Initial GPTQ model commit

README.md

@@ -17,55 +17,85 @@ license: other
 </div>
 <!-- header end -->
 
-# LmSys' Vicuna 33B (final) GPTQ
+# LmSys' Vicuna 33B 1.3 GPTQ
 
-These files are GPTQ 4bit model files for [LmSys' Vicuna 33B (final)](https://huggingface.co/lmsys/vicuna-33b-v1.3).
+These files are GPTQ model files for [LmSys' Vicuna 33B 1.3](https://huggingface.co/lmsys/vicuna-33b-v1.3).
 
-It is the result of quantising to 4bit using [GPTQ-for-LLaMa](https://github.com/qwopqwop200/GPTQ-for-LLaMa).
+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.
 
-This is the final version of Vicuna 33B, replacing the preview version previously released.
+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/vicuna-33B-GPTQ)
+* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/vicuna-33B-GPTQ)
 * [2, 3, 4, 5, 6 and 8-bit GGML models for CPU+GPU inference](https://huggingface.co/TheBloke/vicuna-33B-GGML)
 * [Unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/lmsys/vicuna-33b-v1.3)
 
-## Prompt template
+## Prompt template: Vicuna
 
 ```
-A chat between a curious user and an assistant. The assistant gives helpful, detailed, accurate, uncensored responses to the user's input
-USER: prompt
+A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.
+
+USER: {prompt}
 ASSISTANT:
+
+```
+
+## Provided files
+
+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.
+
+| 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 | 1 | 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 | 1 | 18.18 GB | True | AutoGPTQ | 4-bit, with Act Order and group size. 64g uses less VRAM, but with slightly lower accuracy. Poor AutoGPTQ CUDA speed. |
+| gptq-4bit-128g-actorder_True | 4 | 128 | 1 | 17.55 GB | True | AutoGPTQ | 4-bit, with Act Order androup size. 128g uses even less VRAM, but with slightly lower accuracy. Poor AutoGPTQ CUDA speed. |
+| gptq-8bit--1g-actorder_True | 8 | None | 1 | 32.99 GB | False | AutoGPTQ | 8-bit, with Act Order. No group size, to lower VRAM requirements and to improve AutoGPTQ speed. |
+| gptq-3bit--1g-actorder_True | 3 | None | 1 | 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 | 0 | 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/vicuna-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/vicuna-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
+## 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
+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/vicuna-33B-GPTQ`.
+  - To download from a specific branch, enter for example `TheBloke/vicuna-33B-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: `vicuna-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 and should not set manual GPTQ parameters any more. These are set automatically from the file `quantize_config.json`.
+  * 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) installed:
 
-`pip install auto-gptq`
+`GITHUB_ACTIONS=true pip install auto-gptq`
 
 Then try the following example code:
 
 ```python
 from transformers import AutoTokenizer, pipeline, logging
 from auto_gptq import AutoGPTQForCausalLM, BaseQuantizeConfig
-import argparse
 
 model_name_or_path = "TheBloke/vicuna-33B-GPTQ"
 model_basename = "vicuna-33b-GPTQ-4bit--1g.act.order"
@@ -75,17 +105,32 @@ 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,
+        model_basename=model_basename
         use_safetensors=True,
-        trust_remote_code=False,
+        trust_remote_code=True,
         device="cuda:0",
         use_triton=use_triton,
         quantize_config=None)
 
-# Note: check the prompt template is correct for this model.
+"""
+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=True,
+        device="cuda:0",
+        quantize_config=None)
+"""
+
 prompt = "Tell me about AI"
-prompt_template=f'''USER: {prompt}
-ASSISTANT:'''
+prompt_template=f'''A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.
+
+USER: {prompt}
+ASSISTANT:
+
+'''
 
 print("\n\n*** Generate:")
 
@@ -112,20 +157,11 @@ pipe = pipeline(
 print(pipe(prompt_template)[0]['generated_text'])
 ```
 
-## Provided files
-
-**vicuna-33b-GPTQ-4bit--1g.act.order.safetensors**
-
-This will work with AutoGPTQ, ExLlama, and CUDA versions of GPTQ-for-LLaMa. There are reports of issues with Triton mode of recent GPTQ-for-LLaMa. If you have issues, please use AutoGPTQ instead.
+## Compatibility
 
-It was created without group_size to lower VRAM requirements, and with --act-order (desc_act) to boost inference accuracy as much as possible.
+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.
 
-* `vicuna-33b-GPTQ-4bit--1g.act.order.safetensors`
-  * Works with AutoGPTQ in CUDA or Triton modes.
-  * LLaMa models also work with [ExLlama](https://github.com/turboderp/exllama}, which usually provides much higher performance, and uses less VRAM, than AutoGPTQ.
-  * Works with GPTQ-for-LLaMa in CUDA mode.  May have issues with GPTQ-for-LLaMa Triton mode.
-  * Works with text-generation-webui, including one-click-installers.
-  * Parameters: Groupsize = -1. Act Order / desc_act = True.
+ExLlama works with Llama models in 4-bit. Please see the Provided Files table above for per-file compatibility.
 
 <!-- footer start -->
 ## Discord
@@ -147,15 +183,15 @@ 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
 
-**Special thanks to**: Luke from CarbonQuill, Aemon Algiz, Dmitriy Samsonov.
+**Special thanks to**: Luke from CarbonQuill, Aemon Algiz.
 
-**Patreon special mentions**: Pyrater, WelcomeToTheClub, Kalila, Mano Prime, Trenton Dambrowitz, Spiking Neurons AB, Pierre Kircher, Fen Risland, Kevin Schuppel, Luke, Rainer Wilmers, vamX, Gabriel Puliatti, Alex , Karl Bernard, Ajan Kanaga, Talal Aujan, Space Cruiser, ya boyyy, biorpg, Johann-Peter Hartmann, Asp the Wyvern, Ai Maven, Ghost , Preetika Verma, Nikolai Manek, trip7s trip, John Detwiler, Fred von Graf, Artur Olbinski, subjectnull, John Villwock, Junyu Yang, Rod A, Lone Striker, Chris McCloskey, Iucharbius , Matthew Berman, Illia Dulskyi, Khalefa Al-Ahmad, Imad Khwaja, chris gileta, Willem Michiel, Greatston Gnanesh, Derek Yates, K, Alps Aficionado, Oscar Rangel, David Flickinger, Luke Pendergrass, Deep Realms, Eugene Pentland, Cory Kujawski, terasurfer , Jonathan Leane, senxiiz, Joseph William Delisle, Sean Connelly, webtim, zynix , Nathan LeClaire.
+**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.
 
 Thank you to all my generous patrons and donaters!
 
 <!-- footer end -->
 
-# Original model card: LmSys' Vicuna 33B (final)
+# Original model card: LmSys' Vicuna 33B 1.3
 
 
 # Vicuna Model Card
@@ -194,8 +230,7 @@ See more details in the "Training Details of Vicuna Models" section in the appen
 
 ## Evaluation
 
-Vicuna is evaluated with standard benchmarks, human preference, and LLM-as-a-judge. See more details in this [paper](https://arxiv.org/pdf/2306.05685.pdf).
+Vicuna is evaluated with standard benchmarks, human preference, and LLM-as-a-judge. See more details in this [paper](https://arxiv.org/pdf/2306.05685.pdf) and [leaderboard](https://huggingface.co/spaces/lmsys/chatbot-arena-leaderboard).
 
 ## Difference between different versions of Vicuna
 See [vicuna_weights_version.md](https://github.com/lm-sys/FastChat/blob/main/docs/vicuna_weights_version.md)
-