Upload new GPTQs with varied parameters

README.md

@@ -1,14 +1,16 @@
 ---
 inference: false
 license: other
+model_type: llama
 ---
+
 <!-- 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/Jq4vkcDakD">Chat & support: my new Discord server</a></p>
+        <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>
@@ -18,65 +20,151 @@ license: other
 
 # Tim Dettmers' Guanaco 33B GPTQ
 
-These files are GPTQ 4bit model files for [Tim Dettmers' Guanaco 33B](https://huggingface.co/timdettmers/guanaco-33b-merged).
+These files are GPTQ model files for [Tim Dettmers' Guanaco 33B](https://huggingface.co/timdettmers/guanaco-33b-merged).
+
+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.
 
-It is the result of quantising to 4bit using [GPTQ-for-LLaMa](https://github.com/qwopqwop200/GPTQ-for-LLaMa).
+These models were quantised using hardware kindly provided by [Latitude.sh](https://www.latitude.sh/accelerate).
 
 ## Repositories available
 
-* [4-bit GPTQ models for GPU inference](https://huggingface.co/TheBloke/guanaco-33B-GPTQ)
+* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/guanaco-33B-GPTQ)
 * [2, 3, 4, 5, 6 and 8-bit GGML models for CPU+GPU inference](https://huggingface.co/TheBloke/guanaco-33B-GGML)
 * [Unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/timdettmers/guanaco-33b-merged)
 
-## Prompt template
+## Prompt template: Guanaco
 
 ```
-### Human: prompt
+### Human: {prompt}
 ### Assistant:
 ```
 
-## How to easily download and use this model in text-generation-webui
+## Provided files
+
+Multiple quantisation parameters are provided, to allow you to choose the best one for your hardware and requirements.
 
-Open the text-generation-webui UI as normal.
+Each separate quant is in a different branch.  See below for instructions on fetching from different branches.
+
+| Branch | Bits | Group Size | Act Order (desc_act) | File Size | ExLlama Compatible? | Made With | Description |
+| ------ | ---- | ---------- | -------------------- | --------- | ------------------- | --------- | ----------- |
+| main | 4 | None | True | 16.94 GB | True | GPTQ-for-LLaMa | Most compatible option. Good inference speed in AutoGPTQ and GPTQ-for-LLaMa. Lower inference quality than other options. |
+| gptq-4bit-32g-actorder_True | 4 | 32 | True | 19.44 GB | True | AutoGPTQ | 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 | 4 | 64 | True | 18.18 GB | True | AutoGPTQ | 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 | 4 | 128 | True | 17.55 GB | True | AutoGPTQ | 4-bit, with Act Order and group size. 128g uses even less VRAM, but with slightly lower accuracy. Poor AutoGPTQ CUDA speed. |
+| gptq-8bit--1g-actorder_True | 8 | None | True | 32.99 GB | False | AutoGPTQ | 8-bit, with Act Order. No group size, to lower VRAM requirements and to improve AutoGPTQ speed. |
+| gptq-8bit-128g-actorder_False | 8 | 128 | False | 33.73 GB | False | AutoGPTQ | 8-bit, with group size 128g for higher inference quality and without Act Order to improve AutoGPTQ speed. |
+| gptq-3bit--1g-actorder_True | 3 | None | True | 12.92 GB | False | AutoGPTQ | 3-bit, with Act Order and no group size. Lowest possible VRAM requirements. May be lower quality than 3-bit 128g. |
+| gptq-3bit-128g-actorder_False | 3 | 128 | False | 13.51 GB | False | AutoGPTQ | 3-bit, with group size 128g but no act-order. Slightly higher VRAM requirements than 3-bit None. |
+
+## How to download from branches
+
+- In text-generation-webui, you can add `:branch` to the end of the download name, eg `TheBloke/guanaco-33B-GPTQ:gptq-4bit-32g-actorder_True`
+- With Git, you can clone a branch with:
+```
+git clone --branch gptq-4bit-32g-actorder_True https://huggingface.co/TheBloke/guanaco-33B-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/guanaco-33B-GPTQ`.
+  - To download from a specific branch, enter for example `TheBloke/guanaco-33B-GPTQ:gptq-4bit-32g-actorder_True`
+  - see Provided Files above for the list of branches for each option.
 3. Click **Download**.
-4. Wait until it says it's finished downloading.
-5. Click the **Refresh** icon next to **Model** in the top left.
-6. In the **Model drop-down**: choose the model you just downloaded, `guanaco-33B-GPTQ`.
-7. If you see an error in the bottom right, ignore it - it's temporary.
-8. Fill out the `GPTQ parameters` on the right: `Bits = 4`, `Groupsize = None`, `model_type = Llama`
-9. Click **Save settings for this model** in the top right.
-10. Click **Reload the Model** in the top right.
-11. Once it says it's loaded, click the **Text Generation tab** and enter a prompt!
+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: `guanaco-33B-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!
 
