Instructions to use xtuner/llava-llama-3-8b-v1_1-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use xtuner/llava-llama-3-8b-v1_1-gguf with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="xtuner/llava-llama-3-8b-v1_1-gguf",
	filename="llava-llama-3-8b-v1_1-f16.gguf",
)

llm.create_chat_completion(
	messages = "\"cats.jpg\""
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use xtuner/llava-llama-3-8b-v1_1-gguf with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf xtuner/llava-llama-3-8b-v1_1-gguf:F16
# Run inference directly in the terminal:
llama-cli -hf xtuner/llava-llama-3-8b-v1_1-gguf:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf xtuner/llava-llama-3-8b-v1_1-gguf:F16
# Run inference directly in the terminal:
llama-cli -hf xtuner/llava-llama-3-8b-v1_1-gguf:F16

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 xtuner/llava-llama-3-8b-v1_1-gguf:F16
# Run inference directly in the terminal:
./llama-cli -hf xtuner/llava-llama-3-8b-v1_1-gguf:F16

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 xtuner/llava-llama-3-8b-v1_1-gguf:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf xtuner/llava-llama-3-8b-v1_1-gguf:F16

Use Docker

docker model run hf.co/xtuner/llava-llama-3-8b-v1_1-gguf:F16

LM Studio
Jan
Ollama
How to use xtuner/llava-llama-3-8b-v1_1-gguf with Ollama:
```
ollama run hf.co/xtuner/llava-llama-3-8b-v1_1-gguf:F16
```

Unsloth Studio

How to use xtuner/llava-llama-3-8b-v1_1-gguf 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 xtuner/llava-llama-3-8b-v1_1-gguf 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 xtuner/llava-llama-3-8b-v1_1-gguf to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for xtuner/llava-llama-3-8b-v1_1-gguf to start chatting

Docker Model Runner
How to use xtuner/llava-llama-3-8b-v1_1-gguf with Docker Model Runner:
```
docker model run hf.co/xtuner/llava-llama-3-8b-v1_1-gguf:F16
```

Lemonade

How to use xtuner/llava-llama-3-8b-v1_1-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull xtuner/llava-llama-3-8b-v1_1-gguf:F16

Run and chat with the model

lemonade run user.llava-llama-3-8b-v1_1-gguf-F16

List all available models

lemonade list

pppppM commited on Apr 29, 2024

Commit

326a92a

verified ·

1 Parent(s): 13eff81

Update README.md

Browse files

Files changed (1) hide show

README.md +19 -3

README.md CHANGED Viewed

@@ -61,15 +61,31 @@ wget https://huggingface.co/xtuner/llava-llama-3-8b-v1_1-gguf/resolve/main/llava
 # int4 llm
 wget https://huggingface.co/xtuner/llava-llama-3-8b-v1_1-gguf/resolve/main/llava-llama-3-8b-v1_1-int4.gguf
 ```
-### Build environment
 1. Build [llama.cpp](https://github.com/ggerganov/llama.cpp) ([docs](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage)) .
 2. Build `./llava-cli` ([docs](https://github.com/ggerganov/llama.cpp/tree/master/examples/llava#usage)).
-### Chat by `./llava-cli`
 Note: llava-llama-3-8b-v1_1 uses the Llama-3-instruct chat template.
 ```bash

 # int4 llm
 wget https://huggingface.co/xtuner/llava-llama-3-8b-v1_1-gguf/resolve/main/llava-llama-3-8b-v1_1-int4.gguf
+# (optional) ollama fp16 modelfile
+wget https://huggingface.co/xtuner/llava-llama-3-8b-v1_1-gguf/resolve/main/OLLAMA_MODELFILE_F16
+# (optional) ollama int4 modelfile
+wget https://huggingface.co/xtuner/llava-llama-3-8b-v1_1-gguf/resolve/main/OLLAMA_MODELFILE_INT4
+```
+### Chat by `ollama`
+```bash
+# fp16
+ollama create llava-llama3-f16 -f ./OLLAMA_MODELFILE_F16
+ollama run llava-llama3-f16 "xx.png Describe this image"
+# int4
+ollama create llava-llama3-int4 -f ./OLLAMA_MODELFILE_INT4
+ollama run llava-llama3-int4 "xx.png Describe this image"
 ```
+### Chat by `llama.cpp`
 1. Build [llama.cpp](https://github.com/ggerganov/llama.cpp) ([docs](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage)) .
 2. Build `./llava-cli` ([docs](https://github.com/ggerganov/llama.cpp/tree/master/examples/llava#usage)).
 Note: llava-llama-3-8b-v1_1 uses the Llama-3-instruct chat template.
 ```bash