Instructions to use ckchan/llm.mobile with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ckchan/llm.mobile with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="ckchan/llm.mobile",
	filename="Meta-Llama-3-8B-Instruct-Q4_K_M.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use ckchan/llm.mobile with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf ckchan/llm.mobile:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf ckchan/llm.mobile:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf ckchan/llm.mobile:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf ckchan/llm.mobile: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 ckchan/llm.mobile:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf ckchan/llm.mobile: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 ckchan/llm.mobile:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf ckchan/llm.mobile:Q4_K_M

Use Docker

docker model run hf.co/ckchan/llm.mobile:Q4_K_M

LM Studio
Jan
Ollama
How to use ckchan/llm.mobile with Ollama:
```
ollama run hf.co/ckchan/llm.mobile:Q4_K_M
```

Unsloth Studio new

How to use ckchan/llm.mobile 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 ckchan/llm.mobile 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 ckchan/llm.mobile to start chatting

Using HuggingFace Spaces for Unsloth

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

Docker Model Runner
How to use ckchan/llm.mobile with Docker Model Runner:
```
docker model run hf.co/ckchan/llm.mobile:Q4_K_M
```

Lemonade

How to use ckchan/llm.mobile with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull ckchan/llm.mobile:Q4_K_M

Run and chat with the model

lemonade run user.llm.mobile-Q4_K_M

List all available models

lemonade list

ckchan commited on Jan 10, 2024

Commit

bce1044

1 Parent(s): 26083dc

updated Llama-2, RedPajama, Phi-2, Vicuna.

Browse files

Files changed (4) hide show

Llama-2-7b-chat-hf-q3f16_1.zip +2 -2
RedPajama-INCITE-Chat-3B-v1-q4f16_1.zip +2 -2
phi-2-q4f16_1.zip +2 -2
vicuna-v1-7b-q3f16_0.zip +2 -2

Llama-2-7b-chat-hf-q3f16_1.zip CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:591b326ca456962c546016984459633e8d3b05de6980866e1da2068943fc8636
-size 5117643177

 version https://git-lfs.github.com/spec/v1
+oid sha256:07a13ba5c39c519db4572223721d3323b59cb8a9da4b3199f4616c000f122251
+size 2558769297

RedPajama-INCITE-Chat-3B-v1-q4f16_1.zip CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea896b8f4d5b2c20a03677bfe508ede402658cecfbd7af5fa5afc98cf7122526
-size 2806379264

 version https://git-lfs.github.com/spec/v1
+oid sha256:8ab17d4a9732b4b8fb923200c3f44950c0a188bc7f3b675646e27912999c0176
+size 1403092277

phi-2-q4f16_1.zip CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6aa57ea6938ef8447f9d56f8637cc893232ee1e55ce416a727bc9ec92fd11a65
-size 2794362577

 version https://git-lfs.github.com/spec/v1
+oid sha256:563244ca020dc4ef38d2ec041acf9a6a6a37a9cfaa77881ccec0e0db9f85f2e4
+size 1397057551

vicuna-v1-7b-q3f16_0.zip CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a23ff7e51ced807b99d63d1016987b10749f311b6daf09b4c4d04ef2dcb060d
-size 5239920296

 version https://git-lfs.github.com/spec/v1
+oid sha256:c7cabd573649d76826fe3fa816db0c6270740b6df128ba7ab82f94453d5e16f3
+size 2619892476