Initial GPTQ model commit

README.md

@@ -49,27 +49,42 @@ Below is an instruction that describes a task. Write a response that appropriate
 ### Response:
 ```
 
-## Provided files
+## 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.
 
-| Branch | Bits | Group Size | Act Order (desc_act) | GPTQ Dataset | Size | ExLlama Compat? | Made With | Desc |
-| ------ | ---- | ---------- | -------------------- | ------------ | ---- | --------------- | --------- | ---- |
-| [main](https://huggingface.co/TheBloke/NewHope-GPTQ/tree/main) | 4 | 128 | No | [Evol Instruct Code](https://huggingface.co/datasets/nickrosh/Evol-Instruct-Code-80k-v1) | 7.26 GB | Yes | AutoGPTQ | 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/NewHope-GPTQ/tree/gptq-4bit-32g-actorder_True) | 4 | 32 | Yes | [Evol Instruct Code](https://huggingface.co/datasets/nickrosh/Evol-Instruct-Code-80k-v1) | 8.00 GB | Yes | 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](https://huggingface.co/TheBloke/NewHope-GPTQ/tree/gptq-4bit-64g-actorder_True) | 4 | 64 | Yes | [Evol Instruct Code](https://huggingface.co/datasets/nickrosh/Evol-Instruct-Code-80k-v1) | 7.51 GB | Yes | 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](https://huggingface.co/TheBloke/NewHope-GPTQ/tree/gptq-4bit-128g-actorder_True) | 4 | 128 | Yes | [Evol Instruct Code](https://huggingface.co/datasets/nickrosh/Evol-Instruct-Code-80k-v1) | 7.26 GB | Yes | AutoGPTQ | 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/NewHope-GPTQ/tree/gptq-8bit--1g-actorder_True) | 8 | None | Yes | [Evol Instruct Code](https://huggingface.co/datasets/nickrosh/Evol-Instruct-Code-80k-v1) | 13.36 GB | No | AutoGPTQ | 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/NewHope-GPTQ/tree/gptq-8bit-128g-actorder_True) | 8 | 128 | Yes | [Evol Instruct Code](https://huggingface.co/datasets/nickrosh/Evol-Instruct-Code-80k-v1) | 13.65 GB | No | AutoGPTQ | 8-bit, with group size 128g for higher inference quality and with Act Order for even higher accuracy. Poor AutoGPTQ CUDA speed. |
+All GPTQ files are made with AutoGPTQ.
+
+<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.
+- 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. The dataset used for quantisation can affect the quantisation accuracy. The dataset used for quantisation is not the same as the dataset used to train the model.
+- 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 affects the quantisation accuracy on longer inference sequences.
+- ExLlama Compatibility: Whether this file can be loaded with ExLlama, which currently only supports Llama models in 4-bit.
+
+</details>
+
+| Branch | Bits | GS | Act Order | Damp % | GPTQ Dataset | Seq Len | Size | ExLlama | Desc |
+| ------ | ---- | -- | --------- | ------ | ------------ | ------- | ---- | ------- | ---- |
+| [main](https://huggingface.co/TheBloke/NewHope-GPTQ/tree/main) | 4 | 128 | No | 0.1 | [Evol Instruct Code](https://huggingface.co/datasets/nickrosh/Evol-Instruct-Code-80k-v1) | 4096 | 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/NewHope-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) | 4096 | 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/NewHope-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) | 4096 | 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/NewHope-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) | 4096 | 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/NewHope-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) | 4096 | 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/NewHope-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) | 4096 | 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. |
 
 ## How to download from branches
 
 - In text-generation-webui, you can add `:branch` to the end of the download name, eg `TheBloke/NewHope-GPTQ:gptq-4bit-32g-actorder_True`
 - With Git, you can clone a branch with:
 ```
-git clone --branch --single-branch gptq-4bit-32g-actorder_True https://huggingface.co/TheBloke/NewHope-GPTQ
+git clone --single-branch --branch gptq-4bit-32g-actorder_True https://huggingface.co/TheBloke/NewHope-GPTQ
 ```
 - In Python Transformers code, the branch is the `revision` parameter; see below.
 
@@ -94,9 +109,19 @@ It is strongly recommended to use the text-generation-webui one-click-installers
 
 ## How to use this GPTQ model from Python code
 
-First make sure you have [AutoGPTQ](https://github.com/PanQiWei/AutoGPTQ) installed:
+First make sure you have [AutoGPTQ](https://github.com/PanQiWei/AutoGPTQ) 0.3.1 or later installed:
+
+```
+pip3 install auto-gptq
+```
 
-`GITHUB_ACTIONS=true pip install auto-gptq`
+If you have problems installing AutoGPTQ, please build from source instead:
+```
+pip3 uninstall -y auto-gptq
+git clone https://github.com/PanQiWei/AutoGPTQ
+cd AutoGPTQ
+pip3 install .
+```
 
 Then try the following example code:
 
@@ -105,14 +130,12 @@ from transformers import AutoTokenizer, pipeline, logging
 from auto_gptq import AutoGPTQForCausalLM, BaseQuantizeConfig
 
 model_name_or_path = "TheBloke/NewHope-GPTQ"
-model_basename = "gptq_model-4bit-128g"
 
 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",
@@ -120,11 +143,11 @@ model = AutoGPTQForCausalLM.from_quantized(model_name_or_path,
         quantize_config=None)
 
 """
-To download from a specific branch, use the revision parameter, as in this example:
+# 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",
-        model_basename=model_basename,
         use_safetensors=True,
         trust_remote_code=False,
         device="cuda:0",
@@ -202,105 +225,4 @@ Thank you to all my generous patrons and donaters!
