Instructions to use TheBloke/13B-BlueMethod-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TheBloke/13B-BlueMethod-GGUF with Transformers:

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("TheBloke/13B-BlueMethod-GGUF", dtype="auto")

llama-cpp-python

How to use TheBloke/13B-BlueMethod-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="TheBloke/13B-BlueMethod-GGUF",
	filename="13b-bluemethod.Q2_K.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 TheBloke/13B-BlueMethod-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf TheBloke/13B-BlueMethod-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf TheBloke/13B-BlueMethod-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf TheBloke/13B-BlueMethod-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf TheBloke/13B-BlueMethod-GGUF: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 TheBloke/13B-BlueMethod-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf TheBloke/13B-BlueMethod-GGUF: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 TheBloke/13B-BlueMethod-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf TheBloke/13B-BlueMethod-GGUF:Q4_K_M

Use Docker

docker model run hf.co/TheBloke/13B-BlueMethod-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use TheBloke/13B-BlueMethod-GGUF with Ollama:
```
ollama run hf.co/TheBloke/13B-BlueMethod-GGUF:Q4_K_M
```

Unsloth Studio new

How to use TheBloke/13B-BlueMethod-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 TheBloke/13B-BlueMethod-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 TheBloke/13B-BlueMethod-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for TheBloke/13B-BlueMethod-GGUF to start chatting

Docker Model Runner
How to use TheBloke/13B-BlueMethod-GGUF with Docker Model Runner:
```
docker model run hf.co/TheBloke/13B-BlueMethod-GGUF:Q4_K_M
```

Lemonade

How to use TheBloke/13B-BlueMethod-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull TheBloke/13B-BlueMethod-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.13B-BlueMethod-GGUF-Q4_K_M

List all available models

lemonade list

TheBloke commited on Sep 20, 2023

Commit

c1ee5cb

1 Parent(s): de8ea98

Upload README.md

Browse files

Files changed (1) hide show

README.md +5 -5

README.md CHANGED Viewed

@@ -156,7 +156,7 @@ The following clients/libraries will automatically download models for you, prov
 ### In `text-generation-webui`
-Under Download Model, you can enter the model repo: TheBloke/13B-BlueMethod-GGUF and below it, a specific filename to download, such as: 13b-bluemethod.q4_K_M.gguf.
 Then click Download.
@@ -171,7 +171,7 @@ pip3 install huggingface-hub>=0.17.1
 Then you can download any individual model file to the current directory, at high speed, with a command like this:
 ```shell
-huggingface-cli download TheBloke/13B-BlueMethod-GGUF 13b-bluemethod.q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
 ```
 <details>
@@ -194,7 +194,7 @@ pip3 install hf_transfer
 And set environment variable `HF_HUB_ENABLE_HF_TRANSFER` to `1`:
 ```shell
-HUGGINGFACE_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download TheBloke/13B-BlueMethod-GGUF 13b-bluemethod.q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
 ```
 Windows CLI users: Use `set HUGGINGFACE_HUB_ENABLE_HF_TRANSFER=1` before running the download command.
@@ -207,7 +207,7 @@ Windows CLI users: Use `set HUGGINGFACE_HUB_ENABLE_HF_TRANSFER=1` before running
 Make sure you are using `llama.cpp` from commit [d0cee0d36d5be95a0d9088b674dbb27354107221](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221) or later.
 ```shell
-./main -ngl 32 -m 13b-bluemethod.q4_K_M.gguf --color -c 4096 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "Below is an instruction that describes a task. Write a response that appropriately completes the request.\n\n### Instruction:\n{prompt}\n\n### Response:"
 ```
 Change `-ngl 32` to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.
@@ -247,7 +247,7 @@ CT_METAL=1 pip install ctransformers>=0.2.24 --no-binary ctransformers
 from ctransformers import AutoModelForCausalLM
 # Set gpu_layers to the number of layers to offload to GPU. Set to 0 if no GPU acceleration is available on your system.
-llm = AutoModelForCausalLM.from_pretrained("TheBloke/13B-BlueMethod-GGUF", model_file="13b-bluemethod.q4_K_M.gguf", model_type="llama", gpu_layers=50)
 print(llm("AI is going to"))
 ```

 ### In `text-generation-webui`
+Under Download Model, you can enter the model repo: TheBloke/13B-BlueMethod-GGUF and below it, a specific filename to download, such as: 13b-bluemethod.Q4_K_M.gguf.
 Then click Download.
 Then you can download any individual model file to the current directory, at high speed, with a command like this:
 ```shell
+huggingface-cli download TheBloke/13B-BlueMethod-GGUF 13b-bluemethod.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
 ```
 <details>
 And set environment variable `HF_HUB_ENABLE_HF_TRANSFER` to `1`:
 ```shell
+HUGGINGFACE_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download TheBloke/13B-BlueMethod-GGUF 13b-bluemethod.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
 ```
 Windows CLI users: Use `set HUGGINGFACE_HUB_ENABLE_HF_TRANSFER=1` before running the download command.
 Make sure you are using `llama.cpp` from commit [d0cee0d36d5be95a0d9088b674dbb27354107221](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221) or later.
 ```shell
+./main -ngl 32 -m 13b-bluemethod.Q4_K_M.gguf --color -c 4096 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "Below is an instruction that describes a task. Write a response that appropriately completes the request.\n\n### Instruction:\n{prompt}\n\n### Response:"
 ```
 Change `-ngl 32` to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.
 from ctransformers import AutoModelForCausalLM
 # Set gpu_layers to the number of layers to offload to GPU. Set to 0 if no GPU acceleration is available on your system.
+llm = AutoModelForCausalLM.from_pretrained("TheBloke/13B-BlueMethod-GGUF", model_file="13b-bluemethod.Q4_K_M.gguf", model_type="llama", gpu_layers=50)
 print(llm("AI is going to"))
 ```