Instructions to use cutycat2000x/MeowGPT-3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use cutycat2000x/MeowGPT-3 with Transformers:

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

pipe = pipeline("text-generation", model="cutycat2000x/MeowGPT-3")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("cutycat2000x/MeowGPT-3")
model = AutoModelForCausalLM.from_pretrained("cutycat2000x/MeowGPT-3")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use cutycat2000x/MeowGPT-3 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "cutycat2000x/MeowGPT-3"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "cutycat2000x/MeowGPT-3",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/cutycat2000x/MeowGPT-3

SGLang

How to use cutycat2000x/MeowGPT-3 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 "cutycat2000x/MeowGPT-3" \
    --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": "cutycat2000x/MeowGPT-3",
		"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 "cutycat2000x/MeowGPT-3" \
        --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": "cutycat2000x/MeowGPT-3",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use cutycat2000x/MeowGPT-3 with Docker Model Runner:
```
docker model run hf.co/cutycat2000x/MeowGPT-3
```

Config

by Chickaboo - opened Mar 16, 2024

Discussion

Chickaboo

Mar 16, 2024

•

edited Mar 16, 2024

You should add a config file to the model as since there is no config it leads to many issues when trying to use the model.
You could do something like this for the config file with some of the parameters set to what MeowGPT-3's are:
{
"architectures": [
"LlamaForCausalLM"
],
"attention_bias": false,
"bos_token_id": 1,
"eos_token_id": 2,
"hidden_act": "silu",
"hidden_size": 2048,
"initializer_range": 0.02,
"intermediate_size": 5632,
"max_position_embeddings": 2048,
"model_type": "llama",
"num_attention_heads": 32,
"num_hidden_layers": 22,
"num_key_value_heads": 4,
"pretraining_tp": 1,
"rms_norm_eps": 1e-05,
"rope_scaling": null,
"rope_theta": 10000.0,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.35.0",
"use_cache": true,
"vocab_size": 32000
}

cutycat2000x

Owner Mar 16, 2024

done :)

Chickaboo

Mar 16, 2024

Thanks!

Chickaboo changed discussion status to closed Mar 16, 2024

cutycat2000x

Owner Mar 17, 2024

You're welcome

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment