Instructions to use AlgoAnalytics/Test_model with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use AlgoAnalytics/Test_model with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="AlgoAnalytics/Test_model", trust_remote_code=True)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("AlgoAnalytics/Test_model", trust_remote_code=True) model = AutoModelForCausalLM.from_pretrained("AlgoAnalytics/Test_model", trust_remote_code=True) - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use AlgoAnalytics/Test_model with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "AlgoAnalytics/Test_model" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "AlgoAnalytics/Test_model", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/AlgoAnalytics/Test_model
- SGLang
How to use AlgoAnalytics/Test_model 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 "AlgoAnalytics/Test_model" \ --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": "AlgoAnalytics/Test_model", "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 "AlgoAnalytics/Test_model" \ --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": "AlgoAnalytics/Test_model", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use AlgoAnalytics/Test_model with Docker Model Runner:
docker model run hf.co/AlgoAnalytics/Test_model
Create configuration_phi3.py
Browse files- configuration_phi3.py +20 -0
configuration_phi3.py
ADDED
|
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
from transformers.configuration_utils import PretrainedConfig
|
| 2 |
+
|
| 3 |
+
class Phi3Config(PretrainedConfig):
|
| 4 |
+
model_type = "phi3"
|
| 5 |
+
|
| 6 |
+
def __init__(self,
|
| 7 |
+
vocab_size=32064,
|
| 8 |
+
hidden_size=3072,
|
| 9 |
+
num_hidden_layers=32,
|
| 10 |
+
num_attention_heads=32,
|
| 11 |
+
intermediate_size=8192,
|
| 12 |
+
max_position_embeddings=4096,
|
| 13 |
+
**kwargs):
|
| 14 |
+
super().__init__(**kwargs)
|
| 15 |
+
self.vocab_size = vocab_size
|
| 16 |
+
self.hidden_size = hidden_size
|
| 17 |
+
self.num_hidden_layers = num_hidden_layers
|
| 18 |
+
self.num_attention_heads = num_attention_heads
|
| 19 |
+
self.intermediate_size = intermediate_size
|
| 20 |
+
self.max_position_embeddings = max_position_embeddings
|