Instructions to use TheBloke/Yarn-Llama-2-7B-64K-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TheBloke/Yarn-Llama-2-7B-64K-GGUF with Transformers:

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("TheBloke/Yarn-Llama-2-7B-64K-GGUF", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use TheBloke/Yarn-Llama-2-7B-64K-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/Yarn-Llama-2-7B-64K-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf TheBloke/Yarn-Llama-2-7B-64K-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/Yarn-Llama-2-7B-64K-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf TheBloke/Yarn-Llama-2-7B-64K-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/Yarn-Llama-2-7B-64K-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf TheBloke/Yarn-Llama-2-7B-64K-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/Yarn-Llama-2-7B-64K-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf TheBloke/Yarn-Llama-2-7B-64K-GGUF:Q4_K_M

Use Docker

docker model run hf.co/TheBloke/Yarn-Llama-2-7B-64K-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use TheBloke/Yarn-Llama-2-7B-64K-GGUF with Ollama:
```
ollama run hf.co/TheBloke/Yarn-Llama-2-7B-64K-GGUF:Q4_K_M
```

Unsloth Studio

How to use TheBloke/Yarn-Llama-2-7B-64K-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/Yarn-Llama-2-7B-64K-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/Yarn-Llama-2-7B-64K-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/Yarn-Llama-2-7B-64K-GGUF to start chatting

Docker Model Runner
How to use TheBloke/Yarn-Llama-2-7B-64K-GGUF with Docker Model Runner:
```
docker model run hf.co/TheBloke/Yarn-Llama-2-7B-64K-GGUF:Q4_K_M
```

Lemonade

How to use TheBloke/Yarn-Llama-2-7B-64K-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull TheBloke/Yarn-Llama-2-7B-64K-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Yarn-Llama-2-7B-64K-GGUF-Q4_K_M

List all available models

lemonade list

Atomic Chat

when i use this model to embed a PDF file i get an error : ggml_allocr_alloc: not enough space in the buffer (needed 222784000, largest block available 24166400)

by RajeshkumarV - opened Sep 4, 2023

Discussion

RajeshkumarV

Sep 4, 2023

ggml_allocr_alloc: not enough space in the buffer (needed 222784000, largest block available 24166400)
GGML_ASSERT: C:\Users<name>\AppData\Local\Temp\pip-install-0ohg_aj6\llama-cpp-python_29c4846b4af1471bbb28a41659b32aa3\vendor\llama.cpp\ggml-alloc.c:144: !"not enough space in the buffer"

I tried other models as well .. same iissue
huginn-13b-v4.5.Q5_K_M.gguf
LLaMA-2-7B-32K-Q3_K_S.gguf

DarkCoverUnleashed

Sep 5, 2023

ggml_allocr_alloc: not enough space in the buffer (needed 222784000, largest block available 24166400)
GGML_ASSERT: C:\Users<name>\AppData\Local\Temp\pip-install-0ohg_aj6\llama-cpp-python_29c4846b4af1471bbb28a41659b32aa3\vendor\llama.cpp\ggml-alloc.c:144: !"not enough space in the buffer"

I tried other models as well .. same iissue
huginn-13b-v4.5.Q5_K_M.gguf
LLaMA-2-7B-32K-Q3_K_S.gguf

I think it's probably because you are exceeding your system specs

RajeshkumarV

Sep 5, 2023

I have a 32GB RAM windows 11 Laptop with an I7 processor. Also has a dedicated GPU T1200

jlnbsdfkjlnvksldfjvb

Sep 6, 2023

•

edited Sep 6, 2023

That is not nearly enough memory to load this model in a 64k context. You will need nearly 9x more memory.
Read this from TheBloke: https://huggingface.co/TheBloke/Yarn-Llama-2-13B-64K-GGUF/discussions/1#64f1b7d10b27861b2cb6e956

RajeshkumarV

Sep 6, 2023

is there a 4k version of this model in gguf format pls?

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