Update for Transformers GPTQ support

README.md

@@ -13,17 +13,20 @@ tags:
 ---
 
 <!-- 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;">
+<!-- 200823 -->
+<div style="width: auto; margin-left: auto; margin-right: auto">
+<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 style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://discord.gg/theblokeai">Chat & support: TheBloke's 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>
+        <p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p>
     </div>
 </div>
+<div style="text-align:center; margin-top: 0em; margin-bottom: 0em"><p style="margin-top: 0.25em; margin-bottom: 0em;">TheBloke's LLM work is generously supported by a grant from <a href="https://a16z.com">andreessen horowitz (a16z)</a></p></div>
+<hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
 <!-- header end -->
 
 # Georgia Tech Research Institute's Galactica 30B Evol Instruct 70K GPTQ
@@ -75,7 +78,7 @@ from auto_gptq import AutoGPTQForCausalLM, BaseQuantizeConfig
 import argparse
 
 model_name_or_path = "TheBloke/galactica-30B-evol-instruct-70K-GPTQ"
-model_basename = "gptq_model-4bit--1g"
+model_basename = "model"
 
 use_triton = False
 
@@ -134,11 +137,12 @@ It was created without group_size to lower VRAM requirements, and with --act-ord
   * Parameters: Groupsize = -1. Act Order / desc_act = True.
 
 <!-- footer start -->
+<!-- 200823 -->
 ## 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.
 
@@ -153,12 +157,15 @@ 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
 
-**Special thanks to**: Luke from CarbonQuill, Aemon Algiz, Dmitriy Samsonov.
+**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**: vamX, K, Jonathan Leane, Lone Striker, Sean Connelly, Chris McCloskey, WelcomeToTheClub, Nikolai Manek, John Detwiler, Kalila, David Flickinger, Fen Risland, subjectnull, Johann-Peter Hartmann, Talal Aujan, John Villwock, senxiiz, Khalefa Al-Ahmad, Kevin Schuppel, Alps Aficionado, Derek Yates, Mano Prime, Nathan LeClaire, biorpg, trip7s trip, Asp the Wyvern, chris gileta, Iucharbius , Artur Olbinski, Ai Maven, Joseph William Delisle, Luke Pendergrass, Illia Dulskyi, Eugene Pentland, Ajan Kanaga, Willem Michiel, Space Cruiser, Pyrater, Preetika Verma, Junyu Yang, Oscar Rangel, Spiking Neurons AB, Pierre Kircher, webtim, Cory Kujawski, terasurfer , Trenton Dambrowitz, Gabriel Puliatti, Imad Khwaja, Luke.
 
 Thank you to all my generous patrons and donaters!
 
+And thank you again to a16z for their generous grant.
+
 <!-- footer end -->
 
 # Original model card: Georgia Tech Research Institute's Galactica 30B Evol Instruct 70K
@@ -174,7 +181,7 @@ The HF dataset for Evol-Instruct-70k can be found [here](https://huggingface.co/
 
 ## Model Details
 
-The GALACTICA models are trained on a large-scale scientific corpus and are designed to perform scientific tasks. 
+The GALACTICA models are trained on a large-scale scientific corpus and are designed to perform scientific tasks.
 Evol-instruct-70k is a dataset of evolved instruction-response pairs generated via the Evol-Instruct framework using gpt-3.5-turbo.
 
