Want to contribute? TheBloke's Patreon page

Llama2 13B Orca v2 8K - GGML

Model creator: OpenAssistant
Original model: Llama2 13B Orca v2 8K

Description

This repo contains GGML format model files for OpenAssistant's Llama2 13B Orca v2 8K.

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: OpenAssistant

<|prompter|>{prompt}<|endoftext|><|assistant|>

Compatibility

Original llama.cpp quant methods: `q4_0, q4_1, q5_0, q5_1, q8_0`

These are guaranteed to be compatible with any UIs, tools and libraries released since late May. They may be phased out soon, as they are largely superseded by the new k-quant methods.

New k-quant methods: `q2_K, q3_K_S, q3_K_M, q3_K_L, q4_K_S, q4_K_M, q5_K_S, q6_K`

These new quantisation methods are compatible with llama.cpp as of June 6th, commit 2d43387.

They are now also compatible with recent releases of text-generation-webui, KoboldCpp, llama-cpp-python, ctransformers, rustformers and most others. For compatibility with other tools and libraries, please check their documentation.

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
openassistant-llama2-13b-orca-v2-8k-3166.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.
openassistant-llama2-13b-orca-v2-8k-3166.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
openassistant-llama2-13b-orca-v2-8k-3166.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
openassistant-llama2-13b-orca-v2-8k-3166.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
openassistant-llama2-13b-orca-v2-8k-3166.ggmlv3.q4_0.bin	q4_0	4	7.32 GB	9.82 GB	Original quant method, 4-bit.
openassistant-llama2-13b-orca-v2-8k-3166.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.
openassistant-llama2-13b-orca-v2-8k-3166.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
openassistant-llama2-13b-orca-v2-8k-3166.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
openassistant-llama2-13b-orca-v2-8k-3166.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.
openassistant-llama2-13b-orca-v2-8k-3166.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.
openassistant-llama2-13b-orca-v2-8k-3166.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
openassistant-llama2-13b-orca-v2-8k-3166.ggmlv3.q5_K_S.bin	q5_K_S	5	9.15 GB	11.65 GB	New k-quant method. Uses GGML_TYPE_Q5_K for all tensors
openassistant-llama2-13b-orca-v2-8k-3166.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
openassistant-llama2-13b-orca-v2-8k-3166.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 openassistant-llama2-13b-orca-v2-8k-3166.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.

If you want to have a chat-style conversation, replace the -p <PROMPT> argument with -i -ins

How to run in `text-generation-webui`

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

Patreon: https://patreon.com/TheBlokeAI
Ko-Fi: https://ko-fi.com/TheBlokeAI

Special thanks to: Luke from CarbonQuill, Aemon Algiz.

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

Thank you to all my generous patrons and donaters!

Original model card: OpenAssistant's Llama2 13B Orca v2 8K

wandb: jlhr5cf2
sampling-report: 2023-07-31_OpenAssistant_llama2-13b-orca-v2-8k-3166_sampling_llama2_prompt.json

Model Configuration

llama2-13b-orca-v2-8k:
  rng_seed: 0xe1291f21
  show_dataset_stats: true
  random_offset_probability: 0.0
  use_custom_sampler: true
  sort_by_length: false
  dtype: fp16
  log_dir: /mnt/data/ikka/data_cache/llama2_13b_orcav2_logs
  output_dir: /mnt/data/ikka/data_cache/llama2_13b_orcav2
  learning_rate: 1e-5
  model_name: conceptofmind/LLongMA-2-13b
  deepspeed_config: configs/zero_config_pretrain.json
  weight_decay: 0.000001
  max_length: 8192
  warmup_steps: 100
  peft_model: false
  use_flash_attention: true
  gradient_checkpointing: true
  gradient_accumulation_steps: 4
  per_device_train_batch_size: 2
  per_device_eval_batch_size: 1
  residual_dropout: 0.0
  eval_steps: 200
  save_steps: 200
  num_train_epochs: 1
  save_total_limit: 4
  superhot: false
  superhot_config:
    type: linear
    scaling_factor: 2
  datasets:
    - orca-chat: # shahules786/orca-chat
        data_files: orca-chat-gpt4-8k.json
        max_val_set: 5000
        val_split: 0.1
    - evol-codealpaca-v1: # theblackcat102/evol-codealpaca-v1
        fill_min_length: 20000
        val_split: 0.1
    - megacode: # rombodawg/MegaCodeTraining112k
        fill_min_length: 24000
        val_split: 0.1
        max_val_set: 1000
    - evol_instruct_code: # nickrosh/Evol-Instruct-Code-80k-v1
        fill_min_length: 24000
        val_split: 0.1
        max_val_set: 1000

TheBloke
/

OpenAssistant-Llama2-13B-Orca-v2-8K-3166-GGML

Llama2 13B Orca v2 8K - GGML

Description

Repositories available

Prompt template: OpenAssistant

Compatibility

Original llama.cpp quant methods: `q4_0, q4_1, q5_0, q5_1, q8_0`

New k-quant methods: `q2_K, q3_K_S, q3_K_M, q3_K_L, q4_K_S, q4_K_M, q5_K_S, q6_K`

Explanation of the new k-quant methods

Provided files

How to run in `llama.cpp`

How to run in `text-generation-webui`

Discord

Thanks, and how to contribute.

Original model card: OpenAssistant's Llama2 13B Orca v2 8K

Model Configuration

Datasets used to train TheBloke/OpenAssistant-Llama2-13B-Orca-v2-8K-3166-GGML

Llama2 13B Orca v2 8K - GGML

Description

Repositories available

Prompt template: OpenAssistant

Compatibility

Original llama.cpp quant methods: q4_0, q4_1, q5_0, q5_1, q8_0

New k-quant methods: q2_K, q3_K_S, q3_K_M, q3_K_L, q4_K_S, q4_K_M, q5_K_S, q6_K

Explanation of the new k-quant methods

Provided files

How to run in llama.cpp

How to run in text-generation-webui

Discord

Thanks, and how to contribute.

Original model card: OpenAssistant's Llama2 13B Orca v2 8K

Model Configuration

Datasets used to train TheBloke/OpenAssistant-Llama2-13B-Orca-v2-8K-3166-GGML

Original llama.cpp quant methods: `q4_0, q4_1, q5_0, q5_1, q8_0`

New k-quant methods: `q2_K, q3_K_S, q3_K_M, q3_K_L, q4_K_S, q4_K_M, q5_K_S, q6_K`

How to run in `llama.cpp`

How to run in `text-generation-webui`