Upload new GPTQs with varied parameters

README.md

@@ -1,6 +1,7 @@
 ---
 inference: false
 license: other
+model_type: llama
 ---
 
 <!-- header start -->
@@ -9,7 +10,7 @@ license: other
 </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><a href="https://discord.gg/theblokeai">Chat & support: my new 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>
@@ -19,87 +20,157 @@ license: other
 
 # Teknium's LLaMa Deus 7B v3 GPTQ
 
-These files are GPTQ 4bit model files for [Teknium's LLaMa Deus 7B v3](https://huggingface.co/teknium/llama-deus-7b-v3-lora-merged).
+These files are GPTQ model files for [Teknium's LLaMa Deus 7B v3](https://huggingface.co/teknium/llama-deus-7b-v3-lora-merged).
 
-It is the result of quantising to 4bit using [GPTQ-for-LLaMa](https://github.com/qwopqwop200/GPTQ-for-LLaMa).
+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.
 
-## Other repositories available
+These models were quantised using hardware kindly provided by [Latitude.sh](https://www.latitude.sh/accelerate).
 
-* [4-bit GPTQ models for GPU inference](https://huggingface.co/TheBloke/llama-deus-7b-v3-GPTQ)
-* [4-bit, 5-bit and 8-bit GGML models for CPU(+GPU) inference](https://huggingface.co/TheBloke/llama-deus-7b-v3-GGML)
+## Repositories available
+
+* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/llama-deus-7b-v3-GPTQ)
+* [2, 3, 4, 5, 6 and 8-bit GGML models for CPU+GPU inference](https://huggingface.co/TheBloke/llama-deus-7b-v3-GGML)
 * [Unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/teknium/llama-deus-7b-v3-lora-merged)
 
-## Prompt template
+## Prompt template: Alpaca
 
 ```
-### Instruction:
-<prompt>
+Below is an instruction that describes a task. Write a response that appropriately completes the request.
 
-### Response:
+### Instruction: {prompt}
 
+### Response:
 ```
 
-or
+## Provided files
 
-```
-### Instruction:
-<prompt>
+Multiple quantisation parameters are provided, to allow you to choose the best one for your hardware and requirements.
 
-### Input:
-<input>
+Each separate quant is in a different branch.  See below for instructions on fetching from different branches.
 
-### Response:
+| Branch | Bits | Group Size | Act Order (desc_act) | File Size | ExLlama Compatible? | Made With | Description |
+| ------ | ---- | ---------- | -------------------- | --------- | ------------------- | --------- | ----------- |
+| main | 4 | 128 | False | 4.00 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 | 4.28 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 | 4.02 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 | 3.90 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 | 7.01 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 | 7.16 GB | False | AutoGPTQ | 8-bit, with group size 128g for higher inference quality and without Act Order to improve AutoGPTQ speed. |
+| gptq-8bit-128g-actorder_True | 8 | 128 | True | 7.16 GB | False | 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 | 8 | 64 | True | 7.31 GB | False | AutoGPTQ | 8-bit, with group size 64g and Act Order for maximum inference quality. Poor AutoGPTQ CUDA speed. |
+
+## How to download from branches
 
+- In text-generation-webui, you can add `:branch` to the end of the download name, eg `TheBloke/llama-deus-7b-v3-GPTQ:gptq-4bit-32g-actorder_True`
+- With Git, you can clone a branch with:
 ```
+git clone --branch gptq-4bit-32g-actorder_True https://huggingface.co/TheBloke/llama-deus-7b-v3-GPTQ`
+```
+- In Python Transformers code, the branch is the `revision` parameter; see below.
+
+## How to easily download and use this model in [text-generation-webui](https://github.com/oobabooga/text-generation-webui).
 
-## How to easily download and use this model in text-generation-webui
+Please make sure you're using the latest version of [text-generation-webui](https://github.com/oobabooga/text-generation-webui).
 
-### Downloading the model
+It is strongly recommended to use the text-generation-webui one-click-installers unless you know how to make a manual install.
 
 1. Click the **Model tab**.
 2. Under **Download custom model or LoRA**, enter `TheBloke/llama-deus-7b-v3-GPTQ`.
+  - To download from a specific branch, enter for example `TheBloke/llama-deus-7b-v3-GPTQ:gptq-4bit-32g-actorder_True`
+  - see Provided Files above for the list of branches for each option.
 3. Click **Download**.
-4. Wait until it says it's finished downloading.
-5. Untick "Autoload model"
-6. Click the **Refresh** icon next to **Model** in the top left.
+4. The model will start downloading. Once it's finished it will say "Done"
+5. In the top left, click the refresh icon next to **Model**.
+6. In the **Model** dropdown, choose the model you just downloaded: `llama-deus-7b-v3-GPTQ`
+7. The model will automatically load, and is now ready for use!
+8. If you want any custom settings, set them and then click **Save settings for this model** followed by **Reload the Model** in the top right.
+  * Note that you do not need to set GPTQ parameters any more. These are set automatically from the file `quantize_config.json`.
+9. Once you're ready, click the **Text Generation tab** and enter a prompt to get started!
 
-### To use with AutoGPTQ (if installed)
+## How to use this GPTQ model from Python code
 
-1. In the **Model drop-down**: choose the model you just downloaded, `llama-deus-7b-v3-GPTQ`.
-2. Under **GPTQ**, tick **AutoGPTQ**.
-3. Click **Save settings for this model** in the top right.
-4. Click **Reload the Model** in the top right.
-5. Once it says it's loaded, click the **Text Generation tab** and enter a prompt!
+First make sure you have [AutoGPTQ](https://github.com/PanQiWei/AutoGPTQ) installed:
 
-### To use with GPTQ-for-LLaMa
+`GITHUB_ACTIONS=true pip install auto-gptq`
 
-1. In the **Model drop-down**: choose the model you just downloaded, `llama-deus-7b-v3-GPTQ`.
-2. If you see an error in the bottom right, ignore it - it's temporary.
-3. Fill out the `GPTQ parameters` on the right: `Bits = 4`, `Groupsize = 128`, `model_type = Llama`
-4. Click **Save settings for this model** in the top right.
-5. Click **Reload the Model** in the top right.
-6. Once it says it's loaded, click the **Text Generation tab** and enter a prompt!
+Then try the following example code:
 
-## Provided files
+```python
+from transformers import AutoTokenizer, pipeline, logging
+from auto_gptq import AutoGPTQForCausalLM, BaseQuantizeConfig
+
+model_name_or_path = "TheBloke/llama-deus-7b-v3-GPTQ"
+model_basename = "llama-deus-7b-v3-GPTQ-4bit-128g.no-act.order"
+
+use_triton = False
+
+tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=True)
+
+model = AutoGPTQForCausalLM.from_quantized(model_name_or_path,
+        model_basename=model_basename
+        use_safetensors=True,
+        trust_remote_code=True,
+        device="cuda:0",
+        use_triton=use_triton,
+        quantize_config=None)
 
-**llama-deus-7b-v3-GPTQ-4bit-128g.no-act.order.safetensors**
+"""
+To download from a specific branch, use the revision parameter, as in this example:
 
-This will work with all versions of GPTQ-for-LLaMa, and with AutoGPTQ.
+model = AutoGPTQForCausalLM.from_quantized(model_name_or_path,
+        revision="gptq-4bit-32g-actorder_True",
+        model_basename=model_basename,
+        use_safetensors=True,
+        trust_remote_code=True,
+        device="cuda:0",
+        quantize_config=None)
+"""
 
-It was created with
+prompt = "Tell me about AI"
+prompt_template=f'''Below is an instruction that describes a task. Write a response that appropriately completes the request.
 
-* `llama-deus-7b-v3-GPTQ-4bit-128g.no-act.order.safetensors`
-  * Works with all versions of GPTQ-for-LLaMa code, both Triton and CUDA branches
-  * Works with AutoGPTQ
-  * Works with text-generation-webui one-click-installers
-  * Parameters: Groupsize = 128. Act Order / desc_act = False.
+### Instruction: {prompt}
+
+### Response:
+'''
+
+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)
+print(tokenizer.decode(output[0]))
+
+# Inference can also be done using transformers' pipeline
+
+# Prevent printing spurious transformers error when using pipeline with AutoGPTQ
+logging.set_verbosity(logging.CRITICAL)
+
+print("*** Pipeline:")
+pipe = pipeline(
+    "text-generation",
+    model=model,
+    tokenizer=tokenizer,
+    max_new_tokens=512,
+    temperature=0.7,
+    top_p=0.95,
+    repetition_penalty=1.15
+)
+
+print(pipe(prompt_template)[0]['generated_text'])
+```
+
+## Compatibility
+
+The files provided will work with AutoGPTQ (CUDA and Triton modes), GPTQ-for-LLaMa (only CUDA has been tested), and Occ4m's GPTQ-for-LLaMa fork.
+
+ExLlama works with Llama models in 4-bit. Please see the Provided Files table above for per-file compatibility.
 
 <!-- footer start -->
 ## 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.
 
@@ -114,24 +185,31 @@ 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
 
-**Patreon special mentions**: Aemon Algiz, Dmitriy Samsonov, Nathan LeClaire, Trenton Dambrowitz, Mano Prime, David Flickinger, vamX, Nikolai Manek, senxiiz, Khalefa Al-Ahmad, Illia Dulskyi, Jonathan Leane, Talal Aujan, V. Lukas, Joseph William Delisle, Pyrater, Oscar Rangel, Lone Striker, Luke Pendergrass, Eugene Pentland, Sebastain Graf, Johann-Peter Hartman.
+**Special thanks to**: Luke from CarbonQuill, Aemon Algiz.
+
+**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!
+
 <!-- footer end -->
 
 # Original model card: Teknium's LLaMa Deus 7B v3
 
+---
+license: mit
+---
+
 Base Mode: Llama 7B
 LoRA is fully Merged with llama7b, so you do not need to merge it to load the model.
 
 Llama DEUS v3 is the largest dataset I've trained on yet, including:
 
-GPTeacher - General Instruct - Code Instruct - Roleplay Instruct
-My unreleased Roleplay V2 Instruct
-GPT4-LLM Uncensored + Unnatural Instructions
-WizardLM Uncensored
-CamelAI's 20k Biology, 20k Physics, 20k Chemistry, and 50k Math GPT4 Datasets
-CodeAlpaca
+GPTeacher - General Instruct - Code Instruct - Roleplay Instruct  
+My unreleased Roleplay V2 Instruct  
+GPT4-LLM Uncensored + Unnatural Instructions  
+WizardLM Uncensored  
+CamelAI's 20k Biology, 20k Physics, 20k Chemistry, and 50k Math GPT4 Datasets  
+CodeAlpaca  
 
 This model was trained for 4 epochs over 1 day of training, it's a rank 128 LORA that targets attention heads, LM_Head, and MLP layers
 
@@ -140,9 +218,9 @@ Prompt format:
 ```
 ### Instruction:
 <prompt>
-
+  
 ### Response:
-
+  
 ```
 
 or
@@ -153,7 +231,8 @@ or
 
 ### Input:
 <input>
-
+  
 ### Response:
+  
+```  
 
-```