Upload README.md

README.md

@@ -33,18 +33,24 @@ quantized_by: TheBloke
 - Model creator: [Eric Hartford](https://huggingface.co/ehartford)
 - Original model: [Samantha 1.1 70B](https://huggingface.co/ehartford/Samantha-1.1-70b)
 
+<!-- description start -->
 ## Description
 
 This repo contains GPTQ model files for [Eric Hartford's Samantha 1.1 70B](https://huggingface.co/ehartford/Samantha-1.1-70b).
 
 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.
 
+<!-- description end -->
+<!-- repositories-available start -->
 ## Repositories available
 
 * [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/Samantha-1.1-70B-GPTQ)
-* [2, 3, 4, 5, 6 and 8-bit GGML models for CPU+GPU inference](https://huggingface.co/TheBloke/Samantha-1.1-70B-GGML)
+* [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/Samantha-1.1-70B-GGUF)
+* [2, 3, 4, 5, 6 and 8-bit GGML models for CPU+GPU inference (deprecated)](https://huggingface.co/TheBloke/Samantha-1.1-70B-GGML)
 * [Eric Hartford's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/ehartford/Samantha-1.1-70b)
+<!-- repositories-available end -->
 
+<!-- prompt-template start -->
 ## Prompt template: Samantha
 
 ```
@@ -52,22 +58,26 @@ You are Samantha, a sentient AI companion.
 
 USER: {prompt}
 ASSISTANT:
+
 ```
 
+<!-- prompt-template end -->
+
+<!-- README_GPTQ.md-provided-files start -->
 ## 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.
+All recent GPTQ files are made with AutoGPTQ, and all files in non-main branches are made with AutoGPTQ. Files in the `main` branch which were uploaded before August 2023 were made with GPTQ-for-LLaMa.
 
 <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.
+- Act Order: True or False. Also known as `desc_act`. True results in better quantisation accuracy. Some GPTQ clients have had issues with models that use Act Order plus Group Size, but this is generally resolved now.
 - 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.
@@ -84,6 +94,9 @@ All GPTQ files are made with AutoGPTQ.
 | [gptq-3bit--1g-actorder_True](https://huggingface.co/TheBloke/Samantha-1.1-70B-GPTQ/tree/gptq-3bit--1g-actorder_True) | 3 | None | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 26.77 GB | No | 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_True](https://huggingface.co/TheBloke/Samantha-1.1-70B-GPTQ/tree/gptq-3bit-128g-actorder_True) | 3 | 128 | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 28.03 GB | No | 3-bit, with group size 128g and act-order. Higher quality than 128g-False but poor AutoGPTQ CUDA speed. |
 
+<!-- README_GPTQ.md-provided-files end -->
+
+<!-- README_GPTQ.md-download-from-branches start -->
 ## How to download from branches
 
 - In text-generation-webui, you can add `:branch` to the end of the download name, eg `TheBloke/Samantha-1.1-70B-GPTQ:gptq-4bit-32g-actorder_True`
@@ -92,78 +105,78 @@ All GPTQ files are made with AutoGPTQ.
 git clone --single-branch --branch gptq-4bit-32g-actorder_True https://huggingface.co/TheBloke/Samantha-1.1-70B-GPTQ
 ```
 - In Python Transformers code, the branch is the `revision` parameter; see below.
-
+<!-- README_GPTQ.md-download-from-branches end -->
+<!-- README_GPTQ.md-text-generation-webui start -->
 ## 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.
+It is strongly recommended to use the text-generation-webui one-click-installers unless you're sure you know how to make a manual install.
 
 1. Click the **Model tab**.
 2. Under **Download custom model or LoRA**, enter `TheBloke/Samantha-1.1-70B-GPTQ`.
   - To download from a specific branch, enter for example `TheBloke/Samantha-1.1-70B-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"
+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: `Samantha-1.1-70B-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`.
+  * 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`.
 9. Once you're ready, click the **Text Generation tab** and enter a prompt to get started!
+<!-- README_GPTQ.md-text-generation-webui end -->
 
+<!-- README_GPTQ.md-use-from-python start -->
 ## 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:
+### Install the necessary packages
 
-```
-pip3 install auto-gptq
-```
+Requires: Transformers 4.32.0 or later, Optimum 1.12.0 or later, and AutoGPTQ 0.4.2 or later.
 
-If you have problems installing AutoGPTQ, please build from source instead:
+```shell
+pip3 install transformers>=4.32.0 optimum>=1.12.0
+pip3 install auto-gptq --extra-index-url https://huggingface.github.io/autogptq-index/whl/cu118/  # Use cu117 if on CUDA 11.7
 ```
+
+If you have problems installing AutoGPTQ using the pre-built wheels, install it from source instead:
+
+```shell
 pip3 uninstall -y auto-gptq
 git clone https://github.com/PanQiWei/AutoGPTQ
 cd AutoGPTQ
 pip3 install .
 ```
 
-Then try the following example code:
+### For CodeLlama models only: you must use Transformers 4.33.0 or later.
+
+If 4.33.0 is not yet released when you read this, you will need to install Transformers from source:
+```shell
+pip3 uninstall -y transformers
+pip3 install git+https://github.com/huggingface/transformers.git
+```
+
+### You can then use the following code
 
