Initial GPTQ model commit

README.md

@@ -8,7 +8,7 @@ language:
 license: llama2
 model_creator: OpenAssistant
 model_link: https://huggingface.co/OpenAssistant/codellama-13b-oasst-sft-v10
-model_name: CodeLlama 13B OASST SFT v10
+model_name: CodeLlama 13B SFT v10
 model_type: llama
 quantized_by: TheBloke
 ---
@@ -30,23 +30,28 @@ quantized_by: TheBloke
 <hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
 <!-- header end -->
 
-# CodeLlama 13B OASST SFT v10 - GPTQ
+# CodeLlama 13B SFT v10 - GPTQ
 - Model creator: [OpenAssistant](https://huggingface.co/OpenAssistant)
-- Original model: [CodeLlama 13B OASST SFT v10](https://huggingface.co/OpenAssistant/codellama-13b-oasst-sft-v10)
+- Original model: [CodeLlama 13B SFT v10](https://huggingface.co/OpenAssistant/codellama-13b-oasst-sft-v10)
 
+<!-- description start -->
 ## Description
 
-This repo contains GPTQ model files for [OpenAssistant's CodeLlama 13B OASST SFT v10](https://huggingface.co/OpenAssistant/codellama-13b-oasst-sft-v10).
+This repo contains GPTQ model files for [OpenAssistant's CodeLlama 13B SFT v10](https://huggingface.co/OpenAssistant/codellama-13b-oasst-sft-v10).
 
 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/CodeLlama-13B-oasst-sft-v10-GPTQ)
-* [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/CodeLlama-13B-oasst-sft-v10-GGUF)
-* [2, 3, 4, 5, 6 and 8-bit GGML models for CPU+GPU inference (deprecated)](https://huggingface.co/TheBloke/CodeLlama-13B-oasst-sft-v10-GGML)
+* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/CodeLlama-13B-OASST-SFT-v10-GPTQ)
+* [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/CodeLlama-13B-OASST-SFT-v10-GGUF)
+* [2, 3, 4, 5, 6 and 8-bit GGML models for CPU+GPU inference (deprecated)](https://huggingface.co/TheBloke/CodeLlama-13B-OASST-SFT-v10-GGML)
 * [OpenAssistant's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/OpenAssistant/codellama-13b-oasst-sft-v10)
+<!-- repositories-available end -->
 
+<!-- prompt-template start -->
 ## Prompt template: ChatML
 
 ```
@@ -58,6 +63,9 @@ Multiple GPTQ parameter permutations are provided; see Provided Files below for
 
 ```
 
+<!-- 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.
@@ -71,7 +79,7 @@ All GPTQ files are made with AutoGPTQ.
 
 - 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.
@@ -81,87 +89,89 @@ All GPTQ files are made with AutoGPTQ.
 
