Instructions to use FPHam/Reverso_Expanded_13b_Q_Generator_GPTQ with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use FPHam/Reverso_Expanded_13b_Q_Generator_GPTQ with Transformers:

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

pipe = pipeline("text-generation", model="FPHam/Reverso_Expanded_13b_Q_Generator_GPTQ")

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

tokenizer = AutoTokenizer.from_pretrained("FPHam/Reverso_Expanded_13b_Q_Generator_GPTQ")
model = AutoModelForCausalLM.from_pretrained("FPHam/Reverso_Expanded_13b_Q_Generator_GPTQ", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use FPHam/Reverso_Expanded_13b_Q_Generator_GPTQ with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "FPHam/Reverso_Expanded_13b_Q_Generator_GPTQ"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "FPHam/Reverso_Expanded_13b_Q_Generator_GPTQ",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/FPHam/Reverso_Expanded_13b_Q_Generator_GPTQ

SGLang

How to use FPHam/Reverso_Expanded_13b_Q_Generator_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 "FPHam/Reverso_Expanded_13b_Q_Generator_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": "FPHam/Reverso_Expanded_13b_Q_Generator_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 "FPHam/Reverso_Expanded_13b_Q_Generator_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": "FPHam/Reverso_Expanded_13b_Q_Generator_GPTQ",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use FPHam/Reverso_Expanded_13b_Q_Generator_GPTQ with Docker Model Runner:
```
docker model run hf.co/FPHam/Reverso_Expanded_13b_Q_Generator_GPTQ
```

FPHam commited on Oct 30, 2023

Commit

a34c8ed

1 Parent(s): ec2fd5a

Update README.md

Browse files

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -22,9 +22,9 @@ tags:
 Reversing soon
-As you can guess from the size of the moustache the Reverso Expanded has much wider reach with his questions.
-The original Reverso was finetuned to generate mostly "What...?" type question, Reverso Expanded asks many other more detailed questions (such as Explain..., Write...., Provide..., What if..., Let's say...)
 There are pluses and minuses to this. Reverso Expanded has more refined question asking capabilities (just try it, you'd be SHOCKED), but also understands if something is just a prose without much of any aim and can resort to "Write a long and boring article", which isn't really a question. His pal, Reverso with shorter moustache is forced to ask "What...?" questions, and it will try to apply it to prose as well.

 Reversing soon
+As you can guess from the size of the moustache Reverso Expanded has much wider reach with his questions.
+The original [Reverso](https://huggingface.co/FPHam/Reverso_13b_Q_Generator_GPTQ) was finetuned to generate mostly "What...?" type question, Reverso Expanded asks many other more detailed questions (such as Explain..., Write...., Provide..., What if..., Let's say...)
 There are pluses and minuses to this. Reverso Expanded has more refined question asking capabilities (just try it, you'd be SHOCKED), but also understands if something is just a prose without much of any aim and can resort to "Write a long and boring article", which isn't really a question. His pal, Reverso with shorter moustache is forced to ask "What...?" questions, and it will try to apply it to prose as well.