Hugging Face's logo

TheBloke
/
LosslessMegaCoder-Llama2-13B-Mini-GGML

Transformers
llama
Model card Files Community
3
LosslessMegaCoder-Llama2-13B-Mini-GGML / README.md
TheBloke's picture
TheBloke
Update README.md
6b3331f
preview code
|
raw
history blame
14.5 kB
metadata
datesets:
  - rombodawg/LosslessMegaCodeTrainingV2_1m_Evol_Uncensored
inference: false
license: llama2
model_creator: Rombo Dawg
model_link: https://huggingface.co/rombodawg/LosslessMegaCoder-llama2-13b-mini
model_name: LosslessMegaCoder Llama2 13B Mini
model_type: llama
quantized_by: TheBloke
TheBlokeAI

LosslessMegaCoder Llama2 13B Mini - GGML

Description

This repo contains GGML format model files for Rombo Dawg's LosslessMegaCoder Llama2 13B Mini.

GGML files are for CPU + GPU inference using llama.cpp and libraries and UIs which support this format, such as:

  • text-generation-webui, the most popular web UI. Supports NVidia CUDA GPU acceleration.
  • KoboldCpp, a powerful GGML web UI with GPU acceleration on all platforms (CUDA and OpenCL). Especially good for story telling.
  • LM Studio, a fully featured local GUI with GPU acceleration on both Windows (NVidia and AMD), and macOS.
  • LoLLMS Web UI, a great web UI with CUDA GPU acceleration via the c_transformers backend.
  • ctransformers, a Python library with GPU accel, LangChain support, and OpenAI-compatible AI server.
  • llama-cpp-python, a Python library with GPU accel, LangChain support, and OpenAI-compatible API server.

Repositories available

Prompt template: ChatML 

<|im_start|>system
{system_message}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant

Compatibility

These quantised GGML files are compatible with llama.cpp as of June 6th, commit 2d43387.

They should also be compatible with all UIs, libraries and utilities which use GGML.

Explanation of the new k-quant 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
  • GGML_TYPE_Q8_K - "type-0" 8-bit quantization. Only used for quantizing intermediate results. The difference to the existing Q8_0 is that the block size is 256. All 2-6 bit dot products are implemented for this quantization type.

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
losslessmegacoder-llama2-13b-min.ggmlv3.q2_K.bin q2_K 2 5.74 GB 8.24 GB New k-quant method. Uses GGML_TYPE_Q4_K for the attention.vw and feed_forward.w2 tensors, GGML_TYPE_Q2_K for the other tensors.
losslessmegacoder-llama2-13b-min.ggmlv3.q3_K_L.bin q3_K_L 3 7.14 GB 9.64 GB New k-quant method. Uses GGML_TYPE_Q5_K for the attention.wv, attention.wo, and feed_forward.w2 tensors, else GGML_TYPE_Q3_K
losslessmegacoder-llama2-13b-min.ggmlv3.q3_K_M.bin q3_K_M 3 6.53 GB 9.03 GB New k-quant method. Uses GGML_TYPE_Q4_K for the attention.wv, attention.wo, and feed_forward.w2 tensors, else GGML_TYPE_Q3_K
losslessmegacoder-llama2-13b-min.ggmlv3.q3_K_S.bin q3_K_S 3 5.87 GB 8.37 GB New k-quant method. Uses GGML_TYPE_Q3_K for all tensors
losslessmegacoder-llama2-13b-min.ggmlv3.q4_0.bin q4_0 4 7.32 GB 9.82 GB Original quant method, 4-bit.
losslessmegacoder-llama2-13b-min.ggmlv3.q4_1.bin q4_1 4 8.14 GB 10.64 GB Original quant method, 4-bit. Higher accuracy than q4_0 but not as high as q5_0. However has quicker inference than q5 models.
losslessmegacoder-llama2-13b-min.ggmlv3.q4_K_M.bin q4_K_M 4 8.06 GB 10.56 GB New k-quant method. Uses GGML_TYPE_Q6_K for half of the attention.wv and feed_forward.w2 tensors, else GGML_TYPE_Q4_K
losslessmegacoder-llama2-13b-min.ggmlv3.q4_K_S.bin q4_K_S 4 7.56 GB 10.06 GB New k-quant method. Uses GGML_TYPE_Q4_K for all tensors
losslessmegacoder-llama2-13b-min.ggmlv3.q5_0.bin q5_0 5 8.95 GB 11.45 GB Original quant method, 5-bit. Higher accuracy, higher resource usage and slower inference.
losslessmegacoder-llama2-13b-min.ggmlv3.q5_1.bin q5_1 5 9.76 GB 12.26 GB Original quant method, 5-bit. Even higher accuracy, resource usage and slower inference.
losslessmegacoder-llama2-13b-min.ggmlv3.q5_K_M.bin q5_K_M 5 9.40 GB 11.90 GB New k-quant method. Uses GGML_TYPE_Q6_K for half of the attention.wv and feed_forward.w2 tensors, else GGML_TYPE_Q5_K
losslessmegacoder-llama2-13b-min.ggmlv3.q5_K_S.bin q5_K_S 5 9.14 GB 11.64 GB New k-quant method. Uses GGML_TYPE_Q5_K for all tensors
losslessmegacoder-llama2-13b-min.ggmlv3.q6_K.bin q6_K 6 10.83 GB 13.33 GB New k-quant method. Uses GGML_TYPE_Q8_K for all tensors - 6-bit quantization
losslessmegacoder-llama2-13b-min.ggmlv3.q8_0.bin q8_0 8 13.83 GB 16.33 GB Original quant method, 8-bit. Almost indistinguishable from float16. High resource use and slow. Not recommended for most users.

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 run in llama.cpp

I use the following command line; adjust for your tastes and needs:

./main -t 10 -ngl 32 -m losslessmegacoder-llama2-13b-min.ggmlv3.q4_K_M.bin --color -c 2048 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "### Instruction: Write a story about llamas\n### Response:"

Change -t 10 to the number of physical CPU cores you have. For example if your system has 8 cores/16 threads, use -t 8.

Change -ngl 32 to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.

Change -c 2048 to the desired sequence length for this model. For example, -c 4096 for a Llama 2 model. For models that use RoPE, add --rope-freq-base 10000 --rope-freq-scale 0.5 for doubled context, or --rope-freq-base 10000 --rope-freq-scale 0.25 for 4x context.

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

Further instructions here: text-generation-webui/docs/llama.cpp.md.

Discord

For further support, and discussions on these models and AI in general, join us at:

TheBloke AI's Discord server

Thanks, and how to contribute.

Thanks to the chirper.ai team!

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.

Special thanks to: Luke from CarbonQuill, Aemon Algiz.

Patreon special mentions: Ajan Kanaga, David Ziegler, Raymond Fosdick, SuperWojo, Sam, webtim, Steven Wood, knownsqashed, Tony Hughes, Junyu Yang, J, Olakabola, Dan Guido, Stephen Murray, John Villwock, vamX, William Sang, Sean Connelly, LangChain4j, Olusegun Samson, Fen Risland, Derek Yates, Karl Bernard, transmissions 11, Trenton Dambrowitz, Pieter, Preetika Verma, Swaroop Kallakuri, Andrey, Slarti, Jonathan Leane, Michael Levine, Kalila, Joseph William Delisle, Rishabh Srivastava, Deo Leter, Luke Pendergrass, Spencer Kim, Geoffrey Montalvo, Thomas Belote, Jeffrey Morgan, Mandus, ya boyyy, Matthew Berman, Magnesian, Ai Maven, senxiiz, Alps Aficionado, Luke @flexchar, Raven Klaugh, Imad Khwaja, Gabriel Puliatti, Johann-Peter Hartmann, usrbinkat, Spiking Neurons AB, Artur Olbinski, chris gileta, danny, Willem Michiel, WelcomeToTheClub, Deep Realms, alfie_i, Dave, Leonard Tan, NimbleBox.ai, Randy H, Daniel P. Andersen, Pyrater, Will Dee, Elle, Space Cruiser, Gabriel Tamborski, Asp the Wyvern, Illia Dulskyi, Nikolai Manek, Sid, Brandon Frisco, Nathan LeClaire, Edmond Seymore, Enrico Ros, Pedro Madruga, Eugene Pentland, John Detwiler, Mano Prime, Stanislav Ovsiannikov, Alex, Vitor Caleffi, K, biorpg, Michael Davis, Lone Striker, Pierre Kircher, theTransient, Fred von Graf, Sebastain Graf, Vadim, Iucharbius, Clay Pascal, Chadd, Mesiah Bishop, terasurfer, Rainer Wilmers, Alexandros Triantafyllidis, Stefan Sabev, Talal Aujan, Cory Kujawski, Viktor Bowallius, subjectnull, ReadyPlayerEmma, zynix

Thank you to all my generous patrons and donaters!

Original model card: Rombo Dawg's LosslessMegaCoder Llama2 13B Mini

This is one of the first models trained on the LosslessMegaCodeTrainingV2_1m_Evol_Uncensored dataset. The version of the dataset used for this model was poorly filtered on some loose parameters that arent anything to write home about but plans for much more refined filtering are in the works

  • This model was made as a colaboration between me and andreaskoepf who is an affiliate of Open Assistant.

Prompt template:

  • chatml format is used: "<|im_start|>system\n{system message}<|im_end|>\n<|im_start|>user\n{user prompt}<|im_end|>\n<|im_start|>assistant\n{Assistant answer}<|im_end|>\n"

multi-line:

<|im_start|>system
{system message}<|im_end|>
<|im_start|>user
{user prompt}<|im_end|>
<|im_start|>assistant
{Assistant answer}<|im_end|>

Training data:

The link for the full dataset is bellow:

Link for the filtered dataset used to make this model are bellow:

The original posting for this model was uploaded at the link bellow.