Instructions to use lloorree/mythxl-70b-gptq with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use lloorree/mythxl-70b-gptq with Transformers:

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

pipe = pipeline("text-generation", model="lloorree/mythxl-70b-gptq")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("lloorree/mythxl-70b-gptq")
model = AutoModelForCausalLM.from_pretrained("lloorree/mythxl-70b-gptq", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use lloorree/mythxl-70b-gptq with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "lloorree/mythxl-70b-gptq"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "lloorree/mythxl-70b-gptq",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/lloorree/mythxl-70b-gptq

SGLang

How to use lloorree/mythxl-70b-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 "lloorree/mythxl-70b-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": "lloorree/mythxl-70b-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 "lloorree/mythxl-70b-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": "lloorree/mythxl-70b-gptq",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use lloorree/mythxl-70b-gptq with Docker Model Runner:
```
docker model run hf.co/lloorree/mythxl-70b-gptq
```

lloorree commited on Sep 17, 2023

Commit

9b69de4

1 Parent(s): ab19a77

Update README.md

Browse files

Files changed (1) hide show

README.md +2 -0

README.md CHANGED Viewed

@@ -10,6 +10,8 @@ Differences:
 - Includes a 70B recreation of SuperCOT as in the 1.2 version of Huginn
 - Anywhere Airoboros is merged in, the 1.4.1 version was used instead of 2.X
 License is strictly noncommercial, both to match that of its major dependency [Chronos 70B](https://huggingface.co/elinas/chronos-70b-v2) and in its own right.
 ## Prompt Format (Copied from the MythoMax page, not necessarily optimal)

 - Includes a 70B recreation of SuperCOT as in the 1.2 version of Huginn
 - Anywhere Airoboros is merged in, the 1.4.1 version was used instead of 2.X
+Known limitation: it *strongly* prefers novel format in roleplay, and will revert to it over time regardless of context or conversation history.
 License is strictly noncommercial, both to match that of its major dependency [Chronos 70B](https://huggingface.co/elinas/chronos-70b-v2) and in its own right.
 ## Prompt Format (Copied from the MythoMax page, not necessarily optimal)