Update README.md

README.md

@@ -1,3 +1,99 @@
 ---
 license: other
+inference: false
 ---
+# Vicuna 7B 1.1 GPTQ 4bit 128g
+
+This is a 4-bit GPTQ version of the [Vicuna 7B 1.1 model](https://huggingface.co/lmsys/vicuna-7b-delta-v1.1).
+
+It was created by merging the deltas provided in the above repo with the original Llama 7B model, [using the code provided on their Github page](https://github.com/lm-sys/FastChat#vicuna-weights).
+
+It was then quantized to 4bit using [GPTQ-for-LLaMa](https://github.com/qwopqwop200/GPTQ-for-LLaMa).
+
+## Provided files
+
+Two model files are provided. Ideally use the `safetensors` file. Full details below:
+
+Details of the files provided:
+* `vicuna-7B-1.1-GPTQ-4bit-128g.safetensors`
+  * `safetensors` format, with improved file security, created with the latest [GPTQ-for-LLaMa](https://github.com/qwopqwop200/GPTQ-for-LLaMa) code.
+  * Command to create:
+    * `python3 llama.py vicuna-7B-1.1-HF c4 --wbits 4 --true-sequential --act-order --groupsize 128 --save_safetensors vicuna-7B-1.1-GPTQ-4bit-128g.safetensors`
+* vicuna-7B-1.1-GPTQ-4bit-128g.safetensors.no-act-order.pt`
+  * `pt` format file, created without the `--act-order` flag.
+  * This file may have slightly lower quality, but is included as it can be used without needing to compile the latest GPTQ-for-LLaMa code.
+  * It should hopefully therefore work with one-click-installers on Windows, which include the older GPTQ-for-LLaMa code.
+  * Command to create:
+    * `python3 llama.py vicuna-7B-1.1-HF c4 --wbits 4 --true-sequential --groupsize 128 --save_safetensors vicuna-7B-1.1-GPTQ-4bit-128g.no-act-order.pt`
+
+## How to run in `text-generation-webui`
+
+File `vicuna-7B-1.1-GPTQ-4bit-128g.no-act-order.pt` can be loaded the same as any other GPTQ file, without requiring any updates to [oobaboogas text-generation-webui](https://github.com/oobabooga/text-generation-webui).
+
+The `safetensors` model file was created with the latest GPTQ code, and may be highere quality, but requires that the latest GPTQ-for-LLaMa is used inside the UI.
+
+Here are the commands I used to clone the Triton branch of GPTQ-for-LLaMa, clone text-generation-webui, and install GPTQ into the UI:
+```
+git clone https://github.com/qwopqwop200/GPTQ-for-LLaMa
+git clone https://github.com/oobabooga/text-generation-webui
+mkdir -p text-generation-webui/repositories
+ln -s GPTQ-for-LLaMa text-generation-webui/repositories/GPTQ-for-LLaMa
+```
+
+Then install this model into `text-generation-webui/models` and launch the UI as follows:
+```
+cd text-generation-webui
+python server.py --model vicuna-7B-1.1-GPTQ-4bit-128g --wbits 4 --groupsize 128 --model_type Llama # add any other command line args you want
+```
+
+The above commands assume you have installed all dependencies for GPTQ-for-LLaMa and text-generation-webui. Please see their respective repositories for further information.
+
+If you are on Windows, or cannot use the Triton branch of GPTQ for any other reason, you can instead use the CUDA branch:
+```
+git clone https://github.com/qwopqwop200/GPTQ-for-LLaMa -b cuda
+cd GPTQ-for-LLaMa
+python setup_cuda.py install
+```
+Then link that into `text-generation-webui/repositories` as described above.
+
+Or just use `vicuna-7B-1.1-GPTQ-4bit-128g.no-act-order.pt` as mentioned above.
+
+# Vicuna Model Card
+
+## Model details
+
+**Model type:**
+Vicuna is an open-source chatbot trained by fine-tuning LLaMA on user-shared conversations collected from ShareGPT.
+It is an auto-regressive language model, based on the transformer architecture.
+
+**Model date:**
+Vicuna was trained between March 2023 and April 2023.
+
+**Organizations developing the model:**
+The Vicuna team with members from UC Berkeley, CMU, Stanford, and UC San Diego.
+
+**Paper or resources for more information:**
+https://vicuna.lmsys.org/
+
+**License:**
+Apache License 2.0
+
+**Where to send questions or comments about the model:**
+https://github.com/lm-sys/FastChat/issues
+
+## Intended use
+**Primary intended uses:**
+The primary use of Vicuna is research on large language models and chatbots.
+
+**Primary intended users:**
+The primary intended users of the model are researchers and hobbyists in natural language processing, machine learning, and artificial intelligence.
+
+## Training dataset
+70K conversations collected from ShareGPT.com.
+
+## Evaluation dataset
+A preliminary evaluation of the model quality is conducted by creating a set of 80 diverse questions and utilizing GPT-4 to judge the model outputs. See https://vicuna.lmsys.org/ for more details.
+
+## Major updates of weights v1.1
+- Refactor the tokenization and separator. In Vicuna v1.1, the separator has been changed from `"###"` to the EOS token `"</s>"`. This change makes it easier to determine the generation stop criteria and enables better compatibility with other libraries.
+- Fix the supervised fine-tuning loss computation for better model quality.