初始化项目，由ModelHub XC社区提供模型

Model: QuantFactory/LLaMA-2-7B-32K-GGUF
Source: Original Platform

.gitattributes

@@ -0,0 +1,49 @@
+*.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
+LLaMA-2-7B-32K.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+LLaMA-2-7B-32K.Q4_1.gguf filter=lfs diff=lfs merge=lfs -text
+LLaMA-2-7B-32K.Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+LLaMA-2-7B-32K.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+LLaMA-2-7B-32K.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+LLaMA-2-7B-32K.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+LLaMA-2-7B-32K.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+LLaMA-2-7B-32K.Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+LLaMA-2-7B-32K.Q5_1.gguf filter=lfs diff=lfs merge=lfs -text
+LLaMA-2-7B-32K.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+LLaMA-2-7B-32K.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+LLaMA-2-7B-32K.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+LLaMA-2-7B-32K.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+LLaMA-2-7B-32K.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text

LLaMA-2-7B-32K.Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7156995f931a3a4fe12de46a6bfdb0d185d2944195dfefbcbdc4756a6d920bb6
+size 2532864352

LLaMA-2-7B-32K.Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83a7fe826f4f357e208864d9163fb85987ebade93b07529a9cbf325c5aa67157
+size 3597111648

LLaMA-2-7B-32K.Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19771be5de3192276c8da0c50448f8a0d383102d52a1c231e934f0ab0843e454
+size 3298005344

LLaMA-2-7B-32K.Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4b8148447de20ca6a4abbbc01e13569f6733381e39a9d45a0d7cedcc3b6e219
+size 2948305248

LLaMA-2-7B-32K.Q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfa2256937f0890f10ae3beffa0d11fc30dc1ed8163456311aeb7c32f2dc2678
+size 3825807712

LLaMA-2-7B-32K.Q4_1.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8f3981531379d501f64ad49eaf2ecffbc52e7cf44d64a1481b51f192710436f
+size 4238750048

LLaMA-2-7B-32K.Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:109843b0348f8c15b5ef16d3918ab42485e209cd65736e77fd7ad99b89597a78
+size 4081004896

LLaMA-2-7B-32K.Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6848ec2b61621f1c94c958191a21e2d130177aa7fa4cb7eb14084a5a683119b9
+size 3856740704

LLaMA-2-7B-32K.Q5_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:076f0fa2e4d4f2d7a39dbaad03a0b76d68a04593a304f2d362458ac6fbfbdb93
+size 4651692384

LLaMA-2-7B-32K.Q5_1.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:555a41382d08d15b61059c53645620fd334302d118f6bbb4f8ea998a9caef206
+size 5064634720

LLaMA-2-7B-32K.Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75dc800328fb536a9188c4e4a7d39617cfe1c73a564ed20199cf98948fb85bfb
+size 4783157600

LLaMA-2-7B-32K.Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a06dce6aef1ad09cedaa0e9ed7241dc06b9b72704122ed29b63347efb131f3d9
+size 4651692384

LLaMA-2-7B-32K.Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:022833e37ea44271a89384c2824e139641f6555f50e6cf344633a745fc518289
+size 5529194848

LLaMA-2-7B-32K.Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54e3789e6558ec1ae90a79e3884f19e0a4d309feaf44180ee001a13015db6b5d
+size 7161090400

