Instructions to use second-state/Qwen2-72B-Instruct-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use second-state/Qwen2-72B-Instruct-GGUF with Transformers:

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

pipe = pipeline("text-generation", model="second-state/Qwen2-72B-Instruct-GGUF")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("second-state/Qwen2-72B-Instruct-GGUF")
model = AutoModelForCausalLM.from_pretrained("second-state/Qwen2-72B-Instruct-GGUF")

llama-cpp-python

How to use second-state/Qwen2-72B-Instruct-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="second-state/Qwen2-72B-Instruct-GGUF",
	filename="Qwen2-72B-Instruct-Q2_K.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use second-state/Qwen2-72B-Instruct-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf second-state/Qwen2-72B-Instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf second-state/Qwen2-72B-Instruct-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 second-state/Qwen2-72B-Instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf second-state/Qwen2-72B-Instruct-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 second-state/Qwen2-72B-Instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf second-state/Qwen2-72B-Instruct-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 second-state/Qwen2-72B-Instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf second-state/Qwen2-72B-Instruct-GGUF:Q4_K_M

Use Docker

docker model run hf.co/second-state/Qwen2-72B-Instruct-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use second-state/Qwen2-72B-Instruct-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "second-state/Qwen2-72B-Instruct-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "second-state/Qwen2-72B-Instruct-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/second-state/Qwen2-72B-Instruct-GGUF:Q4_K_M

SGLang

How to use second-state/Qwen2-72B-Instruct-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 "second-state/Qwen2-72B-Instruct-GGUF" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "second-state/Qwen2-72B-Instruct-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "second-state/Qwen2-72B-Instruct-GGUF" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "second-state/Qwen2-72B-Instruct-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use second-state/Qwen2-72B-Instruct-GGUF with Ollama:
```
ollama run hf.co/second-state/Qwen2-72B-Instruct-GGUF:Q4_K_M
```

Unsloth Studio new

How to use second-state/Qwen2-72B-Instruct-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 second-state/Qwen2-72B-Instruct-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 second-state/Qwen2-72B-Instruct-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for second-state/Qwen2-72B-Instruct-GGUF to start chatting

Docker Model Runner
How to use second-state/Qwen2-72B-Instruct-GGUF with Docker Model Runner:
```
docker model run hf.co/second-state/Qwen2-72B-Instruct-GGUF:Q4_K_M
```

Lemonade

How to use second-state/Qwen2-72B-Instruct-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull second-state/Qwen2-72B-Instruct-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Qwen2-72B-Instruct-GGUF-Q4_K_M

List all available models

lemonade list

apepkuss79 commited on Jun 8, 2024

Commit

cfbd2bb

verified ·

1 Parent(s): 619499f

Upload models

Browse files

Files changed (18) hide show

.gitattributes +17 -0
Qwen2-72B-Instruct-Q4_K_S.gguf +3 -0
Qwen2-72B-Instruct-Q5_0-00001-of-00002.gguf +3 -0
Qwen2-72B-Instruct-Q5_0-00002-of-00002.gguf +3 -0
Qwen2-72B-Instruct-Q5_K_M-00001-of-00002.gguf +3 -0
Qwen2-72B-Instruct-Q5_K_M-00002-of-00002.gguf +3 -0
Qwen2-72B-Instruct-Q5_K_S-00001-of-00002.gguf +3 -0
Qwen2-72B-Instruct-Q5_K_S-00002-of-00002.gguf +3 -0
Qwen2-72B-Instruct-Q6_K-00001-of-00002.gguf +3 -0
Qwen2-72B-Instruct-Q6_K-00002-of-00002.gguf +3 -0
Qwen2-72B-Instruct-Q8_0-00001-of-00003.gguf +3 -0
Qwen2-72B-Instruct-Q8_0-00002-of-00003.gguf +3 -0
Qwen2-72B-Instruct-Q8_0-00003-of-00003.gguf +3 -0
Qwen2-72B-Instruct-f16-00001-of-00005.gguf +3 -0
Qwen2-72B-Instruct-f16-00002-of-00005.gguf +3 -0
Qwen2-72B-Instruct-f16-00003-of-00005.gguf +3 -0
Qwen2-72B-Instruct-f16-00004-of-00005.gguf +3 -0
Qwen2-72B-Instruct-f16-00005-of-00005.gguf +3 -0