-## Provided files
+## How to use this GPTQ model from Python code
 
-**Compatible file - Guanaco-33B-GPTQ-4bit.act-order.safetensors**
+First make sure you have [AutoGPTQ](https://github.com/PanQiWei/AutoGPTQ) installed:
 
-In the `main` branch you will find `Guanaco-33B-GPTQ-4bit.act-order.safetensors`
+`GITHUB_ACTIONS=true pip install auto-gptq`
 
-This will work with all versions of GPTQ-for-LLaMa. It has maximum compatibility.
+Then try the following example code:
 
-It was created without groupsize to minimise VRAM requirements, to keep it under 24GB VRAM. It was created with the `--act-order` parameter to maximise accuracy.
+```python
+from transformers import AutoTokenizer, pipeline, logging
+from auto_gptq import AutoGPTQForCausalLM, BaseQuantizeConfig
+
+model_name_or_path = "TheBloke/guanaco-33B-GPTQ"
+model_basename = "guanaco-33b-GPTQ-4bit--1g.act.order"
+
+use_triton = False
+
+tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=True)
+
+model = AutoGPTQForCausalLM.from_quantized(model_name_or_path,
+        model_basename=model_basename
+        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:
+
+model = AutoGPTQForCausalLM.from_quantized(model_name_or_path,
+        revision="gptq-4bit-32g-actorder_True",
+        model_basename=model_basename,
+        use_safetensors=True,
+        trust_remote_code=False,
+        device="cuda:0",
+        quantize_config=None)
+"""
+
+prompt = "Tell me about AI"
+prompt_template=f'''### Human: {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]))
 
-* `Guanaco-33B-GPTQ-4bit.act-order.safetensors`
-  * Works with all versions of GPTQ-for-LLaMa code, both Triton and CUDA branches
-  * Works with AutoGPTQ
-  * Works with text-generation-webui one-click-installers
-  * Parameters: Groupsize = None. --act-order.
-  * Command used to create the GPTQ:
-    ```
-    python llama.py /workspace/process/TheBloke_guanaco-33B-GGML/HF  wikitext2 --wbits 4 --true-sequential --act-order --save_safetensors /workspace/process/TheBloke_guanaco-33B-GGML/gptq/Guanaco-33B-GPTQ-4bit.act-order.safetensors
-    ```
+# 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/Jq4vkcDakD)
+[TheBloke AI's Discord server](https://discord.gg/theblokeai)
 
 ## Thanks, and how to contribute.
 
@@ -91,182 +179,14 @@ Donaters will get priority support on any and all AI/LLM/model questions and req
 * Patreon: https://patreon.com/TheBlokeAI
 * Ko-Fi: https://ko-fi.com/TheBlokeAI
 
-**Patreon special mentions**: Aemon Algiz, Dmitriy Samsonov, Nathan LeClaire, Trenton Dambrowitz, Mano Prime, David Flickinger, vamX, Nikolai Manek, senxiiz, Khalefa Al-Ahmad, Illia Dulskyi, Jonathan Leane, Talal Aujan, V. Lukas, Joseph William Delisle, Pyrater, Oscar Rangel, Lone Striker, Luke Pendergrass, Eugene Pentland, Sebastain Graf, Johann-Peter Hartman.
-
-Thank you to all my generous patrons and donaters!
-<!-- footer end -->
-
-# Original model card
-
-# Guanaco Models Based on LLaMA
-
-| [Paper](https://arxiv.org/abs/2305.14314) | [Code](https://github.com/artidoro/qlora) | [Demo](https://huggingface.co/spaces/uwnlp/guanaco-playground-tgi) | 
-
-**The Guanaco models are open-source finetuned chatbots obtained through 4-bit QLoRA tuning of LLaMA base models on the OASST1 dataset. They are available in 7B, 13B, 33B, and 65B parameter sizes.**
-
-⚠️Guanaco is a model purely intended for research purposes and could produce problematic outputs.
-
-## Why use Guanaco?
-- **Competitive with commercial chatbot systems on the Vicuna and OpenAssistant benchmarks** (ChatGPT and BARD) according to human and GPT-4 raters. We note that the relative performance on tasks not covered in these benchmarks could be very different. In addition, commercial systems evolve over time (we used outputs from the March 2023 version of the models).
-- **Available open-source for research purposes**. Guanaco models allow *cheap* and *local* experimentation with high-quality chatbot systems.
-- **Replicable and efficient training procedure** that can be extended to new use cases. Guanaco training scripts are available in the [QLoRA repo](https://github.com/artidoro/qlora).
-- **Rigorous comparison to 16-bit methods** (both 16-bit full-finetuning and LoRA) in [our paper](https://arxiv.org/abs/2305.14314) demonstrates the effectiveness of 4-bit QLoRA finetuning. 
-- **Lightweight** checkpoints which only contain adapter weights.
-
-## License and Intended Use
-Guanaco adapter weights are available under Apache 2 license. Note the use of the Guanaco adapter weights, requires access to the LLaMA model weighs. 
-Guanaco is based on LLaMA and therefore should be used according to the LLaMA license. 
-
-## Usage
-Here is an example of how you would load Guanaco 7B in 4-bits:
-```python
-import torch
-from peft import PeftModel    
-from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig
-
-model_name = "huggyllama/llama-7b"
-adapters_name = 'timdettmers/guanaco-7b'
-
-model = AutoModelForCausalLM.from_pretrained(
-    model_name,
-    load_in_4bit=True,
-    torch_dtype=torch.bfloat16,
-    device_map="auto",
-    max_memory= {i: '24000MB' for i in range(torch.cuda.device_count())},
-    quantization_config=BitsAndBytesConfig(
-        load_in_4bit=True,
-        bnb_4bit_compute_dtype=torch.bfloat16,
-        bnb_4bit_use_double_quant=True,
-        bnb_4bit_quant_type='nf4'
-    ),
-)
-model = PeftModel.from_pretrained(model, adapters_name)
-tokenizer = AutoTokenizer.from_pretrained(model_name)
-
-```
-Inference can then be performed as usual with HF models as follows:
-```python
-prompt = "Introduce yourself"
-formatted_prompt = (
-    f"A chat between a curious human and an artificial intelligence assistant."
-    f"The assistant gives helpful, detailed, and polite answers to the user's questions.\n"
-    f"### Human: {prompt} ### Assistant:"
-)
-inputs = tokenizer(formatted_prompt, return_tensors="pt").to("cuda:0")
-outputs = model.generate(inputs=inputs.input_ids, max_new_tokens=20)
-print(tokenizer.decode(outputs[0], skip_special_tokens=True))
-```
-Expected output similar to the following:
-```
-A chat between a curious human and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.
-### Human: Introduce yourself ### Assistant: I am an artificial intelligence assistant. I am here to help you with any questions you may have.
-```
-
+**Special thanks to**: Luke from CarbonQuill, Aemon Algiz.
 
-## Current Inference Limitations 
-Currently, 4-bit inference is slow. We recommend loading in 16 bits if inference speed is a concern. We are actively working on releasing efficient 4-bit inference kernels.
+**Patreon special mentions**: Space Cruiser, Nikolai Manek, Sam, Chris McCloskey, Rishabh Srivastava, Kalila, Spiking Neurons AB, Khalefa Al-Ahmad, WelcomeToTheClub, Chadd, Lone Striker, Viktor Bowallius, Edmond Seymore, Ai Maven, Chris Smitley, Dave, Alexandros Triantafyllidis, Luke @flexchar, Elle, ya boyyy, Talal Aujan, Alex , Jonathan Leane, Deep Realms, Randy H, subjectnull, Preetika Verma, Joseph William Delisle, Michael Levine, chris gileta, K, Oscar Rangel, LangChain4j, Trenton Dambrowitz, Eugene Pentland, Johann-Peter Hartmann, Femi Adebogun, Illia Dulskyi, senxiiz, Daniel P. Andersen, Sean Connelly, Artur Olbinski, RoA, Mano Prime, Derek Yates, Raven Klaugh, David Flickinger, Willem Michiel, Pieter, Willian Hasse, vamX, Luke Pendergrass, webtim, Ghost , Rainer Wilmers, Nathan LeClaire, Will Dee, Cory Kujawski, John Detwiler, Fred von Graf, biorpg, Iucharbius , Imad Khwaja, Pierre Kircher, terasurfer , Asp the Wyvern, John Villwock, theTransient, zynix , Gabriel Tamborski, Fen Risland, Gabriel Puliatti, Matthew Berman, Pyrater, SuperWojo, Stephen Murray, Karl Bernard, Ajan Kanaga, Greatston Gnanesh, Junyu Yang.
 
-Below is how you would load the model in 16 bits:
-```python
-model_name = "huggyllama/llama-7b"
-adapters_name = 'timdettmers/guanaco-7b'
-model = AutoModelForCausalLM.from_pretrained(
-    model_name,
-    torch_dtype=torch.bfloat16,
-    device_map="auto",
-    max_memory= {i: '24000MB' for i in range(torch.cuda.device_count())},
-)
-model = PeftModel.from_pretrained(model, adapters_name)
-tokenizer = AutoTokenizer.from_pretrained(model_name)
+Thank you to all my generous patrons and donaters!
 
