初始化项目，由ModelHub XC社区提供模型

Model: amd/PARD-Llama-3.2-1B
Source: Original Platform

.gitattributes

@@ -0,0 +1,36 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,64 @@
+---
+license: mit
+pipeline_tag: text-generation
+library_name: transformers
+---
+
+<img src="https://cdn-uploads.huggingface.co/production/uploads/66a056d0229269a861ac1245/UmJOD5HnhCfvy3nAXgxgE.png" alt="PARD" width="100" align="left">
+<div align="center">
+<h1>PARD: Accelerating LLM Inference with Low-Cost PARallel Draft Model Adaptation</h1>
+</div>
+
+
+<p align="center"> |
+<a href="https://arxiv.org/abs/2504.18583"><b>Paper</b></a> |
+<a href="https://github.com/AMD-AIG-AIMA/PARD"><b>Github</b></a> |
+<a href="https://www.amd.com/en/developer/resources/technical-articles/accelerating-generative-llms-interface-with-parallel-draft-model-pard.html"><b>Blog</b></a> |
+</p>
+
+
+
+## Introduction
+
+PARD is a high-performance speculative decoding method that also enables low-cost adaptation of autoregressive draft models into parallel draft models. It offers the following advantages:
+
+- **Low-Cost Training**: PARD adapts AR (autoregressive) draft models into parallel draft models with minimal overhead. Compared to pure AR draft models, PARD achieves an average inference speedup of 1.78×. By introducing a conditional drop-token strategy, PARD improves training efficiency by up to 3× while maintaining the same level of accuracy.
+
+- **Generalizability**: Thanks to its target-independent design, a single PARD draft model can accelerate an entire family of target models. This contrasts with target-dependent approaches such as Medusa and EAGLE, which require retraining or tuning for each new target. As a result, PARD significantly reduces both deployment complexity and adaptation cost.
+
+- **High Performance**: When integrated into an optimized inference framework called Transformers+ PARD delivers up to a 4.08× speedup, with LLaMA3.1 8B reaches a state-of-the-art 311.5 tokens per second. When integrated into vLLM, PARD delivers up to 3.06× speedup, outperforming other speculative decoding methods in vLLM by 1.51×.
+
+
+<p align="center">
+  <figure style="display: inline-block; text-align: center;">
+    <img src="https://cdn-uploads.huggingface.co/production/uploads/630cb01cc169245d78fe76b6/Dh-7wE-l0YAfU9lXWssKf.png" width="100%">
+    <figcaption style="font-style: italic; margin-top: 2px;">
+      AR and AR+ represent baseline auto-regressive generation using Transformers and Transformers+, respectively. VSD denotes vanilla speculative decoding. PARD refers to the proposed method in this work.
+    </figcaption>
+  </figure>
+</p>
+
+
+## Model Weights
+
+| Model Series | Model Name                            | Download      |
+|--------------|---------------------------------------|---------------|
+| llama3       | PARD-Llama-3.2-1B                     | [🤗 HuggingFace](https://huggingface.co/amd/PARD-Llama-3.2-1B)  |
+| DSR Qwen     | PARD-DeepSeek-R1-Distill-Qwen-1.5B    | [🤗 HuggingFace](https://huggingface.co/amd/PARD-DeepSeek-R1-Distill-Qwen-1.5B) |
+| Qwen         | PARD-Qwen2.5-0.5B                     | [🤗 HuggingFace](https://huggingface.co/amd/PARD-Qwen2.5-0.5B) |
+
+
+## How To Use
+
+Please visit [PARD](https://github.com/AMD-AIG-AIMA/PARD) repo for more information
+
+
+## Citation
+```
+@article{an2025pard,
+  title={PARD: Accelerating LLM Inference with Low-Cost PARallel Draft Model Adaptation},
+  author={An, Zihao and Bai, Huajun and Liu, Ziqiong and Li, Dong and Barsoum, Emad},
+  journal={arXiv preprint arXiv:2504.18583},
+  year={2025}
+}
+```

config.json

@@ -0,0 +1,41 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "spd_type": "pard",
+  "pard_token": 128020,
+  "num_attention_heads": 32,
+  "num_hidden_layers": 16,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 32.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.48.2",
+  "use_cache": true,
+  "vocab_size": 128256
+}

generation_config.json

@@ -0,0 +1,12 @@
+{
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.48.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b2bd0d8c996a5678e65506c5c164d270e6510bbb5596801eb1daa7b70d73ad3
+size 2996982344

special_tokens_map.json

@@ -0,0 +1,17 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|eot_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|eot_id|>"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c85066e7642934ed09b44155e6566b0b5dab2637fb9433439ba5c9c7f8b50d3
+size 17210018