Update README.md
Browse files
README.md
CHANGED
@@ -15,7 +15,7 @@ tags:
|
|
15 |
Qwen2-0.5B-Instruct quantized to FP8 weights and activations using per-tensor quantization through the AutoFP8 repository, ready for inference with vLLM >= 0.5.0.
|
16 |
Calibrated with 512 UltraChat samples to achieve 100% performance recovery on the Open LLM Benchmark evaluations.
|
17 |
Reduces space on disk by ~30%.
|
18 |
-
Part of the FP8 LLMs for vLLM collection.
|
19 |
|
20 |
## Usage and Creation
|
21 |
Produced using [AutoFP8 with calibration samples from ultrachat](https://github.com/neuralmagic/AutoFP8/blob/147fa4d9e1a90ef8a93f96fc7d9c33056ddc017a/example_dataset.py).
|
|
|
15 |
Qwen2-0.5B-Instruct quantized to FP8 weights and activations using per-tensor quantization through the AutoFP8 repository, ready for inference with vLLM >= 0.5.0.
|
16 |
Calibrated with 512 UltraChat samples to achieve 100% performance recovery on the Open LLM Benchmark evaluations.
|
17 |
Reduces space on disk by ~30%.
|
18 |
+
Part of the [FP8 LLMs for vLLM collection](https://huggingface.co/collections/neuralmagic/fp8-llms-for-vllm-666742ed2b78b7ac8df13127).
|
19 |
|
20 |
## Usage and Creation
|
21 |
Produced using [AutoFP8 with calibration samples from ultrachat](https://github.com/neuralmagic/AutoFP8/blob/147fa4d9e1a90ef8a93f96fc7d9c33056ddc017a/example_dataset.py).
|