Instructions to use Trelis/Llama-2-7b-chat-hf-function-calling-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Trelis/Llama-2-7b-chat-hf-function-calling-v2 with Transformers:

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

pipe = pipeline("text-generation", model="Trelis/Llama-2-7b-chat-hf-function-calling-v2")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Trelis/Llama-2-7b-chat-hf-function-calling-v2")
model = AutoModelForCausalLM.from_pretrained("Trelis/Llama-2-7b-chat-hf-function-calling-v2")

llama-cpp-python

How to use Trelis/Llama-2-7b-chat-hf-function-calling-v2 with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Trelis/Llama-2-7b-chat-hf-function-calling-v2",
	filename="ggml-vocab-llama.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use Trelis/Llama-2-7b-chat-hf-function-calling-v2 with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Trelis/Llama-2-7b-chat-hf-function-calling-v2:Q3_K_M
# Run inference directly in the terminal:
llama-cli -hf Trelis/Llama-2-7b-chat-hf-function-calling-v2:Q3_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Trelis/Llama-2-7b-chat-hf-function-calling-v2:Q3_K_M
# Run inference directly in the terminal:
llama-cli -hf Trelis/Llama-2-7b-chat-hf-function-calling-v2:Q3_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 Trelis/Llama-2-7b-chat-hf-function-calling-v2:Q3_K_M
# Run inference directly in the terminal:
./llama-cli -hf Trelis/Llama-2-7b-chat-hf-function-calling-v2:Q3_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 Trelis/Llama-2-7b-chat-hf-function-calling-v2:Q3_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Trelis/Llama-2-7b-chat-hf-function-calling-v2:Q3_K_M

Use Docker

docker model run hf.co/Trelis/Llama-2-7b-chat-hf-function-calling-v2:Q3_K_M

LM Studio
Jan

vLLM

How to use Trelis/Llama-2-7b-chat-hf-function-calling-v2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Trelis/Llama-2-7b-chat-hf-function-calling-v2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Trelis/Llama-2-7b-chat-hf-function-calling-v2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Trelis/Llama-2-7b-chat-hf-function-calling-v2:Q3_K_M

SGLang

How to use Trelis/Llama-2-7b-chat-hf-function-calling-v2 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 "Trelis/Llama-2-7b-chat-hf-function-calling-v2" \
    --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": "Trelis/Llama-2-7b-chat-hf-function-calling-v2",
		"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 "Trelis/Llama-2-7b-chat-hf-function-calling-v2" \
        --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": "Trelis/Llama-2-7b-chat-hf-function-calling-v2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Ollama
How to use Trelis/Llama-2-7b-chat-hf-function-calling-v2 with Ollama:
```
ollama run hf.co/Trelis/Llama-2-7b-chat-hf-function-calling-v2:Q3_K_M
```

Unsloth Studio

How to use Trelis/Llama-2-7b-chat-hf-function-calling-v2 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 Trelis/Llama-2-7b-chat-hf-function-calling-v2 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 Trelis/Llama-2-7b-chat-hf-function-calling-v2 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Trelis/Llama-2-7b-chat-hf-function-calling-v2 to start chatting

Docker Model Runner
How to use Trelis/Llama-2-7b-chat-hf-function-calling-v2 with Docker Model Runner:
```
docker model run hf.co/Trelis/Llama-2-7b-chat-hf-function-calling-v2:Q3_K_M
```

Lemonade

How to use Trelis/Llama-2-7b-chat-hf-function-calling-v2 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Trelis/Llama-2-7b-chat-hf-function-calling-v2:Q3_K_M

Run and chat with the model

lemonade run user.Llama-2-7b-chat-hf-function-calling-v2-Q3_K_M

List all available models

lemonade list

RonanMcGovern commited on Nov 24, 2023

Commit

b3591eb

1 Parent(s): 055776a

add tips on best models

Browse files

Files changed (1) hide show

README.md +8 -2

README.md CHANGED Viewed

@@ -43,14 +43,20 @@ Latest Models:
 Other Models:
 - Llama-13B-chat with function calling ([Base Model](https://huggingface.co/Trelis/Llama-2-13b-chat-hf-function-calling-v2)), ([PEFT Adapters](https://huggingface.co/Trelis/Llama-2-13b-chat-hf-function-calling-adapters-v2)) - Paid, [purchase here](https://buy.stripe.com/9AQ7te3lHdmbdZ68wz)
-## Performance and Tips
 1. Larger models are better at handling function calling. The cross entropy training losses are approximately 0.5 for 7B, 0.4 for 13B, 0.3 for 70B. The absolute numbers don't mean anything but the relative values offer a sense of relative performance.
 1. Provide very clear function descriptions, including whether the arguments are required or what the default values should be.
 1. Make sure to post-process the language model's response to check that all necessary information is provided by the user. If not, prompt the user to let them know they need to provide more info (e.g. their name, order number etc.)
 Check out this video overview of performance [here](https://www.loom.com/share/8d7467de95e04af29ff428c46286946c?sid=683c970e-6063-4f1e-b184-894cc1d96115)
 ## Licensing
 Llama-7B with function calling is licensed according to the Meta Community license.

 Other Models:
 - Llama-13B-chat with function calling ([Base Model](https://huggingface.co/Trelis/Llama-2-13b-chat-hf-function-calling-v2)), ([PEFT Adapters](https://huggingface.co/Trelis/Llama-2-13b-chat-hf-function-calling-adapters-v2)) - Paid, [purchase here](https://buy.stripe.com/9AQ7te3lHdmbdZ68wz)
+## Which model is best for what?
 1. Larger models are better at handling function calling. The cross entropy training losses are approximately 0.5 for 7B, 0.4 for 13B, 0.3 for 70B. The absolute numbers don't mean anything but the relative values offer a sense of relative performance.
 1. Provide very clear function descriptions, including whether the arguments are required or what the default values should be.
 1. Make sure to post-process the language model's response to check that all necessary information is provided by the user. If not, prompt the user to let them know they need to provide more info (e.g. their name, order number etc.)
 Check out this video overview of performance [here](https://www.loom.com/share/8d7467de95e04af29ff428c46286946c?sid=683c970e-6063-4f1e-b184-894cc1d96115)
+Some short tips based on models as of November 2023:
+- DeepSeek Coder (all sizes) = best coding model.
+- Yi 34B = best for long context.
+- Llama 70B = strongest overall model (4k context).
+- Mistral 7B = Best model if you have only 8 GB of VRAM (run with quantization).
+Zephyr is better than Mistral 7B but is not openly licensed for commercial use.
 ## Licensing
 Llama-7B with function calling is licensed according to the Meta Community license.