 ```python
-from transformers import AutoTokenizer, pipeline, logging
-from auto_gptq import AutoGPTQForCausalLM, BaseQuantizeConfig
+from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
 
 model_name_or_path = "TheBloke/Samantha-1.1-70B-GPTQ"
-
-use_triton = False
+# To use a different branch, change revision
+# For example: revision="gptq-4bit-32g-actorder_True"
+model = AutoModelForCausalLM.from_pretrained(model_name_or_path,
+                                             torch_dtype=torch.float16,
+                                             device_map="auto",
+                                             revision="main")
 
 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 Samantha, a sentient AI companion.
 
 USER: {prompt}
 ASSISTANT:
+
 '''
 
 print("\n\n*** Generate:")
@@ -174,9 +187,6 @@ 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",
@@ -190,12 +200,17 @@ pipe = pipeline(
 
 print(pipe(prompt_template)[0]['generated_text'])
 ```
+<!-- README_GPTQ.md-use-from-python end -->
 
+<!-- README_GPTQ.md-compatibility start -->
 ## 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.
+The files provided are tested to work with AutoGPTQ, both via Transformers and using AutoGPTQ directly. They should also work with [Occ4m's GPTQ-for-LLaMa fork](https://github.com/0cc4m/KoboldAI).
 
-ExLlama works with Llama models in 4-bit. Please see the Provided Files table above for per-file compatibility.
+[ExLlama](https://github.com/turboderp/exllama) is compatible with Llama models in 4-bit. Please see the Provided Files table above for per-file compatibility.
+
+[Huggingface Text Generation Inference (TGI)](https://github.com/huggingface/text-generation-inference) is compatible with all GPTQ models.
+<!-- README_GPTQ.md-compatibility end -->
 
 <!-- footer start -->
 <!-- 200823 -->
@@ -220,7 +235,7 @@ Donaters will get priority support on any and all AI/LLM/model questions and req
 
 **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
+**Patreon special mentions**: Russ Johnson, J, alfie_i, Alex, NimbleBox.ai, Chadd, Mandus, Nikolai Manek, Ken Nordquist, ya boyyy, Illia Dulskyi, Viktor Bowallius, vamX, Iucharbius, zynix, Magnesian, Clay Pascal, Pierre Kircher, Enrico Ros, Tony Hughes, Elle, Andrey, knownsqashed, Deep Realms, Jerry Meng, Lone Striker, Derek Yates, Pyrater, Mesiah Bishop, James Bentley, Femi Adebogun, Brandon Frisco, SuperWojo, Alps Aficionado, Michael Dempsey, Vitor Caleffi, Will Dee, Edmond Seymore, usrbinkat, LangChain4j, Kacper Wikieł, Luke Pendergrass, John Detwiler, theTransient, Nathan LeClaire, Tiffany J. Kim, biorpg, Eugene Pentland, Stanislav Ovsiannikov, Fred von Graf, terasurfer, Kalila, Dan Guido, Nitin Borwankar, 阿明, Ai Maven, John Villwock, Gabriel Puliatti, Stephen Murray, Asp the Wyvern, danny, Chris Smitley, ReadyPlayerEmma, S_X, Daniel P. Andersen, Olakabola, Jeffrey Morgan, Imad Khwaja, Caitlyn Gatomon, webtim, Alicia Loh, Trenton Dambrowitz, Swaroop Kallakuri, Erik Bjäreholt, Leonard Tan, Spiking Neurons AB, Luke @flexchar, Ajan Kanaga, Thomas Belote, Deo Leter, RoA, Willem Michiel, transmissions 11, subjectnull, Matthew Berman, Joseph William Delisle, David Ziegler, Michael Davis, Johann-Peter Hartmann, Talal Aujan, senxiiz, Artur Olbinski, Rainer Wilmers, Spencer Kim, Fen Risland, Cap'n Zoog, Rishabh Srivastava, Michael Levine, Geoffrey Montalvo, Sean Connelly, Alexandros Triantafyllidis, Pieter, Gabriel Tamborski, Sam, Subspace Studios, Junyu Yang, Pedro Madruga, Vadim, Cory Kujawski, K, Raven Klaugh, Randy H, Mano Prime, Sebastain Graf, Space Cruiser
 
 
 Thank you to all my generous patrons and donaters!
@@ -262,27 +277,38 @@ ASSISTANT:
 ```
 
