Update for Transformers GPTQ support

README.md

@@ -5,17 +5,20 @@ model_type: llama
 ---
 
 <!-- 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 -->
 
 # Tim Dettmers' Guanaco 65B GPTQ
@@ -47,7 +50,7 @@ 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 | 35.74 GB | True | GPTQ-for-LLaMa | Most compatible option. Good inference speed in AutoGPTQ and GPTQ-for-LLaMa. Lower inference quality than other options. |
+| main | 4 | None | True | 35.74 GB | True | GPTQ-for-LLaMa | 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 | 38.53 GB | 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 | 36.00 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 | 34.73 GB | True | AutoGPTQ | 4-bit, with Act Order and group size. 128g uses even less VRAM, but with slightly lower accuracy. Poor AutoGPTQ CUDA speed. |
@@ -160,6 +163,7 @@ 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:
@@ -179,19 +183,22 @@ 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**: 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**: Space Cruiser, Nikolai Manek, Sam, Chris McCloskey, Rishabh Srivastava, Kalila, Spiking Neurons AB, Khalefa Al-Ahmad, WelcomeToTheClub, Chadd, Lone Striker, Viktor Bowallius, Edmond Seymore, Ai Maven, Chris Smitley, Dave, Alexandros Triantafyllidis, Luke @flexchar, Elle, ya boyyy, Talal Aujan, Alex , Jonathan Leane, Deep Realms, Randy H, subjectnull, Preetika Verma, Joseph William Delisle, Michael Levine, chris gileta, K, Oscar Rangel, LangChain4j, Trenton Dambrowitz, Eugene Pentland, Johann-Peter Hartmann, Femi Adebogun, Illia Dulskyi, senxiiz, Daniel P. Andersen, Sean Connelly, Artur Olbinski, RoA, Mano Prime, Derek Yates, Raven Klaugh, David Flickinger, Willem Michiel, Pieter, Willian Hasse, vamX, Luke Pendergrass, webtim, Ghost , Rainer Wilmers, Nathan LeClaire, Will Dee, Cory Kujawski, John Detwiler, Fred von Graf, biorpg, Iucharbius , Imad Khwaja, Pierre Kircher, terasurfer , Asp the Wyvern, John Villwock, theTransient, zynix , Gabriel Tamborski, Fen Risland, Gabriel Puliatti, Matthew Berman, Pyrater, SuperWojo, Stephen Murray, Karl Bernard, Ajan Kanaga, Greatston Gnanesh, Junyu Yang.
 
 Thank you to all my generous patrons and donaters!
 
+And thank you again to a16z for their generous grant.
+
 <!-- footer end -->
 
 # Original model card: Tim Dettmers' Guanaco 65B
 
 # Guanaco Models Based on LLaMA
 
-| [Paper](https://arxiv.org/abs/2305.14314) | [Code](https://github.com/artidoro/qlora) | [Demo](https://huggingface.co/spaces/uwnlp/guanaco-playground-tgi) | 
+| [Paper](https://arxiv.org/abs/2305.14314) | [Code](https://github.com/artidoro/qlora) | [Demo](https://huggingface.co/spaces/uwnlp/guanaco-playground-tgi) |
 
 **The Guanaco models are open-source finetuned chatbots obtained through 4-bit QLoRA tuning of LLaMA base models on the OASST1 dataset. They are available in 7B, 13B, 33B, and 65B parameter sizes.**
 
@@ -201,18 +208,18 @@ Thank you to all my generous patrons and donaters!
 - **Competitive with commercial chatbot systems on the Vicuna and OpenAssistant benchmarks** (ChatGPT and BARD) according to human and GPT-4 raters. We note that the relative performance on tasks not covered in these benchmarks could be very different. In addition, commercial systems evolve over time (we used outputs from the March 2023 version of the models).
 - **Available open-source for research purposes**. Guanaco models allow *cheap* and *local* experimentation with high-quality chatbot systems.
 - **Replicable and efficient training procedure** that can be extended to new use cases. Guanaco training scripts are available in the [QLoRA repo](https://github.com/artidoro/qlora).
-- **Rigorous comparison to 16-bit methods** (both 16-bit full-finetuning and LoRA) in [our paper](https://arxiv.org/abs/2305.14314) demonstrates the effectiveness of 4-bit QLoRA finetuning. 
+- **Rigorous comparison to 16-bit methods** (both 16-bit full-finetuning and LoRA) in [our paper](https://arxiv.org/abs/2305.14314) demonstrates the effectiveness of 4-bit QLoRA finetuning.
 - **Lightweight** checkpoints which only contain adapter weights.
 
 ## License and Intended Use
-Guanaco adapter weights are available under Apache 2 license. Note the use of the Guanaco adapter weights, requires access to the LLaMA model weighs. 
-Guanaco is based on LLaMA and therefore should be used according to the LLaMA license. 
+Guanaco adapter weights are available under Apache 2 license. Note the use of the Guanaco adapter weights, requires access to the LLaMA model weighs.
+Guanaco is based on LLaMA and therefore should be used according to the LLaMA license.
 
 ## Usage
 Here is an example of how you would load Guanaco 7B in 4-bits:
 ```python
 import torch
-from peft import PeftModel    
+from peft import PeftModel
 from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig
 
 model_name = "huggyllama/llama-7b"
@@ -254,7 +261,7 @@ A chat between a curious human and an artificial intelligence assistant. The ass
 ```
 
 
-## Current Inference Limitations 
+## Current Inference Limitations
 Currently, 4-bit inference is slow. We recommend loading in 16 bits if inference speed is a concern. We are actively working on releasing efficient 4-bit inference kernels.
 
 Below is how you would load the model in 16 bits:
@@ -280,18 +287,18 @@ tokenizer = AutoTokenizer.from_pretrained(model_name)
 
 **Finetuning Data**: Guanaco is finetuned on OASST1. The exact dataset is available at [timdettmers/openassistant-guanaco](https://huggingface.co/datasets/timdettmers/openassistant-guanaco).
 
-**Languages**: The OASST1 dataset is multilingual (see [the paper](https://arxiv.org/abs/2304.07327) for details) and as such Guanaco responds to user queries in different languages. We note, however, that OASST1 is heavy in high-resource languages. In addition, human evaluation of Guanaco was only performed in English and based on qualitative analysis we observed degradation in performance in other languages. 
+**Languages**: The OASST1 dataset is multilingual (see [the paper](https://arxiv.org/abs/2304.07327) for details) and as such Guanaco responds to user queries in different languages. We note, however, that OASST1 is heavy in high-resource languages. In addition, human evaluation of Guanaco was only performed in English and based on qualitative analysis we observed degradation in performance in other languages.
 
 Next, we describe Training and Evaluation details.
 
 ### Training
-Guanaco models are the result of 4-bit QLoRA supervised finetuning on the OASST1 dataset. 
+Guanaco models are the result of 4-bit QLoRA supervised finetuning on the OASST1 dataset.
 
 All models use NormalFloat4 datatype for the base model and LoRA adapters on all linear layers with BFloat16 as computation datatype. We set LoRA $r=64$, $\alpha=16$. We also use Adam beta2 of 0.999, max grad norm of 0.3 and LoRA dropout of 0.1 for models up to 13B and 0.05 for 33B and 65B models.
-For the finetuning process, we use constant learning rate schedule and paged AdamW optimizer. 
+For the finetuning process, we use constant learning rate schedule and paged AdamW optimizer.
 
 ### Training hyperparameters
-Size| Dataset | Batch Size | Learning Rate | Max Steps | Sequence length 
+Size| Dataset | Batch Size | Learning Rate | Max Steps | Sequence length
 ---|---|---|---|---|---
 7B | OASST1      | 16 | 2e-4 | 1875 | 512
 13B | OASST1     | 16 | 2e-4 | 1875 | 512
@@ -299,39 +306,39 @@ Size| Dataset | Batch Size | Learning Rate | Max Steps | Sequence length
 65B | OASST1     | 16 | 1e-4 | 1875 | 512
 
 ### Evaluation
-We test generative language capabilities through both automated and human evaluations. This second set of evaluations relies on queries curated by humans and aims at measuring the quality of model responses. We use the Vicuna and OpenAssistant datasets with 80 and 953 prompts respectively. 
+We test generative language capabilities through both automated and human evaluations. This second set of evaluations relies on queries curated by humans and aims at measuring the quality of model responses. We use the Vicuna and OpenAssistant datasets with 80 and 953 prompts respectively.
 
 In both human and automated evaluations, for each prompt, raters compare all pairs of responses across the models considered. For human raters we randomize the order of the systems, for GPT-4 we evaluate with both orders.
 
-  
+
 Benchmark | Vicuna |  | Vicuna |   | OpenAssistant |   | -
 -----------|----|-----|--------|---|---------------|---|---
 Prompts    | 80 |     | 80     |   | 953           |   |
-Judge | Human | | GPT-4 | | GPT-4 | |  
-Model | Elo | Rank | Elo | Rank | Elo | Rank | **Median Rank** 
-GPT-4 | 1176 | 1 | 1348 | 1 | 1294 | 1 | 1 
-Guanaco-65B | 1023 | 2 | 1022 | 2 | 1008 | 3 | 2 
-Guanaco-33B | 1009 | 4 | 992 | 3 | 1002 | 4 | 4 
-ChatGPT-3.5 Turbo | 916 | 7 | 966 | 5 | 1015 | 2 | 5 
-Vicuna-13B | 984 | 5 | 974 | 4 | 936 | 5 | 5 
-Guanaco-13B | 975 | 6 | 913 | 6 | 885 | 6 | 6 
-Guanaco-7B | 1010 | 3 | 879 | 8 | 860 | 7 | 7 
-Bard | 909 | 8 | 902 | 7 | - | - | 8 
+Judge | Human | | GPT-4 | | GPT-4 | |
+Model | Elo | Rank | Elo | Rank | Elo | Rank | **Median Rank**
+GPT-4 | 1176 | 1 | 1348 | 1 | 1294 | 1 | 1
+Guanaco-65B | 1023 | 2 | 1022 | 2 | 1008 | 3 | 2
+Guanaco-33B | 1009 | 4 | 992 | 3 | 1002 | 4 | 4
+ChatGPT-3.5 Turbo | 916 | 7 | 966 | 5 | 1015 | 2 | 5
+Vicuna-13B | 984 | 5 | 974 | 4 | 936 | 5 | 5
+Guanaco-13B | 975 | 6 | 913 | 6 | 885 | 6 | 6
+Guanaco-7B | 1010 | 3 | 879 | 8 | 860 | 7 | 7
+Bard | 909 | 8 | 902 | 7 | - | - | 8
 
