Not-For-All-Audiences

Instructions to use TheBloke/Spicyboros-13B-2.2-GPTQ with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TheBloke/Spicyboros-13B-2.2-GPTQ with Transformers:

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

pipe = pipeline("text-generation", model="TheBloke/Spicyboros-13B-2.2-GPTQ")

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("TheBloke/Spicyboros-13B-2.2-GPTQ")
model = AutoModelForMultimodalLM.from_pretrained("TheBloke/Spicyboros-13B-2.2-GPTQ")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use TheBloke/Spicyboros-13B-2.2-GPTQ with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "TheBloke/Spicyboros-13B-2.2-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/Spicyboros-13B-2.2-GPTQ",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/TheBloke/Spicyboros-13B-2.2-GPTQ

SGLang

How to use TheBloke/Spicyboros-13B-2.2-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/Spicyboros-13B-2.2-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/Spicyboros-13B-2.2-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/Spicyboros-13B-2.2-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/Spicyboros-13B-2.2-GPTQ",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use TheBloke/Spicyboros-13B-2.2-GPTQ with Docker Model Runner:
```
docker model run hf.co/TheBloke/Spicyboros-13B-2.2-GPTQ
```

TheBloke commited on Sep 27, 2023

Commit

a98140d

1 Parent(s): 5a1cc8c

Update base_model formatting

Browse files

Files changed (1) hide show

README.md +5 -5

README.md CHANGED Viewed

@@ -1,16 +1,16 @@
 ---
-base_model: https://huggingface.co/jondurbin/spicyboros-13b-2.2
 datasets:
 - jondurbin/airoboros-2.2
 inference: false
-license: llama2
 model_creator: Jon Durbin
-model_name: Spicyboros 13B 2.2
 model_type: llama
 prompt_template: "A chat.\nUSER: {prompt}\nASSISTANT: \n"
 quantized_by: TheBloke
-tags:
-- not-for-all-audiences
 ---
 <!-- header start -->

 ---
+license: llama2
+tags:
+- not-for-all-audiences
 datasets:
 - jondurbin/airoboros-2.2
+model_name: Spicyboros 13B 2.2
+base_model: jondurbin/spicyboros-13b-2.2
 inference: false
 model_creator: Jon Durbin
 model_type: llama
 prompt_template: "A chat.\nUSER: {prompt}\nASSISTANT: \n"
 quantized_by: TheBloke
 ---
 <!-- header start -->