Instructions to use Model-SafeTensors/airoboros-l2-13b-gpt4-m2.0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Model-SafeTensors/airoboros-l2-13b-gpt4-m2.0 with Transformers:

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

pipe = pipeline("text-generation", model="Model-SafeTensors/airoboros-l2-13b-gpt4-m2.0")

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

tokenizer = AutoTokenizer.from_pretrained("Model-SafeTensors/airoboros-l2-13b-gpt4-m2.0")
model = AutoModelForCausalLM.from_pretrained("Model-SafeTensors/airoboros-l2-13b-gpt4-m2.0", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Model-SafeTensors/airoboros-l2-13b-gpt4-m2.0 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Model-SafeTensors/airoboros-l2-13b-gpt4-m2.0"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Model-SafeTensors/airoboros-l2-13b-gpt4-m2.0",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Model-SafeTensors/airoboros-l2-13b-gpt4-m2.0

SGLang

How to use Model-SafeTensors/airoboros-l2-13b-gpt4-m2.0 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 "Model-SafeTensors/airoboros-l2-13b-gpt4-m2.0" \
    --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": "Model-SafeTensors/airoboros-l2-13b-gpt4-m2.0",
		"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 "Model-SafeTensors/airoboros-l2-13b-gpt4-m2.0" \
        --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": "Model-SafeTensors/airoboros-l2-13b-gpt4-m2.0",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Model-SafeTensors/airoboros-l2-13b-gpt4-m2.0 with Docker Model Runner:
```
docker model run hf.co/Model-SafeTensors/airoboros-l2-13b-gpt4-m2.0
```

jondurbin commited on Aug 1, 2023

Commit

8ca1d8d

1 Parent(s): 01c41dc

Update README.md

Browse files

Files changed (1) hide show

README.md +11 -0

README.md CHANGED Viewed

@@ -295,6 +295,17 @@ def parse_plan(plan):
         context[parts.group(1)] = method_map[parts.group(2)](parts.group(3), **context)
 ```
 ### Licence and usage restrictions
 The airoboros 2.0/m2.0 models are built on top of either llama or llama-2.  Any model with `-l2-` in the name uses llama2, `..-33b-...` and `...-65b-...` are based on the original llama.

         context[parts.group(1)] = method_map[parts.group(2)](parts.group(3), **context)
 ```
+### Contribute
+If you're interested in new functionality, particularly a new "instructor" type to generate a specific type of training data,
+take a look at the dataset generation tool repo: https://github.com/jondurbin/airoboros and either make a PR or open an issue with details.
+To help me with the OpenAI/compute costs:
+- https://bmc.link/jondurbin
+- ETH 0xce914eAFC2fe52FdceE59565Dd92c06f776fcb11
+- BTC bc1qdwuth4vlg8x37ggntlxu5cjfwgmdy5zaa7pswf
 ### Licence and usage restrictions
 The airoboros 2.0/m2.0 models are built on top of either llama or llama-2.  Any model with `-l2-` in the name uses llama2, `..-33b-...` and `...-65b-...` are based on the original llama.