Instructions to use TheBloke/llama2_70b_chat_uncensored-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TheBloke/llama2_70b_chat_uncensored-GGUF with Transformers:

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("TheBloke/llama2_70b_chat_uncensored-GGUF", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use TheBloke/llama2_70b_chat_uncensored-GGUF with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf TheBloke/llama2_70b_chat_uncensored-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf TheBloke/llama2_70b_chat_uncensored-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf TheBloke/llama2_70b_chat_uncensored-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf TheBloke/llama2_70b_chat_uncensored-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/llama2_70b_chat_uncensored-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf TheBloke/llama2_70b_chat_uncensored-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/llama2_70b_chat_uncensored-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf TheBloke/llama2_70b_chat_uncensored-GGUF:Q4_K_M

Use Docker

docker model run hf.co/TheBloke/llama2_70b_chat_uncensored-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use TheBloke/llama2_70b_chat_uncensored-GGUF with Ollama:
```
ollama run hf.co/TheBloke/llama2_70b_chat_uncensored-GGUF:Q4_K_M
```
Unsloth Desktop
Docker Model Runner
How to use TheBloke/llama2_70b_chat_uncensored-GGUF with Docker Model Runner:
```
docker model run hf.co/TheBloke/llama2_70b_chat_uncensored-GGUF:Q4_K_M
```

Lemonade

How to use TheBloke/llama2_70b_chat_uncensored-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull TheBloke/llama2_70b_chat_uncensored-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.llama2_70b_chat_uncensored-GGUF-Q4_K_M

List all available models

lemonade list

Atomic Chat

Error loading Q5_K_M with text-generation-webui

by uti24 - opened Sep 16, 2023

Discussion

uti24

Sep 16, 2023

This model would not load, when using text-generation-webui. At least llama2_70b_chat_uncensored.Q5_K_M.gguf not loading.
What I get when press "load":
Traceback (most recent call last):

File “S:\oobabooga_windows\text-generation-webui\modules\ui_model_menu.py”, line 196, in load_model_wrapper

shared.model, shared.tokenizer = load_model(shared.model_name, loader)
File “S:\oobabooga_windows\text-generation-webui\modules\models.py”, line 79, in load_model

output = load_func_maploader
File “S:\oobabooga_windows\text-generation-webui\modules\models.py”, line 247, in llamacpp_loader

model, tokenizer = LlamaCppModel.from_pretrained(model_file)
File “S:\oobabooga_windows\text-generation-webui\modules\llamacpp_model.py”, line 105, in from_pretrained

result.model = Llama(**params)
File “S:\oobabooga_windows\installer_files\env\lib\site-packages\llama_cpp_ggml_cuda\llama.py”, line 328, in init

assert self.model is not None
AssertionError

uti24 changed discussion title from Error loading this model with text-generation-webui to Error loading Q5_K_M with text-generation-webui Sep 18, 2023

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment