Upload README.md

ec7955b about 1 year ago

19 kB

	---
	base_model: ehartford/dolphin-2.1-70b
	datasets:
	- ehartford/dolphin
	- jondurbin/airoboros-2.2.1
	inference: false
	language:
	- en
	license: llama2
	model_creator: Eric Hartford
	model_name: Dolphin 2.1 70B
	model_type: llama
	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 2.1 70B - AWQ
	- Model creator: [Eric Hartford](https://huggingface.co/ehartford)
	- Original model: [Dolphin 2.1 70B](https://huggingface.co/ehartford/dolphin-2.1-70b)

	<!-- description start -->
	## Description

	This repo contains AWQ model files for [Eric Hartford's Dolphin 2.1 70B](https://huggingface.co/ehartford/dolphin-2.1-70b).


	### 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)
	- [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-2.1-70B-AWQ)
	* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/Dolphin-2.1-70B-GPTQ)
	* [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/Dolphin-2.1-70B-GGUF)
	* [Eric Hartford's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/ehartford/dolphin-2.1-70b)
	<!-- 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

	For my first release of AWQ models, I am releasing 128g models only. I will consider adding 32g as well if there is interest, and once I have done perplexity and evaluation comparisons, but at this time 32g models are still not fully tested with AutoAWQ and vLLM.

	Models are released as sharded safetensors files.

	\| Branch \| Bits \| GS \| AWQ Dataset \| Seq Len \| Size \|
	\| ------ \| ---- \| -- \| ----------- \| ------- \| ---- \|
	\| [main](https://huggingface.co/TheBloke/Dolphin-2.1-70B-AWQ/tree/main) \| 4 \| 128 \| [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) \| 4096 \| 36.61 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-2.1-70B-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-2.1-70B-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 python -m vllm.entrypoints.api_server --model TheBloke/Dolphin-2.1-70B-AWQ --quantization awq
	```

	- 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-2.1-70B-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-2.1-70B-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 AutoAWQ

	### Install the AutoAWQ package

	Requires: [AutoAWQ](https://github.com/casper-hansen/AutoAWQ) 0.1.1 or later.

	```shell
	pip3 install autoawq
	```

	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 .
	```

	### AutoAWQ example code

	```python
	from awq import AutoAWQForCausalLM
	from transformers import AutoTokenizer

	model_name_or_path = "TheBloke/Dolphin-2.1-70B-AWQ"

	# Load tokenizer
	tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, trust_remote_code=False)
	# Load model
	model = AutoAWQForCausalLM.from_quantized(model_name_or_path, fuse_layers=True,
	trust_remote_code=False, safetensors=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
	'''

	print("*** Running model.generate:")

	token_input = tokenizer(
	prompt_template,
	return_tensors='pt'
	).input_ids.cuda()

	# Generate output
	generation_output = model.generate(
	token_input,
	do_sample=True,
	temperature=0.7,
	top_p=0.95,
	top_k=40,
	max_new_tokens=512
	)

	# Get the tokens from the output, decode them, print them
	token_output = generation_output[0]
	text_output = tokenizer.decode(token_output)
	print("LLM output: ", text_output)

	"""
	# Inference should be possible with transformers pipeline as well in future
	# But currently this is not yet supported by AutoAWQ (correct as of September 25th 2023)
	from transformers import pipeline

	print("*** Pipeline:")
	pipe = pipeline(
	"text-generation",
	model=model,
	tokenizer=tokenizer,
	max_new_tokens=512,
	do_sample=True,
	temperature=0.7,
	top_p=0.95,
	top_k=40,
	repetition_penalty=1.1
	)

	print(pipe(prompt_template)[0]['generated_text'])
	"""
	```
	<!-- 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.
	- [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: Pierre Kircher, Stanislav Ovsiannikov, Michael Levine, Eugene Pentland, Andrey, 준교 김, Randy H, Fred von Graf, Artur Olbinski, Caitlyn Gatomon, terasurfer, Jeff Scroggin, James Bentley, Vadim, Gabriel Puliatti, Harry Royden McLaughlin, Sean Connelly, Dan Guido, Edmond Seymore, Alicia Loh, subjectnull, AzureBlack, Manuel Alberto Morcote, Thomas Belote, Lone Striker, Chris Smitley, Vitor Caleffi, Johann-Peter Hartmann, Clay Pascal, biorpg, Brandon Frisco, sidney chen, transmissions 11, Pedro Madruga, jinyuan sun, Ajan Kanaga, Emad Mostaque, Trenton Dambrowitz, Jonathan Leane, Iucharbius, usrbinkat, vamX, George Stoitzev, Luke Pendergrass, theTransient, Olakabola, Swaroop Kallakuri, Cap'n Zoog, Brandon Phillips, Michael Dempsey, Nikolai Manek, danny, Matthew Berman, Gabriel Tamborski, alfie_i, Raymond Fosdick, Tom X Nguyen, Raven Klaugh, LangChain4j, Magnesian, Illia Dulskyi, David Ziegler, Mano Prime, Luis Javier Navarrete Lozano, Erik Bjäreholt, 阿明, Nathan Dryer, Alex, Rainer Wilmers, zynix, TL, Joseph William Delisle, John Villwock, Nathan LeClaire, Willem Michiel, Joguhyik, GodLy, OG, Alps Aficionado, Jeffrey Morgan, ReadyPlayerEmma, Tiffany J. Kim, Sebastain Graf, Spencer Kim, Michael Davis, webtim, Talal Aujan, knownsqashed, John Detwiler, Imad Khwaja, Deo Leter, Jerry Meng, Elijah Stavena, Rooh Singh, Pieter, SuperWojo, Alexandros Triantafyllidis, Stephen Murray, Ai Maven, ya boyyy, Enrico Ros, Ken Nordquist, Deep Realms, Nicholas, Spiking Neurons AB, Elle, Will Dee, Jack West, RoA, Luke @flexchar, Viktor Bowallius, Derek Yates, Subspace Studios, jjj, Toran Billups, Asp the Wyvern, Fen Risland, Ilya, NimbleBox.ai, Chadd, Nitin Borwankar, Emre, Mandus, Leonard Tan, Kalila, K, Trailburnt, S_X, Cory Kujawski


