Instructions to use akshayballal/phi-3.5-mini-xlam-function-calling with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use akshayballal/phi-3.5-mini-xlam-function-calling with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("unsloth/phi-3.5-mini-instruct-bnb-4bit")
model = PeftModel.from_pretrained(base_model, "akshayballal/phi-3.5-mini-xlam-function-calling")

Transformers

How to use akshayballal/phi-3.5-mini-xlam-function-calling with Transformers:

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

pipe = pipeline("text-generation", model="akshayballal/phi-3.5-mini-xlam-function-calling")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("akshayballal/phi-3.5-mini-xlam-function-calling", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use akshayballal/phi-3.5-mini-xlam-function-calling with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "akshayballal/phi-3.5-mini-xlam-function-calling"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "akshayballal/phi-3.5-mini-xlam-function-calling",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/akshayballal/phi-3.5-mini-xlam-function-calling

SGLang

How to use akshayballal/phi-3.5-mini-xlam-function-calling 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 "akshayballal/phi-3.5-mini-xlam-function-calling" \
    --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": "akshayballal/phi-3.5-mini-xlam-function-calling",
		"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 "akshayballal/phi-3.5-mini-xlam-function-calling" \
        --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": "akshayballal/phi-3.5-mini-xlam-function-calling",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Studio new

How to use akshayballal/phi-3.5-mini-xlam-function-calling 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 akshayballal/phi-3.5-mini-xlam-function-calling 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 akshayballal/phi-3.5-mini-xlam-function-calling to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for akshayballal/phi-3.5-mini-xlam-function-calling to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="akshayballal/phi-3.5-mini-xlam-function-calling",
    max_seq_length=2048,
)

Docker Model Runner
How to use akshayballal/phi-3.5-mini-xlam-function-calling with Docker Model Runner:
```
docker model run hf.co/akshayballal/phi-3.5-mini-xlam-function-calling
```

akshayballal commited on Sep 30, 2024

Commit

41ec4e6

verified ·

1 Parent(s): 4e7d0b2

Update README.md

Browse files

Files changed (1) hide show

README.md +68 -2

README.md CHANGED Viewed

@@ -9,14 +9,80 @@ tags:
 - unsloth
 - llama
 - trl
 ---
 # Uploaded  model
 - **Developed by:** akshayballal
 - **License:** apache-2.0
 - **Finetuned from model :** unsloth/phi-3.5-mini-instruct-bnb-4bit
-This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
-[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)

 - unsloth
 - llama
 - trl
+datasets:
+- Salesforce/xlam-function-calling-60k
+pipeline_tag: text-generation
+library_name: peft
 ---
+# Model Card for Model ID
+This model is a function calling version of [microsoft/phi-3.5-mini-instruct](https://huggingface.co/microsoft/Phi-3.5-mini-instruct) finetuned on the [Salesforce/xlam-function-calling-60k](https://huggingface.co/datasets/Salesforce/xlam-function-calling-60k) dataset.
 # Uploaded  model
 - **Developed by:** akshayballal
 - **License:** apache-2.0
 - **Finetuned from model :** unsloth/phi-3.5-mini-instruct-bnb-4bit
+### Usage
+```python
+from unsloth import FastLanguageModel
+max_seq_length = 2048 # Choose any! We auto support RoPE Scaling internally!
+dtype = None # None for auto detection. Float16 for Tesla T4, V100, Bfloat16 for Ampere+
+load_in_4bit = True # Use 4bit quantization to reduce memory usage. Can be False.
+model, tokenizer = FastLanguageModel.from_pretrained(
+    model_name = "outputs/checkpoint-3000", # YOUR MODEL YOU USED FOR TRAINING
+    max_seq_length = 1024,
+    dtype = dtype,
+    load_in_4bit = load_in_4bit,
+)
+FastLanguageModel.for_inference(model) # Enable native 2x faster inference
+tools = [
+    {
+        "name": "upcoming",
+        "description": "Fetches upcoming CS:GO matches data from the specified API endpoint.",
+        "parameters": {
+            "content_type": {
+                "description": "The content type for the request, default is 'application/json'.",
+                "type": "str",
+                "default": "application/json",
+            },
+            "page": {
+                "description": "The page number to retrieve, default is 1.",
+                "type": "int",
+                "default": "1",
+            },
+            "limit": {
+                "description": "The number of matches to retrieve per page, default is 10.",
+                "type": "int",
+                "default": "10",
+            },
+        },
+    }
+]
+messages = [
+    {
+        "role": "user",
+        "content": f"You are a helpful assistant. Below are the tools that you have access to.  \n\n### Tools: \n{tools} \n\n### Query: \n{query} \n",
+    },
+]
+input = tokenizer.apply_chat_template(
+    messages, tokenize=True, add_generation_prompt=True, return_tensors="pt"
+)
+output = model.generate(
+    input_ids=input, max_new_tokens=512, temperature=0.0
+)
+decoded_output = tokenizer.decode(output[0], skip_special_tokens=True)
+```
+[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)