 
 # Original model card: SLAM-group's NewHope
 
-# NewHope: Harnessing 99% of GPT-4's Programming Capabilities
-
-We introduce NewHope, a fine-tuned chat model based on llama-2-13b, aiming to provide a strong coding capability. NewHope handle different languages including Python, C++, Java, JavaScript, Go, and more. Preliminary evaluation on HumanEval shows that **NewHope possesses 99% of GPT-4's programming capabilities**.
-
-**Contact**: SLAM (<ins>S</ins>UFE <ins>L</ins>arge <ins>A</ins>I <ins>M</ins>odel) is a research group at Shanghai University of Finance and Economics. 
-cui.wanyun@sufe.edu.cn 
-
-**TODO**: We will release more evaluatation results and training details later.
-
-# Evaluation Results
-
-We evaluated NewHope on [HumanEval](https://github.com/openai/human-eval) using the official evaluation script by OpenAI. We compared the Pass@1 metric of NewHope with other models. The results of other models are from PapersWithCode.
-
-| Model | Pass@1 |
-| ----- | ------ |
-| **GPT-4** | **67.0**   |
-| **NewHope** | **66.5**  | 
-| PanGu-Coder2 15B | 61.6   |
-| WizardCoder 15B | 57.3  |
-| phi-1 1.3B | 50.6 |
-| GPT-3.5 | 48.1 |
-| phi-1-small | 45.0 |
-| PaLM-Coder | 36.0 |
-| CodeGeeX2-6B | 35.9 |
-
-# Model Weights
-
-We have open-sourced the model weights [NewHope](https://huggingface.co/SLAM-group/NewHope).
-
-We are uploading the model weights. The weights will be available in a few hours.
-
-
-# Usage
-
-To load the NewHope model using Transformers, use the following code:
-```
-import torch
-from transformers import LlamaTokenizer, LlamaForCausalLM
-
-base_model = "SLAM-group/NewHope"
-tokenizer = LlamaTokenizer.from_pretrained(base_model)
-model = LlamaForCausalLM.from_pretrained(base_model, torch_dtype=torch.float16, device_map="auto")
-# model.config.use_cache is default to `False`. For inference: `model.config.use_cache = True`
-```
-**Note:** At least Huggingface Transformers **4.31.0** is required to load this model!
-
-You can ask NewHope to generate code with instructions. We provide a simple example of how NewHope model generates code with the specific prompt:
-```
-# Suppose required tokenizer and model have already been loaded
-
-instruction = "Write a Python function to tell me what the date is today."
-prompt = f"<s> ### Instruction:\n{instruction}\n\n### Response:\n"
-inputs = tokenizer(prompt, add_special_tokens=False, return_tensors="pt").to("cuda")
-output = model.generate(**inputs, do_sample=True, top_p=0.9, max_new_tokens=2048)[0]
-decoded_output = tokenizer.decode(output, skip_special_tokens=True).split("### Response:\n")[-1].strip()
-print(decoded_output)
-```
-
-You can also interact with NewHope in a dialog manner with the following prompt:
-```
-<s> ### Instruction:\nQ1\n\n### Response:\nA1</s><s> ### Instruction:\nQ2\n\n### Response:\nA2</s>
-```
-
-
-# Evaluation
-
-### Local setup
-1. Install HumanEval for evaluation. [Details](https://github.com/openai/human-eval)
-2. Install dependencies
-
-   ```bash
-   pip install -r requirements.txt
-   ```
-
----
-For HumanEval, we use the following prompt:
-```
-example_input = 'def is_odd(number: int) -> bool:\n    """ Check whether the given number is odd\n    >>> is_odd(3)\n    True\n    >>> is_odd(6)\n    False\n    """\n'
-example_output = 'def is_odd(number: int) -> bool:\n    """ Check whether the given number is odd\n    >>> is_odd(3)\n    True\n    >>> is_odd(6)\n    False\n    """\n    return number % 2 == 1'
-
-task_in_humaneval = "REPLACE `task_in_humaneval` WITH THE SPECIFIC TASK IN HUMANEVAL DATA"
-
-prompt = f"<s> ### Instruction:\nComplete the given function below:\n\n{example_input}\n\n### Response:\n{example_output}</s><s> ### Instruction:\nComplete the given function below:\n\n{task_in_human_eval}\n\n### Response:\n"
-```
-
-To reproduce the results on HumanEval, use the following script:
-```
-python complete.py --base_model SLAM-group/NewHope --output_dir output --n_gpu 8
-```
-The above script will generate `samples.jsonl` in `output_dir`, which can be directly evaluated by HumanEval. [Evaluation procedure](https://github.com/openai/human-eval). We conducted the experiment with `fp16` on 8xA800, 80GB GPUs, reaching `66.5%` on Pass@1 (v.s. GPT4 `67.0%`).
-
-# Citation
-
-```
-@misc{2023newhope,
-    title={NewHope: Harnessing 99% of GPT-4's Programming Capabilities},
-    author={Wanyun Cui and Qianle Wang},
-    howpublished = https://github.com/SLAM-group/newhope,
-    year={2023}
-}
-```
-
+No original model card was provided.