Update for Transformers GPTQ support

README.md

@@ -4,17 +4,20 @@ license: other
 ---
 
 <!-- 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 -->
 
 # Eric Hartford's Samantha 1.1 Llama 13B GPTQ
@@ -67,7 +70,7 @@ from auto_gptq import AutoGPTQForCausalLM, BaseQuantizeConfig
 import argparse
 
 model_name_or_path = "TheBloke/samantha-1.1-llama-13B-GPTQ"
-model_basename = "gptq_model-4bit-128g"
+model_basename = "model"
 
 use_triton = False
 
@@ -125,11 +128,12 @@ It was created with group_size 128 to increase inference accuracy, but without -
   * Parameters: Groupsize = 128. Act Order / desc_act = False.
 
 <!-- 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.
 
@@ -144,12 +148,15 @@ 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**: Oscar Rangel, Eugene Pentland, Talal Aujan, Cory Kujawski, Luke, Asp the Wyvern, Ai Maven, Pyrater, Alps Aficionado, senxiiz, Willem Michiel, Junyu Yang, trip7s trip, Sebastain Graf, Joseph William Delisle, Lone Striker, Jonathan Leane, Johann-Peter Hartmann, David Flickinger, Spiking Neurons AB, Kevin Schuppel, Mano Prime, Dmitriy Samsonov, Sean Connelly, Nathan LeClaire, Alain Rossmann, Fen Risland, Derek Yates, Luke Pendergrass, Nikolai Manek, Khalefa Al-Ahmad, Artur Olbinski, John Detwiler, Ajan Kanaga, Imad Khwaja, Trenton Dambrowitz, Kalila, vamX, webtim, Illia Dulskyi.
 
 Thank you to all my generous patrons and donaters!
 
+And thank you again to a16z for their generous grant.
+
 <!-- footer end -->
 
 # Original model card: Eric Hartford's Samantha 1.1 Llama 13B

config.json

@@ -1,24 +1,35 @@
 {
-    "_name_or_path": "samantha-1.1-llama-13b",
-    "architectures": [
-        "LlamaForCausalLM"
-    ],
-    "bos_token_id": 1,
-    "eos_token_id": 2,
-    "hidden_act": "silu",
-    "hidden_size": 5120,
-    "initializer_range": 0.02,
-    "intermediate_size": 13824,
-    "max_position_embeddings": 2048,
-    "max_sequence_length": 2048,
-    "model_type": "llama",
-    "num_attention_heads": 40,
-    "num_hidden_layers": 40,
-    "pad_token_id": 0,
-    "rms_norm_eps": 1e-06,
-    "tie_word_embeddings": false,
-    "torch_dtype": "float16",
-    "transformers_version": "4.28.1",
-    "use_cache": true,
-    "vocab_size": 32000
+  "_name_or_path": "samantha-1.1-llama-13b",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 13824,
+  "max_position_embeddings": 2048,
+  "max_sequence_length": 2048,
+  "model_type": "llama",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 40,
+  "pad_token_id": 0,
+  "rms_norm_eps": 1e-06,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.28.1",
+  "use_cache": true,
+  "vocab_size": 32000,
+  "quantization_config": {
+    "bits": 4,
+    "group_size": 128,
+    "damp_percent": 0.01,
+    "desc_act": false,
+    "sym": true,
+    "true_sequential": true,
+    "model_name_or_path": null,
+    "model_file_base_name": "model",
+    "quant_method": "gptq"
+  }
 }

gptq_model-4bit-128g.safetensors → model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ad40a0d1647bed4002f6edf73f52a91daeab07a5d355f3813e166f4d8fba094
-size 7259449424
+oid sha256:209282f179d270006333bd725c10a444fc8d24476f2efea9ad14f280d695a038
+size 7259449480

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"
 }