Upload new GPTQs with varied parameters

README.md

@@ -1,14 +1,16 @@
 ---
-license: other
 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>
@@ -16,31 +18,63 @@ inference: false
 </div>
 <!-- header end -->
 
-# WizardLM: An Instruction-following LLM Using Evol-Instruct
+# WizardLM's WizardLM-7B 4bit GPTQ
+
+These files are GPTQ model files for [WizardLM's WizardLM-7B 4bit](https://huggingface.co/WizardLM/WizardLM-7B-V1.0).
 
-These files are the result of merging the [delta weights](https://huggingface.co/victor123/WizardLM) with the original Llama7B model.
+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.
 
-The code for merging is provided in the [WizardLM official Github repo](https://github.com/nlpxucan/WizardLM).
+These models were quantised using hardware kindly provided by [Latitude.sh](https://www.latitude.sh/accelerate).
 
-## WizardLM-7B 4bit GPTQ
+## Repositories available
 
-This repo contains 4bit GPTQ models for GPU inference, quantised using [GPTQ-for-LLaMa](https://github.com/qwopqwop200/GPTQ-for-LLaMa).
+* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/wizardLM-7B-GPTQ)
+* [2, 3, 4, 5, 6 and 8-bit GGML models for CPU+GPU inference](https://huggingface.co/TheBloke/wizardLM-7B-GGML)
+* [Unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/TheBloke/wizardLM-7B-HF)
+
+## Prompt template: WizardLM
+
+```
+{prompt}
+### Response:
+```
+
+## Provided files
 
-## Other repositories available
+Multiple quantisation parameters are provided, to allow you to choose the best one for your hardware and requirements.
 
-* [4bit GGML models for CPU inference](https://huggingface.co/TheBloke/wizardLM-7B-GGML)
-* [Unquantised model in HF format](https://huggingface.co/TheBloke/wizardLM-7B-HF)
+Each separate quant is in a different branch.  See below for instructions on fetching from different branches.
 
-## How to easily download and use this model in text-generation-webui
+| Branch | Bits | Group Size | Act Order (desc_act) | File Size | ExLlama Compatible? | Made With | Description |
+| ------ | ---- | ---------- | -------------------- | --------- | ------------------- | --------- | ----------- |
+| main | 4 | 128 | False | 4.52 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 | 4.28 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 | 4.02 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 | 3.90 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 | 7.01 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 | 7.16 GB | False | AutoGPTQ | 8-bit, with group size 128g for higher inference quality and without Act Order to improve AutoGPTQ speed. |
+| gptq-8bit-128g-actorder_True | 8 | 128 | True | 7.16 GB | False | AutoGPTQ | 8-bit, with group size 128g for higher inference quality and with Act Order for even higher accuracy. Poor AutoGPTQ CUDA speed. |
+| gptq-8bit-64g-actorder_True | 8 | 64 | True | 7.31 GB | False | AutoGPTQ | 8-bit, with group size 64g and Act Order for maximum inference quality. Poor AutoGPTQ CUDA speed. |
 
-Make sure text-generation-webui is updated to the latest version.
+## How to download from branches
 
-## How to easily download and use this model in text-generation-webui
+- In text-generation-webui, you can add `:branch` to the end of the download name, eg `TheBloke/wizardLM-7B-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/wizardLM-7B-GPTQ`
+```
+- In Python Transformers code, the branch is the `revision` parameter; see below.
 
-Please make sure you're using the latest version of 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](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/wizardLM-7B-GPTQ`.
+  - To download from a specific branch, enter for example `TheBloke/wizardLM-7B-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**.
@@ -50,29 +84,87 @@ Please make sure you're using the latest version of text-generation-webui
   * 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
+
+First make sure you have [AutoGPTQ](https://github.com/PanQiWei/AutoGPTQ) installed:
+
+`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
 
-Two files are provided. **The 'latest' file will not work unless you use a recent version of GPTQ-for-LLaMa**
+model_name_or_path = "TheBloke/wizardLM-7B-GPTQ"
+model_basename = "wizardLM-7B-GPTQ-4bit-128g.no-act.order"
 
-Specifically, the 'latest' file uses `--act-order` for maximum quantisation quality and will not work with oobabooga's fork of GPTQ-for-LLaMa. Therefore at this time it will also not work with `text-generation-webui` one-click installers.
+use_triton = False
 
-The 'compat' file will be used by default in text-generation-webui so you don't need to do anything special to use it.  If you want to use the 'latest' file, please remove the 'cmopat' file - but only do this if you are able to use the latest GPTQ-for-LLaMa code.
+tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=True)
 
-* `wizardLM-7B-GPTQ-4bit-128g.compat.no-act-order.safetensors`
-  * Works with all versions of GPTQ-for-LLaMa code, both Triton and CUDA branches
-  * Works with text-generation-webui one-click-installers
-  * Parameters: Groupsize = 128g. No act-order.
-  * Command used to create the GPTQ:
-    ```
-    CUDA_VISIBLE_DEVICES=0 python3 llama.py wizardLM-7B-HF c4 --wbits 4 --true-sequential --groupsize 128 --save_safetensors wizardLM-7B-GPTQ-4bit-128g.no-act-order.safetensors
-    ```
+model = AutoGPTQForCausalLM.from_quantized(model_name_or_path,
+        model_basename=model_basename
+        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:
+
+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'''{prompt}
+### Response:
+'''
+
+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/Jq4vkcDakD)
+[TheBloke AI's Discord server](https://discord.gg/theblokeai)
 
 ## Thanks, and how to contribute.
 
@@ -87,13 +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.
+**Special thanks to**: Luke from CarbonQuill, Aemon Algiz.
+
+**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 info
 
-Overview of Evol-Instruct
-Evol-Instruct is a novel method using LLMs instead of humans to automatically mass-produce open-domain instructions of various difficulty levels and skills range, to improve the performance of LLMs.
+# Original model card: WizardLM's WizardLM-7B 4bit
 
-![info](https://github.com/nlpxucan/WizardLM/raw/main/imgs/git_running.png)
+The WizardLM delta weights.