Instructions to use second-state/OpenChat-3.5-0106-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use second-state/OpenChat-3.5-0106-GGUF with Transformers:

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

pipe = pipeline("text-generation", model="second-state/OpenChat-3.5-0106-GGUF")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("second-state/OpenChat-3.5-0106-GGUF")
model = AutoModelForCausalLM.from_pretrained("second-state/OpenChat-3.5-0106-GGUF")

llama-cpp-python

How to use second-state/OpenChat-3.5-0106-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="second-state/OpenChat-3.5-0106-GGUF",
	filename="openchat-3.5-0106-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/OpenChat-3.5-0106-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/OpenChat-3.5-0106-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf second-state/OpenChat-3.5-0106-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/OpenChat-3.5-0106-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf second-state/OpenChat-3.5-0106-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/OpenChat-3.5-0106-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf second-state/OpenChat-3.5-0106-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/OpenChat-3.5-0106-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf second-state/OpenChat-3.5-0106-GGUF:Q4_K_M

Use Docker

docker model run hf.co/second-state/OpenChat-3.5-0106-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use second-state/OpenChat-3.5-0106-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "second-state/OpenChat-3.5-0106-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/OpenChat-3.5-0106-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/second-state/OpenChat-3.5-0106-GGUF:Q4_K_M

SGLang

How to use second-state/OpenChat-3.5-0106-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/OpenChat-3.5-0106-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/OpenChat-3.5-0106-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/OpenChat-3.5-0106-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/OpenChat-3.5-0106-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use second-state/OpenChat-3.5-0106-GGUF with Ollama:
```
ollama run hf.co/second-state/OpenChat-3.5-0106-GGUF:Q4_K_M
```

Unsloth Studio new

How to use second-state/OpenChat-3.5-0106-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/OpenChat-3.5-0106-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/OpenChat-3.5-0106-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/OpenChat-3.5-0106-GGUF to start chatting

Docker Model Runner
How to use second-state/OpenChat-3.5-0106-GGUF with Docker Model Runner:
```
docker model run hf.co/second-state/OpenChat-3.5-0106-GGUF:Q4_K_M
```

Lemonade

How to use second-state/OpenChat-3.5-0106-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull second-state/OpenChat-3.5-0106-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.OpenChat-3.5-0106-GGUF-Q4_K_M

List all available models

lemonade list

Xin Liu commited on Jan 11, 2024

Commit

cd72d30

1 Parent(s): 146c8f4

Add new gguf models

Browse files

Signed-off-by: Xin Liu <sam@secondstate.io>

Files changed (9) hide show

openchat-3.5-0106-Q2_K.gguf +3 -0
openchat-3.5-0106-Q3_K_L.gguf +3 -0
openchat-3.5-0106-Q3_K_M.gguf +3 -0
openchat-3.5-0106-Q3_K_S.gguf +3 -0
openchat-3.5-0106-Q4_0.gguf +3 -0
openchat-3.5-0106-Q4_K_M.gguf +3 -0
openchat-3.5-0106-Q4_K_S.gguf +3 -0
openchat-3.5-0106-Q5_0.gguf +3 -0
openchat-3.5-0106-Q5_K_S.gguf +3 -0

openchat-3.5-0106-Q2_K.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:4d05ba84d27537ea743a02bf495dbd330b9108a5faebe0f7856f9f6089b11bb2
+size 3084043840

openchat-3.5-0106-Q3_K_L.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:4c149328081b766f47d8c81693b46c2f85c5c1054664074e19969081bafcb9ea
+size 3822971264

openchat-3.5-0106-Q3_K_M.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:95660abeb88ccf9c2deacc40b5970ac03965ba2bb02bd3e2ca878ee433e22d2d
+size 3519932800

openchat-3.5-0106-Q3_K_S.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:211ae33290d876a04c5af590222932d1f083053705b52aa93b703ab83d418f5f
+size 3165514112

openchat-3.5-0106-Q4_0.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:99496a3e5b53d47b936c774b129803e8e3d644790bf4fef9914056908d9264e1
+size 4109864384

openchat-3.5-0106-Q4_K_M.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:c10316cc03ed73641f92cb84e846cf040ac68bda2a847936d14154cde3a31975
+size 4369386944

openchat-3.5-0106-Q4_K_S.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:93fd680c91ef2482a4a98642134faf9e4d9e39d3ed1c8ea536e1f76a85dfe3fe
+size 4141321664

openchat-3.5-0106-Q5_0.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:2f1e96b1ec09e253f608cb462602e7e681262be57608a1b19f2c29eb2a6ff61d
+size 4998664640

openchat-3.5-0106-Q5_K_S.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:5b623af60b210d21af1f30d3ca47034fc4d471e09b80e6fd0ff2464cdf5495b8
+size 4998664640