Instructions to use openthaigpt/openthaigpt-1.0.0-7b-chat with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use openthaigpt/openthaigpt-1.0.0-7b-chat with Transformers:

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

pipe = pipeline("text-generation", model="openthaigpt/openthaigpt-1.0.0-7b-chat")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("openthaigpt/openthaigpt-1.0.0-7b-chat")
model = AutoModelForCausalLM.from_pretrained("openthaigpt/openthaigpt-1.0.0-7b-chat", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use openthaigpt/openthaigpt-1.0.0-7b-chat 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 openthaigpt/openthaigpt-1.0.0-7b-chat:F16
# Run inference directly in the terminal:
llama cli -hf openthaigpt/openthaigpt-1.0.0-7b-chat:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf openthaigpt/openthaigpt-1.0.0-7b-chat:F16
# Run inference directly in the terminal:
llama cli -hf openthaigpt/openthaigpt-1.0.0-7b-chat:F16

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 openthaigpt/openthaigpt-1.0.0-7b-chat:F16
# Run inference directly in the terminal:
./llama-cli -hf openthaigpt/openthaigpt-1.0.0-7b-chat:F16

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 openthaigpt/openthaigpt-1.0.0-7b-chat:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf openthaigpt/openthaigpt-1.0.0-7b-chat:F16

Use Docker

docker model run hf.co/openthaigpt/openthaigpt-1.0.0-7b-chat:F16

LM Studio
Jan

vLLM

How to use openthaigpt/openthaigpt-1.0.0-7b-chat with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "openthaigpt/openthaigpt-1.0.0-7b-chat"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "openthaigpt/openthaigpt-1.0.0-7b-chat",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/openthaigpt/openthaigpt-1.0.0-7b-chat:F16

SGLang

How to use openthaigpt/openthaigpt-1.0.0-7b-chat 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 "openthaigpt/openthaigpt-1.0.0-7b-chat" \
    --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": "openthaigpt/openthaigpt-1.0.0-7b-chat",
		"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 "openthaigpt/openthaigpt-1.0.0-7b-chat" \
        --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": "openthaigpt/openthaigpt-1.0.0-7b-chat",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Ollama
How to use openthaigpt/openthaigpt-1.0.0-7b-chat with Ollama:
```
ollama run hf.co/openthaigpt/openthaigpt-1.0.0-7b-chat:F16
```
Unsloth Desktop
Docker Model Runner
How to use openthaigpt/openthaigpt-1.0.0-7b-chat with Docker Model Runner:
```
docker model run hf.co/openthaigpt/openthaigpt-1.0.0-7b-chat:F16
```

Lemonade

How to use openthaigpt/openthaigpt-1.0.0-7b-chat with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull openthaigpt/openthaigpt-1.0.0-7b-chat:F16

Run and chat with the model

lemonade run user.openthaigpt-1.0.0-7b-chat-F16

List all available models

lemonade list

Atomic Chat

kobkrit

pacozaa commited on Apr 17, 2024

Commit

804fbe8

verified ·

1 Parent(s): 8718bee

Update READMD.md Ollama section (#5)

Browse files

- Update READMD.md Ollama section (6a2cd9d75c47f197f36bea07e91f82b22dcec8e3)

Co-authored-by: Sarin Suriyakoon <pacozaa@users.noreply.huggingface.co>

Files changed (1) hide show

README.md +14 -0

README.md CHANGED Viewed

@@ -236,6 +236,20 @@ curl --location 'http://localhost:8000/completion' \
 }'
 ```
 ### GPU Memory Requirements
 | **Number of Parameters** | **FP 16 bits** | **8 bits (Quantized)** | **4 bits (Quantized)** | **Example Graphic Card for 4 bits** |
 |------------------|----------------|------------------------|------------------------|---------------------------------------------|

 }'
 ```
+### Ollama
+There are two ways to run on ollama
+1. From this repo Modelfile and 4 bit quantized gguf
+```bash
+ollama create -f ./Modelfile
+```
+2. From Ollama CLI
+```bash
+ollama run pacozaa/openthaigpt
+```
 ### GPU Memory Requirements
 | **Number of Parameters** | **FP 16 bits** | **8 bits (Quantized)** | **4 bits (Quantized)** | **Example Graphic Card for 4 bits** |
 |------------------|----------------|------------------------|------------------------|---------------------------------------------|