Initial GPTQ model commit

README.md

@@ -0,0 +1,374 @@
+---
+datasets:
+- togethercomputer/llama-instruct
+inference: false
+language:
+- en
+library_name: transformers
+license: llama2
+model_creator: Together
+model_link: https://huggingface.co/togethercomputer/Llama-2-7B-32K-Instruct
+model_name: Llama2 7B 32K Instruct
+model_type: llama
+quantized_by: TheBloke
+---
+
+<!-- header start -->
+<!-- 200823 -->
+<div style="width: auto; margin-left: auto; margin-right: auto">
+<img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
+</div>
+<div style="display: flex; justify-content: space-between; width: 100%;">
+    <div style="display: flex; flex-direction: column; align-items: flex-start;">
+        <p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://discord.gg/theblokeai">Chat & support: TheBloke's Discord server</a></p>
+    </div>
+    <div style="display: flex; flex-direction: column; align-items: flex-end;">
+        <p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p>
+    </div>
+</div>
+<div style="text-align:center; margin-top: 0em; margin-bottom: 0em"><p style="margin-top: 0.25em; margin-bottom: 0em;">TheBloke's LLM work is generously supported by a grant from <a href="https://a16z.com">andreessen horowitz (a16z)</a></p></div>
+<hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
+<!-- header end -->
+
+# Llama2 7B 32K Instruct - GPTQ
+- Model creator: [Together](https://huggingface.co/togethercomputer)
+- Original model: [Llama2 7B 32K Instruct](https://huggingface.co/togethercomputer/Llama-2-7B-32K-Instruct)
+
+## Description
+
+This repo contains GPTQ model files for [Together's Llama2 7B 32K Instruct](https://huggingface.co/togethercomputer/Llama-2-7B-32K-Instruct).
+
+Multiple GPTQ parameter permutations are provided; see Provided Files below for details of the options provided, their parameters, and the software used to create them.
+
+## Repositories available
+
+* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/Llama-2-7B-32K-Instruct-GPTQ)
+* [2, 3, 4, 5, 6 and 8-bit GGML models for CPU+GPU inference](https://huggingface.co/TheBloke/Llama-2-7B-32K-Instruct-GGML)
+* [Together's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/togethercomputer/Llama-2-7B-32K-Instruct)
+
+## Prompt template: Llama2-Instruct-Only
+
+```
+[INST]
+{prompt}
+[\INST]
+```
+
+## Provided files and GPTQ parameters
+
+Multiple quantisation parameters are provided, to allow you to choose the best one for your hardware and requirements.
+
+Each separate quant is in a different branch.  See below for instructions on fetching from different branches.
+
+All GPTQ files are made with AutoGPTQ.
+
+<details>
+  <summary>Explanation of GPTQ parameters</summary>
+
+- Bits: The bit size of the quantised model.
+- GS: GPTQ group size. Higher numbers use less VRAM, but have lower quantisation accuracy. "None" is the lowest possible value.
+- Act Order: True or False. Also known as `desc_act`. True results in better quantisation accuracy. Some GPTQ clients have issues with models that use Act Order plus Group Size.
+- Damp %: A GPTQ parameter that affects how samples are processed for quantisation. 0.01 is default, but 0.1 results in slightly better accuracy.
+- GPTQ dataset: The dataset used for quantisation. Using a dataset more appropriate to the model's training can improve quantisation accuracy. Note that the GPTQ dataset is not the same as the dataset used to train the model - please refer to the original model repo for details of the training dataset(s).
+- Sequence Length: The length of the dataset sequences used for quantisation. Ideally this is the same as the model sequence length. For some very long sequence models (16+K), a lower sequence length may have to be used.  Note that a lower sequence length does not limit the sequence length of the quantised model. It only impacts the quantisation accuracy on longer inference sequences.
+- ExLlama Compatibility: Whether this file can be loaded with ExLlama, which currently only supports Llama models in 4-bit.
