidden_size=256,
|
| 9 |
+
num_layers=4,
|
| 10 |
+
num_experts=4,
|
| 11 |
+
nhead=8,
|
| 12 |
+
max_position_embeddings=512,
|
| 13 |
+
**kwargs
|
| 14 |
+
):
|
| 15 |
+
super().__init__(**kwargs)
|
| 16 |
+
self.vocab_size = vocab_size
|
| 17 |
+
self.hidden_size = hidden_size
|
| 18 |
+
self.num_layers = num_layers
|
| 19 |
+
self.num_hidden_layers = num_layers
|
| 20 |
+
self.num_experts = num_experts
|
| 21 |
+
self.nhead = nhead
|
| 22 |
+
self.max_position_embeddings = max_position_embeddings
|