Instructions to use bluetrace/SERA-32B-GA-FP8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use bluetrace/SERA-32B-GA-FP8 with Transformers:

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

pipe = pipeline("text-generation", model="bluetrace/SERA-32B-GA-FP8")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("bluetrace/SERA-32B-GA-FP8")
model = AutoModelForCausalLM.from_pretrained("bluetrace/SERA-32B-GA-FP8", 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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use bluetrace/SERA-32B-GA-FP8 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "bluetrace/SERA-32B-GA-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": "bluetrace/SERA-32B-GA-FP8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/bluetrace/SERA-32B-GA-FP8

SGLang

How to use bluetrace/SERA-32B-GA-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 "bluetrace/SERA-32B-GA-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": "bluetrace/SERA-32B-GA-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 "bluetrace/SERA-32B-GA-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": "bluetrace/SERA-32B-GA-FP8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use bluetrace/SERA-32B-GA-FP8 with Docker Model Runner:
```
docker model run hf.co/bluetrace/SERA-32B-GA-FP8
```

SERA-32B-GA-FP8 / README.md

ikarabulut-dev

Update README.md

c5c9027 verified 7 months ago

preview code

Raw History Blame Contribute Delete

2.45 kB

metadata

base_model: allenai/SERA-32B-GA
base_model_relation: quantized
pipeline_tag: text-generation
library_name: transformers
language:
  - en
license: mit
tags:
  - fp8
  - quantized
  - llmcompressor
  - vllm
datasets:
  - allenai/Sera-4.5A-Lite-T2

SERA-32B-GA-FP8

FP8 quantization of allenai/SERA-32B-GA, produced with llmcompressor and validated with vLLM.

Quantization Details

Parameter	Value
Method	FP8 (W8A8) via `llmcompressor` `oneshot`
Targets	All `Linear` layers except `lm_head`
Calibration dataset	`allenai/Sera-4.5A-Lite-T2`
Calibration samples	512
Calibration sequence length	2048 tokens
llmcompressor version	0.9.0.2
Hardware	AWS g6e.4xlarge (NVIDIA L40S, 48 GB VRAM)
Model size (uploaded)	~31.7 GB (7 safetensors shards)

The quantization pipeline processes one decoder layer at a time (pipeline="sequential") and offloads activations to CPU between layers, allowing 32B+ models to be quantized on a single GPU without OOM.

GPU Stats

1x L40 (g6e.xlarge)
Total time: 1 hr

Usage

from vllm import LLM, SamplingParams

llm = LLM(model="ikarabulut-dev/SERA-32B-GA-FP8", max_model_len=16384)
params = SamplingParams(temperature=0.7, max_tokens=512)

outputs = llm.generate(
    [{"role": "user", "content": "Explain quantum entanglement simply."}],
    params,
)
print(outputs[0].outputs[0].text)

Note: This model was validated with --max-model-len 16384. Attempting a larger context on a single 48 GB GPU may OOM.

Validation

After quantization the model was loaded into vLLM and a test chat completion request was sent. The model became healthy in ~120 seconds and produced a well-formed thinking-style response — validation passed.

Limitations

Quality degradation relative to the BF16 base model has not been formally benchmarked. FP8 quantization with 512 calibration samples is generally low-loss for instruction-tuned models, but edge cases may differ.
Maximum recommended context length is 16 384 tokens on a single L40S GPU.
The lm_head layer is kept in BF16 (not quantized) to preserve output distribution.

Base model: allenai/SERA-32B-GA
Quantization tooling: vllm-project/llm-compressor

bluetrace
/

SERA-32B-GA-FP8