Initial GPTQ model commit

README.md

@@ -0,0 +1,266 @@
+---
+datasets:
+- totally-not-an-llm/EverythingLM-data
+inference: false
+license: other
+model_creator: Kai Howard
+model_link: https://huggingface.co/totally-not-an-llm/EverythingLM-13b-16k
+model_name: EverythingLM 13B 16K
+model_type: llama
+quantized_by: TheBloke
+---
+
+<!-- header start -->
+<div style="width: 100%;">
+    <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><a href="https://discord.gg/theblokeai">Chat & support: my new Discord server</a></p>
+    </div>
+    <div style="display: flex; flex-direction: column; align-items: flex-end;">
+        <p><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p>
+    </div>
+</div>
+<!-- header end -->
+
+# EverythingLM 13B 16K - GPTQ
+- Model creator: [Kai Howard](https://huggingface.co/totally-not-an-llm)
+- Original model: [EverythingLM 13B 16K](https://huggingface.co/totally-not-an-llm/EverythingLM-13b-16k)
+
+## Description
+
+This repo contains GPTQ model files for [Kai Howard's EverythingLM 13B 16K](https://huggingface.co/totally-not-an-llm/EverythingLM-13b-16k).
+
+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/EverythingLM-13B-16K-GPTQ)
+* [2, 3, 4, 5, 6 and 8-bit GGML models for CPU+GPU inference](https://huggingface.co/TheBloke/EverythingLM-13B-16K-GGML)
+* [Kai Howard's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/totally-not-an-llm/EverythingLM-13b-16k)
+
+## Prompt template: Vicuna-Short
+
+```
+You are a helpful AI assistant.
+
+USER: {prompt}
+ASSISTANT:
+```
+
+## 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/EverythingLM-13B-16K-GPTQ/tree/main) | 4 | 128 | No | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 8192 | 7.26 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/EverythingLM-13B-16K-GPTQ/tree/gptq-4bit-32g-actorder_True) | 4 | 32 | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 8192 | 8.00 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/EverythingLM-13B-16K-GPTQ/tree/gptq-4bit-64g-actorder_True) | 4 | 64 | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 8192 | 7.51 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/EverythingLM-13B-16K-GPTQ/tree/gptq-4bit-128g-actorder_True) | 4 | 128 | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 8192 | 7.26 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/EverythingLM-13B-16K-GPTQ/tree/gptq-8bit--1g-actorder_True) | 8 | None | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 8192 | 13.36 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/EverythingLM-13B-16K-GPTQ/tree/gptq-8bit-128g-actorder_True) | 8 | 128 | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 8192 | 13.65 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/EverythingLM-13B-16K-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/EverythingLM-13B-16K-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/EverythingLM-13B-16K-GPTQ`.
+  - To download from a specific branch, enter for example `TheBloke/EverythingLM-13B-16K-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: `EverythingLM-13B-16K-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/EverythingLM-13B-16K-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=False,
+        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=False,
+        device="cuda:0",
+        quantize_config=None)
+"""
+
+prompt = "Tell me about AI"
+prompt_template=f'''You are a helpful AI assistant.
+
+USER: {prompt}
+ASSISTANT:
+'''
+
+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 -->
+## 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**: Luke from CarbonQuill, Aemon Algiz.
+
+**Patreon special mentions**: Ajan Kanaga, David Ziegler, Raymond Fosdick, SuperWojo, Sam, webtim, Steven Wood, knownsqashed, Tony Hughes, Junyu Yang, J, Olakabola, Dan Guido, Stephen Murray, John Villwock, vamX, William Sang, Sean Connelly, LangChain4j, Olusegun Samson, Fen Risland, Derek Yates, Karl Bernard, transmissions 11, Trenton Dambrowitz, Pieter, Preetika Verma, Swaroop Kallakuri, Andrey, Slarti, Jonathan Leane, Michael Levine, Kalila, Joseph William Delisle, Rishabh Srivastava, Deo Leter, Luke Pendergrass, Spencer Kim, Geoffrey Montalvo, Thomas Belote, Jeffrey Morgan, Mandus, ya boyyy, Matthew Berman, Magnesian, Ai Maven, senxiiz, Alps Aficionado, Luke @flexchar, Raven Klaugh, Imad Khwaja, Gabriel Puliatti, Johann-Peter Hartmann, usrbinkat, Spiking Neurons AB, Artur Olbinski, chris gileta, danny, Willem Michiel, WelcomeToTheClub, Deep Realms, alfie_i, Dave, Leonard Tan, NimbleBox.ai, Randy H, Daniel P. Andersen, Pyrater, Will Dee, Elle, Space Cruiser, Gabriel Tamborski, Asp the Wyvern, Illia Dulskyi, Nikolai Manek, Sid, Brandon Frisco, Nathan LeClaire, Edmond Seymore, Enrico Ros, Pedro Madruga, Eugene Pentland, John Detwiler, Mano Prime, Stanislav Ovsiannikov, Alex, Vitor Caleffi, K, biorpg, Michael Davis, Lone Striker, Pierre Kircher, theTransient, Fred von Graf, Sebastain Graf, Vadim, Iucharbius, Clay Pascal, Chadd, Mesiah Bishop, terasurfer, Rainer Wilmers, Alexandros Triantafyllidis, Stefan Sabev, Talal Aujan, Cory Kujawski, Viktor Bowallius, subjectnull, ReadyPlayerEmma, zynix
+
+
+Thank you to all my generous patrons and donaters!
+
+<!-- footer end -->
+
+# Original model card: Kai Howard's EverythingLM 13B 16K
+
+
+# EverythingLM-13b-16k
+
+Introducing EverythingLM, a llama-2 based, general-purpose 13b model with 16k context thanks to LlongMa.  The model is trained on the EverythingLM dataset, more info can be found on the dataset page.
+
+The model is completely uncensored.
+
+This model is an early test of the EverythingLM dataset and some new experimental principles, so don't consider it SOTA.
+
+### Notable features:
+- Automatically triggered CoT reasoning.
+- Verbose and detailed replies.
+- Creative stories.
+- Better prompt understanding.
+
+### Prompt format:
+It is a modified Vicuna format, the same used in many of ehartford's models.
+```
+You are a helpful AI assistant.
+
+USER: <prompt>
+ASSISTANT:
+```
+
+Training took about 1 hour using QLoRa on 1xA100, so this model can be recreated for about $3.  QLoRa model can be found here: https://huggingface.co/totally-not-an-llm/EverythingLM-13b-peft.
+
+### Model quirks:
+- Due to the nature of the dataset, it does better with more detail.  I've found it gives much better stories when I provide more requirements.
+- It really likes to use numbered lists.  I don't necessarilly have a problem with this but it's something to note when training on the dataset.
+- It likes to write fairy tales over anything else, which is strange.  This can easily be fixed by prompting.
+- Occasionally it will fall into repetition, this seems to be a commmon issue with llama-2 models.
+- Haven't tested pushing it all the way to 16k context.
+
+### Future plans:
+- Native finetune.
+- Other model sizes.
+- Improve dataset by:
+  - Regenerating using gpt-4.
+  - A bit more data with more diversity.
+- Refactor dataset generation script.
+- Test some model merges using this model.