Instructions to use TheBloke/AquilaChat2-34B-AWQ with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TheBloke/AquilaChat2-34B-AWQ with Transformers:

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

pipe = pipeline("text-generation", model="TheBloke/AquilaChat2-34B-AWQ", trust_remote_code=True, device_map="auto")

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("TheBloke/AquilaChat2-34B-AWQ", trust_remote_code=True, dtype="auto", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use TheBloke/AquilaChat2-34B-AWQ with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "TheBloke/AquilaChat2-34B-AWQ"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "TheBloke/AquilaChat2-34B-AWQ",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/TheBloke/AquilaChat2-34B-AWQ

SGLang

How to use TheBloke/AquilaChat2-34B-AWQ 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/AquilaChat2-34B-AWQ" \
    --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/AquilaChat2-34B-AWQ",
		"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/AquilaChat2-34B-AWQ" \
        --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/AquilaChat2-34B-AWQ",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use TheBloke/AquilaChat2-34B-AWQ with Docker Model Runner:
```
docker model run hf.co/TheBloke/AquilaChat2-34B-AWQ
```

FileNotFoundError - the tokenizer.model file could not be found

by goodromka - opened Nov 13, 2023

Discussion

goodromka

Nov 13, 2023

Thank you for providing the gguf version of the model. I followed your suggestion and utilized make-ggml.py as instructed earlier. However, I encountered an error: FileNotFoundError - the tokenizer.model file could not be found. It seems that this file is not present in their directory. Can you confirm if you used the same make-ggml.py script as previously recommended? If affirmative, could you please specify where you obtained the tokenizer.model file?

TheBloke

Owner Nov 13, 2023

This model uses a different tokenizer format, without tokenizer.model. Pass --vocabtype bpe to convert.py and it should work to make the FP16, from which you can make quantisations as usual.

Or just use my GGUFs? Or are you trying to make GGUF of an AquilaChat fine tune?

goodromka

Nov 15, 2023

I would like to express my appreciation for your advice. I successfully quantized my fine-tuned AquilaChat model using --vocabtype bpe.

goodromka changed discussion status to closed Nov 15, 2023

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