Instructions to use theprint/phi-3-mini-4k-python with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use theprint/phi-3-mini-4k-python with Transformers:

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

pipe = pipeline("text-generation", model="theprint/phi-3-mini-4k-python")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("theprint/phi-3-mini-4k-python")
model = AutoModelForCausalLM.from_pretrained("theprint/phi-3-mini-4k-python")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

llama-cpp-python

How to use theprint/phi-3-mini-4k-python with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="theprint/phi-3-mini-4k-python",
	filename="phi-3-mini-4k-python-unsloth.F16.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use theprint/phi-3-mini-4k-python with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf theprint/phi-3-mini-4k-python:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf theprint/phi-3-mini-4k-python:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf theprint/phi-3-mini-4k-python:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf theprint/phi-3-mini-4k-python:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf theprint/phi-3-mini-4k-python:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf theprint/phi-3-mini-4k-python:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf theprint/phi-3-mini-4k-python:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf theprint/phi-3-mini-4k-python:Q4_K_M

Use Docker

docker model run hf.co/theprint/phi-3-mini-4k-python:Q4_K_M

LM Studio
Jan

vLLM

How to use theprint/phi-3-mini-4k-python with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "theprint/phi-3-mini-4k-python"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "theprint/phi-3-mini-4k-python",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/theprint/phi-3-mini-4k-python:Q4_K_M

SGLang

How to use theprint/phi-3-mini-4k-python 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 "theprint/phi-3-mini-4k-python" \
    --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": "theprint/phi-3-mini-4k-python",
		"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 "theprint/phi-3-mini-4k-python" \
        --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": "theprint/phi-3-mini-4k-python",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use theprint/phi-3-mini-4k-python with Ollama:
```
ollama run hf.co/theprint/phi-3-mini-4k-python:Q4_K_M
```

Unsloth Studio new

How to use theprint/phi-3-mini-4k-python with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for theprint/phi-3-mini-4k-python to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for theprint/phi-3-mini-4k-python to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for theprint/phi-3-mini-4k-python to start chatting

Docker Model Runner
How to use theprint/phi-3-mini-4k-python with Docker Model Runner:
```
docker model run hf.co/theprint/phi-3-mini-4k-python:Q4_K_M
```

Lemonade

How to use theprint/phi-3-mini-4k-python with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull theprint/phi-3-mini-4k-python:Q4_K_M

Run and chat with the model

lemonade run user.phi-3-mini-4k-python-Q4_K_M

List all available models

lemonade list

theprint commited on Jun 5, 2024

Commit

5872cd1

verified ·

1 Parent(s): b632a9d

Upload model trained with Unsloth

Browse files

Upload model trained with Unsloth 2x faster

Files changed (2) hide show

adapter_config.json +6 -6
adapter_model.safetensors +1 -1

adapter_config.json CHANGED Viewed

@@ -10,7 +10,7 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 16,
   "lora_dropout": 0,
   "megatron_config": null,
   "megatron_core": "megatron.core",
@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": "unsloth",
   "target_modules": [
-    "v_proj",
-    "q_proj",
-    "down_proj",
     "k_proj",
-    "up_proj",
     "o_proj",
-    "gate_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
+  "lora_alpha": 32,
   "lora_dropout": 0,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "rank_pattern": {},
   "revision": "unsloth",
   "target_modules": [
     "k_proj",
     "o_proj",
+    "gate_proj",
+    "q_proj",
+    "up_proj",
+    "down_proj",
+    "v_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1fa49f0d29735518a26bea3e365040cdfa6e406118f1c45855e49e10b51eb2e4
 size 119597408

 version https://git-lfs.github.com/spec/v1
+oid sha256:a6dee022f99fa40d68c3457d142867e6f8243b4e1f19123faa0dac925ebe916c
 size 119597408