commit d7968242e914469b75dbaeeb3ae86c4243eda227 Author: ModelHub XC Date: Fri Jun 5 20:30:12 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: FreedomIntelligence/RAG-Instruct-Llama3-8B Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..c4cb545 --- /dev/null +++ b/.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 +*.json filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..6c355d2 --- /dev/null +++ b/README.md @@ -0,0 +1,70 @@ +--- +license: apache-2.0 +datasets: +- FreedomIntelligence/RAG-Instruct +language: +- en +metrics: +- accuracy +base_model: +- meta-llama/Llama-3.1-8B +pipeline_tag: text-generation +--- +## Introduction + +RAG-Instruct is a method for generating diverse and high-quality RAG instruction data. It synthesizes instruction datasets based on any source corpus, leveraging the following approaches: + +- **Five RAG paradigms**, which represent diverse query-document relationships to enhance model generalization across tasks. +- **Instruction simulation**, which enriches instruction diversity and quality by utilizing the strengths of existing instruction datasets. + +Using this approach, we constructed [RAG-Instruct](https://huggingface.co/datasets/FreedomIntelligence/RAG-Instruct), covering a wide range of RAG scenarios and tasks. + +Our RAG-Instruct-Llama3-8B is trained on [RAG-Instruct](https://huggingface.co/datasets/FreedomIntelligence/RAG-Instruct) data, which significantly enhances the RAG ability of LLMs, demonstrating remarkable improvements in RAG performance across various tasks. + +| Model | WQA (acc) | PQA (acc) | TQA (acc) | OBQA (EM) | Pub (EM) | ARC (EM) | 2WIKI (acc) | HotP (acc) | MSQ (acc) | CFQA (EM) | PubMed (EM) | +|--------------------------------|-----------|-----------|-----------|-----------|----------|----------|-------------|------------|-----------|-----------|-------------| +| Llama3.1-8B | 59.5 | 60.8 | 73.4 | 82.0 | 56.7 | 77.1 | 65.6 | 45.6 | 18.7 | 56.5 | 73.9 | +| Llama3.1-8B + **RAG-Instruct** | 69.7 | 68.4 | 79.3 | 84.8 | 77.2 | 79.9 | 79.3 | 56.4 | 30.3 | 57.8 | 77.0 | + + +# Usage +RAG-Instruct-Llama3-8B can be used just like `Llama-3.1-8B-Instruct`. You can deploy it with tools like [vllm](https://github.com/vllm-project/vllm) or [Sglang](https://github.com/sgl-project/sglang), or perform direct inference: +```python +from transformers import AutoModelForCausalLM, AutoTokenizer + +# Load the model and tokenizer +model = AutoModelForCausalLM.from_pretrained("FreedomIntelligence/RAG-Instruct-Llama3-8B",torch_dtype="auto",device_map="auto") +tokenizer = AutoTokenizer.from_pretrained("FreedomIntelligence/RAG-Instruct-Llama3-8B") + +# Example input +input_text = """### Paragraph: +[1] structure is at risk from new development... +[2] as Customs and Excise stores... +[3] Powis Street is partly underway... +... + +### Instruction: +Which organization is currently using a building in Woolwich that holds historical importance? +""" + +# Tokenize and prepare input +messages = [{"role": "user", "content": input_text}] +inputs = tokenizer(tokenizer.apply_chat_template(messages, tokenize=False,add_generation_prompt=True), return_tensors="pt").to(model.device) + +# Generate output +outputs = model.generate(**inputs, max_new_tokens=2048) +print(tokenizer.decode(outputs[0], skip_special_tokens=True)) +``` + +## Citation +``` +@misc{liu2024raginstructboostingllmsdiverse, + title={RAG-Instruct: Boosting LLMs with Diverse Retrieval-Augmented Instructions}, + author={Wanlong Liu and Junying Chen and Ke Ji and Li Zhou and Wenyu Chen and Benyou Wang}, + year={2024}, + eprint={2501.00353}, + archivePrefix={arXiv}, + primaryClass={cs.CL}, + url={https://arxiv.org/abs/2501.00353}, +} +``` \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..700f8f9 --- /dev/null +++ b/config.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c8d6ab0b4a9aa92238f51ccbe4efdb498d0a5b74adcfd4eb8dd1c7b6c3e9cdf +size 874 diff --git a/configuration.json b/configuration.json new file mode 100644 index 0000000..1b87bb5 --- /dev/null +++ b/configuration.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:625c81a3527ce4f7a739854b431f380a987dc4af5e07e099b568e50e2e3b248c +size 64 diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..2dfb106 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:46650402223e517e09ac32797ba8cff47cf4cfea248aed800a76a0c50ba4e92d +size 184 diff --git a/model-00001-of-00004.safetensors b/model-00001-of-00004.safetensors new file mode 100644 index 0000000..72d0be3 --- /dev/null +++ b/model-00001-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d0e18cb8c3f167034241c7439510d24b58e70cdee499148b3d1c699d0156537 +size 4976698672 diff --git a/model-00002-of-00004.safetensors b/model-00002-of-00004.safetensors new file mode 100644 index 0000000..dc85466 --- /dev/null +++ b/model-00002-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5809c3a65fdeb0435559d1a9269292c9dbddc89e0756adb010bdb98b7ba5578f +size 4999802720 diff --git a/model-00003-of-00004.safetensors b/model-00003-of-00004.safetensors new file mode 100644 index 0000000..b2d24e2 --- /dev/null +++ b/model-00003-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5153fae9dddec8af078672bc0fb29ca704c307b370cde4205daa481dbe4f64a0 +size 4915916176 diff --git a/model-00004-of-00004.safetensors b/model-00004-of-00004.safetensors new file mode 100644 index 0000000..f0159df --- /dev/null +++ b/model-00004-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:165fa1c19ebe9535d5869abe7b65e3cc1258009ca0dae899aa4537c76d6b0ce1 +size 1168138808 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000..a054aad --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:146776fce3f6db1103aa6f249e65ee5544c5923ce6f971b092eee79aa6e5d37b +size 23950 diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..3694a40 --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bda86b58160cf8afef85cdbd3f8c12b95e5a5bbdb36a02c82060dbacfefb2444 +size 320 diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..1c1d8d5 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b +size 17209920 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..747bc73 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a93da578ee664393ef110b85e96f6ead945b2ea545d0732fa292c39a594a6078 +size 55401