 
 We also use the MMLU benchmark to measure performance on a range of language understanding tasks. This is a multiple-choice benchmark covering 57 tasks including elementary mathematics, US history, computer science, law, and more. We report 5-shot test accuracy.
 
- Dataset | 7B | 13B | 33B | 65B 
+ Dataset | 7B | 13B | 33B | 65B
 ---|---|---|---|---
- LLaMA no tuning | 35.1 | 46.9 | 57.8 | 63.4 
- Self-Instruct | 36.4 | 33.3 | 53.0 | 56.7 
- Longform | 32.1 | 43.2 | 56.6 | 59.7 
- Chip2 | 34.5 | 41.6 | 53.6 | 59.8 
- HH-RLHF | 34.9 | 44.6 | 55.8 | 60.1 
- Unnatural Instruct | 41.9 | 48.1 | 57.3 | 61.3 
- OASST1 (Guanaco) | 36.6 | 46.4 | 57.0 | 62.2 
- Alpaca | 38.8 | 47.8 | 57.3 | 62.5 
- FLAN v2 | 44.5 | 51.4 | 59.2 | 63.9 
+ LLaMA no tuning | 35.1 | 46.9 | 57.8 | 63.4
+ Self-Instruct | 36.4 | 33.3 | 53.0 | 56.7
+ Longform | 32.1 | 43.2 | 56.6 | 59.7
+ Chip2 | 34.5 | 41.6 | 53.6 | 59.8
+ HH-RLHF | 34.9 | 44.6 | 55.8 | 60.1
+ Unnatural Instruct | 41.9 | 48.1 | 57.3 | 61.3
+ OASST1 (Guanaco) | 36.6 | 46.4 | 57.0 | 62.2
+ Alpaca | 38.8 | 47.8 | 57.3 | 62.5
+ FLAN v2 | 44.5 | 51.4 | 59.2 | 63.9
 
 ## Risks and Biases
 The model can produce factually incorrect output, and should not be relied on to produce factually accurate information. The model was trained on various public datasets; it is possible that this model could generate lewd, biased, or otherwise offensive outputs.

config.json

@@ -1,24 +1,35 @@
 {
-    "_name_or_path": "/workspace/models/huggyllama_llama-65b",
-    "architectures": [
-        "LlamaForCausalLM"
-    ],
-    "bos_token_id": 1,
-    "eos_token_id": 2,
-    "hidden_act": "silu",
-    "hidden_size": 8192,
-    "initializer_range": 0.02,
-    "intermediate_size": 22016,
-    "max_position_embeddings": 2048,
-    "max_sequence_length": 2048,
-    "model_type": "llama",
-    "num_attention_heads": 64,
-    "num_hidden_layers": 80,
-    "pad_token_id": 0,
-    "rms_norm_eps": 1e-05,
-    "tie_word_embeddings": false,
-    "torch_dtype": "float16",
-    "transformers_version": "4.29.2",
-    "use_cache": true,
-    "vocab_size": 32000
+  "_name_or_path": "/workspace/models/huggyllama_llama-65b",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 8192,
+  "initializer_range": 0.02,
+  "intermediate_size": 22016,
+  "max_position_embeddings": 2048,
+  "max_sequence_length": 2048,
+  "model_type": "llama",
+  "num_attention_heads": 64,
+  "num_hidden_layers": 80,
+  "pad_token_id": 0,
+  "rms_norm_eps": 1e-05,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.29.2",
+  "use_cache": true,
+  "vocab_size": 32000,
+  "quantization_config": {
+    "bits": 3,
+    "group_size": 64,
+    "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-3bit-64g.safetensors → model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea1187b9a55a125b1b49de4bcb7ff19b5f9a82ae137d1b9068b36b95ec436ddb
-size 27776178320
+oid sha256:8c4e11f25dca597ca9b8621832c569023670296dfc43484c22a8d6f6dd3d02d1
+size 27776178376

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"
 }