Upload README.md

README.md

@@ -1,10 +1,22 @@
 ---
+base_model: https://huggingface.co/elinas/chronos-70b-v2
 inference: false
 license: cc-by-nc-4.0
 model_creator: Elinas
-model_link: https://huggingface.co/elinas/chronos-70b-v2
 model_name: Chronos 70B v2
 model_type: llama
+prompt_template: 'Below is an instruction that describes a task. Write a response
+  that appropriately completes the request.
+
+
+  ### Instruction:
+
+  {prompt}
+
+
+  ### Response:
+
+  '
 quantized_by: TheBloke
 tags:
 - chat
@@ -40,18 +52,11 @@ This repo contains GPTQ model files for [Elinas's Chronos 70B v2](https://huggin
 
 Multiple GPTQ parameter permutations are provided; see Provided Files below for details of the options provided, their parameters, and the software used to create them.
 
-## Licensing
-
-The creator of the source model has listed its license as `cc-by-nc-4.0`, and this quantization has therefore used the same license.
-
-As this model is based on Llama 2, it is also subject to the Meta Llama 2 license terms, and the license files for that are additionally included.
-
-Any questions regarding licensing and the interaction of these two licenses should be directed to the original model repository: [Chronos 70B v2](https://huggingface.co/elinas/chronos-70b-v2).
-
 <!-- description end -->
 <!-- repositories-available start -->
 ## Repositories available
 
+* [AWQ model(s) for GPU inference.](https://huggingface.co/TheBloke/Chronos-70B-v2-AWQ)
 * [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/Chronos-70B-v2-GPTQ)
 * [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/Chronos-70B-v2-GGUF)
 * [Elinas's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/elinas/chronos-70b-v2)
@@ -71,7 +76,15 @@ Below is an instruction that describes a task. Write a response that appropriate
 ```
 
 <!-- prompt-template end -->
+<!-- licensing start -->
+## Licensing
 
+The creator of the source model has listed its license as `cc-by-nc-4.0`, and this quantization has therefore used that same license.
+
+As this model is based on Llama 2, it is also subject to the Meta Llama 2 license terms, and the license files for that are additionally included. It should therefore be considered as being claimed to be licensed under both licenses. I contacted Hugging Face for clarification on dual licensing but they do not yet have an official position. Should this change, or should Meta provide any feedback on this situation, I will update this section accordingly.
+
+In the meantime, any questions regarding licensing, and in particular how these two licenses might interact, should be directed to the original model repository: [Elinas's Chronos 70B v2](https://huggingface.co/elinas/chronos-70b-v2).
+<!-- licensing end -->
 <!-- README_GPTQ.md-provided-files start -->
 ## Provided files and GPTQ parameters
 
@@ -96,22 +109,22 @@ All recent GPTQ files are made with AutoGPTQ, and all files in non-main branches
 
 | Branch | Bits | GS | Act Order | Damp % | GPTQ Dataset | Seq Len | Size | ExLlama | Desc |
 | ------ | ---- | -- | --------- | ------ | ------------ | ------- | ---- | ------- | ---- |
-| main | 4 | None | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 35.33 GB | Yes | 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 | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 40.66 GB | Yes | 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 | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 37.99 GB | Yes | 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 | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 36.65 GB | Yes | 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-3bit--1g-actorder_True | 3 | None | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 26.77 GB | No | 3-bit, with Act Order and no group size. Lowest possible VRAM requirements. May be lower quality than 3-bit 128g. | 
-| gptq-3bit-128g-actorder_True | 3 | 128 | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 28.03 GB | No | 3-bit, with group size 128g and act-order. Higher quality than 128g-False but poor AutoGPTQ CUDA speed. |
+| [main](https://huggingface.co/TheBloke/Chronos-70B-v2-GPTQ/tree/main) | 4 | None | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 35.33 GB | Yes | 4-bit, with Act Order. No group size, to lower VRAM requirements. | 
+| [gptq-4bit-32g-actorder_True](https://huggingface.co/TheBloke/Chronos-70B-v2-GPTQ/tree/gptq-4bit-32g-actorder_True) | 4 | 32 | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 40.66 GB | Yes | 4-bit, with Act Order and group size 32g. Gives highest possible inference quality, with maximum VRAM usage. | 
+| [gptq-4bit-64g-actorder_True](https://huggingface.co/TheBloke/Chronos-70B-v2-GPTQ/tree/gptq-4bit-64g-actorder_True) | 4 | 64 | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 37.99 GB | Yes | 4-bit, with Act Order and group size 64g. Uses less VRAM than 32g, but with slightly lower accuracy. | 
+| [gptq-4bit-128g-actorder_True](https://huggingface.co/TheBloke/Chronos-70B-v2-GPTQ/tree/gptq-4bit-128g-actorder_True) | 4 | 128 | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 36.65 GB | Yes | 4-bit, with Act Order and group size 128g. Uses even less VRAM than 64g, but with slightly lower accuracy. | 
+| [gptq-3bit--1g-actorder_True](https://huggingface.co/TheBloke/Chronos-70B-v2-GPTQ/tree/gptq-3bit--1g-actorder_True) | 3 | None | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 26.77 GB | No | 3-bit, with Act Order and no group size. Lowest possible VRAM requirements. May be lower quality than 3-bit 128g. | 