 | Branch | Bits | GS | Act Order | Damp % | GPTQ Dataset | Seq Len | Size | ExLlama | Desc |
 | ------ | ---- | -- | --------- | ------ | ------------ | ------- | ---- | ------- | ---- |
-| [main](https://huggingface.co/TheBloke/CodeLlama-13B-oasst-sft-v10-GPTQ/tree/main) | 4 | 128 | No | 0.1 | [Evol Instruct Code](https://huggingface.co/datasets/nickrosh/Evol-Instruct-Code-80k-v1) | 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/CodeLlama-13B-oasst-sft-v10-GPTQ/tree/gptq-4bit-32g-actorder_True) | 4 | 32 | Yes | 0.1 | [Evol Instruct Code](https://huggingface.co/datasets/nickrosh/Evol-Instruct-Code-80k-v1) | 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/CodeLlama-13B-oasst-sft-v10-GPTQ/tree/gptq-4bit-64g-actorder_True) | 4 | 64 | Yes | 0.1 | [Evol Instruct Code](https://huggingface.co/datasets/nickrosh/Evol-Instruct-Code-80k-v1) | 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/CodeLlama-13B-oasst-sft-v10-GPTQ/tree/gptq-4bit-128g-actorder_True) | 4 | 128 | Yes | 0.1 | [Evol Instruct Code](https://huggingface.co/datasets/nickrosh/Evol-Instruct-Code-80k-v1) | 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/CodeLlama-13B-oasst-sft-v10-GPTQ/tree/gptq-8bit--1g-actorder_True) | 8 | None | Yes | 0.1 | [Evol Instruct Code](https://huggingface.co/datasets/nickrosh/Evol-Instruct-Code-80k-v1) | 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/CodeLlama-13B-oasst-sft-v10-GPTQ/tree/gptq-8bit-128g-actorder_True) | 8 | 128 | Yes | 0.1 | [Evol Instruct Code](https://huggingface.co/datasets/nickrosh/Evol-Instruct-Code-80k-v1) | 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. |
+| main | 4 | 128 | No | 0.1 | [Evol Instruct Code](https://huggingface.co/datasets/nickrosh/Evol-Instruct-Code-80k-v1) | 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 | 4 | 32 | Yes | 0.1 | [Evol Instruct Code](https://huggingface.co/datasets/nickrosh/Evol-Instruct-Code-80k-v1) | 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 | 4 | 64 | Yes | 0.1 | [Evol Instruct Code](https://huggingface.co/datasets/nickrosh/Evol-Instruct-Code-80k-v1) | 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 | 4 | 128 | Yes | 0.1 | [Evol Instruct Code](https://huggingface.co/datasets/nickrosh/Evol-Instruct-Code-80k-v1) | 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 | 8 | None | Yes | 0.1 | [Evol Instruct Code](https://huggingface.co/datasets/nickrosh/Evol-Instruct-Code-80k-v1) | 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 | 8 | 128 | Yes | 0.1 | [Evol Instruct Code](https://huggingface.co/datasets/nickrosh/Evol-Instruct-Code-80k-v1) | 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. |
+
+<!-- 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/CodeLlama-13B-oasst-sft-v10-GPTQ:gptq-4bit-32g-actorder_True`
+- In text-generation-webui, you can add `:branch` to the end of the download name, eg `TheBloke/CodeLlama-13B-OASST-SFT-v10-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/CodeLlama-13B-oasst-sft-v10-GPTQ
+git clone --single-branch --branch gptq-4bit-32g-actorder_True https://huggingface.co/TheBloke/CodeLlama-13B-OASST-SFT-v10-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/CodeLlama-13B-oasst-sft-v10-GPTQ`.
-  - To download from a specific branch, enter for example `TheBloke/CodeLlama-13B-oasst-sft-v10-GPTQ:gptq-4bit-32g-actorder_True`
+2. Under **Download custom model or LoRA**, enter `TheBloke/CodeLlama-13B-OASST-SFT-v10-GPTQ`.
+  - To download from a specific branch, enter for example `TheBloke/CodeLlama-13B-OASST-SFT-v10-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: `CodeLlama-13B-oasst-sft-v10-GPTQ`
+6. In the **Model** dropdown, choose the model you just downloaded: `CodeLlama-13B-OASST-SFT-v10-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!
+<!-- 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:
-
-```python
-from transformers import AutoTokenizer, pipeline, logging
-from auto_gptq import AutoGPTQForCausalLM, BaseQuantizeConfig
+### For CodeLlama models only: you must use Transformers 4.33.0 or later.
 
-model_name_or_path = "TheBloke/CodeLlama-13B-oasst-sft-v10-GPTQ"
+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
+```
 
-use_triton = False
+### You can then use the following code
 
-tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=True)
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
 
-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)
+model_name_or_path = "TheBloke/CodeLlama-13B-OASST-SFT-v10-GPTQ"
+# 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.bfloat16,
+                                             device_map="auto",
+                                             revision="main")
 
-"""
-# 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)
-"""
+tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=True)
 
 prompt = "Tell me about AI"
 prompt_template=f'''<|im_start|>system
@@ -180,9 +190,6 @@ 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",
@@ -196,12 +203,17 @@ 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](https://github.com/turboderp/exllama) is compatible with Llama models in 4-bit. Please see the Provided Files table above for per-file compatibility.
 
-ExLlama works 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 -->
@@ -235,7 +247,7 @@ And thank you again to a16z for their generous grant.
 
 <!-- footer end -->
 
-# Original model card: OpenAssistant's CodeLlama 13B OASST SFT v10
+# Original model card: OpenAssistant's CodeLlama 13B SFT v10
 
 # Open-Assistant CodeLlama 13B SFT v10