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/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 -->
 
 # Upstage's Llama 30B Instruct 2048 GPTQ
@@ -40,10 +43,16 @@ Many thanks to William Beauchamp from [Chai](https://chai-research.com/) for pro
 * [2, 3, 4, 5, 6 and 8-bit GGML models for CPU+GPU inference](https://huggingface.co/TheBloke/upstage-llama-30b-instruct-2048-GGML)
 * [Original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/upstage/llama-30b-instruct-2048)
 
-## Prompt template: Unknown
+## Prompt template: Orca-Hashes
 
 ```
+### System:
+{System}
+
+### User:
 {prompt}
+
+### Assistant:
 ```
 
 ## Provided files
@@ -54,13 +63,13 @@ 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 | None | True | 16.94 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 | 19.44 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 | 18.18 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 | 17.55 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. | 
-| gptq-8bit--1g-actorder_True | 8 | None | True | 32.99 GB | False | AutoGPTQ | 8-bit, with Act Order. No group size, to lower VRAM requirements and to improve AutoGPTQ speed. | 
-| gptq-8bit-128g-actorder_False | 8 | 128 | False | 33.73 GB | False | AutoGPTQ | 8-bit, with group size 128g for higher inference quality and without Act Order to improve AutoGPTQ speed. | 
-| gptq-3bit-128g-actorder_False | 3 | 128 | False | 13.51 GB | False | AutoGPTQ | 3-bit, with group size 128g but no act-order. Slightly higher VRAM requirements than 3-bit None. | 
+| main | 4 | None | True | 16.94 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 | 19.44 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 | 18.18 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 | 17.55 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. |
+| gptq-8bit--1g-actorder_True | 8 | None | True | 32.99 GB | False | AutoGPTQ | 8-bit, with Act Order. No group size, to lower VRAM requirements and to improve AutoGPTQ speed. |
+| gptq-8bit-128g-actorder_False | 8 | 128 | False | 33.73 GB | False | AutoGPTQ | 8-bit, with group size 128g for higher inference quality and without Act Order to improve AutoGPTQ speed. |
+| gptq-3bit-128g-actorder_False | 3 | 128 | False | 13.51 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 | 13.51 GB | False | AutoGPTQ | 3-bit, with group size 128g and act-order. Higher quality than 128g-False but poor AutoGPTQ CUDA speed. |
 
 ## How to download from branches
@@ -104,7 +113,7 @@ from transformers import AutoTokenizer, pipeline, logging
 from auto_gptq import AutoGPTQForCausalLM, BaseQuantizeConfig
 
 model_name_or_path = "TheBloke/upstage-llama-30b-instruct-2048-GPTQ"
-model_basename = "gptq_model-4bit--1g"
+model_basename = "model"
 
 use_triton = False
 
@@ -131,8 +140,14 @@ model = AutoGPTQForCausalLM.from_quantized(model_name_or_path,
 """
 
 prompt = "Tell me about AI"
-prompt_template=f'''{prompt}
-'''
+system = "You are a helpful assistant"
+prompt_template=f'''### System:
+{system}
+
+### User:
+{prompt}
+
+### Assistant:'''
 
 print("\n\n*** Generate:")
 
@@ -166,6 +181,7 @@ 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:
@@ -185,26 +201,97 @@ 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: Upstage's Llama 30B Instruct 2048
 
-# LLaMa-30b-instruct-2048 model card
+## Model Details
 
-## Contact Us, Why Upstage LLM?
-- [Upstage](https://en.upstage.ai)'s LLM research has yielded remarkable results. Our 30B model size **outperforms all models worldwide**, establishing itself as the leading performer. Recognizing the immense potential for private LLM adoption within companies, we invite you to effortlessly implement a private LLM and fine-tune it with your own data. For a seamless and tailored solution, please don't hesitate to reach out to us [(click here to mail)].
+### Model Developers
+- [Upstage](https://en.upstage.ai)
+
+### Backbone Model
+- [LLaMA](https://github.com/facebookresearch/llama/tree/llama_v1)
 
-## Model and Dataset Details
-- Please refer to the model card of [upstage/llama-30b-instruct](https://huggingface.co/upstage/llama-30b-instruct) as this one is almost the same.
+### Variations
+- It has different model parameter sizes and sequence lengths: [30B/1024](https://huggingface.co/upstage/llama-30b-instruct), [30B/2048](https://huggingface.co/upstage/llama-30b-instruct-2048), [65B/1024](https://huggingface.co/upstage/llama-65b-instruct).
 
-## License
+### Input
+- Models solely process textual input.
+
+### Output
+- Models solely generate textual output.
+
+### License
 - This model is under a **Non-commercial** Bespoke License and governed by the Meta license. You should only use this repository if you have been granted access to the model by filling out [this form](https://docs.google.com/forms/d/e/1FAIpQLSfqNECQnMkycAp2jP4Z9TFX0cGR4uf7b_fBxjY_OjhJILlKGA/viewform), but have either lost your copy of the weights or encountered issues converting them to the Transformers format.
 
+### Where to send comments
+- Instructions on how to provide feedback or comments on a model can be found by opening an issue in the [Hugging Face community's model repository](https://huggingface.co/upstage/llama-30b-instruct-2048/discussions).
+
+## Dataset Details
+
+### Used Datasets
+- [openbookqa](https://huggingface.co/datasets/openbookqa)
+- [sciq](https://huggingface.co/datasets/sciq)
+- [Open-Orca/OpenOrca](https://huggingface.co/datasets/Open-Orca/OpenOrca)
+- [metaeval/ScienceQA_text_only](https://huggingface.co/datasets/metaeval/ScienceQA_text_only)
+- [GAIR/lima](https://huggingface.co/datasets/GAIR/lima)
+
+## Hardware and Software
+
+### Hardware
+- We utilized an A100 for training our model.
+
+### Training Factors
+- We fine-tuned this model using a combination of the [DeepSpeed library](https://github.com/microsoft/DeepSpeed) and the [HuggingFace trainer](https://huggingface.co/docs/transformers/main_classes/trainer).
+
+## Evaluation Results
+
+### Overview
+- We conducted a performance evaluation based on the tasks being evaluated on the [Open LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard).
+We evaluated our model on four benchmark datasets, which include `ARC-Challenge`, `HellaSwag`, `MMLU`, and `TruthfulQA`.
+We used the [lm-evaluation-harness repository](https://github.com/EleutherAI/lm-evaluation-harness), specifically commit [b281b0921b636bc36ad05c0b0b0763bd6dd43463](https://github.com/EleutherAI/lm-evaluation-harness/tree/b281b0921b636bc36ad05c0b0b0763bd6dd43463).
+
+### Main Results
+| Model                                         | Average | ARC   | HellaSwag | MMLU  | TruthfulQA |
+|-----------------------------------------------|---------|-------|-----------|-------|------------|
+| llama-65b-instruct (***Ours***, ***Local Reproduction***) | **69.4** | **67.6** | **86.5** | **64.9** | **58.8** |
+| llama-30b-instruct-2048 (***Ours***, ***Open LLM Leaderboard***) | 67.0 | 64.9 | 84.9 | 61.9 | 56.3 |
+| Llama-2-70b-chat-hf | 66.8 | 64.6 | 85.9 | 63.9 | 52.8 |
+| llama-30b-instruct (***Ours***, ***Open LLM Leaderboard***) | 65.2 | 62.5 | 86.2 | 59.4 | 52.8 |
+| falcon-40b-instruct | 63.4 | 61.6 | 84.3 | 55.4 | 52.5 |
+| llama-65b | 62.1 | 57.6 | 84.3 | 63.4 | 43.0 |
+
+### Scripts
+- Prepare evaluation environments:
+```
+# clone the repository
+git clone https://github.com/EleutherAI/lm-evaluation-harness.git
+
+# check out the specific commit
+git checkout b281b0921b636bc36ad05c0b0b0763bd6dd43463
+
+# change to the repository directory
+cd lm-evaluation-harness
+```
+
+## Ethical Issues
+
+### Ethical Considerations
+- There were no ethical issues involved, as we did not include the benchmark test set or the training set in the model's training process.
+
+## Contact Us
+
+### Why Upstage LLM?
+- [Upstage](https://en.upstage.ai)'s LLM research has yielded remarkable results. Our 30B model size **outperforms all models worldwide**, establishing itself as the leading performer. Recognizing the immense potential for private LLM adoption within companies, we invite you to effortlessly implement a private LLM and fine-tune it with your own data. For a seamless and tailored solution, please don't hesitate to reach out to us [(click here to mail)].
+
 [(click here to mail)]: mailto:contact@upstage.ai

config.json

@@ -1,24 +1,35 @@
 {
-    "_name_or_path": "/data/project/private/ynot/checkpoint-6628/",
-    "architectures": [
-        "LlamaForCausalLM"
-    ],
-    "bos_token_id": 1,
-    "eos_token_id": 2,
-    "hidden_act": "silu",
-    "hidden_size": 6656,
-    "initializer_range": 0.02,
-    "intermediate_size": 17920,
-    "max_position_embeddings": 2048,
-    "max_sequence_length": 2048,
-    "model_type": "llama",
-    "num_attention_heads": 52,
-    "num_hidden_layers": 60,
-    "pad_token_id": 0,
-    "rms_norm_eps": 1e-06,
-    "tie_word_embeddings": false,
-    "torch_dtype": "bfloat16",
-    "transformers_version": "4.30.2",
-    "use_cache": true,
-    "vocab_size": 32000
+  "_name_or_path": "/data/project/private/ynot/checkpoint-6628/",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 6656,
+  "initializer_range": 0.02,
+  "intermediate_size": 17920,
+  "max_position_embeddings": 2048,
+  "max_sequence_length": 2048,
+  "model_type": "llama",
+  "num_attention_heads": 52,
+  "num_hidden_layers": 60,
+  "pad_token_id": 0,
+  "rms_norm_eps": 1e-06,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.30.2",
+  "use_cache": true,
+  "vocab_size": 32000,
+  "quantization_config": {
+    "bits": 4,
+    "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-4bit-64g.safetensors → model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e42e73f2f9332de4abe308e126ab6408f60a62841540ef55eb4942310eb0a9e6
-size 18181100672
+oid sha256:4a83f55d5ef40b484d8ee4ec31c4b8c4b75da8e53ddb27a063271c1d42223316
+size 18181100728

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"
 }