Instructions to use Naphula/Ancient-Awakening-12B-MPOA with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Naphula/Ancient-Awakening-12B-MPOA with Transformers:

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

pipe = pipeline("text-generation", model="Naphula/Ancient-Awakening-12B-MPOA")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Naphula/Ancient-Awakening-12B-MPOA")
model = AutoModelForCausalLM.from_pretrained("Naphula/Ancient-Awakening-12B-MPOA", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

NeMo
How to use Naphula/Ancient-Awakening-12B-MPOA with NeMo:
```
# tag did not correspond to a valid NeMo domain.
```
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Naphula/Ancient-Awakening-12B-MPOA with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Naphula/Ancient-Awakening-12B-MPOA"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Naphula/Ancient-Awakening-12B-MPOA",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Naphula/Ancient-Awakening-12B-MPOA

SGLang

How to use Naphula/Ancient-Awakening-12B-MPOA 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 "Naphula/Ancient-Awakening-12B-MPOA" \
    --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": "Naphula/Ancient-Awakening-12B-MPOA",
		"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 "Naphula/Ancient-Awakening-12B-MPOA" \
        --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": "Naphula/Ancient-Awakening-12B-MPOA",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Naphula/Ancient-Awakening-12B-MPOA with Docker Model Runner:
```
docker model run hf.co/Naphula/Ancient-Awakening-12B-MPOA
```

Can we get the rest of the static quants?

by HottyYoungThug - opened Mar 22

Discussion

HottyYoungThug

Mar 22

Wanna some i1-Q4_K_M -_-

Naphula

Owner Mar 22

Yeah I can try to add these later unless @mradermacher is able to

HottyYoungThug

Mar 22

Ohh, shish, I forgot that you just recently released this model and mradermacher hasn't done his masterwork yet. Sorry!

shrimpfriedrice-bricks

Mar 22

This one and Riemannian Redshift too. Though I suppose nobody filed a request to mradermacher, so that's why. But quants would be appreciated, if possible.

Naphula

Owner Mar 24

•

edited Mar 26

imatrix will take longer but I can get some regular quants up soon

added these to the upload queue

    echo hf upload Naphula/Ancient-Awakening-12B-GGUF B:\12B\models--Naphula--Ancient-Awakening-12B\Ancient-Awakening-12B-Q2_K.gguf
    echo hf upload Naphula/Ancient-Awakening-12B-GGUF B:\12B\models--Naphula--Ancient-Awakening-12B\Ancient-Awakening-12B-Q3_K_M.gguf
    echo hf upload Naphula/Ancient-Awakening-12B-GGUF B:\12B\models--Naphula--Ancient-Awakening-12B\Ancient-Awakening-12B-Q4_K_M.gguf
    echo hf upload Naphula/Ancient-Awakening-12B-GGUF B:\12B\models--Naphula--Ancient-Awakening-12B\Ancient-Awakening-12B-Q5_K_M.gguf
    
    echo hf upload Naphula/Ancient-Awakening-12B-MPOA-GGUF B:\12B\models--Naphula--Ancient-Awakening-12B-MPOA\Ancient-Awakening-12B-MPOA-Q2_K.gguf
    echo hf upload Naphula/Ancient-Awakening-12B-MPOA-GGUF B:\12B\models--Naphula--Ancient-Awakening-12B-MPOA\Ancient-Awakening-12B-MPOA-Q3_K_M.gguf
    echo hf upload Naphula/Ancient-Awakening-12B-MPOA-GGUF B:\12B\models--Naphula--Ancient-Awakening-12B-MPOA\Ancient-Awakening-12B-MPOA-Q4_K_M.gguf
    echo hf upload Naphula/Ancient-Awakening-12B-MPOA-GGUF B:\12B\models--Naphula--Ancient-Awakening-12B-MPOA\Ancient-Awakening-12B-MPOA-Q5_K_M.gguf
    
    echo hf upload Naphula/Riemannian-Redshift-12B-v1-GGUF B:\12B\models--Naphula--Riemannian-Redshift-12B-v1\Riemannian-Redshift-12B-v1-Q2_K.gguf
    echo hf upload Naphula/Riemannian-Redshift-12B-v1-GGUF B:\12B\models--Naphula--Riemannian-Redshift-12B-v1\Riemannian-Redshift-12B-v1-Q3_K_M.gguf
    echo hf upload Naphula/Riemannian-Redshift-12B-v1-GGUF B:\12B\models--Naphula--Riemannian-Redshift-12B-v1\Riemannian-Redshift-12B-v1-Q4_K_M.gguf
    echo hf upload Naphula/Riemannian-Redshift-12B-v1-GGUF B:\12B\models--Naphula--Riemannian-Redshift-12B-v1\Riemannian-Redshift-12B-v1-Q5_K_M.gguf

Updated conversion sequence for Redshift

python convert_hf_to_gguf.py B:\12B\models--Naphula--Riemannian-Redshift-12B-v1 --outfile B:\12B\models--Naphula--Riemannian-Redshift-12B-v1\RR_input.gguf --outtype bf16
llama-quantize B:\12B\models--Naphula--Riemannian-Redshift-12B-v1\RR_input.gguf B:\12B\models--Naphula--Riemannian-Redshift-12B-v1\Riemannian-Redshift-12B-v1-Q5_K_M.gguf Q5_K_M
llama-quantize B:\12B\models--Naphula--Riemannian-Redshift-12B-v1\RR_input.gguf B:\12B\models--Naphula--Riemannian-Redshift-12B-v1\Riemannian-Redshift-12B-v1-Q4_K_M.gguf Q4_K_M
llama-quantize B:\12B\models--Naphula--Riemannian-Redshift-12B-v1\RR_input.gguf B:\12B\models--Naphula--Riemannian-Redshift-12B-v1\Riemannian-Redshift-12B-v1-Q3_K_M.gguf Q3_K_M
llama-quantize B:\12B\models--Naphula--Riemannian-Redshift-12B-v1\RR_input.gguf B:\12B\models--Naphula--Riemannian-Redshift-12B-v1\Riemannian-Redshift-12B-v1-Q2_K.gguf Q2_K
llama-quantize B:\12B\models--Naphula--Riemannian-Redshift-12B-v1\RR_input.gguf B:\12B\models--Naphula--Riemannian-Redshift-12B-v1\Riemannian-Redshift-12B-v1-Q8_0.gguf Q8_0
hf upload Naphula/Riemannian-Redshift-12B-v1-GGUF B:\12B\models--Naphula--Riemannian-Redshift-12B-v1\Riemannian-Redshift-12B-v1-Q5_K_M.gguf
hf upload Naphula/Riemannian-Redshift-12B-v1-GGUF B:\12B\models--Naphula--Riemannian-Redshift-12B-v1\Riemannian-Redshift-12B-v1-Q4_K_M.gguf
hf upload Naphula/Riemannian-Redshift-12B-v1-GGUF B:\12B\models--Naphula--Riemannian-Redshift-12B-v1\Riemannian-Redshift-12B-v1-Q3_K_M.gguf
hf upload Naphula/Riemannian-Redshift-12B-v1-GGUF B:\12B\models--Naphula--Riemannian-Redshift-12B-v1\Riemannian-Redshift-12B-v1-Q2_K.gguf
hf upload Naphula/Riemannian-Redshift-12B-v1-GGUF B:\12B\models--Naphula--Riemannian-Redshift-12B-v1\Riemannian-Redshift-12B-v1-Q8_0.gguf

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