 Example:
-```
-USER: I would like you to be my relationship coach.  I am dating again, after a long divorce.  Can you please give me advice about how to gain confidence and success?  
-ASSISTANT: Of course! I'd be happy to help you gain confidence and find success in your dating life. Here are a few tips to get you started:
-1. Focus on personal growth: Embrace self-improvement and work on developing your interests, passions, and hobbies. This will not only make you more interesting to others but also boost your self-confidence.
-2. Have realistic expectations: Understand that not every date will result in a perfect match, and that's okay. Embrace the learning process and be open to new experiences.
-3. Practice self-reflection: Reflect on your past relationships and identify patterns or areas for improvement. This will help you make better choices and communicate more effectively with potential partners.
-4. Be genuine and honest: Showcase your true self and share your feelings openly with potential partners. Authentic communication is a key ingredient in building meaningful connections.
-5. Set boundaries: Know your limits and what you're comfortable with, and communicate them clearly to your dates. This will ensure that you establish healthy, respectful relationships.
-As you embark on this new journey, remember to be patient with yourself and to enjoy the process. Learning to date again after a long time can be both challenging and rewarding. I'm here to support you and offer advice whenever you need it. Good luck and have fun!
-USER: Please give me a specific agenda for the next week.  I can spend 2 hours per day on this.  Plan my "me" time for the next week, so that my dating skills and confidence are maxii                                                                                                                                                                                     ee                                                                                                                                                                                     ..
-ASSISTANT: Here's a suggested agenda to help you improve your dating skills and confidence over the next week:
-1. Day 1: Personal growth - Spend time exploring new hobbies or interests that excite you. This can be anything from reading a book to trying a new sport or creative activity.
-2. Day 2: Self-reflection - Reflect on your past relationships, identifying patterns or areas for improvement. Write down your thoughts and insights.
-3. Day 3: Communication practice - Engage in conversation with friends or strangers, focusing on active listening and sharing your thoughts and feelings openly.
-4. Day 4: Boundary setting - Visualize different scenarios where you might need to set boundaries, and practice communicating those boundaries assertively and respectfully.
-5. Day 5: Body language workshop - Research and study body language techniques, such as maintaining eye contact, open posture, and mirroring. Practice implementing these techniques in a mirror or with friends.
-6. Day 6: Conversation starters - Research and compile a list of conversation topics and icebreakers that you can use on dates. Practice these with friends or family members.
-7. Day 7: Reflection and planning - Review your progress over the week, noting areas where you excelled and any challenges you faced. Use this reflection to plan your approach for future dates.
-
-Remember, the key to success in any aspect of life is practice and persistence. Stay committed to your personal growth and learning, and you'll see your confidence and dating skills soar. I'm here to support you every step of the way!
-```
+
+> **USER:**
+> 
+> I would like you to be my relationship coach.  I am dating again, after a long divorce.  Can you please give me advice about how to gain confidence and success?
+> 
+> **ASSISTANT:**
+> 
+> Of course! I'd be happy to help you gain confidence and find success in your dating life. Here are a few tips to get you started:
+> 1. Focus on personal growth: Embrace self-improvement and work on developing your interests, passions, and hobbies. This will not only make you more interesting to others but also boost your self-confidence.
+> 2. Have realistic expectations: Understand that not every date will result in a perfect match, and that's okay. Embrace the learning process and be open to new experiences.
+> 3. Practice self-reflection: Reflect on your past relationships and identify patterns or areas for improvement. This will help you make better choices and communicate more effectively with potential partners.
+> 4. Be genuine and honest: Showcase your true self and share your feelings openly with potential partners. Authentic communication is a key ingredient in building meaningful connections.
+> 5. Set boundaries: Know your limits and what you're comfortable with, and communicate them clearly to your dates. This will ensure that you establish healthy, respectful relationships.
+> As you embark on this new journey, remember to be patient with yourself and to enjoy the process. Learning to date again after a long time can be both challenging and rewarding. I'm here to support you and offer advice whenever you need it. Good luck and have fun!
+> 
+> **USER:**
+> 
+> Please give me a specific agenda for the next week.  I can spend 2 hours per day on this.  Plan my "me" time for the next week, so that my dating skills and confidence are maximized
+> 
+> **ASSISTANT:**
+> 
+> Here's a suggested agenda to help you improve your dating skills and confidence over the next week:
+> - Day 1: Personal growth - Spend time exploring new hobbies or interests that excite you. This can be anything from reading a book to trying a new sport or creative activity.
+> - Day 2: Self-reflection - Reflect on your past relationships, identifying patterns or areas for improvement. Write down your thoughts and insights.
+> - Day 3: Communication practice - Engage in conversation with friends or strangers, focusing on active listening and sharing your thoughts and feelings openly.
+> - Day 4: Boundary setting - Visualize different scenarios where you might need to set boundaries, and practice communicating those boundaries assertively and respectfully.
+> - Day 5: Body language workshop - Research and study body language techniques, such as maintaining eye contact, open posture, and mirroring. Practice implementing these techniques in a mirror or with friends.
+> - Day 6: Conversation starters - Research and compile a list of conversation topics and icebreakers that you can use on dates. Practice these with friends or family members.
+> - Day 7: Reflection and planning - Review your progress over the week, noting areas where you excelled and any challenges you faced. Use this reflection to plan your approach for future dates.
+> 
+> Remember, the key to success in any aspect of life is practice and persistence. Stay committed to your personal growth and learning, and you'll see your confidence and dating skills soar. I'm here to support you every step of the way!
+
 
 Official character card: (thanks MortalWombat)
 ![](https://files.catbox.moe/zx9hfh.png)