Instructions to use microsoft/Phi-3-small-8k-instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use microsoft/Phi-3-small-8k-instruct with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="microsoft/Phi-3-small-8k-instruct", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("microsoft/Phi-3-small-8k-instruct", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use microsoft/Phi-3-small-8k-instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "microsoft/Phi-3-small-8k-instruct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "microsoft/Phi-3-small-8k-instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/microsoft/Phi-3-small-8k-instruct

SGLang

How to use microsoft/Phi-3-small-8k-instruct 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 "microsoft/Phi-3-small-8k-instruct" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "microsoft/Phi-3-small-8k-instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "microsoft/Phi-3-small-8k-instruct" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "microsoft/Phi-3-small-8k-instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use microsoft/Phi-3-small-8k-instruct with Docker Model Runner:
```
docker model run hf.co/microsoft/Phi-3-small-8k-instruct
```

Update tokenization_phi3_small.py

#29

by XirenZhou - opened Aug 29, 2024

base: refs/heads/main

←

from: refs/pr/29

Discussion Files changed

+26

-1

Files changed (1) hide show

tokenization_phi3_small.py +26 -1

tokenization_phi3_small.py CHANGED Viewed

@@ -5,6 +5,7 @@ from typing import Collection, List, Optional, Dict, Set, Tuple, Union
 from functools import cached_property
 import base64
 from transformers import PreTrainedTokenizer, AddedToken, AutoConfig
 from transformers.models.auto.tokenization_auto import get_tokenizer_config
@@ -102,7 +103,31 @@ class Phi3SmallTokenizer(PreTrainedTokenizer):
         super().__init__(**kwargs)
         self.errors = errors
-        base = tiktoken.get_encoding("cl100k_base")
         if vocab_file is None:
             self.mergeable_ranks: Dict[bytes, int] = base._mergeable_ranks
         else:

 from functools import cached_property
 import base64
+import requests
 from transformers import PreTrainedTokenizer, AddedToken, AutoConfig
 from transformers.models.auto.tokenization_auto import get_tokenizer_config
         super().__init__(**kwargs)
         self.errors = errors
+        try:
+            base = tiktoken.get_encoding("cl100k_base")
+        # This deals with the scenario where user has restricted internet access
+        # and thus fails to download the tokenizer file from https://openaipublic.blob.core.windows.net/encodings/cl100k_base.tiktoken
+        # It is assumed that user should be able to access files on huggingface hub.
+        except requests.RequestException:
+            import hashlib
+            from transformers.utils import cached_file
+            cached_tokenizer_path = cached_file(
+                    "microsoft/Phi-3-small-8k-instruct",
+                    "cl100k_base.tiktoken",
+                    _raise_exceptions_for_gated_repo=False,
+                    _raise_exceptions_for_missing_entries=False,
+                    _raise_exceptions_for_connection_errors=False
+                )
+            tiktoken_cache_dir = os.path.dirname(cached_tokenizer_path)
+            tiktoken_cache_path = os.path.join(
+                tiktoken_cache_dir,
+                hashlib.sha1("https://openaipublic.blob.core.windows.net/encodings/cl100k_base.tiktoken".encode()).hexdigest()
+            )
+            if not os.path.exists(tiktoken_cache_path):
+                os.rename(cached_tokenizer_path, tiktoken_cache_path)
+            os.environ["TIKTOKEN_CACHE_DIR"] = tiktoken_cache_dir
+            base = tiktoken.get_encoding("cl100k_base")
         if vocab_file is None:
             self.mergeable_ranks: Dict[bytes, int] = base._mergeable_ranks
         else: