Hugging Face's logo

TheBloke
/
Llama2-70B-OASST-SFT-v10-GGML

Text Generation
Transformers
4 datasets
English
llama
sft
text-generation-inference
Model card Files Community
Llama2-70B-OASST-SFT-v10-GGML / README.md
TheBloke's picture
TheBloke
Initial GGML model commit
6ee214f
preview code
|
raw
history blame
No virus
26.2 kB
metadata
datasets:
  - rombodawg/LosslessMegaCodeTrainingV2_1m_Evol_Uncensored
  - OpenAssistant/oasst1
  - ehartford/dolphin
  - argilla/databricks-dolly-15k-curated-multilingual
inference: false
language:
  - en
library_name: transformers
license: llama2
model_creator: OpenAssistant
model_link: https://huggingface.co/OpenAssistant/llama2-70b-oasst-sft-v10
model_name: Llama2 70B SFT v10
model_type: llama
pipeline_tag: text-generation
quantized_by: TheBloke
tags:
  - sft
TheBlokeAI

TheBloke's LLM work is generously supported by a grant from andreessen horowitz (a16z)

Llama2 70B SFT v10 - GGML

Description

This repo contains GGML format model files for OpenAssistant's Llama2 70B SFT v10.

Important note regarding GGML files.

The GGML format has now been superseded by GGUF. As of August 21st 2023, llama.cpp no longer supports GGML models. Third party clients and libraries are expected to still support it for a time, but many may also drop support.

About GGML

GPU acceleration is now available for Llama 2 70B GGML files, with both CUDA (NVidia) and Metal (macOS). The following clients/libraries are known to work with these files, including with GPU acceleration:

  • llama.cpp, commit e76d630 and later.
  • text-generation-webui, the most widely used web UI.
  • KoboldCpp, version 1.37 and later. A powerful GGML web UI, especially good for story telling.
  • LM Studio, a fully featured local GUI with GPU acceleration for both Windows and macOS. Use 0.1.11 or later for macOS GPU acceleration with 70B models.
  • llama-cpp-python, version 0.1.77 and later. A Python library with LangChain support, and OpenAI-compatible API server.
  • ctransformers, version 0.2.15 and later. A Python library with 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

Works with llama.cpp commit e76d630 until August 21st, 2023

Will not work with llama.cpp after commit dadbed99e65252d79f81101a392d0d6497b86caa.

For compatibility with latest llama.cpp, please use GGUF files instead.

Or one of the other tools and libraries listed above.

To use in llama.cpp, you must add -gqa 8 argument.

For other UIs and libraries, please check the docs.

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
llama2-70b-oasst-sft-v10.ggmlv3.Q2_K.bin Q2_K 2 28.96 GB 31.46 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.
llama2-70b-oasst-sft-v10.ggmlv3.Q3_K_S.bin Q3_K_S 3 30.09 GB 32.59 GB New k-quant method. Uses GGML_TYPE_Q3_K for all tensors
llama2-70b-oasst-sft-v10.ggmlv3.Q3_K_M.bin Q3_K_M 3 33.39 GB 35.89 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
llama2-70b-oasst-sft-v10.ggmlv3.Q3_K_L.bin Q3_K_L 3 36.49 GB 38.99 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
llama2-70b-oasst-sft-v10.ggmlv3.Q4_0.bin Q4_0 4 38.80 GB 41.30 GB Original quant method, 4-bit.
llama2-70b-oasst-sft-v10.ggmlv3.Q4_K_S.bin Q4_K_S 4 39.18 GB 41.68 GB New k-quant method. Uses GGML_TYPE_Q4_K for all tensors
llama2-70b-oasst-sft-v10.ggmlv3.Q4_K_M.bin Q4_K_M 4 41.69 GB 44.19 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
llama2-70b-oasst-sft-v10.ggmlv3.Q4_1.bin Q4_1 4 43.12 GB 45.62 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.
llama2-70b-oasst-sft-v10.ggmlv3.Q5_0.bin Q5_0 5 47.43 GB 49.93 GB Original quant method, 5-bit. Higher accuracy, higher resource usage and slower inference.
llama2-70b-oasst-sft-v10.ggmlv3.Q5_K_S.bin Q5_K_S 5 47.74 GB 50.24 GB New k-quant method. Uses GGML_TYPE_Q5_K for all tensors
llama2-70b-oasst-sft-v10.ggmlv3.Q5_K_M.bin Q5_K_M 5 49.03 GB 51.53 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

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

Make sure you are using llama.cpp from commit dadbed99e65252d79f81101a392d0d6497b86caa or earlier.

For compatibility with latest llama.cpp, please use GGUF files instead.

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

./main -t 10 -ngl 40 -gqa 8 -m llama2-70b-oasst-sft-v10.ggmlv3.q4_K_M.bin --color -c 4096 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "<|im_start|>system\nYou are a story writing assistant.<|im_end|>\n<|im_start|>user\nWrite a story about llamas<|im_end|>\n<|im_start|>assistant"

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. If you are fully offloading the model to GPU, use -t 1

Change -ngl 40 to the number of GPU layers you have VRAM for. Use -ngl 100 to offload all layers to VRAM - if you have a 48GB card, or 2 x 24GB, or similar. Otherwise you can partially offload as many as you have VRAM for, on one or more GPUs.

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

Remember the -gqa 8 argument, required for Llama 70B models.

Change -c 4096 to the desired sequence length for this 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.

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-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.

Special thanks to: Aemon Algiz.

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

Thank you to all my generous patrons and donaters!

And thank you again to a16z for their generous grant.

Original model card: OpenAssistant's Llama2 70B SFT v10

Open-Assistant Llama2 70B SFT v10

This model is an Open-Assistant fine-tuning of Meta's Llama2 70B LLM. It was fine-tuned in two stages, first on a mix of synthetic instrunctions and coding tasks and then in a "polishing" stage on the best human demonstrations collected at open-assistant.io up to July 23, 2023 (see Configuration Details below).

Model Details

Prompting / Prompt Template

Due to public demand (see survey) we changed the prompt-template for this model from custom prompter/assistant tokens to OpenAI's chatml standard prompt format. We hope that this leads to greater compatibility with chat inference/frontend applications.

Prompt dialogue template:

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

The model input can contain multiple conversation turns between user and assistant, e.g.

<|im_start|>user
{prompt 1}<|im_end|>
<|im_start|>assistant
{reply 1}<|im_end|>
<|im_start|>user
{prompt 2}<|im_end|>
<|im_start|>assistant
(...)

The model was partly trained with orca system messages.
For inference we recommend to use the official Llama2 system message:

<|im_start|>system
You are a helpful, respectful and honest assistant. Always answer as helpfully as possible, while being safe. Your answers should not include any harmful, unethical, racist, sexist, toxic, dangerous, or illegal content. Please ensure that your responses are socially unbiased and positive in nature.

If a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct. If you don't know the answer to a question, please don't share false information.
<|im_end|>

Credits & Special Thanks

We want to especially thank everyone who contributed in the crowed-sourced Open-Assistant dataset creation on https://open-assistant.io/ - without you this project would not have been possible.

Ethical Considerations and Limitations

Testing conducted to date has been in English, and has not covered, nor could it cover all scenarios. For these reasons, as with all LLMs, the potential outputs of llama2-70b-oasst-sft-v10 cannot be predicted in advance, and the model may in some instances produce inaccurate, biased or other objectionable responses to user prompts. Therefore, before deploying any applications of llama2-70b-oasst-sft-v10, developers should perform safety testing and tuning tailored to their specific applications of the model.

Please see Meta's Responsible Use Guide.

Note regarding inference with TGI

During evaluation we noticed that this 70B model produced extremely poor outputs when loaded it was loaded in 16 bit precision sharded in TGI. In contrast the model could be evaluated without problem using vLLM. The model also worked decently well when loaded with TGI on a single GPPU nf4 quantized via TimDettmers/bitsandbytes. Will will get it touch with the TGI authors to find out why sharded 16-bit inference doesn't work as expected.

Configuration Details

The "pretokenizer" utility used to tokenize the datamix is part of the Open-Assistant github repository and can be found here: model/pretokenizer.

Stage 1 Pretokenizer Configuration

Entries of the dataset with assistant replies shorter than 25 tokens were excluded from training.

oasst_pre10_min25:
  datasets:
    - megacode2:
        fraction: 0.5
        val_split: 0.01
        max_val_set: 1000
    - orca-chat:
        val_split: 0.01
        max_val_set: 1000
    - dolly15k_multilingual:
        val_split: 0.05
        max_val_set: 300
    - oa_leet10k:
        val_split: 0.05
        max_val_set: 250
  output_dir: "output/oasst_pre10_min25"
  filename_prefix: "oasst_pre10"
  min_assistant_tokens: 25

Stage 1 dataset statistics:

# Stats for output/oasst_pre10_min25_llama2

## Stats for 'Subset of InstructionDataset (megacode2)' (466364 samples (50.0%))
-----------------
  Accepted: 398223/466364 (85.4%)
  Accepted tokens: 167676873
  Skipped: 68141 (14.6%)
  Min tokens per sample: 36
  Max tokens per sample: 11810
  Avg tokens per sample: 421.063
-----------------

## Stats for 'Subset of OrcaChat (orca-chat)' (325616 samples (100.0%))
-----------------
  Accepted: 325616/325616 (100.0%)
  Accepted tokens: 178307574
  Skipped: 0 (0.0%)
  Min tokens per sample: 105
  Max tokens per sample: 10408
  Avg tokens per sample: 547.601
-----------------

## Stats for 'Subset of Dolly15kMultilingual' (57020 samples (100.0%))
-----------------
  Accepted: 47494/57020 (83.3%)
  Accepted tokens: 13883177
  Skipped: 9526 (16.7%)
  Min tokens per sample: 34
  Max tokens per sample: 9172
  Avg tokens per sample: 292.314
-----------------

## Stats for 'Subset of InstructionDataset (oa_leet10k)' (22236 samples (100.0%))
-----------------
  Accepted: 22236/22236 (100.0%)
  Accepted tokens: 15905296
  Skipped: 0 (0.0%)
  Min tokens per sample: 168
  Max tokens per sample: 10588
  Avg tokens per sample: 715.295
-----------------

## Stats for 'total' (871236 samples (100.0%))
-----------------
  Accepted: 793569/871236 (91.1%)
  Accepted tokens: 375772920
  Skipped: 77667 (8.9%)
  Min tokens per sample: 34
  Max tokens per sample: 11810
  Avg tokens per sample: 473.523
-----------------

Stage 2 Pretokenizer Configuration 

oasst_top1:
  datasets:
    - oasst_export:
        lang: "bg,ca,cs,da,de,en,es,fr,hr,hu,it,nl,pl,pt,ro,ru,sl,sr,sv,uk"
        input_file_path: 2023-07-23_oasst_ready.tar.gz
        top_k: 1
        val_split: 0.05
  output_dir: "output/oasst_top1_2023-07-23"
  filename_prefix: "oasst_top1"

Stage 2 dataset statistics:

# Stats for output/oasst_top1_2023-07-23_llama2

## Stats for 'ListDataset' (11441 samples (100.0%))
-----------------
  Accepted: 11441/11441 (100.0%)
  Accepted tokens: 5315368
  Skipped: 0 (0.0%)
  Min tokens per sample: 20
  Max tokens per sample: 5407
  Avg tokens per sample: 464.58945896337735
-----------------

## Stats for 'total' (11441 samples (100.0%))
-----------------
  Accepted: 11441/11441 (100.0%)
  Accepted tokens: 5315368
  Skipped: 0 (0.0%)
  Min tokens per sample: 20
  Max tokens per sample: 5407
  Avg tokens per sample: 464.58945896337735
-----------------

Megatron Fine-Tuning Arguments for Stage 1 (Instruction Tuning): 

--tensor_model_parallel_size 8
--pipeline_model_parallel_size 4
--load ./checkpoints/llama2-70b-tp8-pp4
--save ./checkpoints/llama2-70b-tp8-pp4-oasst_pre10
--tensorboard_dir ./checkpoints/llama2-70b-tp8-pp4-oasst_pre10/logging
--data_path ./data/oasst_pre10_min25_llama2/oasst_sft10-train
--model_name llama2
--tokenizer_type SentencePieceTokenizer
--bf16
--global_batch_size 64
--micro_batch_size 2
--vocab_file=./llama2/Llama-2-7b/tokenizer.model
--use_rms_norm
--glu_activation swiglu
--no_tie_embed_logits
--vocab_extra_ids_list "\"<|im_start|>,<|im_end|>\""
--layernorm_epsilon 1e-5
--use_flash_attn
--no_bias_gelu_fusion
--seq_length 4096
--max_position_embeddings 4096
--log_interval 1
--save_interval 500
--eval_interval 50
--eval_iters 10
--hidden_dropout 0.0
--position_embedding_type rotary
--no_bias_dropout_fusion
--use_checkpoint_args
--train_iters 12000
--attention_dropout 0.0
--adam_beta1 0.9
--adam_beta2 0.95
--adam_eps 1e-12
--lr_decay_style cosine
--lr_warmup_iters 100
--lr 1e-5
--min_lr 1e-6
--weight_decay 0.000001
--sequence_parallel
--recompute_granularity selective
--log_timers_to_tensorboard
--rope_scaling_factor 1.0
--wandb_logger

Megatron Fine-Tuning Arguments for Stage 2 (OASST Polishing, LIMA Dropout): 

--tensor_model_parallel_size 8
--pipeline_model_parallel_size 4
--load ./checkpoints/llama2-70b-tp8-pp4-oasst_pre10
--save ./checkpoints/llama2-70b-tp8-pp4-oasst_sft10
--tensorboard_dir ./checkpoints/llama2-70b-tp8-pp4-oasst_sft10/logging
--data_path ./data/oasst_top1_2023-07-23_llama2/oasst_top1-train
--model_name llama2
--tokenizer_type SentencePieceTokenizer
--bf16
--global_batch_size 64
--micro_batch_size 2
--vocab_file=./llama2/Llama-2-7b/tokenizer.model
--use_rms_norm
--glu_activation swiglu
--no_tie_embed_logits
--vocab_extra_ids_list "\"<|im_start|>,<|im_end|>\""
--layernorm_epsilon 1e-5
--use_flash_attn
--no_bias_gelu_fusion
--seq_length 4096
--max_position_embeddings 4096
--log_interval 1
--save_interval 346
--eval_interval 50
--eval_iters 10
--hidden_dropout 0.25
--lima_dropout
--position_embedding_type rotary
--no_bias_dropout_fusion
--use_checkpoint_args
--train_iters 519
--attention_dropout 0.0
--adam_beta1 0.9
--adam_beta2 0.95
--adam_eps 1e-12
--lr_decay_style cosine
--lr_warmup_iters 100
--lr 1e-5
--min_lr 1e-6
--weight_decay 0.000001
--sequence_parallel
--recompute_granularity selective
--log_timers_to_tensorboard
--rope_scaling_factor 1.0
--finetune
--wandb_logger