+| [gptq-3bit-128g-actorder_True](https://huggingface.co/TheBloke/Chronos-70B-v2-GPTQ/tree/gptq-3bit-128g-actorder_True) | 3 | 128 | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 28.03 GB | No | 3-bit, with group size 128g and act-order. Higher quality than 128g-False. |
 
 <!-- README_GPTQ.md-provided-files end -->
 
 <!-- README_GPTQ.md-download-from-branches start -->
 ## How to download from branches
 
-- In text-generation-webui, you can add `:branch` to the end of the download name, eg `TheBloke/Chronos-70B-v2-GPTQ:gptq-4bit-32g-actorder_True`
+- In text-generation-webui, you can add `:branch` to the end of the download name, eg `TheBloke/Chronos-70B-v2-GPTQ:main`
 - With Git, you can clone a branch with:
 ```
-git clone --single-branch --branch gptq-4bit-32g-actorder_True https://huggingface.co/TheBloke/Chronos-70B-v2-GPTQ
+git clone --single-branch --branch main https://huggingface.co/TheBloke/Chronos-70B-v2-GPTQ
 ```
 - In Python Transformers code, the branch is the `revision` parameter; see below.
 <!-- README_GPTQ.md-download-from-branches end -->
@@ -124,7 +137,7 @@ It is strongly recommended to use the text-generation-webui one-click-installers
 
 1. Click the **Model tab**.
 2. Under **Download custom model or LoRA**, enter `TheBloke/Chronos-70B-v2-GPTQ`.
-  - To download from a specific branch, enter for example `TheBloke/Chronos-70B-v2-GPTQ:gptq-4bit-32g-actorder_True`
+  - To download from a specific branch, enter for example `TheBloke/Chronos-70B-v2-GPTQ:main`
   - see Provided Files above for the list of branches for each option.
 3. Click **Download**.
 4. The model will start downloading. Once it's finished it will say "Done".
@@ -172,10 +185,10 @@ from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
 
 model_name_or_path = "TheBloke/Chronos-70B-v2-GPTQ"
 # To use a different branch, change revision
-# For example: revision="gptq-4bit-32g-actorder_True"
+# For example: revision="main"
 model = AutoModelForCausalLM.from_pretrained(model_name_or_path,
-                                             torch_dtype=torch.float16,
                                              device_map="auto",
+                                             trust_remote_code=False,
                                              revision="main")
 
 tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=True)
@@ -193,7 +206,7 @@ prompt_template=f'''Below is an instruction that describes a task. Write a respo
 print("\n\n*** Generate:")
 
 input_ids = tokenizer(prompt_template, return_tensors='pt').input_ids.cuda()
-output = model.generate(inputs=input_ids, temperature=0.7, max_new_tokens=512)
+output = model.generate(inputs=input_ids, temperature=0.7, do_sample=True, top_p=0.95, top_k=40, max_new_tokens=512)
 print(tokenizer.decode(output[0]))
 
 # Inference can also be done using transformers' pipeline
@@ -204,9 +217,11 @@ pipe = pipeline(
     model=model,
     tokenizer=tokenizer,
     max_new_tokens=512,
+    do_sample=True,
     temperature=0.7,
     top_p=0.95,
-    repetition_penalty=1.15
+    top_k=40,
+    repetition_penalty=1.1
 )
 
 print(pipe(prompt_template)[0]['generated_text'])
@@ -231,10 +246,12 @@ For further support, and discussions on these models and AI in general, join us
 
 [TheBloke AI's Discord server](https://discord.gg/theblokeai)
 
-## Thanks, and how to contribute.
+## Thanks, and how to contribute
 
 Thanks to the [chirper.ai](https://chirper.ai) team!
 
+Thanks to Clay from [gpus.llm-utils.org](llm-utils)!
+
 I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training.
 
 If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects.
@@ -246,7 +263,7 @@ Donaters will get priority support on any and all AI/LLM/model questions and req
 
