初始化项目，由ModelHub XC社区提供模型

Model: unsloth/ERNIE-4.5-0.3B-PT-GGUF Source: Original Platform
2026-05-29 13:24:12 +08:00
commit 31d54d7ce3
22 changed files with 279 additions and 0 deletions
--- a/.gitattributes
+++ b/.gitattributes
@@ -0,0 +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
+*.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 -text
--- a/ERNIE-4.5-0.3B-PT-F16.gguf
+++ b/ERNIE-4.5-0.3B-PT-F16.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7dc17ec890cc0aaf1654e724eb45e232ef0945cb56a1cf1eb8e7cd9a09e0e9d7
+size 723955168
--- a/ERNIE-4.5-0.3B-PT-Q2_K.gguf
+++ b/ERNIE-4.5-0.3B-PT-Q2_K.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7907c3d76ad35a1c40c568efa0607d9b083a454365cc4c3b0b80ab52e4beed29
+size 183709152
--- a/ERNIE-4.5-0.3B-PT-Q2_K_L.gguf
+++ b/ERNIE-4.5-0.3B-PT-Q2_K_L.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7907c3d76ad35a1c40c568efa0607d9b083a454365cc4c3b0b80ab52e4beed29
+size 183709152
--- a/ERNIE-4.5-0.3B-PT-Q3_K_M.gguf
+++ b/ERNIE-4.5-0.3B-PT-Q3_K_M.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:798f3f2878f702fe489012c26e7708589e54a649bcddfa09ebade8c6231a03dd
+size 212516320
--- a/ERNIE-4.5-0.3B-PT-Q3_K_S.gguf
+++ b/ERNIE-4.5-0.3B-PT-Q3_K_S.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5dc56ee3b0d5e84162be25dbadd44f1bff58c01ac98a968fde4557449d862c8
+size 198897120
--- a/ERNIE-4.5-0.3B-PT-Q4_0.gguf
+++ b/ERNIE-4.5-0.3B-PT-Q4_0.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95acb8aaac992e3637bced4722ab4d4072b5381b6cd92eabf003d7c5f059a145
+size 232738272
--- a/ERNIE-4.5-0.3B-PT-Q4_1.gguf
+++ b/ERNIE-4.5-0.3B-PT-Q4_1.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db6316902f34ee3eefd92c3e1c419215bdeb1ffa89b2c4a97083c02c7373b7df
+size 248663520
--- a/ERNIE-4.5-0.3B-PT-Q4_K_M.gguf
+++ b/ERNIE-4.5-0.3B-PT-Q4_K_M.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9842768d0fa26c6565611161c2d6135e79275a3726141478719cfa191cc670dd
+size 240645600
--- a/ERNIE-4.5-0.3B-PT-Q4_K_S.gguf
+++ b/ERNIE-4.5-0.3B-PT-Q4_K_S.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d369d5a476a2e9962fced622a6b9f69714c5e8165937b2b9bd3178fe87d3759f
+size 233655776
--- a/ERNIE-4.5-0.3B-PT-Q5_K_M.gguf
+++ b/ERNIE-4.5-0.3B-PT-Q5_K_M.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6bdd700c4b088c07d600d6c1e4cb6fb9d1a63698b7d1546e24c2a93aac5ed7b
+size 268662240
--- a/ERNIE-4.5-0.3B-PT-Q5_K_S.gguf
+++ b/ERNIE-4.5-0.3B-PT-Q5_K_S.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64cd74be80a801303eecef9c79fff6099ad05b47d4a0ecd7f28391b20ff27f83
+size 264588768
--- a/ERNIE-4.5-0.3B-PT-Q6_K.gguf
+++ b/ERNIE-4.5-0.3B-PT-Q6_K.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ef5743979de38524327542e39696202eb12c0c0a18f708719a82097ffba1fd1
+size 298429920
--- a/ERNIE-4.5-0.3B-PT-Q8_0.gguf
+++ b/ERNIE-4.5-0.3B-PT-Q8_0.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca1655e92ce4f0d6d7df5a003dbbf95aaf8767d8afcc1f5b33f9ac8e9571673c
+size 385789408
--- a/ERNIE-4.5-0.3B-PT-UD-Q2_K_XL.gguf
+++ b/ERNIE-4.5-0.3B-PT-UD-Q2_K_XL.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7907c3d76ad35a1c40c568efa0607d9b083a454365cc4c3b0b80ab52e4beed29
+size 183709152
--- a/ERNIE-4.5-0.3B-PT-UD-Q3_K_XL.gguf
+++ b/ERNIE-4.5-0.3B-PT-UD-Q3_K_XL.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:798f3f2878f702fe489012c26e7708589e54a649bcddfa09ebade8c6231a03dd
+size 212516320
--- a/ERNIE-4.5-0.3B-PT-UD-Q4_K_XL.gguf
+++ b/ERNIE-4.5-0.3B-PT-UD-Q4_K_XL.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9842768d0fa26c6565611161c2d6135e79275a3726141478719cfa191cc670dd
+size 240645600
--- a/ERNIE-4.5-0.3B-PT-UD-Q5_K_XL.gguf
+++ b/ERNIE-4.5-0.3B-PT-UD-Q5_K_XL.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6bdd700c4b088c07d600d6c1e4cb6fb9d1a63698b7d1546e24c2a93aac5ed7b
+size 268662240
--- a/ERNIE-4.5-0.3B-PT-UD-Q6_K_XL.gguf
+++ b/ERNIE-4.5-0.3B-PT-UD-Q6_K_XL.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c99cd4ee46b801208fa548e4a5ed41f7b05b1ef598fb7d66bbac721736408cea
