Instructions to use snakeying/llama3.1-8B-LongWriter with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- llama-cpp-python
How to use snakeying/llama3.1-8B-LongWriter with llama-cpp-python:
# !pip install llama-cpp-python from llama_cpp import Llama llm = Llama.from_pretrained( repo_id="snakeying/llama3.1-8B-LongWriter", filename="llama3.1-8B-LongWriter-q8_0.gguf", )
output = llm( "Once upon a time,", max_tokens=512, echo=True ) print(output)
- Notebooks
- Google Colab
- Kaggle
- Local Apps
- llama.cpp
How to use snakeying/llama3.1-8B-LongWriter with llama.cpp:
Install from brew
brew install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf snakeying/llama3.1-8B-LongWriter:Q8_0 # Run inference directly in the terminal: llama-cli -hf snakeying/llama3.1-8B-LongWriter:Q8_0
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf snakeying/llama3.1-8B-LongWriter:Q8_0 # Run inference directly in the terminal: llama-cli -hf snakeying/llama3.1-8B-LongWriter: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 snakeying/llama3.1-8B-LongWriter:Q8_0 # Run inference directly in the terminal: ./llama-cli -hf snakeying/llama3.1-8B-LongWriter: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 snakeying/llama3.1-8B-LongWriter:Q8_0 # Run inference directly in the terminal: ./build/bin/llama-cli -hf snakeying/llama3.1-8B-LongWriter:Q8_0
Use Docker
docker model run hf.co/snakeying/llama3.1-8B-LongWriter:Q8_0
- LM Studio
- Jan
- Ollama
How to use snakeying/llama3.1-8B-LongWriter with Ollama:
ollama run hf.co/snakeying/llama3.1-8B-LongWriter:Q8_0
- Unsloth Studio new
How to use snakeying/llama3.1-8B-LongWriter 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 snakeying/llama3.1-8B-LongWriter 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 snakeying/llama3.1-8B-LongWriter to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for snakeying/llama3.1-8B-LongWriter to start chatting
- Docker Model Runner
How to use snakeying/llama3.1-8B-LongWriter with Docker Model Runner:
docker model run hf.co/snakeying/llama3.1-8B-LongWriter:Q8_0
- Lemonade
How to use snakeying/llama3.1-8B-LongWriter with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull snakeying/llama3.1-8B-LongWriter:Q8_0
Run and chat with the model
lemonade run user.llama3.1-8B-LongWriter-Q8_0
List all available models
lemonade list
output = llm(
"Once upon a time,",
max_tokens=512,
echo=True
)
print(output)YAML Metadata Warning:empty or missing yaml metadata in repo card
Check out the documentation for more information.
TEMPLATE for Ollama Modelfile
TEMPLATE """ {{- range $i, $_ := .Messages }} {{- if eq .Role "user" }} {{- if and $.Tools (le (len (slice $.Messages $i)) 2) }}[AVAILABLE_TOOLS] {{ $.Tools }}[/AVAILABLE_TOOLS] {{- end }}[INST] {{ if and $.System (eq (len (slice $.Messages $i)) 1) }}{{ $.System }}
{{ end }}{{ .Content }}[/INST] {{- else if eq .Role "assistant" }} {{- if .Content }} {{ .Content }}{{ if not (eq (len (slice $.Messages $i)) 1) }}{{ end }} {{- else if .ToolCalls }}[TOOL_CALLS] [ {{- range .ToolCalls }}{"name": "{{ .Function.Name }}", "arguments": {{ .Function.Arguments }}} {{- end }}] {{- end }} {{- else if eq .Role "tool" }}[TOOL_RESULTS] {"content": {{ .Content }}} [/TOOL_RESULTS] {{- end }} {{- end }} """
PARAMETER stop "[INST]" PARAMETER stop "[/INST]"
- Downloads last month
- 4
8-bit
# !pip install llama-cpp-python from llama_cpp import Llama llm = Llama.from_pretrained( repo_id="snakeying/llama3.1-8B-LongWriter", filename="llama3.1-8B-LongWriter-q8_0.gguf", )