Instructions to use nathanrchn/phi with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use nathanrchn/phi with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="nathanrchn/phi", trust_remote_code=True)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("nathanrchn/phi", trust_remote_code=True) model = AutoModelForCausalLM.from_pretrained("nathanrchn/phi", trust_remote_code=True) - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use nathanrchn/phi with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "nathanrchn/phi" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "nathanrchn/phi", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/nathanrchn/phi
- SGLang
How to use nathanrchn/phi 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 "nathanrchn/phi" \ --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": "nathanrchn/phi", "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 "nathanrchn/phi" \ --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": "nathanrchn/phi", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use nathanrchn/phi with Docker Model Runner:
docker model run hf.co/nathanrchn/phi
Commit ·
15f8807
1
Parent(s): 0f0156b
Update modeling_phi.py
Browse files- modeling_phi.py +6 -1
modeling_phi.py
CHANGED
|
@@ -756,8 +756,13 @@ class ParallelBlock(nn.Module):
|
|
| 756 |
self.resid_dropout = nn.Dropout(config.resid_pdrop)
|
| 757 |
self.block_idx = block_idx
|
| 758 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 759 |
self.mixer = MHA(config, layer_idx=block_idx)
|
| 760 |
-
self.mlp = MLP(config)
|
| 761 |
|
| 762 |
def forward(
|
| 763 |
self,
|
|
|
|
| 756 |
self.resid_dropout = nn.Dropout(config.resid_pdrop)
|
| 757 |
self.block_idx = block_idx
|
| 758 |
|
| 759 |
+
if block_idx % 2 == 0:
|
| 760 |
+
n_inner = 4 * config.n_embd
|
| 761 |
+
else:
|
| 762 |
+
n_inner = 1024
|
| 763 |
+
|
| 764 |
self.mixer = MHA(config, layer_idx=block_idx)
|
| 765 |
+
self.mlp = MLP(config, n_inner)
|
| 766 |
|
| 767 |
def forward(
|
| 768 |
self,
|