Upload folder using huggingface_hub

.gitattributes

@@ -1,35 +1,47 @@
-*.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
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bin.* filter=lfs diff=lfs merge=lfs -text
+*.bz2 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
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack 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
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* 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
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zstandard filter=lfs diff=lfs merge=lfs -text
+*.tfevents* filter=lfs diff=lfs merge=lfs -text
+*.db* filter=lfs diff=lfs merge=lfs -text
+*.ark* filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.gguf* filter=lfs diff=lfs merge=lfs -text
+*.ggml filter=lfs diff=lfs merge=lfs -text
+*.llamafile* filter=lfs diff=lfs merge=lfs -text
+*.pt2 filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -textimatrix_unsloth.dat filter=lfs diff=lfs merge=lfs -text

ERNIE-4.5-21B-A3B-PT-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:150e2463d7644d52ce88e116115ed1e664854edc5cbe619134793e72b019ba1d
+size 13245828608

README.md

@@ -1,3 +1,135 @@
----
-license: apache-2.0
----
+---
+base_model:
+- baidu/ERNIE-4.5-21B-A3B-PT
+license: apache-2.0
+language:
+- en
+- zh
+pipeline_tag: text-generation
+tags:
+- ERNIE4.5
+- unsloth
+library_name: transformers
+---
+
+<div align="center" style="line-height: 1;">
+  <a href="https://ernie.baidu.com/" target="_blank" style="margin: 2px;">
+    <img alt="Chat" src="https://img.shields.io/badge/🤖_Chat-ERNIE_Bot-blue" style="display: inline-block; vertical-align: middle;"/>
+  </a>
+  <a href="https://huggingface.co/baidu" target="_blank" style="margin: 2px;">
+    <img alt="Hugging Face" src="https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-Baidu-ffc107?color=ffc107&logoColor=white" style="display: inline-block; vertical-align: middle;"/>
+  </a>
+  <a href="https://github.com/PaddlePaddle/ERNIE" target="_blank" style="margin: 2px;">
+    <img alt="Github" src="https://img.shields.io/badge/GitHub-ERNIE-000?logo=github&color=0000FF" style="display: inline-block; vertical-align: middle;"/>
+  </a>
+  <a href="https://ernie.baidu.com/blog/ernie4.5" target="_blank" style="margin: 2px;">
+    <img alt="Blog" src="https://img.shields.io/badge/🖖_Blog-ERNIE4.5-A020A0" style="display: inline-block; vertical-align: middle;"/>
+  </a>
+</div>
+
+<div align="center" style="line-height: 1;">
+  <a href="#license" style="margin: 2px;">
+    <img alt="License" src="https://img.shields.io/badge/License-Apache2.0-A5de54" style="display: inline-block; vertical-align: middle;"/>
+  </a>
+</div>
+
+# ERNIE-4.5-21B
+
+> [!NOTE]
+> Note: "**-Paddle**" models use [PaddlePaddle](https://github.com/PaddlePaddle/Paddle) weights, while "**-PT**" models use Transformer-style PyTorch weights.
+
+
+## ERNIE 4.5 Highlights
+
+The advanced capabilities of the ERNIE 4.5 models, particularly the MoE-based A47B and A3B series, are underpinned by several key technical innovations:
+
+1. **Multimodal Heterogeneous MoE Pre-Training:** Our models are jointly trained on both textual and visual modalities to better capture the nuances of multimodal information and improve performance on tasks involving text understanding and generation, image understanding, and cross-modal reasoning. To achieve this without one modality hindering the learning of another, we designed a *heterogeneous MoE structure*, incorporated *modality-isolated routing*, and employed *router orthogonal loss* and *multimodal token-balanced loss*. These architectural choices ensure that both modalities are effectively represented, allowing for mutual reinforcement during training.
+