README.md

@@ -0,0 +1,121 @@
+
+---
+
+license: llama2
+datasets:
+- togethercomputer/RedPajama-Data-1T
+- togethercomputer/RedPajama-Data-Instruct
+- EleutherAI/pile
+- togethercomputer/Long-Data-Collections
+language:
+- en
+library_name: transformers
+
+---
+
+[![QuantFactory Banner](https://lh7-rt.googleusercontent.com/docsz/AD_4nXeiuCm7c8lEwEJuRey9kiVZsRn2W-b4pWlu3-X534V3YmVuVc2ZL-NXg2RkzSOOS2JXGHutDuyyNAUtdJI65jGTo8jT9Y99tMi4H4MqL44Uc5QKG77B0d6-JfIkZHFaUA71-RtjyYZWVIhqsNZcx8-OMaA?key=xt3VSDoCbmTY7o-cwwOFwQ)](https://hf.co/QuantFactory)
+
+
+# QuantFactory/LLaMA-2-7B-32K-GGUF
+This is quantized version of [togethercomputer/LLaMA-2-7B-32K](https://huggingface.co/togethercomputer/LLaMA-2-7B-32K) created using llama.cpp
+
+# Original Model Card
+
+
+# LLaMA-2-7B-32K
+
+## Model Description
+
+LLaMA-2-7B-32K is an open-source, long context language model developed by Together, fine-tuned from Meta's original Llama-2 7B model. 
+This model represents our efforts to contribute to the rapid progress of the open-source ecosystem for large language models. 
+The model has been extended to a context length of 32K with position interpolation, 
+allowing applications on multi-document QA, long text summarization, etc.
+
+## What's new?
+
+This model introduces several improvements and new features:
+
+1. **Extended Context:** The model has been trained to handle context lengths up to 32K, which is a significant improvement over the previous versions.
+
+2. **Pre-training and Instruction Tuning:** We have shared our data recipe, which consists of a mixture of pre-training and instruction tuning data.
+
+3. **Fine-tuning Examples:** We provide examples of how to fine-tune the model for specific applications, including book summarization and long context question and answering.
+
+4. **Software Support:** We have updated both the inference and training stack to allow efficient inference and fine-tuning for 32K context.
+
+## Model Architecture
+
+The model follows the architecture of Llama-2-7B and extends it to handle a longer context. It leverages the recently released FlashAttention-2 and a range of other optimizations to improve the speed and efficiency of inference and training.
+
+## Training and Fine-tuning
+
+The model has been trained using a mixture of pre-training and instruction tuning data. 
+- In the first training phase of continued pre-training, our data mixture contains 25% RedPajama Book, 25% RedPajama ArXiv (including abstracts), 25% other data from RedPajama, and 25% from the UL2 Oscar Data, which is a part of OIG (Open-Instruction-Generalist), asking the model to fill in missing chunks, or complete the text. 
+To enhance the long-context ability, we exclude data shorter than 2K word. The inclusion of UL2 Oscar Data is effective in compelling the model to read and utilize long-range context.
+- We then fine-tune the model to focus on its few shot capacity under long context, including 20% Natural Instructions (NI), 20% Public Pool of Prompts (P3), 20% the Pile. We decontaminated all data against HELM core scenarios . We teach the model to leverage the in-context examples by packing examples into one 32K-token sequence. To maintain the knowledge learned from the first piece of data, we incorporate 20% RedPajama-Data Book and 20% RedPajama-Data ArXiv.
+
+Next, we provide examples of how to fine-tune the model for specific applications. 
+The example datasets are placed in [togethercomputer/Long-Data-Collections](https://huggingface.co/datasets/togethercomputer/Long-Data-Collections)
+You can use the [OpenChatKit](https://github.com/togethercomputer/OpenChatKit) to fine-tune your own 32K model over LLaMA-2-7B-32K.
+Please refer to [OpenChatKit](https://github.com/togethercomputer/OpenChatKit) for step-by-step illustrations.
+
+1. Long Context QA.
+
+   We take as an example the multi-document question answering task from the paper “Lost in the Middle: How Language Models Use Long Contexts”. The input for the model consists of (i) a question that requires an answer and (ii) k documents, which are passages extracted from Wikipedia. Notably, only one of these documents contains the answer to the question, while the remaining k − 1 documents, termed as "distractor" documents, do not. To successfully perform this task, the model must identify and utilize the document containing the answer from its input context. 
+
+   With OCK, simply run the following command to fine-tune:
+   ```
+   bash training/finetune_llama-2-7b-32k-mqa.sh
+   ```
+
+2. Summarization.
+
+   Another example is BookSum, a unique dataset designed to address the challenges of long-form narrative summarization. This dataset features source documents from the literature domain, including novels, plays, and stories, and offers human-written, highly abstractive summaries. We here focus on chapter-level data.  BookSum poses a unique set of challenges, necessitating that the model comprehensively read through each chapter.
+
+   With OCK, simply run the following command to fine-tune:
+   ```
+   bash training/finetune_llama-2-7b-32k-booksum.sh
+   ```
+
+
+## Inference
+
+You can use the [Together API](https://together.ai/blog/api-announcement) to try out LLaMA-2-7B-32K for inference. 
+The updated inference stack allows for efficient inference.
+
+To run the model locally, we strongly recommend to install Flash Attention V2, which is necessary to obtain the best performance:
+```
+# Please update the path of `CUDA_HOME`
+export CUDA_HOME=/usr/local/cuda-11.8
+pip install transformers==4.31.0
+pip install sentencepiece
+pip install ninja
+pip install flash-attn --no-build-isolation
+pip install git+https://github.com/HazyResearch/flash-attention.git#subdirectory=csrc/rotary
+```
+
+You can use this model directly from the Hugging Face Model Hub or fine-tune it on your own data using the OpenChatKit.
+
+```python
+from transformers import AutoTokenizer, AutoModelForCausalLM
+
+tokenizer = AutoTokenizer.from_pretrained("togethercomputer/LLaMA-2-7B-32K")
+model = AutoModelForCausalLM.from_pretrained("togethercomputer/LLaMA-2-7B-32K", trust_remote_code=True, torch_dtype=torch.float16)
+
+input_context = "Your text here"
+input_ids = tokenizer.encode(input_context, return_tensors="pt")
+output = model.generate(input_ids, max_length=128, temperature=0.7)
+output_text = tokenizer.decode(output[0], skip_special_tokens=True)
+print(output_text)
+```
+
+Alternatively, you can set `trust_remote_code=False` if you prefer not to use flash attention.
+
+
+## Limitations and Bias
+
+As with all language models, LLaMA-2-7B-32K may generate incorrect or biased content. It's important to keep this in mind when using the model.
+
+## Community
+
+Join us on [Together Discord](https://discord.gg/6ZVDU8tTD4)

configuration.json

@@ -0,0 +1 @@
+{"framework": "pytorch", "task": "others", "allow_remote": true}