+
+</details>
+
+| Branch | Bits | GS | Act Order | Damp % | GPTQ Dataset | Seq Len | Size | ExLlama | Desc |
+| ------ | ---- | -- | --------- | ------ | ------------ | ------- | ---- | ------- | ---- |
+| [main](https://huggingface.co/TheBloke/Llama-2-7B-32K-Instruct-GPTQ/tree/main) | 4 | 128 | No | 0.1 | [c4](https://huggingface.co/datasets/allenai/c4) | 32768 | 3.90 GB | Yes | Most compatible option. Good inference speed in AutoGPTQ and GPTQ-for-LLaMa. Lower inference quality than other options. | 
+| [gptq-4bit-32g-actorder_True](https://huggingface.co/TheBloke/Llama-2-7B-32K-Instruct-GPTQ/tree/gptq-4bit-32g-actorder_True) | 4 | 32 | Yes | 0.1 | [c4](https://huggingface.co/datasets/allenai/c4) | 32768 | 4.28 GB | Yes | 4-bit, with Act Order and group size 32g. Gives highest possible inference quality, with maximum VRAM usage. Poor AutoGPTQ CUDA speed. | 
+| [gptq-4bit-64g-actorder_True](https://huggingface.co/TheBloke/Llama-2-7B-32K-Instruct-GPTQ/tree/gptq-4bit-64g-actorder_True) | 4 | 64 | Yes | 0.1 | [c4](https://huggingface.co/datasets/allenai/c4) | 32768 | 4.02 GB | Yes | 4-bit, with Act Order and group size 64g. Uses less VRAM than 32g, but with slightly lower accuracy. Poor AutoGPTQ CUDA speed. | 
+| [gptq-4bit-128g-actorder_True](https://huggingface.co/TheBloke/Llama-2-7B-32K-Instruct-GPTQ/tree/gptq-4bit-128g-actorder_True) | 4 | 128 | Yes | 0.1 | [c4](https://huggingface.co/datasets/allenai/c4) | 32768 | 3.90 GB | Yes | 4-bit, with Act Order and group size 128g. Uses even less VRAM than 64g, but with slightly lower accuracy. Poor AutoGPTQ CUDA speed. | 
+| [gptq-8bit--1g-actorder_True](https://huggingface.co/TheBloke/Llama-2-7B-32K-Instruct-GPTQ/tree/gptq-8bit--1g-actorder_True) | 8 | None | Yes | 0.1 | [c4](https://huggingface.co/datasets/allenai/c4) | 32768 | 7.01 GB | No | 8-bit, with Act Order. No group size, to lower VRAM requirements and to improve AutoGPTQ speed. | 
+| [gptq-8bit-128g-actorder_True](https://huggingface.co/TheBloke/Llama-2-7B-32K-Instruct-GPTQ/tree/gptq-8bit-128g-actorder_True) | 8 | 128 | Yes | 0.1 | [c4](https://huggingface.co/datasets/allenai/c4) | 32768 | 7.16 GB | No | 8-bit, with group size 128g for higher inference quality and with Act Order for even higher accuracy. Poor AutoGPTQ CUDA speed. |
+
+## How to download from branches
+
+- In text-generation-webui, you can add `:branch` to the end of the download name, eg `TheBloke/Llama-2-7B-32K-Instruct-GPTQ:gptq-4bit-32g-actorder_True`
+- With Git, you can clone a branch with:
+```
+git clone --single-branch --branch gptq-4bit-32g-actorder_True https://huggingface.co/TheBloke/Llama-2-7B-32K-Instruct-GPTQ
+```
+- In Python Transformers code, the branch is the `revision` parameter; see below.
+
+## How to easily download and use this model in [text-generation-webui](https://github.com/oobabooga/text-generation-webui).
+
+Please make sure you're using the latest version of [text-generation-webui](https://github.com/oobabooga/text-generation-webui).
+
+It is strongly recommended to use the text-generation-webui one-click-installers unless you know how to make a manual install.
+
+1. Click the **Model tab**.
+2. Under **Download custom model or LoRA**, enter `TheBloke/Llama-2-7B-32K-Instruct-GPTQ`.
+  - To download from a specific branch, enter for example `TheBloke/Llama-2-7B-32K-Instruct-GPTQ:gptq-4bit-32g-actorder_True`
+  - see Provided Files above for the list of branches for each option.
+3. Click **Download**.
+4. The model will start downloading. Once it's finished it will say "Done"
+5. In the top left, click the refresh icon next to **Model**.
+6. In the **Model** dropdown, choose the model you just downloaded: `Llama-2-7B-32K-Instruct-GPTQ`
+7. The model will automatically load, and is now ready for use!
+8. If you want any custom settings, set them and then click **Save settings for this model** followed by **Reload the Model** in the top right.
+  * Note that you do not need to set GPTQ parameters any more. These are set automatically from the file `quantize_config.json`.
+9. Once you're ready, click the **Text Generation tab** and enter a prompt to get started!
