Instructions to use onicai/llama_cpp_canister_models with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use onicai/llama_cpp_canister_models with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="onicai/llama_cpp_canister_models",
	filename="stories110Mtok32000.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use onicai/llama_cpp_canister_models with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf onicai/llama_cpp_canister_models
# Run inference directly in the terminal:
llama cli -hf onicai/llama_cpp_canister_models

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf onicai/llama_cpp_canister_models
# Run inference directly in the terminal:
llama cli -hf onicai/llama_cpp_canister_models

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 onicai/llama_cpp_canister_models
# Run inference directly in the terminal:
./llama-cli -hf onicai/llama_cpp_canister_models

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 onicai/llama_cpp_canister_models
# Run inference directly in the terminal:
./build/bin/llama-cli -hf onicai/llama_cpp_canister_models

Use Docker

docker model run hf.co/onicai/llama_cpp_canister_models

LM Studio
Jan
Ollama
How to use onicai/llama_cpp_canister_models with Ollama:
```
ollama run hf.co/onicai/llama_cpp_canister_models
```

Unsloth Studio

How to use onicai/llama_cpp_canister_models 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 onicai/llama_cpp_canister_models 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 onicai/llama_cpp_canister_models to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for onicai/llama_cpp_canister_models to start chatting

Atomic Chat new
Docker Model Runner
How to use onicai/llama_cpp_canister_models with Docker Model Runner:
```
docker model run hf.co/onicai/llama_cpp_canister_models
```

Lemonade

How to use onicai/llama_cpp_canister_models with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull onicai/llama_cpp_canister_models

Run and chat with the model

lemonade run user.llama_cpp_canister_models-{{QUANT_TAG}}

List all available models

lemonade list

icpp commited on Sep 26, 2024

Commit

cb8528a

verified ·

1 Parent(s): 4b89f3a

Update README.md

Browse files

Files changed (1) hide show

README.md +1 -14

README.md CHANGED Viewed

@@ -12,16 +12,6 @@ language:
 - Try them out at [ICGPT](https://icgpt.icpp.world/)
 - The models were created with the training procedure outlined in [karpathy/llama2.c](https://github.com/karpathy/llama2.c) and then converted into *.gguf format as described below.
-## TinyStories models
-| model | notes |
-|-------|-------|
-| stories260Ktok512.guff       | Use this for development & debugging |
-| stories15Mtok4096.guff       | Fits in canister & works well ! |
-| stories42Mtok4096.guff       | As of April 28, hits instruction limit of canister |
-| stories42Mtok32000.guff   | As of April 28, hits instruction limit of canister |
-| stories110Mtok32000.guff  | As of April 28, hits instruction limit of canister |
 ## Setup local git with lfs
@@ -77,10 +67,7 @@ convert-llama2c-to-ggml --llama2c-model stories110Mtok32000.bin --copy-vocab-fro
 convert-llama2c-to-ggml --llama2c-model stories42Mtok32000.bin --copy-vocab-from-model models/ggml-vocab-llama.gguf --llama2c-output-model stories42Mtok32000.gguf
 # Run it local, like this
-main -m stories15Mtok4096.gguf -p "Joe loves writing stories" -n 600 -c 128
-# Quantization
-# TODO
 ```

 - Try them out at [ICGPT](https://icgpt.icpp.world/)
 - The models were created with the training procedure outlined in [karpathy/llama2.c](https://github.com/karpathy/llama2.c) and then converted into *.gguf format as described below.
 ## Setup local git with lfs
 convert-llama2c-to-ggml --llama2c-model stories42Mtok32000.bin --copy-vocab-from-model models/ggml-vocab-llama.gguf --llama2c-output-model stories42Mtok32000.gguf
 # Run it local, like this
+./llama-cli -m stories15Mtok4096.gguf -p "Joe loves writing stories" -n 600 -c 128
 ```