Upload README.md

fef1f9d 12 months ago

20.4 kB

	---
	base_model: FPHam/Writing_Partner_Mistral_7B
	inference: false
	language:
	- en
	license: apache-2.0
	model_creator: FPHam
	model_name: Writing Partner Mistral 7B
	model_type: mistral
	prompt_template: '<\|im_start\|>system

	{system_message}<\|im_end\|>

	<\|im_start\|>user

	{prompt}<\|im_end\|>

	<\|im_start\|>assistant

	'
	quantized_by: TheBloke
	tags:
	- mistral
	- instruct
	- finetune
	- chatml
	- gpt4
	---
	<!-- 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 -->

	# Writing Partner Mistral 7B - AWQ
	- Model creator: [FPHam](https://huggingface.co/FPHam)
	- Original model: [Writing Partner Mistral 7B](https://huggingface.co/FPHam/Writing_Partner_Mistral_7B)

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

	This repo contains AWQ model files for [FPHam's Writing Partner Mistral 7B](https://huggingface.co/FPHam/Writing_Partner_Mistral_7B).

	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/Writing_Partner_Mistral_7B-AWQ)
	* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/Writing_Partner_Mistral_7B-GPTQ)
	* [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/Writing_Partner_Mistral_7B-GGUF)
	* [FPHam's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/FPHam/Writing_Partner_Mistral_7B)
	<!-- 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/Writing_Partner_Mistral_7B-AWQ/tree/main) \| 4 \| 128 \| [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-raw-v1) \| 4096 \| 4.15 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/Writing_Partner_Mistral_7B-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: `Writing_Partner_Mistral_7B-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/Writing_Partner_Mistral_7B-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/Writing_Partner_Mistral_7B-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/Writing_Partner_Mistral_7B-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/Writing_Partner_Mistral_7B-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: FPHam's Writing Partner Mistral 7B


	<!-- header start -->
	<div style="display: flex; flex-direction: column; align-items: center;">
	</div>
	<div style="width: 100%;">
	<img src="https://huggingface.co/FPHam/Writing_Partner_Mistral_7B/resolve/main/writer5.jpg" alt="Writing Partner" style="width: 70%; min-width: 200px; display: block; margin: auto;">
	</div>
	<div style="display: flex; flex-direction: column; align-items: center;">
	<p><a href="https://ko-fi.com/Q5Q5MOB4M">Support me at Ko-fi</a></p>
	</div>
	<!-- header end -->


	Hi there! I'm your writing assistant.

	Think of me as your partner in crime---or rather, your partner in writing. When you hit a wall (and trust me, you will), I'll be there to knock it down for you.

	If you find yourself stumped, I can help you think outside the box, whether you need to figure out what happens next, develop interesting sidekicks, or create a believable love interest. And if you get stuck on names for people or places, well, that's my specialty.

	Just give me a shout if you have questions, need advice, or want to bounce an idea off someone. Together, we'll turn your novel into a best seller!

	# Intended Use

	The purpose of this model isn't to write content for you (although it can), but rather to engage in a conversation about your writing process.

	# Model uses ChatML

	```
	<\|im_start\|>system
	<\|im_end\|>
	<\|im_start\|>user
	How to plot my story?<\|im_end\|>
	<\|im_start\|>assistant
	```

	Example 1: (I had ChatGPT generate a paragraph for a sci-fi story.)

	Here is an opening of my story:

	In the distant reaches of the cosmos, where starlight weaves a tapestry of unknown wonders, Captain Alara Voss navigated her spacecraft, the Celestial Serenity, through the interstellar currents. The ship hummed with the pulsating energy of the quantum drive, propelling them toward the uncharted nebula known as the Veil of Eternity. Alara's gaze was fixed on the swirling cosmic clouds ahead, her mind ablaze with the anticipation of discovery. As the Serenity pierced the ethereal veil, the fabric of reality seemed to dance with a mysterious resonance. Little did the intrepid crew know that beyond the shimmering curtain lay a realm where time itself wove a narrative that defied mortal understanding, setting the stage for an odyssey that would reshape the boundaries of human perception.

	>I like this opening! It sets up some interesting questions and intrigue right off the bat. But I do think you might want to reconsider your point of view in the first paragraph. Right now it sounds more like a summary than an actual scene because there isn't any dialogue or action. Consider starting with something more immediate, perhaps from Alara's perspective. You could even begin with her looking out at the stars, thinking about what she sees. This will give us a chance to get to know her better before you launch into the big picture stuff. Here's an example:
	>
	>Alara Voss leaned against the cold metal railing of the observation deck, staring out into the infinite expanse of blackness that surrounded her ship. Stars dotted the night sky like scattered diamonds, each one a potential destination, each one a mystery waiting to be solved. She took a deep breath and let it out slowly, savoring the feeling of freedom that washed over her. It had been months since they'd left Earth, and already their journey had taken them light-years away from everything they knew. Her thoughts were interrupted by the low hum of the quantum drive kicking in, signaling that they were ready to make another jump. She watched as the stars began to blur together, forming a shimmering pathway that led the way to their next adventure.
	>
	>"Captain," came the voice of her second-in-command over the intercom. "We're entering the Veil of Eternity."
	>
	>"Thank you, Ensign," Alara replied, not taking her eyes off the swirling vortex ahead. "Let's see what lies beyond."


	Example 2:

	How to write proper dialogue?

	>Dialogue is a very important part of writing fiction. It's the way characters speak, and it helps define who they are. It also moves the story forward and adds tension, humor, or emotion. Dialogue must be realistic and natural-sounding, but it doesn't have to be boring. You want your readers to pay attention to what the characters are saying, so make sure that each line of dialogue counts.
	>
	>Here are some tips on how to write good dialogue:
	>
	>- Keep it short. Long speeches get tedious quickly. If one character talks for more than two sentences, break up his speech with an action or interjection from another character.
	>
	>- Use contractions (I'm, he'll). They sound more like real conversation than formal language does.
	>
	>- Vary sentence structure. This makes dialogue easier to read and understand.
	>
	>- Don't use slang unless it fits the setting or character perfectly. Slang dates easily and may not mean anything to future generations.
	>
	>- Avoid using too many adverbs in dialogue tags. Instead of "he said loudly," try something like "he bellowed." Or "she whispered."
	>
	>- Be careful not to give away too much information in dialogue tags. For example, if you say "Sarah laughed nervously," you're telling the reader she was nervous rather than showing her anxiety through her words or actions.
	>
	>- Make sure your characters don't all talk alike. Each person should have a unique voice, based on his background, education, age, gender, etc.
	>
	>- Don't forget about body language. The way someone holds himself, sits, stands, fidgets, or looks at others can add depth to a scene.
	>
	>- Use dialogue to reveal character traits and motivations. Listen carefully to people around you, and then translate those conversations onto paper.
	>
	>- Finally, remember that dialogue needs to serve a purpose in your story. Whether it advances the plot, sets the mood, or creates conflict, every word spoken by your characters should move the narrative along.