These files were quantised using hardware kindly provided by Massed Compute.
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.
Below is an instruction that describes a task. Write a response that appropriately completes the request.
### Instruction:
{system_message}
{prompt}
### Response:
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.
Please ensure you are using vLLM version 0.2 or later.
When using vLLM as a server, pass the --quantization awq parameter.
For example:
python3 -m vllm.entrypoints.api_server --model TheBloke/bagel-34b-v0.2-AWQ --quantization awq --dtype auto
When using vLLM from Python code, again set quantization=awq.
For example:
python
1from vllm import LLM, SamplingParams
23prompts =[4"Tell me about AI",5"Write a story about llamas",6"What is 291 - 150?",7"How much wood would a woodchuck chuck if a woodchuck could chuck wood?",8]9prompt_template=f'''Below is an instruction that describes a task. Write a response that appropriately completes the request.
1011### Instruction:
12{system_message}13{prompt}1415### Response:
16'''1718prompts =[prompt_template.format(prompt=prompt)for prompt in prompts]1920sampling_params = SamplingParams(temperature=0.8, top_p=0.95)2122llm = LLM(model="TheBloke/bagel-34b-v0.2-AWQ", quantization="awq", dtype="auto")2324outputs = llm.generate(prompts, sampling_params)2526# Print the outputs.27for output in outputs:28 prompt = output.prompt
29 generated_text = output.outputs[0].text
30print(f"Prompt: {prompt!r}, Generated text: {generated_text!r}")
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 Python code for interfacing with TGI (requires huggingface-hub 0.17.0 or later):
pip3 install huggingface-hub
python
1from huggingface_hub import InferenceClient
23endpoint_url ="https://your-endpoint-url-here"45prompt ="Tell me about AI"6prompt_template=f'''Below is an instruction that describes a task. Write a response that appropriately completes the request.
78### Instruction:
9{system_message}10{prompt}1112### Response:
13'''1415client = InferenceClient(endpoint_url)16response = client.text_generation(prompt,17 max_new_tokens=128,18 do_sample=True,19 temperature=0.7,20 top_p=0.95,21 top_k=40,22 repetition_penalty=1.1)2324print(f"Model output: ", response)
Transformers example code (requires Transformers 4.35.0 and later)
python
1from transformers import AutoModelForCausalLM, AutoTokenizer, TextStreamer
23model_name_or_path ="TheBloke/bagel-34b-v0.2-AWQ"45tokenizer = AutoTokenizer.from_pretrained(model_name_or_path)6model = AutoModelForCausalLM.from_pretrained(7 model_name_or_path,8 low_cpu_mem_usage=True,9 device_map="cuda:0"10)1112# Using the text streamer to stream output one token at a time13streamer = TextStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True)1415prompt ="Tell me about AI"16prompt_template=f'''Below is an instruction that describes a task. Write a response that appropriately completes the request.
1718### Instruction:
19{system_message}20{prompt}2122### Response:
23'''2425# Convert prompt to tokens26tokens = tokenizer(27 prompt_template,28 return_tensors='pt'29).input_ids.cuda()3031generation_params ={32"do_sample":True,33"temperature":0.7,34"top_p":0.95,35"top_k":40,36"max_new_tokens":512,37"repetition_penalty":1.138}3940# Generate streamed output, visible one token at a time41generation_output = model.generate(42 tokens,43 streamer=streamer,44**generation_params
45)4647# Generation without a streamer, which will include the prompt in the output48generation_output = model.generate(49 tokens,50**generation_params
51)5253# Get the tokens from the output, decode them, print them54token_output = generation_output[0]55text_output = tokenizer.decode(token_output)56print("model.generate output: ", text_output)5758# Inference is also possible via Transformers' pipeline59from transformers import pipeline
6061pipe = pipeline(62"text-generation",63 model=model,64 tokenizer=tokenizer,65**generation_params
66)6768pipe_output = pipe(prompt_template)[0]['generated_text']69print("pipeline output: ", pipe_output)70
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 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.
Original model card: Jon Durbin's Bagel 34B v0.2
A bagel, with everything (except DPO)
bagel
Overview
An experimental fine-tune of yi-34b-200k using bagel
This is the model after the SFT phase, before DPO has been applied. You'll likely want to use the DPO'd version, rather than this one, but since I had it, I uploaded it.
Data sources
Yes, you will see benchmark names in the list, but this only uses the train splits, and a decontamination by cosine similarity is performed at the end as a sanity check
Only the train splits were used (if a split was provided), and an additional pass of decontamination is performed using approximate nearest neighbor search (via faiss).
Prompt formatting
In sticking with the theme of the bagel, I didn't want to use a single prompt format, so I used 4 - vicuna, llama-2, alpaca, and chat-ml (sorta).
I also didn't want to randomly select a single prompt format for each item (hoping each instruction would generalize more when used in a variety of prompt formats), so each instruction is actually converted into every prompt format.
This means each epoch of our fine-tune is really basically 4 epochs. So, for the fine-tunes, I would recommend only doing 1 epoch (or 0.75 epochs). I am testing with a single epoch using a relatively low learning rate.
Alpaca (sort of)
Below is an instruction that describes a task. Write a response that appropriately completes the request.
### Instruction:
{system prompt, if provided}
{instruction}
### Response:
The main difference here is that because of the dataset formatting and variety of data sources, it would have been much to tedious to add an ### Input: block, so the inputs are just in the instruction section.
Vicuna
{system prompt, if provided, randomly defaulting to "A chat between a user and an unbiased, uncensored assistant."}
USER: {instruction}
ASSISTANT:
ChatML (sort of)
I don't really understand the point of having special tokens for <|im_start|> and <|im_end|>, because in practice they just act as BOS and EOS tokens (but, please correct me if I'm wrong).
So, instead of:
text
1{bos}<|im_start|>{role}
2{text}
3<|im_end|>{eos}
I just changed it to:
text
1{bos}{role}
2{text}
3{eos}
If you really want to use <|im_start|> and <|im_end|>, just update your tokenizer_config.json to use <|im_start|> instead of <s> and <|im_end|> instead of </s> and when tokenizing. And if you still don't like what I've done to this chat-ml-ish format, feel free to cry into your pillow or fork the code and do a new fine-tune.
