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

Libraries

How to use TheBloke/Llama-2-7B-Chat-GGUF with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="TheBloke/Llama-2-7B-Chat-GGUF")

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

llama-cpp-python

How to use TheBloke/Llama-2-7B-Chat-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="TheBloke/Llama-2-7B-Chat-GGUF",
	filename="llama-2-7b-chat.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/Llama-2-7B-Chat-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/Llama-2-7B-Chat-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf TheBloke/Llama-2-7B-Chat-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/Llama-2-7B-Chat-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf TheBloke/Llama-2-7B-Chat-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/Llama-2-7B-Chat-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf TheBloke/Llama-2-7B-Chat-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/Llama-2-7B-Chat-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf TheBloke/Llama-2-7B-Chat-GGUF:Q4_K_M

Use Docker

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

LM Studio
Jan

vLLM

How to use TheBloke/Llama-2-7B-Chat-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "TheBloke/Llama-2-7B-Chat-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "TheBloke/Llama-2-7B-Chat-GGUF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

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

SGLang

How to use TheBloke/Llama-2-7B-Chat-GGUF with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "TheBloke/Llama-2-7B-Chat-GGUF" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "TheBloke/Llama-2-7B-Chat-GGUF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "TheBloke/Llama-2-7B-Chat-GGUF" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "TheBloke/Llama-2-7B-Chat-GGUF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Ollama
How to use TheBloke/Llama-2-7B-Chat-GGUF with Ollama:
```
ollama run hf.co/TheBloke/Llama-2-7B-Chat-GGUF:Q4_K_M
```

Unsloth Studio new

How to use TheBloke/Llama-2-7B-Chat-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/Llama-2-7B-Chat-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/Llama-2-7B-Chat-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/Llama-2-7B-Chat-GGUF to start chatting

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

Lemonade

How to use TheBloke/Llama-2-7B-Chat-GGUF with Lemonade:

Pull the model

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

Run and chat with the model

lemonade run user.Llama-2-7B-Chat-GGUF-Q4_K_M

List all available models

lemonade list

New discussion

Resources

View closed (1)

Update README.md

#37 opened 8 months ago by

yve36

Upload llama-2-7b-chat.gguf

#36 opened about 1 year ago by

leveejr123

dscacaa

#35 opened over 1 year ago by

Alyasan3de2d

does not appear to have a file named pytorch_model.bin, model.safetensors, tf_model.h5, model.ckpt or flax_model.msgpack.

#34 opened over 1 year ago by

pythonchatbot05

Trying to use llama-2-7b-chat.Q4_K_M.gguf with/without tensorflow weights

#33 opened about 2 years ago by

cgthayer

Fine tuning

#32 opened about 2 years ago by

MD1998

How to know which bit model deploying using sagemaker

#31 opened about 2 years ago by

sarvanand

GGUF Model not loading at all

#30 opened about 2 years ago by

jdhadljasnajd

Waiting for Meta-Llama-3-8B-Instruct-gguf

#29 opened about 2 years ago by

anuragrawal

Local model changing in model.py

#28 opened about 2 years ago by

aaromal

Update Discord Invite link

#27 opened about 2 years ago by

ZennyKenny

Refer the model on HuggingFace

#26 opened about 2 years ago by

vidhiparikh

how to deal with number of tokens exceeded maximum context length

#25 opened about 2 years ago by

Janmejay123

Connect to vector store through azure ai search index

#24 opened about 2 years ago by

Janmejay123

Help with llama-2-7b-chat.Q4_K_M.gguf already in local downloads

#23 opened about 2 years ago by

elisharukovo

401 authentication error

#22 opened about 2 years ago by

Madhumitha19

Why "llama-2-7b-chat.Q8_0.gguf" model is not recommended

👍 1

#21 opened over 2 years ago by

AhmetOnur

RMSNorm eps value is wrong

👍 1

#20 opened over 2 years ago by

qnixsynapse

RMSNorm eps value is wrong

#19 opened over 2 years ago by

qnixsynapse

Problem while making multiple request at a time from seperate chat bot instances

#18 opened over 2 years ago by

krishnapiya

Model is responding for out of context answer also need to know from where its taking the answer?

#17 opened over 2 years ago by

AdarshaAG

[AUTOMATED] Model Memory Requirements

#16 opened over 2 years ago by

model-sizer-bot

Is there any linguistic model that supports the Arabic language?

#15 opened over 2 years ago by

abdellatif1

How to use system prompts?

#14 opened over 2 years ago by

luissimoes

Produced Output Stability

#13 opened over 2 years ago by

luissimoes

proper embedding for llama-2-7b-chat.Q4_K_M.gguf

#12 opened over 2 years ago by

awarity-dev

"TheBloke/Llama-2-7b-Chat-GGUF does not appear to have a file named pytorch_model.bin, tf_model.h5, model.ckpt or flax_model.msgpack."

#11 opened over 2 years ago by

swvajanyatek

Running locally: Cannot load model "llama-2-7b-chat.Q2_K.gguf"

#10 opened over 2 years ago by

Learner

Check the model's maximum input value

#9 opened over 2 years ago by

minhdang

Error while using CTransformers: Model file 'llama-2-7b-chat.q4_K_M.gguf' not found

#7 opened over 2 years ago by

gaukelkar

error loading model: GGUF with latest llama_cpp_python 0.2.11

#6 opened over 2 years ago by

Kerlion

What model and minimum gpu requirements are required for PDF-QA?

#5 opened over 2 years ago by

saifhassan

This model giving the correct answer but twice

#4 opened over 2 years ago by

Srp7

Llama 2 GGUF streaming support?

#3 opened over 2 years ago by

latinostats

Inconsistent Model Name

👍❤️ 3

#2 opened over 2 years ago by

Yao-Lirong

Error with runpod

👍 1

#1 opened over 2 years ago by

sunshein