Instructions to use TheBloke/koOpenChat-sft-GPTQ with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TheBloke/koOpenChat-sft-GPTQ with Transformers:

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

pipe = pipeline("text-generation", model="TheBloke/koOpenChat-sft-GPTQ")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("TheBloke/koOpenChat-sft-GPTQ")
model = AutoModelForCausalLM.from_pretrained("TheBloke/koOpenChat-sft-GPTQ", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use TheBloke/koOpenChat-sft-GPTQ with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/TheBloke/koOpenChat-sft-GPTQ

SGLang

How to use TheBloke/koOpenChat-sft-GPTQ 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/koOpenChat-sft-GPTQ" \
    --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/koOpenChat-sft-GPTQ",
		"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/koOpenChat-sft-GPTQ" \
        --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/koOpenChat-sft-GPTQ",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use TheBloke/koOpenChat-sft-GPTQ with Docker Model Runner:
```
docker model run hf.co/TheBloke/koOpenChat-sft-GPTQ
```

TheBloke commited on Nov 23, 2023

Commit

96f2836

1 Parent(s): de2fd35

Upload README.md

Browse files

Files changed (1) hide show

README.md +6 -6

README.md CHANGED Viewed

@@ -113,12 +113,12 @@ Most GPTQ files are made with AutoGPTQ. Mistral models are currently made with T
 | Branch | Bits | GS | Act Order | Damp % | GPTQ Dataset | Seq Len | Size | ExLlama | Desc |
 | ------ | ---- | -- | --------- | ------ | ------------ | ------- | ---- | ------- | ---- |
-| [main](https://huggingface.co/TheBloke/koOpenChat-sft-GPTQ/tree/main) | 4 | 128 | Yes | 0.1 | [korean](https://huggingface.co/datasets/beomi/KoAlpaca-v1.1a/viewer/) | 4096 | 4.16 GB | Yes | 4-bit, with Act Order and group size 128g. Uses even less VRAM than 64g, but with slightly lower accuracy. |
-| [gptq-4bit-32g-actorder_True](https://huggingface.co/TheBloke/koOpenChat-sft-GPTQ/tree/gptq-4bit-32g-actorder_True) | 4 | 32 | Yes | 0.1 | [korean](https://huggingface.co/datasets/beomi/KoAlpaca-v1.1a/viewer/) | 4096 | 4.57 GB | Yes | 4-bit, with Act Order and group size 32g. Gives highest possible inference quality, with maximum VRAM usage. |
-| [gptq-8bit--1g-actorder_True](https://huggingface.co/TheBloke/koOpenChat-sft-GPTQ/tree/gptq-8bit--1g-actorder_True) | 8 | None | Yes | 0.1 | [korean](https://huggingface.co/datasets/beomi/KoAlpaca-v1.1a/viewer/) | 4096 | 7.52 GB | No | 8-bit, with Act Order. No group size, to lower VRAM requirements. |
-| [gptq-8bit-128g-actorder_True](https://huggingface.co/TheBloke/koOpenChat-sft-GPTQ/tree/gptq-8bit-128g-actorder_True) | 8 | 128 | Yes | 0.1 | [korean](https://huggingface.co/datasets/beomi/KoAlpaca-v1.1a/viewer/) | 4096 | 7.68 GB | No | 8-bit, with group size 128g for higher inference quality and with Act Order for even higher accuracy. |
-| [gptq-8bit-32g-actorder_True](https://huggingface.co/TheBloke/koOpenChat-sft-GPTQ/tree/gptq-8bit-32g-actorder_True) | 8 | 32 | Yes | 0.1 | [korean](https://huggingface.co/datasets/beomi/KoAlpaca-v1.1a/viewer/) | 4096 | 8.17 GB | No | 8-bit, with group size 32g and Act Order for maximum inference quality. |
-| [gptq-4bit-64g-actorder_True](https://huggingface.co/TheBloke/koOpenChat-sft-GPTQ/tree/gptq-4bit-64g-actorder_True) | 4 | 64 | Yes | 0.1 | [korean](https://huggingface.co/datasets/beomi/KoAlpaca-v1.1a/viewer/) | 4096 | 4.30 GB | Yes | 4-bit, with Act Order and group size 64g. Uses less VRAM than 32g, but with slightly lower accuracy. |
 <!-- README_GPTQ.md-provided-files end -->

 | Branch | Bits | GS | Act Order | Damp % | GPTQ Dataset | Seq Len | Size | ExLlama | Desc |
 | ------ | ---- | -- | --------- | ------ | ------------ | ------- | ---- | ------- | ---- |
+| [main](https://huggingface.co/TheBloke/koOpenChat-sft-GPTQ/tree/main) | 4 | 128 | Yes | 0.1 | [Korean Alpaca](https://huggingface.co/datasets/beomi/KoAlpaca-v1.1a/viewer/) | 4096 | 4.16 GB | Yes | 4-bit, with Act Order and group size 128g. Uses even less VRAM than 64g, but with slightly lower accuracy. |
+| [gptq-4bit-32g-actorder_True](https://huggingface.co/TheBloke/koOpenChat-sft-GPTQ/tree/gptq-4bit-32g-actorder_True) | 4 | 32 | Yes | 0.1 | [Korean Alpaca](https://huggingface.co/datasets/beomi/KoAlpaca-v1.1a/viewer/) | 4096 | 4.57 GB | Yes | 4-bit, with Act Order and group size 32g. Gives highest possible inference quality, with maximum VRAM usage. |
+| [gptq-8bit--1g-actorder_True](https://huggingface.co/TheBloke/koOpenChat-sft-GPTQ/tree/gptq-8bit--1g-actorder_True) | 8 | None | Yes | 0.1 | [Korean Alpaca](https://huggingface.co/datasets/beomi/KoAlpaca-v1.1a/viewer/) | 4096 | 7.52 GB | No | 8-bit, with Act Order. No group size, to lower VRAM requirements. |
+| [gptq-8bit-128g-actorder_True](https://huggingface.co/TheBloke/koOpenChat-sft-GPTQ/tree/gptq-8bit-128g-actorder_True) | 8 | 128 | Yes | 0.1 | [Korean Alpaca](https://huggingface.co/datasets/beomi/KoAlpaca-v1.1a/viewer/) | 4096 | 7.68 GB | No | 8-bit, with group size 128g for higher inference quality and with Act Order for even higher accuracy. |
+| [gptq-8bit-32g-actorder_True](https://huggingface.co/TheBloke/koOpenChat-sft-GPTQ/tree/gptq-8bit-32g-actorder_True) | 8 | 32 | Yes | 0.1 | [Korean Alpaca](https://huggingface.co/datasets/beomi/KoAlpaca-v1.1a/viewer/) | 4096 | 8.17 GB | No | 8-bit, with group size 32g and Act Order for maximum inference quality. |
+| [gptq-4bit-64g-actorder_True](https://huggingface.co/TheBloke/koOpenChat-sft-GPTQ/tree/gptq-4bit-64g-actorder_True) | 4 | 64 | Yes | 0.1 | [Korean Alpaca](https://huggingface.co/datasets/beomi/KoAlpaca-v1.1a/viewer/) | 4096 | 4.30 GB | Yes | 4-bit, with Act Order and group size 64g. Uses less VRAM than 32g, but with slightly lower accuracy. |
 <!-- README_GPTQ.md-provided-files end -->