+size 324079072
--- a/ERNIE-4.5-0.3B-PT-UD-Q8_K_XL.gguf
+++ b/ERNIE-4.5-0.3B-PT-UD-Q8_K_XL.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:584f1f004fc190953555d12bfb5859953a5565955d8b6c86dd075aceec53d8c3
+size 485076448
--- a/README.md
+++ b/README.md
@@ -0,0 +1,174 @@
+---
+base_model:
+- baidu/ERNIE-4.5-0.3B-PT
+license: apache-2.0
+language:
+- en
+- zh
+pipeline_tag: text-generation
+tags:
+- ERNIE4.5
+- unsloth
+library_name: transformers
+---
+<div>
+<p style="margin-top: 0;margin-bottom: 0;">
+    <em><a href="https://docs.unsloth.ai/basics/unsloth-dynamic-v2.0-gguf">Unsloth Dynamic 2.0</a> achieves superior accuracy & outperforms other leading quants.</em>
+  </p>
+  <div style="display: flex; gap: 5px; align-items: center; ">
+    <a href="https://github.com/unslothai/unsloth/">
+      <img src="https://github.com/unslothai/unsloth/raw/main/images/unsloth%20new%20logo.png" width="133">
+    </a>
+    <a href="https://discord.gg/unsloth">
+      <img src="https://github.com/unslothai/unsloth/raw/main/images/Discord%20button.png" width="173">
+    </a>
+    <a href="https://docs.unsloth.ai/">
+      <img src="https://raw.githubusercontent.com/unslothai/unsloth/refs/heads/main/images/documentation%20green%20button.png" width="143">
+    </a>
+  </div>
+</div>
+
+
+<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-4.5-0.3B
+
+## 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-4.5-0.3B is a text dense Post-trained model. The following are the model configuration details:
+
+| Key            | Value        |
+| -------------- | ------------ |
+| Modality       | Text         |
+| Training Stage | Posttraining |
+| Params         | 0.36B        |
+| Layers         | 18           |
+| Heads(Q/KV)    | 16 / 2       |
+| Context Length | 131072       |
+
+## Quickstart
+
+### Model Finetuning with ERNIEKit
+
+[ERNIEKit](https://github.com/PaddlePaddle/ERNIE) is a training toolkit based on PaddlePaddle, specifically designed for the ERNIE series of open-source large models. It provides comprehensive support for scenarios such as instruction fine-tuning (SFT, LoRA) and alignment training (DPO), ensuring optimal performance.
+
+Usage Examples:
+
+```bash
+# Download Model
+huggingface-cli download baidu/ERNIE-4.5-0.3B-Paddle --local-dir baidu/ERNIE-4.5-0.3B-Paddle
+# SFT
+erniekit train examples/configs/ERNIE-4.5-0.3B/sft/run_sft_8k.yaml
+# DPO
+erniekit train examples/configs/ERNIE-4.5-0.3B/dpo/run_dpo_8k.yaml
+```
+
+For more detailed examples, including SFT with LoRA, multi-GPU configurations, and advanced scripts, please refer to the examples folder within the [ERNIEKit](https://github.com/PaddlePaddle/ERNIE) repository.
+
+### FastDeploy Inference
+
+Service deployment can be quickly completed using FastDeploy in the following command. For more detailed usage instructions, please refer to the [FastDeploy Repository](https://github.com/PaddlePaddle/FastDeploy).
+
+```bash
+python -m fastdeploy.entrypoints.openai.api_server \
+       --model baidu/ERNIE-4.5-0.3B-Paddle \
+       --port 8180 \
+       --metrics-port 8181 \
+       --engine-worker-queue-port 8182 \
+       --max-model-len 32768 \
+       --max-num-seqs 32
+```
+
+### Using `transformers` library
+
+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-4.5-0.3B-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 is currently being adapted, priority can be given to using our forked repository [vllm](https://github.com/CSWYF3634076/vllm/tree/ernie). We are working with the community to fully support ERNIE4.5 models, stay tuned.
+
+```bash
+vllm serve baidu/ERNIE-4.5-0.3B-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={}
+}
+```
--- a/configuration.json
+++ b/configuration.json
@@ -0,0 +1 @@
+{"framework": "pytorch", "task": "text-generation", "allow_remote": true}
				`@@ -0,0 +1 @@`
				`{"framework": "pytorch", "task": "text-generation", "allow_remote": true}`