@@ -39,3 +39,20 @@ Qwen2-72B-Instruct-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
 Qwen2-72B-Instruct-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
 Qwen2-72B-Instruct-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
 Qwen2-72B-Instruct-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text

 Qwen2-72B-Instruct-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
 Qwen2-72B-Instruct-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
 Qwen2-72B-Instruct-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2-72B-Instruct-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2-72B-Instruct-Q5_0-00001-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2-72B-Instruct-Q5_0-00002-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2-72B-Instruct-Q5_K_M-00001-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2-72B-Instruct-Q5_K_M-00002-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2-72B-Instruct-Q5_K_S-00001-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2-72B-Instruct-Q5_K_S-00002-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2-72B-Instruct-Q6_K-00001-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2-72B-Instruct-Q6_K-00002-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2-72B-Instruct-Q8_0-00001-of-00003.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2-72B-Instruct-Q8_0-00002-of-00003.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2-72B-Instruct-Q8_0-00003-of-00003.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2-72B-Instruct-f16-00001-of-00005.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2-72B-Instruct-f16-00002-of-00005.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2-72B-Instruct-f16-00003-of-00005.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2-72B-Instruct-f16-00004-of-00005.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2-72B-Instruct-f16-00005-of-00005.gguf filter=lfs diff=lfs merge=lfs -text

+version https://git-lfs.github.com/spec/v1
+oid sha256:187f6015b74d36584793a2a7894f00e737155f5785f893f73d702fbf4ba02f22
+size 43889220064

+version https://git-lfs.github.com/spec/v1
+oid sha256:73c17a32d6827fe5e5480f9e1611e3eb230ec6d8c7a66211345666a62dd355a4
+size 32192298464

+version https://git-lfs.github.com/spec/v1
+oid sha256:26d2768b6fcdf7694a15cb6457c0b5da696b590e4f18b869f0aa9670b138dfe3
+size 17971731648

+version https://git-lfs.github.com/spec/v1
+oid sha256:0a417516b9fe9958798f192e4cf131973d34568affbd402d1e77e864cd533fe3
+size 32194753312

+version https://git-lfs.github.com/spec/v1
+oid sha256:e399826cfdfaf91da667f14e911f6d23f9fbc37905aa79b328e2ba6c54b45126
+size 22252709760

+version https://git-lfs.github.com/spec/v1
+oid sha256:2872d2d72ee500b03404e6f552fc4d0c5b974a58e2477590c2caebd3fd51b17c
+size 32079702816

+version https://git-lfs.github.com/spec/v1
+oid sha256:3f314de640c96c377228e0eab19fd3c4ae882f395a136a322f3a1102c813ce2a
+size 19295432576

+version https://git-lfs.github.com/spec/v1
+oid sha256:ffe5e1f47b53c97a54e14bf4eaf3cbdbc08d688c9ab14c2c520059d1ac5caade
+size 32176795264

+version https://git-lfs.github.com/spec/v1
+oid sha256:f2be4e6b245d70f170e0aca04df54dcbe200700565cff2bacb9ed2cde1909363
+size 32170830880

+version https://git-lfs.github.com/spec/v1
+oid sha256:d3d06e839a9ee165ff64f0812e7911674ba7b5cf2897462c05d299825227c33e
+size 32105954208

	@@ -0,0 +1,3 @@

	@@ -0,0 +1,3 @@

	@@ -0,0 +1,3 @@

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:4a2fe4882f13434c16d6efc9f7d10abf2653af67b564ad5ebe4a0fb910435cd1
+size 31966403616

+version https://git-lfs.github.com/spec/v1
+oid sha256:a1fe5772d46e1d48974a023932cd348b17a7248afd30383e999379764c2fc9c3
+size 13190251360

+version https://git-lfs.github.com/spec/v1
+oid sha256:cd9274d6196f9d98993447cda51ead254de66d5f6f69de463dc61998a11af35f
+size 31855071232

+version https://git-lfs.github.com/spec/v1
+oid sha256:2cd1f0bb03fe5dced5538688b02cc2b1114e915e4665010459a38eff85ff0f6b
+size 32082129280

+version https://git-lfs.github.com/spec/v1
+oid sha256:b8d390b2b6d00f0914dbf86bf142dad0e7143c326c546c9bee669cf8619cbf6a
+size 32082063648

+version https://git-lfs.github.com/spec/v1
+oid sha256:81c5e1143bec0eab7ce03d7e0e5a89281fca21f80300ff7eba812dde9c6f252a
+size 17321343072