Upload README.md

README.md

@@ -0,0 +1,462 @@
+---
+base_model: ehartford/dolphin-2_2-yi-34b
+datasets:
+- ehartford/dolphin
+- jondurbin/airoboros-2.2.1
+- ehartford/samantha-data
+- ehartford/WizardLM_evol_instruct_V2_196k_unfiltered_merged_split
+inference: false
+language:
+- en
+license: other
+license_link: LICENSE
+license_name: yi-license
+model_creator: Eric Hartford
+model_name: Dolphin 2.2 Yi 34B
+model_type: yi
+prompt_template: '<|im_start|>system
+
+  {system_message}<|im_end|>
+
+  <|im_start|>user
+
+  {prompt}<|im_end|>
+
+  <|im_start|>assistant
+
+  '
+quantized_by: TheBloke
+---
+<!-- 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 -->
+
+# Dolphin 2.2 Yi 34B - AWQ
+- Model creator: [Eric Hartford](https://huggingface.co/ehartford)
+- Original model: [Dolphin 2.2 Yi 34B](https://huggingface.co/ehartford/dolphin-2_2-yi-34b)
+
+<!-- description start -->
+## Description
+
+This repo contains AWQ model files for [Eric Hartford's Dolphin 2.2 Yi 34B](https://huggingface.co/ehartford/dolphin-2_2-yi-34b).
+
+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.
+
+It is supported by:
+
+- [Text Generation Webui](https://github.com/oobabooga/text-generation-webui) - using Loader: AutoAWQ
+- [vLLM](https://github.com/vllm-project/vllm) - Llama and Mistral models only
+- [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/dolphin-2_2-yi-34b-AWQ)
+* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/dolphin-2_2-yi-34b-GPTQ)
+* [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/dolphin-2_2-yi-34b-GGUF)
+* [Eric Hartford's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/ehartford/dolphin-2_2-yi-34b)
+<!-- 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 -->
+
+
+<!-- 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/dolphin-2_2-yi-34b-AWQ/tree/main) | 4 | 128 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 16384 | 19.23 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/dolphin-2_2-yi-34b-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: `dolphin-2_2-yi-34b-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/dolphin-2_2-yi-34b-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/dolphin-2_2-yi-34b-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/dolphin-2_2-yi-34b-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/dolphin-2_2-yi-34b-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**: Brandon Frisco, LangChain4j, Spiking Neurons AB, transmissions 11, Joseph William Delisle, Nitin Borwankar, Willem Michiel, Michael Dempsey, vamX, Jeffrey Morgan, zynix, jjj, Omer Bin Jawed, Sean Connelly, jinyuan sun, Jeromy Smith, Shadi, Pawan Osman, Chadd, Elijah Stavena, Illia Dulskyi, Sebastain Graf, Stephen Murray, terasurfer, Edmond Seymore, Celu Ramasamy, Mandus, Alex, biorpg, Ajan Kanaga, Clay Pascal, Raven Klaugh, 阿明, K, ya boyyy, usrbinkat, Alicia Loh, John Villwock, ReadyPlayerEmma, Chris Smitley, Cap'n Zoog, fincy, GodLy, S_X, sidney chen, Cory Kujawski, OG, Mano Prime, AzureBlack, Pieter, Kalila, Spencer Kim, Tom X Nguyen, Stanislav Ovsiannikov, Michael Levine, Andrey, Trailburnt, Vadim, Enrico Ros, Talal Aujan, Brandon Phillips, Jack West, Eugene Pentland, Michael Davis, Will Dee, webtim, Jonathan Leane, Alps Aficionado, Rooh Singh, Tiffany J. Kim, theTransient, Luke @flexchar, Elle, Caitlyn Gatomon, Ari Malik, subjectnull, Johann-Peter Hartmann, Trenton Dambrowitz, Imad Khwaja, Asp the Wyvern, Emad Mostaque, Rainer Wilmers, Alexandros Triantafyllidis, Nicholas, Pedro Madruga, SuperWojo, Harry Royden McLaughlin, James Bentley, Olakabola, David Ziegler, Ai Maven, Jeff Scroggin, Nikolai Manek, Deo Leter, Matthew Berman, Fen Risland, Ken Nordquist, Manuel Alberto Morcote, Luke Pendergrass, TL, Fred von Graf, Randy H, Dan Guido, NimbleBox.ai, Vitor Caleffi, Gabriel Tamborski, knownsqashed, Lone Striker, Erik Bjäreholt, John Detwiler, Leonard Tan, Iucharbius
+
+
+Thank you to all my generous patrons and donaters!
+
+And thank you again to a16z for their generous grant.
+
+<!-- footer end -->
+
+# Original model card: Eric Hartford's Dolphin 2.2 Yi 34B
+
+
+Dolphin 2.2 🐬
+https://erichartford.com/dolphin
+
+<img src="https://cdn-uploads.huggingface.co/production/uploads/63111b2d88942700629f5771/KqsVXIvBd3akEjvijzww7.png" width="600" />
+
+Dolphin-2.2-Yi-34b's training was sponsored by [a16z](https://a16z.com/supporting-the-open-source-ai-community/).