 ## Model Use
@@ -184,11 +191,11 @@ The original GALACTICA models are available under a non-commercial CC BY-NC 4.0
 
 <details>
   <summary> Example Outputs </summary>
-  
+
 *__Full Prompt:__*
 ```
 ### Instruction:
-Write out and explain Maxwell's equations using markdown and latex syntax. Highlight the key implication of each equation. 
+Write out and explain Maxwell's equations using markdown and latex syntax. Highlight the key implication of each equation.
 
 ### Response:
 ```
@@ -208,11 +215,11 @@ This equation states that the divergence of the magnetic field B is always zero.
 - **Maxwell-Faraday Equation:**
 $$\nabla \times \mathbf{E} = -\frac{\partial \mathbf{B}}{\partial t}$$
 This equation states that the curl of the electric field is equal to the negative of the time derivative of the magnetic field. This means that changing magnetic fields can create electric fields, and vice versa.
-  
+
 - **Ampere's Law with Maxwell's Addition:**
 $$\nabla \times \mathbf{B} = \mu_0 \left( \mathbf{J} + \epsilon_0 \frac{\partial \mathbf{E}}{\partial t} \right)$$
 This equation states that the curl of the magnetic field is equal to the product of the vacuum permeability μ0 and the sum of the electric current density J and the time derivative of the electric field. This means that changing electric fields can create magnetic fields, and that electric currents can also create magnetic fields.
-  
+
 **Implications**
 - Gauss's Laws imply that electric charges must be conserved, since the net charge in a closed system must always be zero.
 - The Maxwell-Faraday Equation implies that electromagnetic waves can travel through space, since changing magnetic fields can create electric fields, which can create changing magnetic fields, and so on. This is the basis for radio waves, microwaves, and other forms of electromagnetic radiation.
@@ -273,7 +280,7 @@ Qualitative evaluation suggests that the evol-instruct-70k fine-tuned Galactica
 
 ```bibtex
 @misc{xu2023wizardlm,
-      title={WizardLM: Empowering Large Language Models to Follow Complex Instructions}, 
+      title={WizardLM: Empowering Large Language Models to Follow Complex Instructions},
       author={Can Xu and Qingfeng Sun and Kai Zheng and Xiubo Geng and Pu Zhao and Jiazhan Feng and Chongyang Tao and Daxin Jiang},
       year={2023},
       eprint={2304.12244},

config.json

@@ -1,32 +1,43 @@
 {
-    "_name_or_path": "./galactica-30b-evol-instruct-70k/",
-    "_remove_final_layer_norm": false,
-    "activation_dropout": 0.0,
-    "activation_function": "gelu",
-    "architectures": [
-        "OPTForCausalLM"
-    ],
-    "attention_dropout": 0.1,
-    "bos_token_id": 0,
-    "do_layer_norm_before": true,
-    "dropout": 0.1,
-    "enable_bias": true,
-    "eos_token_id": 2,
-    "ffn_dim": 28672,
-    "hidden_size": 7168,
-    "init_std": 0.02,
-    "layer_norm_elementwise_affine": true,
-    "layerdrop": 0.0,
-    "learned_embeddings": true,
-    "max_position_embeddings": 2048,
-    "model_type": "opt",
-    "num_attention_heads": 56,
-    "num_hidden_layers": 48,
-    "pad_token_id": 1,
-    "scale_embeddings": false,
-    "torch_dtype": "bfloat16",
-    "transformers_version": "4.29.2",
-    "use_cache": true,
-    "vocab_size": 50000,
-    "word_embed_proj_dim": 7168
+  "_name_or_path": "./galactica-30b-evol-instruct-70k/",
+  "_remove_final_layer_norm": false,
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "architectures": [
+    "OPTForCausalLM"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 0,
+  "do_layer_norm_before": true,
+  "dropout": 0.1,
+  "enable_bias": true,
+  "eos_token_id": 2,
+  "ffn_dim": 28672,
+  "hidden_size": 7168,
+  "init_std": 0.02,
+  "layer_norm_elementwise_affine": true,
+  "layerdrop": 0.0,
+  "learned_embeddings": true,
+  "max_position_embeddings": 2048,
+  "model_type": "opt",
+  "num_attention_heads": 56,
+  "num_hidden_layers": 48,
+  "pad_token_id": 1,
+  "scale_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.29.2",
+  "use_cache": true,
+  "vocab_size": 50000,
+  "word_embed_proj_dim": 7168,
+  "quantization_config": {
+    "bits": 4,
+    "group_size": -1,
+    "damp_percent": 0.01,
+    "desc_act": true,
+    "sym": true,
+    "true_sequential": true,
+    "model_name_or_path": null,
+    "model_file_base_name": "model",
+    "quant_method": "gptq"
+  }
 }

gptq_model-4bit--1g.safetensors → model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92168124525e9c8d908944fb6492437d10d22cd786fa5982ad8fce94d00c5852
-size 16289789784
+oid sha256:66612ab8598796dc477b4ee8126f79e382261a310997a0b0ee312dbd61f40c5c
+size 16289789840

quantize_config.json

@@ -6,5 +6,5 @@
   "sym": true,
   "true_sequential": true,
   "model_name_or_path": null,
-  "model_file_base_name": null
+  "model_file_base_name": "model"
 }