Update README.md

README.md

@@ -23,13 +23,28 @@ These files are GPTQ 4bit model files for [Panchovix's merge of Guanaco 33B and
 
 It is the result of quantising to 4bit using [GPTQ-for-LLaMa](https://github.com/qwopqwop200/GPTQ-for-LLaMa).
 
+**This is an experimental new GPTQ which offers up to 8K context size**
+
+The increased context is tested to work with [ExLlama](https://github.com/turboderp/exllama), via the latest release of [text-generation-webui](https://github.com/oobabooga/text-generation-webui).
+
+It has also been tested from Python code using AutoGPTQ, and `trust_remote_code=True`.
+
+Code credits:
+- Original concept and code for inreasing context length: [kaiokendev](https://huggingface.co/kaiokendev)
+- Updated Llama modelling code that includes this automatically via trust_remote_code: [emozilla](https://huggingface.co/emozilla).
+
+Please read carefully below to see how to use it.
+
+**NOTE**: Using the full 8K context on a 30B model will exceed 24GB VRAM.
+
+GGML versions are not yet provided, as there is not yet support for SuperHOT in llama.cpp. This is being investigated and will hopefully come soon.
+
 ## Repositories available
 
 * [4-bit GPTQ models for GPU inference](https://huggingface.co/TheBloke/Guanaco-33B-SuperHOT-8K-GPTQ)
-* [2, 3, 4, 5, 6 and 8-bit GGML models for CPU+GPU inference](https://huggingface.co/none)
 * [Unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/Panchovix/Guanaco-33B-SuperHOT-8k)
 
-## How to easily download and use this model in text-generation-webui
+## How to easily download and use this model in text-generation-webui with ExLlama
 
 Please make sure you're using the latest version of text-generation-webui
 
@@ -37,20 +52,25 @@ Please make sure you're using the latest version of text-generation-webui
 2. Under **Download custom model or LoRA**, enter `TheBloke/Guanaco-33B-SuperHOT-8K-GPTQ`.
 3. Click **Download**.
 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: `Guanaco-33B-SuperHOT-8K-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 and should not set manual 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!
+5. Untick **Autoload the model**
+6. In the top left, click the refresh icon next to **Model**.
+7. In the **Model** dropdown, choose the model you just downloaded: `Guanaco-33B-SuperHOT-8K-GPTQ`
+8. To use the increased context, set the **Loader** to **ExLlama**, set **max_seq_len** to 8192 or 4096, and set **compress_pos_emb** to **4** for 8192 context, or to **2** for 4096 context.
+9. Now click **Save Settings** followed by **Reload**
+10. The model will automatically load, and is now ready for use!
+11. Once you're ready, click the **Text Generation tab** and enter a prompt to get started!
 
-## How to use this GPTQ model from Python code
+## How to use this GPTQ model from Python code with AutoGPTQ
 
-First make sure you have [AutoGPTQ](https://github.com/PanQiWei/AutoGPTQ) installed:
+First make sure you have AutoGPTQ and Einops installed:
 
-`pip install auto-gptq`
+```
+pip3 install einops auto-gptq
+```
 
-Then try the following example code:
+Then run the following code. Note that in order to get this to work, `config.json` has been hardcoded to a sequence length of 8192.
+
+If you want to try 4096 instead to reduce VRAM usage, please manually edit `config.json` to set `max_position_embeddings` to the value you want.
 
 ```python
 from transformers import AutoTokenizer, pipeline, logging
@@ -67,11 +87,13 @@ 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=False,
-        device="cuda:0",
+        trust_remote_code=True,
+        device_map='auto',
         use_triton=use_triton,
         quantize_config=None)
 
+model.seqlen = 8192
+
 # Note: check the prompt template is correct for this model.
 prompt = "Tell me about AI"
 prompt_template=f'''USER: {prompt}
@@ -102,6 +124,12 @@ pipe = pipeline(
 print(pipe(prompt_template)[0]['generated_text'])
 ```
 
+## Using other UIs: monkey patch
+
+Provided in the repo is `llama_rope_scaled_monkey_patch.py`, written by @kaiokendev.
+
+It can be theoretically be added to any Python UI or custom code to enable the same result as `trust_remote_code=True`.  I have not tested this, and it should be superseded by using `trust_remote_code=True`, but I include it for completeness and for interest.
+
 ## Provided files
 
 **guanaco-33b-superhot-8k-GPTQ-4bit--1g.act.order.safetensors**