Instructions to use neuronpedia-org/nla-gemma3-27b-av-FP8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use neuronpedia-org/nla-gemma3-27b-av-FP8 with Transformers:

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

pipe = pipeline("text-generation", model="neuronpedia-org/nla-gemma3-27b-av-FP8")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("neuronpedia-org/nla-gemma3-27b-av-FP8")
model = AutoModelForCausalLM.from_pretrained("neuronpedia-org/nla-gemma3-27b-av-FP8")
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]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use neuronpedia-org/nla-gemma3-27b-av-FP8 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "neuronpedia-org/nla-gemma3-27b-av-FP8"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "neuronpedia-org/nla-gemma3-27b-av-FP8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/neuronpedia-org/nla-gemma3-27b-av-FP8

SGLang

How to use neuronpedia-org/nla-gemma3-27b-av-FP8 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 "neuronpedia-org/nla-gemma3-27b-av-FP8" \
    --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": "neuronpedia-org/nla-gemma3-27b-av-FP8",
		"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 "neuronpedia-org/nla-gemma3-27b-av-FP8" \
        --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": "neuronpedia-org/nla-gemma3-27b-av-FP8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use neuronpedia-org/nla-gemma3-27b-av-FP8 with Docker Model Runner:
```
docker model run hf.co/neuronpedia-org/nla-gemma3-27b-av-FP8
```

kitft/nla-gemma3-27b-av (FP8, compressed-tensors)

NLA action verbalizer with FP8_DYNAMIC weight-only FP8 quantization via llmcompressor. Saved in compressed-tensors format with FP8 weights (*.safetensors) and quantization_config in config.json, so sgl.Engine loads it directly with no bf16 staging transient.

FP8_DYNAMIC quantization on every nn.Linear weight in the backbone (lm_head is NOT quantized — output projection numerics matter).
All upstream files (nla_meta.yaml, prompt templates, model card, license, generation config, tokenizer extras, …) are preserved verbatim. The upstream README.md is renamed to README_upstream.md.

Usage with `apps/nla/server.py`

export NLA_VERBALIZER_MODEL=<this repo>
export NLA_VERBALIZER_QUANTIZATION=compressed-tensors
# Do NOT set NLA_FP8_VERBALIZER — it is overridden by the explicit
# --verbalizer-quantization (or NLA_VERBALIZER_QUANTIZATION) anyway.
uv run server.py --truncate-source --fp8-source --int4-reconstructor

apps/nla/server.py will pass quantization="compressed-tensors" to sgl.Engine, which loads the pre-quantized FP8 weights with no bf16 load-time peak. See the apps/nla README's "Multi-GPU > Layout E" for the full per-GPU memory budget.

Comparison vs `apps/nla/build_quantized_models.py --target verbalizer-fp8`

That sibling script uses torchao (AffineQuantizedTensor-backed) FP8. Sglang 0.5.x has no "torchao" entry in its quantization registry, so that output is not loadable by apps/nla/server.py. Use this checkpoint for the sglang verbalizer; reserve the torchao path for the HF source/reconstructor (which transformers consumes natively).

Downloads last month: 7

Safetensors

Model size

27B params

Tensor type

BF16

F8_E4M3

Model tree for neuronpedia-org/nla-gemma3-27b-av-FP8

Base model

google/gemma-3-27b-pt

Finetuned

google/gemma-3-27b-it

Finetuned

kitft/nla-gemma3-27b-L41-av

Quantized

(1)

this model

kitft/nla-gemma3-27b-av (FP8, compressed-tensors)

Usage with apps/nla/server.py

Comparison vs apps/nla/build_quantized_models.py --target verbalizer-fp8

Model tree for neuronpedia-org/nla-gemma3-27b-av-FP8

Usage with `apps/nla/server.py`

Comparison vs `apps/nla/build_quantized_models.py --target verbalizer-fp8`