Add README.md

README.md

@@ -0,0 +1,51 @@
+---
+base_model: IndexTeam/Index-Translate-9B
+library_name: transformers
+tags:
+- fp8
+- compressed-tensors
+- translation
+- index
+license: apache-2.0
+---
+
+# Index-Translate-9B-FP8
+
+Official FP8 (W8A8) quantization of [IndexTeam/Index-Translate-9B](https://huggingface.co/IndexTeam/Index-Translate-9B), part of the **Index-Translate** multilingual translation model family (150 languages, terminology/format-constrained translation, controlled dubbing translation, long-document translation).
+
+- Technical report: [Index-Translate: A Multilingual Translation Model Family](https://arxiv.org/abs/2609.40181)
+- Code: [github.com/bilibili/Index-Translate](https://github.com/bilibili/Index-Translate)
+
+## Quantization
+
+- Scheme: `FP8_DYNAMIC` (FP8 E4M3 weights, per-token dynamic FP8 activations), produced with [llm-compressor](https://github.com/vllm-project/llm-compressor) (`quantization_scheme` recorded in `recipe.yaml`).
+- All `Linear` layers of the language model are quantized; the vision tower, multi-modal projector, `lm_head`, and embeddings are kept in BF16. MTP (multi-token prediction) weights are preserved.
+- Format: [compressed-tensors](https://github.com/neuralmagic/compressed-tensors) safetensors — load directly with vLLM (`quantization="compressed-tensors"`) or transformers.
+
+## Consistency validation
+
+Measured on an NVIDIA A100 against the original BF16 checkpoint (greedy decoding, official translation prompt):
+
+| Metric | BF16 | FP8 | Delta |
+|:-------|-----:|----:|------:|
+| Perplexity (fixed corpus) | 2.7722 | 2.7838 | +0.42% |
+| zh→en generation identical | — | — | yes |
+| en→zh generation identical | — | — | yes |
+
+## Usage
+
+```bash
+vllm serve IndexTeam/Index-Translate-9B-FP8 --host 127.0.0.1 --port 8000 --max-model-len 4096
+```
+
+Translation prompt format (greedy decoding, temperature=0 recommended):
+
+```text
+请将以下文本翻译为{target-language}，直接输出翻译结果，不要进行任何解释。
+
+{source-text}
+```
+
+See the [base model card](https://huggingface.co/IndexTeam/Index-Translate-9B) for the full instTrans constrained-translation format and serving presets. GGUF builds for local inference are published in [Index-Translate-9B-GGUF](https://huggingface.co/IndexTeam/Index-Translate-9B-GGUF).
+
+*Quantized and published by the Index team, 2026-10-03.*