Upload README.md

README.md

@@ -0,0 +1,462 @@
+---
+base_model: Locutusque/Orca-2-13b-SFT_v5
+datasets:
+- HuggingFaceH4/no_robots
+- mlabonne/guanaco-llama2-1k
+- OpenAssistant/oasst_top1_2023-08-25
+- totally-not-an-llm/EverythingLM-data-V3
+- garage-bAInd/Open-Platypus
+inference: false
+language:
+- en
+- fr
+- es
+- hi
+- zh
+- code
+license: other
+model_creator: Sebastian Gabarain
+model_name: Orca 2 13B SFT V5
+model_type: llama
+prompt_template: '<|im_start|>system
+
+  {system_message}<|im_end|>
+
+  <|im_start|>user
+
+  {prompt}<|im_end|>
+
+  <|im_start|>assistant
+
+  '
+quantized_by: TheBloke
+widget:
+- example_title: folklore
+  output:
+    text: 'The Nahanni Valley in Canada is a remote and rugged region that has long
+      been shrouded in mystery. It is home to the South Nahanni River, which was designated
+      as a UNESCO World Heritage Site due to its exceptional natural beauty and biodiversity.
+      The valley''s history includes tales of gold prospectors, fur traders, and indigenous
+      populations, but it also features some unexplained events and legends. One such
+      story involves two prospectors who allegedly encountered an unknown creature
+      that led them into the forest before returning without their heads. This tale
+      has been passed down through generations, but there are no definitive answers
+      regarding its veracity.
+
+
+      It is important to note that these stories may have originated from local folklore
+      or were exaggerated over time. There is no concrete evidence to support the
+      existence of supernatural creatures or paranormal occurrences within the Nahanni
+      Valley. Nonetheless, the area remains a captivating destination for those seeking
+      adventure and exploration. If you have any questions about this topic or need
+      assistance related to traveling to the Nahanni Valley, please feel free to ask!'
+  text: '<|im_start|>user
+
+    Are the stories of Nahanni Valley, like the decapitated men, true?
+
+    <|im_end|>
+
+    <|im_start|>assistant
+
+    '
+- example_title: Alan Turing
+  output:
+    text: 'Alan Turing, a renowned mathematician and computer scientist who played
+      a crucial role in breaking the German Enigma code during World War II, faced
+      significant challenges due to his homosexuality. In 1952, he was convicted of
+      "gross indecency" for engaging in a consensual relationship with another man,
+      which led to him being sentenced to hormone therapy designed to reduce his sex
+      drive. This treatment included the administration of estrogen, which had the
+      side effect of causing breast growth.
+
+
+      In an effort to avoid this unwanted physical change, Turing requested that his
+      doctors cease the hormone treatments. However, they ignored his request and
+      continued the therapy without his consent. As a result, Turing''s breasts began
+      to grow, leading him to undergo surgery to remove them. The operation, known
+      as a mastectomy, caused considerable pain and discomfort, further contributing
+      to his emotional turmoil.
+
+
+      It is important to note that Turing''s castration was not directly carried out
+      by the authorities but rather resulted from the unintended consequences of the
+      forced hormone therapy.'
+  text: '<|im_start|>user
+
+    Why was Alan Turing castrated?
+
+    <|im_end|>
+
+    <|im_start|>assistant
+
+    '
+---
+<!-- markdownlint-disable MD041 -->
+
+<!-- header start -->
+<!-- 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 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 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 -->
+
+# Orca 2 13B SFT V5 - AWQ
+- Model creator: [Sebastian Gabarain](https://huggingface.co/Locutusque)
+- Original model: [Orca 2 13B SFT V5](https://huggingface.co/Locutusque/Orca-2-13b-SFT_v5)
+
+<!-- description start -->
+## Description
+
+This repo contains AWQ model files for [Sebastian Gabarain's Orca 2 13B SFT V5](https://huggingface.co/Locutusque/Orca-2-13b-SFT_v5).
+
+These files were quantised using hardware kindly provided by [Massed Compute](https://massedcompute.com/).
+
+
+### About AWQ
+
+AWQ is an efficient, accurate and blazing-fast low-bit weight quantization method, currently supporting 4-bit quantization. Compared to GPTQ, it offers faster Transformers-based inference with equivalent or better quality compared to the most commonly used GPTQ settings.
+
+AWQ models are currently supported on Linux and Windows, with NVidia GPUs only. macOS users: please use GGUF models instead.
+
+It is supported by:
+
+- [Text Generation Webui](https://github.com/oobabooga/text-generation-webui) - using Loader: AutoAWQ
+- [vLLM](https://github.com/vllm-project/vllm) - version 0.2.2 or later for support for all model types.
+- [Hugging Face Text Generation Inference (TGI)](https://github.com/huggingface/text-generation-inference)
+- [Transformers](https://huggingface.co/docs/transformers) version 4.35.0 and later, from any code or client that supports Transformers
+- [AutoAWQ](https://github.com/casper-hansen/AutoAWQ) - for use from Python code
+
+<!-- description end -->
+<!-- repositories-available start -->
+## Repositories available
+
+* [AWQ model(s) for GPU inference.](https://huggingface.co/TheBloke/Orca-2-13B-SFT_v5-AWQ)
+* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/Orca-2-13B-SFT_v5-GPTQ)
+* [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/Orca-2-13B-SFT_v5-GGUF)
+* [Sebastian Gabarain's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/Locutusque/Orca-2-13b-SFT_v5)
+<!-- repositories-available end -->
+
+<!-- prompt-template start -->
+## Prompt template: ChatML
+
+```
+<|im_start|>system
+{system_message}<|im_end|>
+<|im_start|>user
+{prompt}<|im_end|>
+<|im_start|>assistant
+
+```
+
+<!-- prompt-template end -->
+<!-- licensing start -->
+## Licensing
+
+The creator of the source model has listed its license as `other`, 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: [Sebastian Gabarain's Orca 2 13B SFT V5](https://huggingface.co/Locutusque/Orca-2-13b-SFT_v5).
+<!-- licensing end -->
+<!-- README_AWQ.md-provided-files start -->
+## Provided files, and AWQ parameters
+
+I currently release 128g GEMM models only. The addition of group_size 32 models, and GEMV kernel models, is being actively considered.
+
+Models are released as sharded safetensors files.
+
+| Branch | Bits | GS | AWQ Dataset | Seq Len | Size |
+| ------ | ---- | -- | ----------- | ------- | ---- |
+| [main](https://huggingface.co/TheBloke/Orca-2-13B-SFT_v5-AWQ/tree/main) | 4 | 128 | [VMware Open Instruct](https://huggingface.co/datasets/VMware/open-instruct/viewer/) | 4096 | 7.25 GB
+
+<!-- README_AWQ.md-provided-files end -->
+
+<!-- README_AWQ.md-text-generation-webui start -->
+## How to easily download and use this model in [text-generation-webui](https://github.com/oobabooga/text-generation-webui)
+
+Please make sure you're using the latest version of [text-generation-webui](https://github.com/oobabooga/text-generation-webui).
+
+It is strongly recommended to use the text-generation-webui one-click-installers unless you're sure you know how to make a manual install.
+
+1. Click the **Model tab**.
+2. Under **Download custom model or LoRA**, enter `TheBloke/Orca-2-13B-SFT_v5-AWQ`.
+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: `Orca-2-13B-SFT_v5-AWQ`
+7. Select **Loader: AutoAWQ**.
+8. Click Load, and the model will load and is now ready for use.
+9. 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.
+10. Once you're ready, click the **Text Generation** tab and enter a prompt to get started!
+<!-- README_AWQ.md-text-generation-webui end -->
+
+<!-- README_AWQ.md-use-from-vllm start -->
+## Multi-user inference server: vLLM
+
+Documentation on installing and using vLLM [can be found here](https://vllm.readthedocs.io/en/latest/).
+
+- Please ensure you are using vLLM version 0.2 or later.
+- When using vLLM as a server, pass the `--quantization awq` parameter.
+
+For example:
+
+```shell
+python3 -m vllm.entrypoints.api_server --model TheBloke/Orca-2-13B-SFT_v5-AWQ --quantization awq --dtype auto
+```
+
+- When using vLLM from Python code, again set `quantization=awq`.
+
+For example:
+
+```python
+from vllm import LLM, SamplingParams
+
+prompts = [
+    "Tell me about AI",
+    "Write a story about llamas",
+    "What is 291 - 150?",
+    "How much wood would a woodchuck chuck if a woodchuck could chuck wood?",
+]
+prompt_template=f'''<|im_start|>system
+{system_message}<|im_end|>
+<|im_start|>user
+{prompt}<|im_end|>
+<|im_start|>assistant
+'''
+
+prompts = [prompt_template.format(prompt=prompt) for prompt in prompts]
+
+sampling_params = SamplingParams(temperature=0.8, top_p=0.95)
+
+llm = LLM(model="TheBloke/Orca-2-13B-SFT_v5-AWQ", quantization="awq", dtype="auto")
+
+outputs = llm.generate(prompts, sampling_params)
+
+# Print the outputs.
+for output in outputs:
+    prompt = output.prompt
+    generated_text = output.outputs[0].text
+    print(f"Prompt: {prompt!r}, Generated text: {generated_text!r}")
+```
+<!-- README_AWQ.md-use-from-vllm start -->
+
+<!-- README_AWQ.md-use-from-tgi start -->
+## Multi-user inference server: Hugging Face Text Generation Inference (TGI)
+
+Use TGI version 1.1.0 or later. The official Docker container is: `ghcr.io/huggingface/text-generation-inference:1.1.0`
+
+Example Docker parameters:
+
+```shell
+--model-id TheBloke/Orca-2-13B-SFT_v5-AWQ --port 3000 --quantize awq --max-input-length 3696 --max-total-tokens 4096 --max-batch-prefill-tokens 4096
+```
+
+Example Python code for interfacing with TGI (requires [huggingface-hub](https://github.com/huggingface/huggingface_hub) 0.17.0 or later):
+
+```shell
+pip3 install huggingface-hub
+```
+
+```python
+from huggingface_hub import InferenceClient
+
+endpoint_url = "https://your-endpoint-url-here"
+
+prompt = "Tell me about AI"
+prompt_template=f'''<|im_start|>system
+{system_message}<|im_end|>
+<|im_start|>user
+{prompt}<|im_end|>
+<|im_start|>assistant
+'''
+
+client = InferenceClient(endpoint_url)
+response = client.text_generation(prompt,
+                                  max_new_tokens=128,
+                                  do_sample=True,
+                                  temperature=0.7,
+                                  top_p=0.95,
+                                  top_k=40,
+                                  repetition_penalty=1.1)
+
+print(f"Model output: ", response)
+```
+<!-- README_AWQ.md-use-from-tgi end -->
+
+<!-- README_AWQ.md-use-from-python start -->
+## Inference from Python code using Transformers
+
+### Install the necessary packages
+
+- Requires: [Transformers](https://huggingface.co/docs/transformers) 4.35.0 or later.
+- Requires: [AutoAWQ](https://github.com/casper-hansen/AutoAWQ) 0.1.6 or later.
+
+```shell
+pip3 install --upgrade "autoawq>=0.1.6" "transformers>=4.35.0"
+```
+
+Note that if you are using PyTorch 2.0.1, the above AutoAWQ command will automatically upgrade you to PyTorch 2.1.0.
+
+If you are using CUDA 11.8 and wish to continue using PyTorch 2.0.1, instead run this command:
+
+```shell
+pip3 install https://github.com/casper-hansen/AutoAWQ/releases/download/v0.1.6/autoawq-0.1.6+cu118-cp310-cp310-linux_x86_64.whl
+```
+
+If you have problems installing [AutoAWQ](https://github.com/casper-hansen/AutoAWQ) using the pre-built wheels, install it from source instead:
+
+```shell
+pip3 uninstall -y autoawq
+git clone https://github.com/casper-hansen/AutoAWQ
+cd AutoAWQ
+pip3 install .
+```
+
+### Transformers example code (requires Transformers 4.35.0 and later)
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer, TextStreamer
+
+model_name_or_path = "TheBloke/Orca-2-13B-SFT_v5-AWQ"
+
+tokenizer = AutoTokenizer.from_pretrained(model_name_or_path)
+model = AutoModelForCausalLM.from_pretrained(
+    model_name_or_path,
+    low_cpu_mem_usage=True,
+    device_map="cuda:0"
+)
+
+# Using the text streamer to stream output one token at a time
+streamer = TextStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True)
+
+prompt = "Tell me about AI"
+prompt_template=f'''<|im_start|>system
+{system_message}<|im_end|>
+<|im_start|>user
+{prompt}<|im_end|>
+<|im_start|>assistant
+'''
+
+# Convert prompt to tokens
+tokens = tokenizer(
+    prompt_template,
+    return_tensors='pt'
+).input_ids.cuda()
+
+generation_params = {
+    "do_sample": True,
+    "temperature": 0.7,
+    "top_p": 0.95,
+    "top_k": 40,
+    "max_new_tokens": 512,
+    "repetition_penalty": 1.1
+}
+
+# Generate streamed output, visible one token at a time
+generation_output = model.generate(
+    tokens,
+    streamer=streamer,
+    **generation_params
+)
+
+# Generation without a streamer, which will include the prompt in the output
+generation_output = model.generate(
+    tokens,
+    **generation_params
+)
+
+# Get the tokens from the output, decode them, print them
+token_output = generation_output[0]
+text_output = tokenizer.decode(token_output)
+print("model.generate output: ", text_output)
+
+# Inference is also possible via Transformers' pipeline
+from transformers import pipeline
+
+pipe = pipeline(
+    "text-generation",
+    model=model,
+    tokenizer=tokenizer,
+    **generation_params
+)
+
+pipe_output = pipe(prompt_template)[0]['generated_text']
+print("pipeline output: ", pipe_output)
+
+```
+<!-- README_AWQ.md-use-from-python end -->
+
+<!-- README_AWQ.md-compatibility start -->
+## Compatibility
+
+The files provided are tested to work with:
+
+- [text-generation-webui](https://github.com/oobabooga/text-generation-webui) using `Loader: AutoAWQ`.