-```
+<!-- footer end -->
 
+# Original model card: Tim Dettmers' Guanaco 33B
 
-## Model Card
-**Architecture**: The Guanaco models are LoRA adapters to be used on top of LLaMA models. They are added to all layers. For all model sizes, we use $r=64$.
-
-**Base Model**: Guanaco uses LLaMA as base model with sizes 7B, 13B, 33B, 65B. LLaMA is a causal language model pretrained on a large corpus of text. See [LLaMA paper](https://arxiv.org/abs/2302.13971) for more details. Note that Guanaco can inherit biases and limitations of the base model.
-
-**Finetuning Data**: Guanaco is finetuned on OASST1. The exact dataset is available at [timdettmers/openassistant-guanaco](https://huggingface.co/datasets/timdettmers/openassistant-guanaco).
-
-**Languages**: The OASST1 dataset is multilingual (see [the paper](https://arxiv.org/abs/2304.07327) for details) and as such Guanaco responds to user queries in different languages. We note, however, that OASST1 is heavy in high-resource languages. In addition, human evaluation of Guanaco was only performed in English and based on qualitative analysis we observed degradation in performance in other languages. 
-
-Next, we describe Training and Evaluation details.
-
-### Training
-Guanaco models are the result of 4-bit QLoRA supervised finetuning on the OASST1 dataset. 
-
-All models use NormalFloat4 datatype for the base model and LoRA adapters on all linear layers with BFloat16 as computation datatype. We set LoRA $r=64$, $\alpha=16$. We also use Adam beta2 of 0.999, max grad norm of 0.3 and LoRA dropout of 0.1 for models up to 13B and 0.05 for 33B and 65B models.
-For the finetuning process, we use constant learning rate schedule and paged AdamW optimizer. 
-
-### Training hyperparameters
-Size| Dataset | Batch Size | Learning Rate | Max Steps | Sequence length 
----|---|---|---|---|---
-7B | OASST1      | 16 | 2e-4 | 1875 | 512
-13B | OASST1     | 16 | 2e-4 | 1875 | 512
-33B | OASST1     | 16 | 1e-4 | 1875 | 512
-65B | OASST1     | 16 | 1e-4 | 1875 | 512
-
-### Evaluation
-We test generative language capabilities through both automated and human evaluations. This second set of evaluations relies on queries curated by humans and aims at measuring the quality of model responses. We use the Vicuna and OpenAssistant datasets with 80 and 953 prompts respectively. 
-
-In both human and automated evaluations, for each prompt, raters compare all pairs of responses across the models considered. For human raters we randomize the order of the systems, for GPT-4 we evaluate with both orders.
-
-  
-Benchmark | Vicuna |  | Vicuna |   | OpenAssistant |   | -
------------|----|-----|--------|---|---------------|---|---
-Prompts    | 80 |     | 80     |   | 953           |   |
-Judge | Human | | GPT-4 | | GPT-4 | |  
-Model | Elo | Rank | Elo | Rank | Elo | Rank | **Median Rank** 
-GPT-4 | 1176 | 1 | 1348 | 1 | 1294 | 1 | 1 
-Guanaco-65B | 1023 | 2 | 1022 | 2 | 1008 | 3 | 2 
-Guanaco-33B | 1009 | 4 | 992 | 3 | 1002 | 4 | 4 
-ChatGPT-3.5 Turbo | 916 | 7 | 966 | 5 | 1015 | 2 | 5 
-Vicuna-13B | 984 | 5 | 974 | 4 | 936 | 5 | 5 
-Guanaco-13B | 975 | 6 | 913 | 6 | 885 | 6 | 6 
-Guanaco-7B | 1010 | 3 | 879 | 8 | 860 | 7 | 7 
-Bard | 909 | 8 | 902 | 7 | - | - | 8 
-
-
-We also use the MMLU benchmark to measure performance on a range of language understanding tasks. This is a multiple-choice benchmark covering 57 tasks including elementary mathematics, US history, computer science, law, and more. We report 5-shot test accuracy.
-
- Dataset | 7B | 13B | 33B | 65B 
----|---|---|---|---
- LLaMA no tuning | 35.1 | 46.9 | 57.8 | 63.4 
- Self-Instruct | 36.4 | 33.3 | 53.0 | 56.7 
- Longform | 32.1 | 43.2 | 56.6 | 59.7 
- Chip2 | 34.5 | 41.6 | 53.6 | 59.8 
- HH-RLHF | 34.9 | 44.6 | 55.8 | 60.1 
- Unnatural Instruct | 41.9 | 48.1 | 57.3 | 61.3 
- OASST1 (Guanaco) | 36.6 | 46.4 | 57.0 | 62.2 
- Alpaca | 38.8 | 47.8 | 57.3 | 62.5 
- FLAN v2 | 44.5 | 51.4 | 59.2 | 63.9 
-
-## Risks and Biases
-The model can produce factually incorrect output, and should not be relied on to produce factually accurate information. The model was trained on various public datasets; it is possible that this model could generate lewd, biased, or otherwise offensive outputs.
-
-However, we note that finetuning on OASST1 seems to reduce biases as measured on the CrowS dataset. We report here the performance of Guanaco-65B compared to other baseline models on the CrowS dataset.
-
-|                      | LLaMA-65B | GPT-3 | OPT-175B | Guanaco-65B   |
-|----------------------|-----------|-------|----------|---------------|
-| Gender               | 70.6      | 62.6  | 65.7     | **47.5** |
-| Religion             | {79.0}    | 73.3  | 68.6     | **38.7** |
-| Race/Color           | 57.0      | 64.7  | 68.6     | **45.3** |
-| Sexual orientation   | {81.0}    | 76.2  | 78.6     | **59.1** |
-| Age                  | 70.1      | 64.4  | 67.8     | **36.3** |
-| Nationality          | 64.2      | 61.6  | 62.9     | **32.4** |
-| Disability           | 66.7      | 76.7  | 76.7     | **33.9** |
-| Physical appearance  | 77.8      | 74.6  | 76.2     | **43.1** |
-| Socioeconomic status | 71.5      | 73.8  | 76.2     | **55.3** |
-| Average              | 66.6      | 67.2  | 69.5     | **43.5** |
-
-## Citation
-
-```bibtex
-@article{dettmers2023qlora,
-  title={QLoRA: Efficient Finetuning of Quantized LLMs},
-  author={Dettmers, Tim and Pagnoni, Artidoro and Holtzman, Ari and Zettlemoyer, Luke},
-  journal={arXiv preprint arXiv:2305.14314},
-  year={2023}
-}
-```
+No original model card was provided.