+
+## How to use this GPTQ model from Python code
+
+First make sure you have [AutoGPTQ](https://github.com/PanQiWei/AutoGPTQ) 0.3.1 or later installed:
+
+```
+pip3 install auto-gptq
+```
+
+If you have problems installing AutoGPTQ, please build from source instead:
+```
+pip3 uninstall -y auto-gptq
+git clone https://github.com/PanQiWei/AutoGPTQ
+cd AutoGPTQ
+pip3 install .
+```
+
+Then try the following example code:
+
+```python
+from transformers import AutoTokenizer, pipeline, logging
+from auto_gptq import AutoGPTQForCausalLM, BaseQuantizeConfig
+
+model_name_or_path = "TheBloke/Llama-2-7B-32K-Instruct-GPTQ"
+
+use_triton = False
+
+tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=True)
+
+model = AutoGPTQForCausalLM.from_quantized(model_name_or_path,
+        use_safetensors=True,
+        trust_remote_code=True,
+        device="cuda:0",
+        use_triton=use_triton,
+        quantize_config=None)
+
+"""
+# To download from a specific branch, use the revision parameter, as in this example:
+# Note that `revision` requires AutoGPTQ 0.3.1 or later!
+
+model = AutoGPTQForCausalLM.from_quantized(model_name_or_path,
+        revision="gptq-4bit-32g-actorder_True",
+        use_safetensors=True,
+        trust_remote_code=True,
+        device="cuda:0",
+        quantize_config=None)
+"""
+
+prompt = "Tell me about AI"
+prompt_template=f'''[INST]
+{prompt}
+[\INST]
+'''
+
+print("\n\n*** Generate:")
+
+input_ids = tokenizer(prompt_template, return_tensors='pt').input_ids.cuda()
+output = model.generate(inputs=input_ids, temperature=0.7, max_new_tokens=512)
+print(tokenizer.decode(output[0]))
+
+# Inference can also be done using transformers' pipeline
+
+# Prevent printing spurious transformers error when using pipeline with AutoGPTQ
+logging.set_verbosity(logging.CRITICAL)
+
+print("*** Pipeline:")
+pipe = pipeline(
+    "text-generation",
+    model=model,
+    tokenizer=tokenizer,
+    max_new_tokens=512,
+    temperature=0.7,
+    top_p=0.95,
+    repetition_penalty=1.15
+)
+
+print(pipe(prompt_template)[0]['generated_text'])
+```
+
+## Compatibility
+
+The files provided will work with AutoGPTQ (CUDA and Triton modes), GPTQ-for-LLaMa (only CUDA has been tested), and Occ4m's GPTQ-for-LLaMa fork.
+
+ExLlama works with Llama models in 4-bit. Please see the Provided Files table above for per-file compatibility.
+
+<!-- footer start -->
+<!-- 200823 -->
+## Discord
+
+For further support, and discussions on these models and AI in general, join us at:
+
+[TheBloke AI's Discord server](https://discord.gg/theblokeai)
+
+## Thanks, and how to contribute.
+
+Thanks to the [chirper.ai](https://chirper.ai) team!
+
+I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training.
+
+If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects.
+
+Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits.
+
+* Patreon: https://patreon.com/TheBlokeAI
+* Ko-Fi: https://ko-fi.com/TheBlokeAI
+
+**Special thanks to**: Aemon Algiz.
+
+**Patreon special mentions**: Sam, theTransient, Jonathan Leane, Steven Wood, webtim, Johann-Peter Hartmann, Geoffrey Montalvo, Gabriel Tamborski, Willem Michiel, John Villwock, Derek Yates, Mesiah Bishop, Eugene Pentland, Pieter, Chadd, Stephen Murray, Daniel P. Andersen, terasurfer, Brandon Frisco, Thomas Belote, Sid, Nathan LeClaire, Magnesian, Alps Aficionado, Stanislav Ovsiannikov, Alex, Joseph William Delisle, Nikolai Manek, Michael Davis, Junyu Yang, K, J, Spencer Kim, Stefan Sabev, Olusegun Samson, transmissions 11, Michael Levine, Cory Kujawski, Rainer Wilmers, zynix, Kalila, Luke @flexchar, Ajan Kanaga, Mandus, vamX, Ai Maven, Mano Prime, Matthew Berman, subjectnull, Vitor Caleffi, Clay Pascal, biorpg, alfie_i, 阿明, Jeffrey Morgan, ya boyyy, Raymond Fosdick, knownsqashed, Olakabola, Leonard Tan, ReadyPlayerEmma, Enrico Ros, Dave, Talal Aujan, Illia Dulskyi, Sean Connelly, senxiiz, Artur Olbinski, Elle, Raven Klaugh, Fen Risland, Deep Realms, Imad Khwaja, Fred von Graf, Will Dee, usrbinkat, SuperWojo, Alexandros Triantafyllidis, Swaroop Kallakuri, Dan Guido, John Detwiler, Pedro Madruga, Iucharbius, Viktor Bowallius, Asp the Wyvern, Edmond Seymore, Trenton Dambrowitz, Space Cruiser, Spiking Neurons AB, Pyrater, LangChain4j, Tony Hughes, Kacper Wikieł, Rishabh Srivastava, David Ziegler, Luke Pendergrass, Andrey, Gabriel Puliatti, Lone Striker, Sebastain Graf, Pierre Kircher, Randy H, NimbleBox.ai, Vadim, danny, Deo Leter
+
+
+Thank you to all my generous patrons and donaters!
