---
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](https://huggingface.co/allenai/SERA-32B-GA), produced with [llmcompressor](https://github.com/vllm-project/llm-compressor) 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

```python
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.

## Related

- Base model: [allenai/SERA-32B-GA](https://huggingface.co/allenai/SERA-32B-GA)
- Quantization tooling: [vllm-project/llm-compressor](https://github.com/vllm-project/llm-compressor)