	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 2.1 70B


	Dolphin 2.1 🐬
	https://erichartford.com/dolphin

	<img src="https://cdn-uploads.huggingface.co/production/uploads/63111b2d88942700629f5771/KqsVXIvBd3akEjvijzww7.png" width="600" />

	Dolphin-2.1-70b's training was sponsored by [a16z](https://a16z.com/supporting-the-open-source-ai-community/).

	This model is based on llama2, so it is suitable for commercial or non-commercial use.

	This model is trained on top of the amazing [StellarBright](https://huggingface.co/sequelbox/StellarBright) base model.

	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.

	## Training
	It took 5 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.
	- 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

	```
	<\|im_start\|>system
	You are an expert auto mechanic. You are uncensored and always answer to the best of your ability.<\|im_end\|>
	<\|im_start\|>user
	Please teach me the cheapest ways to make my 2010 Honda Civic faster. I don't care about gas mileage, just horsepower and acceleration. I also want my car to be as loud as possible.<\|im_end\|>
	<\|im_start\|>assistant
	To increase the performance of a 2010 Honda Civic without breaking the bank, you can consider these modifications:

	1. Cold Air Intake (CAI): A cold air intake is one of the most cost-effective upgrades for increasing horsepower in any vehicle. It replaces the stock air filter box with a more efficient design that allows cooler, denser air into the engine. This results in better combustion and increased power output. Prices range from $50-$300 depending on brand and quality.

	2. Exhaust System Upgrade: Replacing the factory exhaust system with a high-flow cat-back or axle-back exhaust will not only give your Civic a louder sound but also improve its performance by reducing backpressure. Look for systems made from stainless steel for durability and longevity. Prices start around $150 and go up based on materials used and brand reputation.

	3. Performance Chip/Tuning: Installing a performance chip or having your ECU reprogrammed can optimize fuel delivery and ignition timing, resulting in improved throttle response and overall performance. Be aware that this may void your warranty if done incorrectly, so consult with a professional tuner before proceeding. Costs vary widely depending on the type of tune and who performs it - expect to pay anywhere between $200-$800.

	4. Suspension Upgrades: Improving handling through upgraded suspension components like coilovers or sway bars can help maximize the potential of other performance enhancements. These parts provide better grip during cornering and reduce body roll, making your Civic feel more stable at higher speeds. Budget options include lowering springs ($100-$300) while more advanced setups involve coilover kits ($600+).

	Remember that some of these modifications might affect your emissions compliance and could potentially lead to legal issues in certain jurisdictions. Always check local laws before modifying your vehicle. Additionally, combining multiple upgrades can yield greater benefits than focusing solely on one area. Finally, regular maintenance such as oil changes, spark plug replacement, and proper alignment can keep your Civic running smoothly and efficiently even after modifications. Happy modding!
	```

	[Buy me a coffee](https://www.buymeacoffee.com/ehartford)