Instructions to use cassioblaz/llama3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- llama-cpp-python
How to use cassioblaz/llama3 with llama-cpp-python:
# !pip install llama-cpp-python from llama_cpp import Llama llm = Llama.from_pretrained( repo_id="cassioblaz/llama3", filename="unsloth.Q8_0.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 cassioblaz/llama3 with llama.cpp:
Install from brew
brew install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf cassioblaz/llama3:Q8_0 # Run inference directly in the terminal: llama-cli -hf cassioblaz/llama3:Q8_0
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf cassioblaz/llama3:Q8_0 # Run inference directly in the terminal: llama-cli -hf cassioblaz/llama3:Q8_0
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 cassioblaz/llama3:Q8_0 # Run inference directly in the terminal: ./llama-cli -hf cassioblaz/llama3:Q8_0
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 cassioblaz/llama3:Q8_0 # Run inference directly in the terminal: ./build/bin/llama-cli -hf cassioblaz/llama3:Q8_0
Use Docker
docker model run hf.co/cassioblaz/llama3:Q8_0
- LM Studio
- Jan
- Ollama
How to use cassioblaz/llama3 with Ollama:
ollama run hf.co/cassioblaz/llama3:Q8_0
- Unsloth Studio new
How to use cassioblaz/llama3 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 cassioblaz/llama3 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 cassioblaz/llama3 to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for cassioblaz/llama3 to start chatting
- Pi new
How to use cassioblaz/llama3 with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama-server -hf cassioblaz/llama3:Q8_0
Configure the model in Pi
# Install Pi: npm install -g @mariozechner/pi-coding-agent # Add to ~/.pi/agent/models.json: { "providers": { "llama-cpp": { "baseUrl": "http://localhost:8080/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "cassioblaz/llama3:Q8_0" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Hermes Agent new
How to use cassioblaz/llama3 with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama-server -hf cassioblaz/llama3:Q8_0
Configure Hermes
# Install Hermes: curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash hermes setup # Point Hermes at the local server: hermes config set model.provider custom hermes config set model.base_url http://127.0.0.1:8080/v1 hermes config set model.default cassioblaz/llama3:Q8_0
Run Hermes
hermes
- Docker Model Runner
How to use cassioblaz/llama3 with Docker Model Runner:
docker model run hf.co/cassioblaz/llama3:Q8_0
- Lemonade
How to use cassioblaz/llama3 with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull cassioblaz/llama3:Q8_0
Run and chat with the model
lemonade run user.llama3-Q8_0
List all available models
lemonade list
(Trained with Unsloth)
Browse files
Modelfile
CHANGED
|
@@ -1,20 +1,14 @@
|
|
| 1 |
-
|
| 2 |
FROM /content/cassioblaz/llama3/unsloth.Q8_0.gguf
|
| 3 |
-
|
| 4 |
-
{{
|
| 5 |
-
{{
|
| 6 |
-
{{ .
|
| 7 |
-
|
| 8 |
-
|
| 9 |
-
|
| 10 |
-
|
| 11 |
-
|
| 12 |
-
|
| 13 |
-
|
| 14 |
-
PARAMETER
|
| 15 |
-
|
| 16 |
-
PARAMETER temperature 0.1
|
| 17 |
-
PARAMETER min_p 0.0
|
| 18 |
-
PARAMETER top_k 64
|
| 19 |
-
PARAMETER top_p 0.95
|
| 20 |
-
PARAMETER num_predict 32768
|
|
|
|
|
|
|
| 1 |
FROM /content/cassioblaz/llama3/unsloth.Q8_0.gguf
|
| 2 |
+
|
| 3 |
+
TEMPLATE """{{ if .System }}{{ .System }}{{ end }}{{ if .Prompt }}
|
| 4 |
+
USER: {{ .Prompt }}{{ end }}
|
| 5 |
+
ASSISTANT: {{ .Response }}<|eot_id|>"""
|
| 6 |
+
|
| 7 |
+
PARAMETER stop "<|end_header_id|>"
|
| 8 |
+
PARAMETER stop "<|end_of_text|>"
|
| 9 |
+
PARAMETER stop "<|start_header_id|>"
|
| 10 |
+
PARAMETER stop "<|eot_id|>"
|
| 11 |
+
PARAMETER stop "<|reserved_special_token_"
|
| 12 |
+
PARAMETER temperature 1.5
|
| 13 |
+
PARAMETER min_p 0.1
|
| 14 |
+
SYSTEM "Below are some instructions that describe some tasks. Write responses that appropriately complete each request."
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|