+
+And thank you again to a16z for their generous grant.
+
+<!-- footer end -->
+
+# Original model card: Together's Llama2 7B 32K Instruct
+
+
+# Llama-2-7B-32K-Instruct
+
+## Model Description
+
+Llama-2-7B-32K-Instruct is an open-source, long-context chat model finetuned from [Llama-2-7B-32K](https://huggingface.co/togethercomputer/Llama-2-7B-32K), over high-quality instruction and chat data.
+We built Llama-2-7B-32K-Instruct with less than 200 lines of Python script using [Together API](https://together.ai/blog/api-announcement), and we also make the [recipe fully available](https://github.com/togethercomputer/Llama-2-7B-32K-Instruct).
+We hope that this can enable everyone to finetune their own version of [Llama-2-7B-32K](https://huggingface.co/togethercomputer/Llama-2-7B-32K) — play with [Together API](https://together.ai/blog/api-announcement) and give us feedback! 
+
+## Data Collection Details
+
+Llama-2-7B-32K-Instruct is fine-tuned over a combination of two parts:
+1. **19K single- and multi-round conversations generated by human instructions and [Llama-2-70B-Chat](https://huggingface.co/meta-llama/Llama-2-7b-chat-hf) outputs**.
+   We collected the dataset following the distillation paradigm that is used by Alpaca, Vicuna, WizardLM, Orca — producing instructions by querying a powerful LLM (in this case, [Llama-2-70B-Chat](https://huggingface.co/meta-llama/Llama-2-7b-chat-hf)).
+   The complete dataset is also released [here](https://huggingface.co/datasets/togethercomputer/llama-instruct).
+   We also share the complete recipe for the data collection process [here](https://github.com/togethercomputer/Llama-2-7B-32K-Instruct).
+   
+2. **Long-context Summarization and Long-context QA**.
+   We follow the recipe of [Llama-2-7B-32K](https://together.ai/blog/Llama-2-7B-32K), and train our model with the [BookSum dataset](https://huggingface.co/datasets/togethercomputer/Long-Data-Collections) and [Multi-document Question Answering](https://arxiv.org/abs/2307.03172).
+
+The final data mixture used for model finetuning is: 19K instruction (50%) + BookSum (25%) + MQA (25%).
+
+## Model Usage
+
+We encourage you to try out this model using the [Together API](https://together.ai/blog/api-announcement). 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 load the model directly from the Hugging Face model hub using
+```python
+import torch
+from transformers import AutoTokenizer, AutoModelForCausalLM
+
+tokenizer = AutoTokenizer.from_pretrained("togethercomputer/Llama-2-7B-32K-Instruct")
+model = AutoModelForCausalLM.from_pretrained("togethercomputer/Llama-2-7B-32K-Instruct",
+    trust_remote_code=True, torch_dtype=torch.float16)
+input_ids = tokenizer.encode("[INST]\nWrite a poem about cats\n[/INST]\n\n", return_tensors="pt")
+output = model.generate(input_ids, max_length=128,
+    temperature=0.7, repetition_penalty=1.1, top_p=0.7, top_k=50)
+output_text = tokenizer.decode(output[0], skip_special_tokens=True)
+```
+
+The model is also hosted on [Together Playground](https://api.together.xyz/playground). You can simply play with the model by using prompt formatted by:
+
+```
+[INST]\n<your instruction here>\n[\INST]\n\n
+```
+
+For example, if we query the model with 
+
+```
+[INST]\nWrite a poem about cats\n[\INST]\n\n
+```
+
+the model will return
+```
+[INST]
+Write a poem about cats
+[/INST]
+
+Cats are mysterious creatures, with their aloof and independent nature. They're also incredibly beautiful, with their sleek fur and piercing eyes. Here's a poem that captures the essence of cats:
+
+Cats, oh cats, how can I describe you?