+2. **Scaling-Efficient Infrastructure:** We propose a novel heterogeneous hybrid parallelism and hierarchical load balancing strategy for efficient training of ERNIE 4.5 models. By using intra-node expert parallelism, memory-efficient pipeline scheduling, FP8 mixed-precision training and finegrained recomputation methods, we achieve remarkable pre-training throughput. For inference, we propose *multi-expert parallel collaboration* method and *convolutional code quantization* algorithm to achieve 4-bit/2-bit lossless quantization. Furthermore, we introduce PD disaggregation with dynamic role switching for effective resource utilization to enhance inference performance for ERNIE 4.5 MoE models. Built on [PaddlePaddle](https://github.com/PaddlePaddle/Paddle), ERNIE 4.5 delivers high-performance inference across a wide range of hardware platforms.
+
+3. **Modality-Specific Post-Training:** To meet the diverse requirements of real-world applications, we fine-tuned variants of the pre-trained model for specific modalities. Our LLMs are optimized for general-purpose language understanding and generation. The VLMs focuses on visuallanguage understanding and supports both thinking and non-thinking modes. Each model employed a combination of *Supervised Fine-tuning (SFT)*, *Direct Preference Optimization (DPO)* or a modified reinforcement learning method named *Unified Preference Optimization (UPO)* for post-training.
+
+## Model Overview
+
+ERNIE-4.5-21B-A3B is a text MoE Post-trained model, with 21B total parameters and 3B activated parameters for each token. The following are the model configuration details:
+
+| Key                               | Value        |
+| --------------------------------- | ------------ |
+| Modality                          | Text         |
+| Training Stage                    | Posttraining |
+| Params(Total / Activated)         | 21B / 3B     |
+| Layers                            | 28           |
+| Heads(Q/KV)                       | 20 / 4       |
+| Text Experts(Total / Activated)   | 64 / 6       |
+| Vision Experts(Total / Activated) | 64 / 6       |
+| Shared Experts                    | 2            |
+| Context Length                    | 131072       |
+
+## Quickstart
+
+### Using `transformers` library
+
+**Note**: Before using the model, please ensure you have the `transformers` library installed (version 4.50.0 or higher)
+
+The following contains a code snippet illustrating how to use the model generate content based on given inputs.
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model_name = "baidu/ERNIE-4.5-21B-A3B-PT"
+
+# load the tokenizer and the model
+tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
+model = AutoModelForCausalLM.from_pretrained(model_name, trust_remote_code=True)
+
+# prepare the model input
+prompt = "Give me a short introduction to large language model."
+messages = [
+    {"role": "user", "content": prompt}
+]
+text = tokenizer.apply_chat_template(
+    messages,
+    tokenize=False,
+    add_generation_prompt=True
+)
+model_inputs = tokenizer([text], add_special_tokens=False, return_tensors="pt").to(model.device)
+
+# conduct text completion
+generated_ids = model.generate(
+    model_inputs.input_ids,
+    max_new_tokens=1024
+)
+output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist()
+
+# decode the generated ids
+generate_text = tokenizer.decode(output_ids, skip_special_tokens=True).strip("\n")
+print("generate_text:", generate_text)
+```
+
+### vLLM inference
+
+[vllm](https://github.com/vllm-project/vllm/tree/main) github library. Python-only [build](https://docs.vllm.ai/en/latest/getting_started/installation/gpu.html#set-up-using-python-only-build-without-compilation).
+
+```bash
+vllm serve baidu/ERNIE-4.5-21B-A3B-PT --trust-remote-code
+```
+
+## License
+
+The ERNIE 4.5 models are provided under the Apache License 2.0. This license permits commercial use, subject to its terms and conditions. Copyright (c) 2025 Baidu, Inc. All Rights Reserved.
+
+## Citation
+
+If you find ERNIE 4.5 useful or wish to use it in your projects, please kindly cite our technical report:
+
+```bibtex
+@misc{ernie2025technicalreport,
+      title={ERNIE 4.5 Technical Report},
+      author={Baidu ERNIE Team},
+      year={2025},
+      eprint={},
+      archivePrefix={arXiv},
+      primaryClass={cs.CL},
+      url={}
+}
+```

configuration.json

@@ -0,0 +1 @@
+{"framework":"Pytorch","task":"text-generation"}

imatrix_unsloth.dat

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ad7d92645df843c07534de2417c94eb21c6012aea1707f96440330da34e3088
+size 48395091