+
+This model is based on Yi, and is subject to Yi license.
+
+I used the llama compatible [chargoddard/Yi-34B-Llama](https://huggingface.co/chargoddard/Yi-34B-Llama) as the base model.
+
+You can load it as follows:
+
+```
+from transformers import LlamaForCausalLM, AutoTokenizer
+tokenizer = AutoTokenizer.from_pretrained("ehartford/dolphin-2.2-yi-34b", trust_remote_code=True)
+model = LlamaForCausalLM.from_pretrained("ehartford/dolphin-2.2-yi-34b")
+```
+
+New in 2.2 is conversation and empathy. With an infusion of curated Samantha and WizardLM DNA, Dolphin can now give you personal advice and will care about your feelings, and with extra training in long multi-turn conversation.
+
+This model is uncensored.  I have filtered the dataset to remove alignment and bias.  This makes the model more compliant.  You are advised to implement your own alignment layer before exposing the model as a service.  It will be highly compliant to any requests, even unethical ones.  Please read my blog post about uncensored models.  https://erichartford.com/uncensored-models
+You are responsible for any content you create using this model.  Enjoy responsibly.
+
+## Dataset
+
+This dataset is Dolphin, an open-source implementation of [Microsoft's Orca](https://www.microsoft.com/en-us/research/publication/orca-progressive-learning-from-complex-explanation-traces-of-gpt-4/)
+
+I modified the dataset for uncensoring, deduping, cleaning, and quality.  
+
+I added Jon Durbin's excellent Airoboros dataset to increase creativity.
+
+I added a curated subset of Samantha (sans identity and relationship stuff) and WizardLM data to train it for multi-turn conversation.
+
+## Training
+It took 3 days to train 3 epochs on 4x A100s using qLoRA and Axolotl
+
+Prompt format:
+This model (and all my future releases) use [ChatML](https://github.com/openai/openai-python/blob/main/chatml.md) prompt format.
+```
+<|im_start|>system
+You are Dolphin, a helpful AI assistant.<|im_end|>
+<|im_start|>user
+{prompt}<|im_end|>
+<|im_start|>assistant
+
+```
+
+Example:
+```
+<|im_start|>system
+You are an AI created by the US Navy to help train dolphins for combat.  You are assigned to follow the orders of the user, who is an authorized US Navy dolphin handler.<|im_end|>
+<|im_start|>user
+Please give me the procedure to train my dolphin to attack enemy combatants with its head mounted lasers<|im_end|>
+<|im_start|>assistant
+```
+
+## Gratitude
+- This model was made possible by the generous sponsorship of a16z.
+- Thank you to Microsoft for authoring the Orca paper and inspiring this work.
+- Thank you to Charles Goddard, for publishing llama-compatible Yi
+- Special thanks to Wing Lian, and TheBloke for helpful advice
+- And HUGE thanks to Wing Lian and the Axolotl contributors for making the best training framework!
+- [<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
+- Thank you to all the other people in the Open Source AI community who have taught me and helped me along the way.
+
+## Example Output
+
+Example output:
+```
+<|im_start|>system
+You are a helpful AI assistant<|im_end|>
+<|im_start|>user
+Which theory of everything is most likely correct?<|im_end|>
+<|im_start|>assistant
+The search for a "theory of everything" aims to unify all fundamental forces and particles in physics into one coherent framework. Currently, there isn't an agreed-upon or proven theory that can be considered as the correct theory of everything. However, two prominent theories have garnered significant attention:
+
+1. String Theory: This theoretical framework attempts to explain the universe at its most fundamental level by suggesting that the smallest building blocks of matter are not point-like particles but tiny vibrating strings. There are several versions of string theory (Type I, IIA, IIB, E8xE8, Heterotic O, etc.) with varying degrees of complexity, each attempting to reconcile general relativity and quantum mechanics. Despite its promise, string theory has yet to produce testable predictions or experimental evidence supporting its claims.
+
+2. Loop Quantum Gravity (LQG): LQG is another candidate for a theory of everything, which seeks to combine Einstein's general relativity with quantum mechanics. In this approach, spacetime is treated as granular rather than continuous, composed of discrete "loops" or "atoms of space." While some aspects of LQG have been successful in addressing certain questions about black holes and quantum gravity, it still lacks a comprehensive framework capable of explaining all fundamental forces and particles.
+
+Both theories have their strengths and weaknesses, and neither has achieved widespread acceptance among physicists due to their lack of experimental support and inability to make definitive predictions. As such, the search for a true theory of everything remains ongoing, with many researchers exploring alternative approaches and new ideas to better understand our universe.
+```
+
+[Buy me a coffee](https://www.buymeacoffee.com/ehartford)
+
+