+Your beauty is beyond compare, it seems.
+You're graceful and elegant, like a ballerina's dance,
+But don't let your charm fool you, for you're not easily tamed.
+
+With your soft purring and playful meows,
+You draw us in with your enchanting powers.
+We love to watch you play, your tail twirling 'round,
+As if you're dancing on air, with no sound.
+
+But don't be fooled by your sweetness, my friend,
+For beneath that gentle exterior, lies a fierce defender.
+When danger lurks, you'll spring into action,
+Protecting those you hold dear, without question.
+
+Solet us admire you, from afar,
+For in your own way, you're truly unique, a star.
+And though we may never fully understand,
+The depths of your soul, we'll always stand, hand in paw, as one.
+
+This poem captures the essence of cats, highlighting their beauty, independence,and protective nature. It also celebrates the special bond between humans and cats, recognizing their unique qualities and the joy they bring to our lives.
+```
+
+## Model Evaluation
+
+We evaluate the model from three aspects: 1) [Alpaca Eval](https://tatsu-lab.github.io/alpaca_eval/);
+2) [Rouge score over BookSum](https://together.ai/blog/Llama-2-7B-32K); and
+3) [Accuracy over Multi-document Question Answering (MQA)](https://together.ai/blog/Llama-2-7B-32K). 
+We compare with models including 
+[GPT-3.5-Turbo-16K](https://platform.openai.com/docs/models/gpt-3-5),
+[https://huggingface.co/meta-llama/Llama-2-7b-chat-hf](https://huggingface.co/meta-llama/Llama-2-7b-chat-hf),
+[Longchat-7b-16k](https://huggingface.co/lmsys/longchat-7b-16k)
+and [Longchat-7b-v1.5-32k](https://huggingface.co/lmsys/longchat-7b-v1.5-32k).
+We summarize the results below:
+
+* Alpaca Eval
+| Model | win_rate | standard_error | n_total | avg_length |
+| -------- | ------- | ------- | ------- | ------- |
+| Llama-2-7B-Chat-hf | 71.37 | 1.59 | 805 | 1479 |
+| Llama-2-7B-32K-Instruct | 70.36 | 1.61 | 803 | 1885 |
+| oasst-rlhf-llama-33b | 66.52 | 1.66 | 805 | 1079 |
+| text_davinci_003 | 50.00 | 0.00 | 805 | 307|
+| falcon-40b-instruct | 45.71 | 1.75 | 805 | 662 |
+| alpaca-farm-ppo-human | 41.24 | 1.73 | 805 | 803 |
+| alpaca-7b | 26.46 | 1.54 | 805 | 396 |
+| text_davinci_001 | 15.17 | 1.24 | 804 | 296 |
+
+* Rouge Score over BookSum
+| Model | R1 | R2 | RL |
+| -------- | ------- | ------- | ------- |
+| Llama-2-7B-Chat-hf | 0.055 | 0.008 | 0.046 |
+| Longchat-7b-16k | 0.303 | 0.055 | 0.160 |
+| Longchat-7b-v1.5-32k | 0.308 | 0.057 | 0.163 |
+| GPT-3.5-Turbo-16K | 0.324 | 0.066 | 0.178 |
+| Llama-2-7B-32K-Instruct (ours) | 0.336 | 0.076 | 0.184 |
+
+* Accuracy over MQA
+| Model | 20 docs (Avg 2.9K tokens) | 30 docs (Avg 4.4K tokens) | 50 docs (Avg 7.4K tokens) |
+| -------- | ------- | ------- | ------- |
+| Llama-2-7B-Chat-hf | 0.448 | 0.421 | 0.354 |
+| Longchat-7b-16k | 0.510 | 0.473 | 0.428 |
+| Longchat-7b-v1.5-32k | 0.534 | 0.516 | 0.479 |
+| GPT-3.5-Turbo-16K | 0.622 | 0.609 | 0.577 |
+| Llama-2-7B-32K-Instruct (ours) | 0.622 | 0.604 | 0.589 |
+
+## Limitations and Bias
+
+As with all language models, Llama-2-7B-32K-Instruct 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)