Instructions to use PanocularAI/PanoLM-380M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use PanocularAI/PanoLM-380M with Transformers:

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

pipe = pipeline("text-generation", model="PanocularAI/PanoLM-380M", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("PanocularAI/PanoLM-380M", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use PanocularAI/PanoLM-380M with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "PanocularAI/PanoLM-380M"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "PanocularAI/PanoLM-380M",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/PanocularAI/PanoLM-380M

SGLang

How to use PanocularAI/PanoLM-380M 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 "PanocularAI/PanoLM-380M" \
    --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": "PanocularAI/PanoLM-380M",
		"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 "PanocularAI/PanoLM-380M" \
        --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": "PanocularAI/PanoLM-380M",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use PanocularAI/PanoLM-380M with Docker Model Runner:
```
docker model run hf.co/PanocularAI/PanoLM-380M
```

PanoLM-380M / README.md

aryamazaheri

Update README.md

78ddc7c verified about 1 month ago

preview code

Raw

History Blame Contribute Delete

2.58 kB

metadata

library_name: transformers
license: apache-2.0
language:
  - en
pipeline_tag: text-generation
tags:
  - panolm
  - linear-attention

PanoLM-380M

This repo contains the base 380M PanoLM model, which is a linear-attention causal language.

Training Data

Pretrained on a weighted mixture of three web-scale English corpora:

Weight	Dataset
0.45	FineWeb-Edu (100B-token subset)
0.30	DCLM (100B-token subset)
0.25	FinePDFs-Edu (100B-token subset)

Requirements

torch==2.12.0
transformers==5.8.1
flash-linear-attention==0.5.0

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained(
    "PanocularAI/PanoLM-380M",
    trust_remote_code=True,
).cuda()  # fla's RMSNorm uses Triton kernels that only run on CUDA tensors.
print(model)
tokenizer = AutoTokenizer.from_pretrained(repo_id, trust_remote_code=True)

prompt = "I am PanoLM, an edge device friendly language model."
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
# use_cache=False: HF's generate() would pass a DynamicCache that fla's KDA
# layer indexes as a list, which the new transformers API no longer supports.
outputs = model.generate(
    **inputs,
    max_length=512,
    top_k=10,
    use_cache=False,
    do_sample=True,
    trust_remote_code=True,
)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Evaluation

All scores are 0-shot, evaluated with lm-evaluation-harness. For multi-choice tasks we report length-normalized accuracy (acc_norm); for Based-suite recall tasks we report contains (soft answer match), which is the metric the suite was designed around.

Commonsense reasoning & general QA

Task	Metric	Value	Stderr
arc_challenge	acc_norm	0.2910	± 0.0133
arc_easy	acc_norm	0.5349	± 0.0102
commonsense_qa	acc	0.1892	± 0.0112
hellaswag	acc_norm	0.4137	± 0.0049
piqa	acc_norm	0.6741	± 0.0109
winogrande	acc	0.5304	± 0.0140

Associative recall (Based suite)

Task	Metric	Value
drop	contains	0.2286
fda	contains	0.0499
nq_2048	contains	0.0687
squadv2	contains	0.3542
swde	contains	0.2439
triviaqa	contains	0.4680