+- [vLLM](https://github.com/vllm-project/vllm) version 0.2.0 and later.
+- [Hugging Face Text Generation Inference (TGI)](https://github.com/huggingface/text-generation-inference) version 1.1.0 and later.
+- [Transformers](https://huggingface.co/docs/transformers) version 4.35.0 and later.
+- [AutoAWQ](https://github.com/casper-hansen/AutoAWQ) version 0.1.1 and later.
+
+<!-- README_AWQ.md-compatibility end -->
+
+<!-- footer start -->
+<!-- 200823 -->
+## Discord
+
+For further support, and discussions on these models and AI in general, join us at:
+
+[TheBloke AI's Discord server](https://discord.gg/theblokeai)
+
+## 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.
+
+Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits.
+
+* Patreon: https://patreon.com/TheBlokeAI
+* Ko-Fi: https://ko-fi.com/TheBlokeAI
+
+**Special thanks to**: Aemon Algiz.
+
+**Patreon special mentions**: Michael Levine, 阿明, Trailburnt, Nikolai Manek, John Detwiler, Randy H, Will Dee, Sebastain Graf, NimbleBox.ai, Eugene Pentland, Emad Mostaque, Ai Maven, Jim Angel, Jeff Scroggin, Michael Davis, Manuel Alberto Morcote, Stephen Murray, Robert, Justin Joy, Luke @flexchar, Brandon Frisco, Elijah Stavena, S_X, Dan Guido, Undi ., Komninos Chatzipapas, Shadi, theTransient, Lone Striker, Raven Klaugh, jjj, Cap'n Zoog, Michel-Marie MAUDET (LINAGORA), Matthew Berman, David, Fen Risland, Omer Bin Jawed, Luke Pendergrass, Kalila, OG, Erik Bjäreholt, Rooh Singh, Joseph William Delisle, Dan Lewis, TL, John Villwock, AzureBlack, Brad, Pedro Madruga, Caitlyn Gatomon, K, jinyuan sun, Mano Prime, Alex, Jeffrey Morgan, Alicia Loh, Illia Dulskyi, Chadd, transmissions 11, fincy, Rainer Wilmers, ReadyPlayerEmma, knownsqashed, Mandus, biorpg, Deo Leter, Brandon Phillips, SuperWojo, Sean Connelly, Iucharbius, Jack West, Harry Royden McLaughlin, Nicholas, terasurfer, Vitor Caleffi, Duane Dunston, Johann-Peter Hartmann, David Ziegler, Olakabola, Ken Nordquist, Trenton Dambrowitz, Tom X Nguyen, Vadim, Ajan Kanaga, Leonard Tan, Clay Pascal, Alexandros Triantafyllidis, JM33133, Xule, vamX, ya boyyy, subjectnull, Talal Aujan, Alps Aficionado, wassieverse, Ari Malik, James Bentley, Woland, Spencer Kim, Michael Dempsey, Fred von Graf, Elle, zynix, William Richards, Stanislav Ovsiannikov, Edmond Seymore, Jonathan Leane, Martin Kemka, usrbinkat, Enrico Ros
+
+
+Thank you to all my generous patrons and donaters!
+
+And thank you again to a16z for their generous grant.
+
+<!-- footer end -->
+
+# Original model card: Sebastian Gabarain's Orca 2 13B SFT V5
+
+The "microsoft/Orca-2-13b" model fully fine-tuned on HuggingFaceH4/no_robots, totally-not-an-llm/EverythingLM-data-V3, mlabonne/guanaco-llama2-1k, OpenAssistant/oasst_top1_2023-08-25, and garage-bAInd/Open-Platypus. This model achieved a test loss of 0.38.
+
+Make sure to comply with the microsoft research license. Please read it before using this model.
+
+This model was trained on the ChatML prompt template.
+
+The responses seen in the inference API were generated using the following sampling parameters:
+
+temperature = 0.1
+
+top_p = 0.14
+
+top_k = 41
+
+repetition_penalty = 1.176