Instructions to use TheBloke/MegaDolphin-120b-GPTQ with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TheBloke/MegaDolphin-120b-GPTQ with Transformers:

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

pipe = pipeline("text-generation", model="TheBloke/MegaDolphin-120b-GPTQ")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("TheBloke/MegaDolphin-120b-GPTQ")
model = AutoModelForCausalLM.from_pretrained("TheBloke/MegaDolphin-120b-GPTQ", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use TheBloke/MegaDolphin-120b-GPTQ with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "TheBloke/MegaDolphin-120b-GPTQ"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "TheBloke/MegaDolphin-120b-GPTQ",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/TheBloke/MegaDolphin-120b-GPTQ

SGLang

How to use TheBloke/MegaDolphin-120b-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/MegaDolphin-120b-GPTQ" \
    --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": "TheBloke/MegaDolphin-120b-GPTQ",
		"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 "TheBloke/MegaDolphin-120b-GPTQ" \
        --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": "TheBloke/MegaDolphin-120b-GPTQ",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use TheBloke/MegaDolphin-120b-GPTQ with Docker Model Runner:
```
docker model run hf.co/TheBloke/MegaDolphin-120b-GPTQ
```

TheBloke commited on Jan 14, 2024

Commit

22e8a4d

verified ·

1 Parent(s): e7ca235

Upload README.md

Browse files

Files changed (1) hide show

README.md +5 -3

README.md CHANGED Viewed

@@ -122,10 +122,12 @@ 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/MegaDolphin-120b-GPTQ/tree/main) | 4 | None | Yes | 0.1 | [VMware Open Instruct](https://huggingface.co/datasets/VMware/open-instruct/viewer/) | 4096 | 61.04 GB | Yes | 4-bit, with Act Order. No group size, to lower VRAM requirements. |
-| [gptq-4bit-128g-actorder_True](https://huggingface.co/TheBloke/MegaDolphin-120b-GPTQ/tree/gptq-4bit-128g-actorder_True) | 4 | 128 | Yes | 0.1 | [VMware Open Instruct](https://huggingface.co/datasets/VMware/open-instruct/viewer/) | 4096 | 63.36 GB | Yes | 4-bit, with Act Order and group size 128g. Uses even less VRAM than 64g, but with slightly lower accuracy. |
 | [gptq-3bit--1g-actorder_True](https://huggingface.co/TheBloke/MegaDolphin-120b-GPTQ/tree/gptq-3bit--1g-actorder_True) | 3 | None | Yes | 0.1 | [VMware Open Instruct](https://huggingface.co/datasets/VMware/open-instruct/viewer/) | 4096 | 46.07 GB | No | 3-bit, with Act Order and no group size. Lowest possible VRAM requirements. May be lower quality than 3-bit 128g. |
-| [gptq-3bit-128g-actorder_True](https://huggingface.co/TheBloke/MegaDolphin-120b-GPTQ/tree/gptq-3bit-128g-actorder_True) | 3 | 128 | Yes | 0.1 | [VMware Open Instruct](https://huggingface.co/datasets/VMware/open-instruct/viewer/) | 4096 | 48.26 GB | No | 3-bit, with group size 128g and act-order. Higher quality than 128g-False. |
 <!-- README_GPTQ.md-provided-files end -->

 | Branch | Bits | GS | Act Order | Damp % | GPTQ Dataset | Seq Len | Size | ExLlama | Desc |
 | ------ | ---- | -- | --------- | ------ | ------------ | ------- | ---- | ------- | ---- |
+| [main](https://huggingface.co/TheBloke/MegaDolphin-120b-GPTQ/tree/main) | 4 | None | Yes | 0.1 | [VMware Open Instruct](https://huggingface.co/datasets/VMware/open-instruct/viewer/) | 4096 | 48.99 GB | Yes | 4-bit, with Act Order. No group size, to lower VRAM requirements. |
+| [gptq-4bit-128g-actorder_True](https://huggingface.co/TheBloke/MegaDolphin-120b-GPTQ/tree/gptq-4bit-128g-actorder_True) | 4 | 128 | Yes | 0.1 | [VMware Open Instruct](https://huggingface.co/datasets/VMware/open-instruct/viewer/) | 4096 | 48.91 GB | Yes | 4-bit, with Act Order and group size 128g. Uses even less VRAM than 64g, but with slightly lower accuracy. |
 | [gptq-3bit--1g-actorder_True](https://huggingface.co/TheBloke/MegaDolphin-120b-GPTQ/tree/gptq-3bit--1g-actorder_True) | 3 | None | Yes | 0.1 | [VMware Open Instruct](https://huggingface.co/datasets/VMware/open-instruct/viewer/) | 4096 | 46.07 GB | No | 3-bit, with Act Order and no group size. Lowest possible VRAM requirements. May be lower quality than 3-bit 128g. |
+| [gptq-3bit-128g-actorder_True](https://huggingface.co/TheBloke/MegaDolphin-120b-GPTQ/tree/gptq-3bit-128g-actorder_True) | 3 | 128 | Yes | 0.1 | [VMware Open Instruct](https://huggingface.co/datasets/VMware/open-instruct/viewer/) | 4096 | 48.26 GB | No | 3-bit, with group size 128g and act-order. Higher quality than 128g-False. |
+| [gptq-8bit--1g-actorder_True](https://huggingface.co/TheBloke/MegaDolphin-120b-GPTQ/tree/gptq-8bit--1g-actorder_True) | 8 | None | Yes | 0.1 | [VMware Open Instruct](https://huggingface.co/datasets/VMware/open-instruct/viewer/) | 4096 | 48.87 GB | No | 8-bit, with Act Order. No group size, to lower VRAM requirements. |
+| [gptq-8bit-128g-actorder_True](https://huggingface.co/TheBloke/MegaDolphin-120b-GPTQ/tree/gptq-8bit-128g-actorder_True) | 8 | 128 | Yes | 0.1 | [VMware Open Instruct](https://huggingface.co/datasets/VMware/open-instruct/viewer/) | 4096 | 48.87 GB | No | 8-bit, with group size 128g for higher inference quality and with Act Order for even higher accuracy. |
 <!-- README_GPTQ.md-provided-files end -->