base_model: migtissera/Synthia-MoE-v3-Mixtral-8x7B
inference: false
license: apache-2.0
model_creator: Migel Tissera
model_name: Synthia MoE v3 Mixtral 8x7B
model_type: mixtral
prompt_template: >
SYSTEM: Elaborate on the topic using a Tree of Thoughts and backtrack when
necessary to construct a clear, cohesive Chain of Thought reasoning. Always
answer without hesitation.
USER: {prompt}
ASSISTANT:
quantized_by: TheBloke
TheBloke's LLM work is generously supported by a grant from andreessen horowitz (a16z)
Synthia MoE v3 Mixtral 8x7B - GGUF
- Model creator: Migel Tissera
- Original model: Synthia MoE v3 Mixtral 8x7B
Description
This repo contains GGUF format model files for Migel Tissera's Synthia MoE v3 Mixtral 8x7B.
EXPERIMENTAL - REQUIRES LLAMA.CPP PR
These are experimental GGUF files, created using a llama.cpp PR found here: https://github.com/ggerganov/llama.cpp/pull/4406.
THEY WILL NOT WORK WITH LLAMA.CPP FROM main, OR ANY DOWNSTREAM LLAMA.CPP CLIENT - such as LM Studio, llama-cpp-python, text-generation-webui, etc.
To test these GGUFs, please build llama.cpp from the above PR.
I have tested CUDA acceleration and it works great. Metal works too, but has a couple of bugs at the moment.
Repositories available
- GPTQ models for GPU inference, with multiple quantisation parameter options.
- 2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference
- Migel Tissera's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions
Prompt template: Synthia-CoT
SYSTEM: Elaborate on the topic using a Tree of Thoughts and backtrack when necessary to construct a clear, cohesive Chain of Thought reasoning. Always answer without hesitation.
USER: {prompt}
ASSISTANT:
Explanation of quantisation methods
Click to see details
The new methods available are:
- GGML_TYPE_Q2_K - "type-1" 2-bit quantization in super-blocks containing 16 blocks, each block having 16 weight. Block scales and mins are quantized with 4 bits. This ends up effectively using 2.5625 bits per weight (bpw)
- GGML_TYPE_Q3_K - "type-0" 3-bit quantization in super-blocks containing 16 blocks, each block having 16 weights. Scales are quantized with 6 bits. This end up using 3.4375 bpw.
- GGML_TYPE_Q4_K - "type-1" 4-bit quantization in super-blocks containing 8 blocks, each block having 32 weights. Scales and mins are quantized with 6 bits. This ends up using 4.5 bpw.
- GGML_TYPE_Q5_K - "type-1" 5-bit quantization. Same super-block structure as GGML_TYPE_Q4_K resulting in 5.5 bpw
- GGML_TYPE_Q6_K - "type-0" 6-bit quantization. Super-blocks with 16 blocks, each block having 16 weights. Scales are quantized with 8 bits. This ends up using 6.5625 bpw
Refer to the Provided Files table below to see what files use which methods, and how.
Provided files
| Name | Quant method | Bits | Size | Max RAM required | Use case |
|---|---|---|---|---|---|
| synthia-moe-v3-mixtral-8x7b.Q2_K.gguf | Q2_K | 2 | 15.64 GB | 18.14 GB | smallest, significant quality loss - not recommended for most purposes |
| synthia-moe-v3-mixtral-8x7b.Q3_K_M.gguf | Q3_K_M | 3 | 20.36 GB | 22.86 GB | very small, high quality loss |
| synthia-moe-v3-mixtral-8x7b.Q4_0.gguf | Q4_0 | 4 | 26.44 GB | 28.94 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| synthia-moe-v3-mixtral-8x7b.Q4_K_M.gguf | Q4_K_M | 4 | 26.44 GB | 28.94 GB | medium, balanced quality - recommended |
| synthia-moe-v3-mixtral-8x7b.Q5_0.gguf | Q5_0 | 5 | 32.23 GB | 34.73 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| synthia-moe-v3-mixtral-8x7b.Q5_K_M.gguf | Q5_K_M | 5 | 32.23 GB | 34.73 GB | large, very low quality loss - recommended |
| synthia-moe-v3-mixtral-8x7b.Q6_K.gguf | Q6_K | 6 | 38.38 GB | 40.88 GB | very large, extremely low quality loss |
| synthia-moe-v3-mixtral-8x7b.Q8_0.gguf | Q8_0 | 8 | 49.62 GB | 52.12 GB | very large, extremely low quality loss - not recommended |
Note: the above RAM figures assume no GPU offloading. If layers are offloaded to the GPU, this will reduce RAM usage and use VRAM instead.
How to download GGUF files
Note for manual downloaders: You almost never want to clone the entire repo! Multiple different quantisation formats are provided, and most users only want to pick and download a single file.
On the command line, including multiple files at once
I recommend using the huggingface-hub Python library:
pip3 install huggingface-hub
Then you can download any individual model file to the current directory, at high speed, with a command like this:
huggingface-cli download TheBloke/Synthia-MoE-v3-Mixtral-8x7B-GGUF synthia-moe-v3-mixtral-8x7b.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
More advanced huggingface-cli download usage (click to read)
You can also download multiple files at once with a pattern:
huggingface-cli download TheBloke/Synthia-MoE-v3-Mixtral-8x7B-GGUF --local-dir . --local-dir-use-symlinks False --include='*Q4_K*gguf'
For more documentation on downloading with huggingface-cli, please see: HF -> Hub Python Library -> Download files -> Download from the CLI.
To accelerate downloads on fast connections (1Gbit/s or higher), install hf_transfer:
pip3 install hf_transfer
And set environment variable HF_HUB_ENABLE_HF_TRANSFER to 1:
HF_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download TheBloke/Synthia-MoE-v3-Mixtral-8x7B-GGUF synthia-moe-v3-mixtral-8x7b.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
Windows Command Line users: You can set the environment variable by running set HF_HUB_ENABLE_HF_TRANSFER=1 before the download command.
Example llama.cpp command
Make sure you are using llama.cpp from commit d0cee0d or later.
./main -ngl 35 -m synthia-moe-v3-mixtral-8x7b.Q4_K_M.gguf --color -c 32768 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "SYSTEM: Elaborate on the topic using a Tree of Thoughts and backtrack when necessary to construct a clear, cohesive Chain of Thought reasoning. Always answer without hesitation.\nUSER: {prompt}\nASSISTANT:"
Change -ngl 32 to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.
Change -c 32768 to the desired sequence length. For extended sequence models - eg 8K, 16K, 32K - the necessary RoPE scaling parameters are read from the GGUF file and set by llama.cpp automatically. Note that longer sequence lengths require much more resources, so you may need to reduce this value.
If you want to have a chat-style conversation, replace the -p <PROMPT> argument with -i -ins
For other parameters and how to use them, please refer to the llama.cpp documentation
How to run in text-generation-webui
Not yet supported
How to run from Python code
Not yet supported
Discord
For further support, and discussions on these models and AI in general, join us at:
Thanks, and how to contribute
Thanks to the chirper.ai team!
Thanks to Clay from gpus.llm-utils.org!
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.
Original model card: Migel Tissera's Synthia MoE v3 Mixtral 8x7B
This is Synthia trained on the official Mistral MoE version (Mixtral-8x7B).
import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
model_path = "/home/Synthia-MoE-v3-Mixtral8x7B"
output_file_path = "/home/conversations.jsonl"
model = AutoModelForCausalLM.from_pretrained(
model_path,
torch_dtype=torch.float16,
device_map="auto",
load_in_4bit=False,
trust_remote_code=True,
)
tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)
def generate_text(instruction):
tokens = tokenizer.encode(instruction)
tokens = torch.LongTensor(tokens).unsqueeze(0)
tokens = tokens.to("cuda")
instance = {
"input_ids": tokens,
"top_p": 1.0,
"temperature": 0.75,
"generate_len": 1024,
"top_k": 50,
}
length = len(tokens[0])
with torch.no_grad():
rest = model.generate(
input_ids=tokens,
max_length=length + instance["generate_len"],
use_cache=True,
do_sample=True,
top_p=instance["top_p"],
temperature=instance["temperature"],
top_k=instance["top_k"],
num_return_sequences=1,
)
output = rest[0][length:]
string = tokenizer.decode(output, skip_special_tokens=True)
answer = string.split("USER:")[0].strip()
return f"{answer}"
conversation = "SYSTEM: Answer the question thoughtfully and intelligently. Always answer without hesitation."
while True:
user_input = input("You: ")
llm_prompt = f"{conversation} \nUSER: {user_input} \nASSISTANT: "
answer = generate_text(llm_prompt)
print(answer)
conversation = f"{llm_prompt}{answer}"
json_data = {"prompt": user_input, "answer": answer}
with open(output_file_path, "a") as output_file:
output_file.write(json.dumps(json_data) + "\n")