Update for Transformers GPTQ support

README.md

@@ -17,17 +17,20 @@ 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/theblokeai">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 -->
 
 # Vigogne 2 7B Instruct - GPTQ
@@ -65,13 +68,13 @@ Each separate quant is in a different branch.  See below for instructions on fet
 
 | Branch | Bits | Group Size | Act Order (desc_act) | GPTQ Dataset | Size | ExLlama Compat? | Made With | Desc |
 | ------ | ---- | ---------- | -------------------- | ------------ | ---- | --------------- | --------- | ---- |
-| [main](https://huggingface.co/TheBloke/Vigogne-2-7B-Instruct-GPTQ/tree/main) | 4 | 128 | No | [French news](https://huggingface.co/datasets/gustavecortal/diverse_french_news) | 3.90 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/Vigogne-2-7B-Instruct-GPTQ/tree/gptq-4bit-32g-actorder_True) | 4 | 32 | Yes | [French news](https://huggingface.co/datasets/gustavecortal/diverse_french_news) | 4.28 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/Vigogne-2-7B-Instruct-GPTQ/tree/gptq-4bit-64g-actorder_True) | 4 | 64 | Yes | [French news](https://huggingface.co/datasets/gustavecortal/diverse_french_news) | 4.02 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/Vigogne-2-7B-Instruct-GPTQ/tree/gptq-4bit-128g-actorder_True) | 4 | 128 | Yes | [French news](https://huggingface.co/datasets/gustavecortal/diverse_french_news) | 3.90 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/Vigogne-2-7B-Instruct-GPTQ/tree/gptq-8bit--1g-actorder_True) | 8 | None | Yes | [French news](https://huggingface.co/datasets/gustavecortal/diverse_french_news) | 7.01 GB | No | AutoGPTQ | 8-bit, with Act Order. No group size, to lower VRAM requirements and to improve AutoGPTQ speed. | 
-| [gptq-8bit-128g-actorder_False](https://huggingface.co/TheBloke/Vigogne-2-7B-Instruct-GPTQ/tree/gptq-8bit-128g-actorder_False) | 8 | 128 | No | [French news](https://huggingface.co/datasets/gustavecortal/diverse_french_news) | 7.16 GB | No | AutoGPTQ | 8-bit, with group size 128g for higher inference quality and without Act Order to improve AutoGPTQ speed. | 
-| [gptq-8bit-128g-actorder_True](https://huggingface.co/TheBloke/Vigogne-2-7B-Instruct-GPTQ/tree/gptq-8bit-128g-actorder_True) | 8 | 128 | Yes | [French news](https://huggingface.co/datasets/gustavecortal/diverse_french_news) | 7.16 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. | 
+| [main](https://huggingface.co/TheBloke/Vigogne-2-7B-Instruct-GPTQ/tree/main) | 4 | 128 | No | [French news](https://huggingface.co/datasets/gustavecortal/diverse_french_news) | 3.90 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/Vigogne-2-7B-Instruct-GPTQ/tree/gptq-4bit-32g-actorder_True) | 4 | 32 | Yes | [French news](https://huggingface.co/datasets/gustavecortal/diverse_french_news) | 4.28 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/Vigogne-2-7B-Instruct-GPTQ/tree/gptq-4bit-64g-actorder_True) | 4 | 64 | Yes | [French news](https://huggingface.co/datasets/gustavecortal/diverse_french_news) | 4.02 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/Vigogne-2-7B-Instruct-GPTQ/tree/gptq-4bit-128g-actorder_True) | 4 | 128 | Yes | [French news](https://huggingface.co/datasets/gustavecortal/diverse_french_news) | 3.90 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/Vigogne-2-7B-Instruct-GPTQ/tree/gptq-8bit--1g-actorder_True) | 8 | None | Yes | [French news](https://huggingface.co/datasets/gustavecortal/diverse_french_news) | 7.01 GB | No | AutoGPTQ | 8-bit, with Act Order. No group size, to lower VRAM requirements and to improve AutoGPTQ speed. |
+| [gptq-8bit-128g-actorder_False](https://huggingface.co/TheBloke/Vigogne-2-7B-Instruct-GPTQ/tree/gptq-8bit-128g-actorder_False) | 8 | 128 | No | [French news](https://huggingface.co/datasets/gustavecortal/diverse_french_news) | 7.16 GB | No | AutoGPTQ | 8-bit, with group size 128g for higher inference quality and without Act Order to improve AutoGPTQ speed. |
+| [gptq-8bit-128g-actorder_True](https://huggingface.co/TheBloke/Vigogne-2-7B-Instruct-GPTQ/tree/gptq-8bit-128g-actorder_True) | 8 | 128 | Yes | [French news](https://huggingface.co/datasets/gustavecortal/diverse_french_news) | 7.16 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. |
 | [gptq-8bit-64g-actorder_True](https://huggingface.co/TheBloke/Vigogne-2-7B-Instruct-GPTQ/tree/gptq-8bit-64g-actorder_True) | 8 | 64 | Yes | [French news](https://huggingface.co/datasets/gustavecortal/diverse_french_news) | 7.31 GB | No | AutoGPTQ | 8-bit, with group size 64g and Act Order for maximum inference quality. Poor AutoGPTQ CUDA speed. |
 
 ## How to download from branches
@@ -115,7 +118,7 @@ from transformers import AutoTokenizer, pipeline, logging
 from auto_gptq import AutoGPTQForCausalLM, BaseQuantizeConfig
 
 model_name_or_path = "TheBloke/Vigogne-2-7B-Instruct-GPTQ"
-model_basename = "gptq_model-4bit-128g"
+model_basename = "model"
 
 use_triton = False
 
@@ -182,6 +185,7 @@ The files provided will work with AutoGPTQ (CUDA and Triton modes), GPTQ-for-LLa
 ExLlama works with Llama models in 4-bit. Please see the Provided Files table above for per-file compatibility.
 
 <!-- footer start -->
+<!-- 200823 -->
 ## Discord
 
 For further support, and discussions on these models and AI in general, join us at:
@@ -201,13 +205,15 @@ 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.
+**Special thanks to**: Aemon Algiz.
 
-**Patreon special mentions**: Slarti, Chadd, John Detwiler, Pieter, zynix, K, Mano Prime, ReadyPlayerEmma, Ai Maven, Leonard Tan, Edmond Seymore, Joseph William Delisle, Luke @flexchar, Fred von Graf, Viktor Bowallius, Rishabh Srivastava, Nikolai Manek, Matthew Berman, Johann-Peter Hartmann, ya boyyy, Greatston Gnanesh, Femi Adebogun, Talal Aujan, Jonathan Leane, terasurfer, David Flickinger, William Sang, Ajan Kanaga, Vadim, Artur Olbinski, Raven Klaugh, Michael Levine, Oscar Rangel, Randy H, Cory Kujawski, RoA, Dave, Alex, Alexandros Triantafyllidis, Fen Risland, Eugene Pentland, vamX, Elle, Nathan LeClaire, Khalefa Al-Ahmad, Rainer Wilmers, subjectnull, Junyu Yang, Daniel P. Andersen, SuperWojo, LangChain4j, Mandus, Kalila, Illia Dulskyi, Trenton Dambrowitz, Asp the Wyvern, Derek Yates, Jeffrey Morgan, Deep Realms, Imad Khwaja, Pyrater, Preetika Verma, biorpg, Gabriel Tamborski, Stephen Murray, Spiking Neurons AB, Iucharbius, Chris Smitley, Willem Michiel, Luke Pendergrass, Sebastain Graf, senxiiz, Will Dee, Space Cruiser, Karl Bernard, Clay Pascal, Lone Striker, transmissions 11, webtim, WelcomeToTheClub, Sam, theTransient, Pierre Kircher, chris gileta, John Villwock, Sean Connelly, Willian Hasse
+**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
 
 
 Thank you to all my generous patrons and donaters!
 
+And thank you again to a16z for their generous grant.
+
 <!-- footer end -->
 
 # Original model card: bofenghuang's Vigogne 2 7B Instruct
@@ -267,7 +273,7 @@ You can also infer this model by using the following Google Colab Notebook.
 Explique le théorème central limite à un enfant de six ans.
 
 ***Vigogne-2-7B-Instruct:***
- 
+
 Le théorème central limite est un concept mathématique qui dit que si vous prenez beaucoup de mesures de la même chose, la moyenne de ces mesures sera proche de la moyenne de toutes les mesures. C'est comme si vous prenait des photos d'un objet et que la moyenne de toutes les photos était proche de la vraie forme de l'objet.
 
 <details><summary>Other models</summary>
@@ -294,7 +300,7 @@ Le théorème central limite est un concept mathématique qui explique comment l
 Je suis actuellement orienté vers l'est. Ensuite je vais tourner à droite. De quel côté serai-je orienté ?
 
 ***Vigogne-2-7B-Instruct:***
- 
+
 Vous serez orienté vers le sud.
 
 <details><summary>Other models</summary>
@@ -318,7 +324,7 @@ Vous serez orienté vers le nord.
 Parmi les aliments suivants, lequel est le plus susceptible de provoquer une intoxication alimentaire ? A, poisson cru, B, poulet cuit, C, légumes cuits, D, pain grillé.
 
 ***Vigogne-2-7B-Instruct:***
- 
+
 A, poisson cru.
 
 <details><summary>Other models</summary>
@@ -341,7 +347,7 @@ Le plus susceptible de provoquer une intoxication alimentaire est le poisson cru
 Écrivez une fonction qui prend une liste de chaînes de caractères et renvoie une liste sans doublons.
 
 ***Vigogne-2-7B-Instruct:***
- 
+
 ```
 def remove_duplicates(lst):
     return list(set(lst))

config.json

@@ -1,27 +1,38 @@
 {
-    "_name_or_path": "meta-llama/Llama-2-7b-hf",
-    "architectures": [
-        "LlamaForCausalLM"
-    ],
-    "bos_token_id": 1,
-    "eos_token_id": 2,
-    "hidden_act": "silu",
-    "hidden_size": 4096,
-    "initializer_range": 0.02,
-    "intermediate_size": 11008,
-    "max_length": 4096,
-    "max_position_embeddings": 2048,
-    "model_type": "llama",
-    "num_attention_heads": 32,
-    "num_hidden_layers": 32,
-    "num_key_value_heads": 32,
-    "pad_token_id": 0,
-    "pretraining_tp": 1,
-    "rms_norm_eps": 1e-05,
-    "rope_scaling": null,
-    "tie_word_embeddings": false,
-    "torch_dtype": "float16",
-    "transformers_version": "4.32.0.dev0",
-    "use_cache": true,
-    "vocab_size": 32000
+  "_name_or_path": "meta-llama/Llama-2-7b-hf",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_length": 4096,
+  "max_position_embeddings": 2048,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.32.0.dev0",
+  "use_cache": true,
+  "vocab_size": 32000,
+  "quantization_config": {
+    "bits": 4,
+    "group_size": 128,
+    "damp_percent": 0.1,
+    "desc_act": false,
+    "sym": true,
+    "true_sequential": true,
+    "model_name_or_path": null,
+    "model_file_base_name": "model",
+    "quant_method": "gptq"
+  }
 }

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"
 }