 **Special thanks to**: Aemon Algiz.
 
-**Patreon special mentions**: Russ Johnson, J, alfie_i, Alex, NimbleBox.ai, Chadd, Mandus, Nikolai Manek, Ken Nordquist, ya boyyy, Illia Dulskyi, Viktor Bowallius, vamX, Iucharbius, zynix, Magnesian, Clay Pascal, Pierre Kircher, Enrico Ros, Tony Hughes, Elle, Andrey, knownsqashed, Deep Realms, Jerry Meng, Lone Striker, Derek Yates, Pyrater, Mesiah Bishop, James Bentley, Femi Adebogun, Brandon Frisco, SuperWojo, Alps Aficionado, Michael Dempsey, Vitor Caleffi, Will Dee, Edmond Seymore, usrbinkat, LangChain4j, Kacper Wikieł, Luke Pendergrass, John Detwiler, theTransient, Nathan LeClaire, Tiffany J. Kim, biorpg, Eugene Pentland, Stanislav Ovsiannikov, Fred von Graf, terasurfer, Kalila, Dan Guido, Nitin Borwankar, 阿明, Ai Maven, John Villwock, Gabriel Puliatti, Stephen Murray, Asp the Wyvern, danny, Chris Smitley, ReadyPlayerEmma, S_X, Daniel P. Andersen, Olakabola, Jeffrey Morgan, Imad Khwaja, Caitlyn Gatomon, webtim, Alicia Loh, Trenton Dambrowitz, Swaroop Kallakuri, Erik Bjäreholt, Leonard Tan, Spiking Neurons AB, Luke @flexchar, Ajan Kanaga, Thomas Belote, Deo Leter, RoA, Willem Michiel, transmissions 11, subjectnull, Matthew Berman, Joseph William Delisle, David Ziegler, Michael Davis, Johann-Peter Hartmann, Talal Aujan, senxiiz, Artur Olbinski, Rainer Wilmers, Spencer Kim, Fen Risland, Cap'n Zoog, Rishabh Srivastava, Michael Levine, Geoffrey Montalvo, Sean Connelly, Alexandros Triantafyllidis, Pieter, Gabriel Tamborski, Sam, Subspace Studios, Junyu Yang, Pedro Madruga, Vadim, Cory Kujawski, K, Raven Klaugh, Randy H, Mano Prime, Sebastain Graf, Space Cruiser
+**Patreon special mentions**: Alicia Loh, Stephen Murray, K, Ajan Kanaga, RoA, Magnesian, Deo Leter, Olakabola, Eugene Pentland, zynix, Deep Realms, Raymond Fosdick, Elijah Stavena, Iucharbius, Erik Bjäreholt, Luis Javier Navarrete Lozano, Nicholas, theTransient, John Detwiler, alfie_i, knownsqashed, Mano Prime, Willem Michiel, Enrico Ros, LangChain4j, OG, Michael Dempsey, Pierre Kircher, Pedro Madruga, James Bentley, Thomas Belote, Luke @flexchar, Leonard Tan, Johann-Peter Hartmann, Illia Dulskyi, Fen Risland, Chadd, S_X, Jeff Scroggin, Ken Nordquist, Sean Connelly, Artur Olbinski, Swaroop Kallakuri, Jack West, Ai Maven, David Ziegler, Russ Johnson, transmissions 11, John Villwock, Alps Aficionado, Clay Pascal, Viktor Bowallius, Subspace Studios, Rainer Wilmers, Trenton Dambrowitz, vamX, Michael Levine, 준교 김, Brandon Frisco, Kalila, Trailburnt, Randy H, Talal Aujan, Nathan Dryer, Vadim, 阿明, ReadyPlayerEmma, Tiffany J. Kim, George Stoitzev, Spencer Kim, Jerry Meng, Gabriel Tamborski, Cory Kujawski, Jeffrey Morgan, Spiking Neurons AB, Edmond Seymore, Alexandros Triantafyllidis, Lone Striker, Cap'n Zoog, Nikolai Manek, danny, ya boyyy, Derek Yates, usrbinkat, Mandus, TL, Nathan LeClaire, subjectnull, Imad Khwaja, webtim, Raven Klaugh, Asp the Wyvern, Gabriel Puliatti, Caitlyn Gatomon, Joseph William Delisle, Jonathan Leane, Luke Pendergrass, SuperWojo, Sebastain Graf, Will Dee, Fred von Graf, Andrey, Dan Guido, Daniel P. Andersen, Nitin Borwankar, Elle, Vitor Caleffi, biorpg, jjj, NimbleBox.ai, Pieter, Matthew Berman, terasurfer, Michael Davis, Alex, Stanislav Ovsiannikov
 
 
 Thank you to all my generous patrons and donaters!
@@ -260,7 +277,7 @@ And thank you again to a16z for their generous grant.
 
 # chronos-70b-v2
 
-This is the FP16 PyTorch / HF version of **chronos-70b-v2** based on the **Llama v2 Base** model.
+This is the FP16 PyTorch / HF version of **chronos-70b-v2** based on the **Llama v2 Base** model. This version will **not fit on a consumer GPU**, use a quantized type of model from those linked below!
 
 Big thank you to the Pygmalion team for providing compute. Reach out to me if you would like individual credit.
 
@@ -286,13 +303,16 @@ Your instruction or question here.
 ```
 Not using the format will make the model perform significantly worse than intended.
 
-## Other Versions
+## Tips
+
+Sampling and settings can make a significant difference for this model, so play around with them. I was also informed by a user that if you are using **KoboldCPP** that using the flag
+`--unbantokens` may improve model performance **significantly**. This has not been tested by myself, but that is something to keep in mind.
 
-[GGML Versions provided by @TheBloke]()
+## Quantized Versions for Consumer GPU Usage
 
-[4bit GPTQ Quantized version]()
+[LlamaCPP Versions provided by @TheBloke](https://huggingface.co/TheBloke/Chronos-70B-v2-GGUF)
 
-Only use this version for further quantization or if you would like to run in full precision, as long as you have the VRAM required.
+[GPTQ Quantized Versions provided by @TheBloke](https://huggingface.co/TheBloke/Chronos-70B-v2-GPTQ)
 
 
 **Support Development of New Models**