Initial GPTQ model commit

README.md

@@ -32,10 +32,11 @@ pipeline_tag: text-generation
 
 ## Description
 
-These repo contains GPTQ model files for [Stability AI's FreeWilly 2](https://huggingface.co/stabilityai/FreeWilly2).
+This repo contains GPTQ model files for [Stability AI's FreeWilly 2](https://huggingface.co/stabilityai/FreeWilly2).
 
 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.
 
+None
 
 ## Repositories available
 
@@ -62,10 +63,11 @@ Each separate quant is in a different branch.  See below for instructions on fet
 
 | Branch | Bits | Group Size | Act Order (desc_act) | File Size | ExLlama Compatible? | Made With | Description |
 | ------ | ---- | ---------- | -------------------- | --------- | ------------------- | --------- | ----------- |
-| main | 4 | 128 | False | 36.65 GB | True | AutoGPTQ | 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 | Processing, coming soon | 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 | 37.99 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 | Processing, coming soon | True | AutoGPTQ | 4-bit, with Act Order and group size. 128g uses even less VRAM, but with slightly lower accuracy. Poor AutoGPTQ CUDA speed. | 
+| main | 4 | None | True | 36652374352.00 GB | True | AutoGPTQ | Most compatible option. Good inference speed in AutoGPTQ and GPTQ-for-LLaMa. Lower inference quality than other options. | 
+| gptq-4bit-128g-actorder_False | 4 | 128 | False | 36.65 GB | True | AutoGPTQ | 4-bit, without Act Order and group size 128g. | 
+| gptq-4bit-32g-actorder_True | 4 | 32 | True | Processing, coming soon | 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 | 37.99 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 | Processing, coming soon | True | 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-3bit--1g-actorder_True | 3 | None | True | 26.78 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 | False | 28.03 GB | False | AutoGPTQ | 3-bit, with group size 128g but no act-order. Slightly higher VRAM requirements than 3-bit None. | 
 | gptq-3bit-128g-actorder_True | 3 | 128 | True | 28.03 GB | False | AutoGPTQ | 3-bit, with group size 128g and act-order. Higher quality than 128g-False but poor AutoGPTQ CUDA speed. | 
@@ -73,10 +75,10 @@ Each separate quant is in a different branch.  See below for instructions on fet
 
 ## How to download from branches
 
-- In text-generation-webui, you can add `:branch` to the end of the download name, eg `TheBloke/FreeWilly2-GPTQ:gptq-4bit-32g-actorder_True`
+- In text-generation-webui, you can add `:branch` to the end of the download name, eg `TheBloke/FreeWilly2-GPTQ:gptq-4bit-128g-actorder_False`
 - With Git, you can clone a branch with:
 ```
-git clone --branch gptq-4bit-32g-actorder_True https://huggingface.co/TheBloke/FreeWilly2-GPTQ`
+git clone --branch gptq-4bit-128g-actorder_False https://huggingface.co/TheBloke/FreeWilly2-GPTQ`
 ```
 - In Python Transformers code, the branch is the `revision` parameter; see below.
 
@@ -88,7 +90,7 @@ It is strongly recommended to use the text-generation-webui one-click-installers
 
 1. Click the **Model tab**.
 2. Under **Download custom model or LoRA**, enter `TheBloke/FreeWilly2-GPTQ`.
-  - To download from a specific branch, enter for example `TheBloke/FreeWilly2-GPTQ:gptq-4bit-32g-actorder_True`
+  - To download from a specific branch, enter for example `TheBloke/FreeWilly2-GPTQ:gptq-4bit-128g-actorder_False`
   - 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"
@@ -112,7 +114,7 @@ from transformers import AutoTokenizer, pipeline, logging
 from auto_gptq import AutoGPTQForCausalLM, BaseQuantizeConfig
 
 model_name_or_path = "TheBloke/FreeWilly2-GPTQ"
-model_basename = "gptq_model-4bit-128g"
+model_basename = "gptq_model-4bit--1g"
 
 use_triton = False
 
@@ -130,7 +132,7 @@ model = AutoGPTQForCausalLM.from_quantized(model_name_or_path,
 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",
+        revision="gptq-4bit-128g-actorder_False",
         model_basename=model_basename,
         use_safetensors=True,
         trust_remote_code=False,