---
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
---
# Llama2 70B SFT v10 - GPTQ
- Model creator: [OpenAssistant](https://huggingface.co/OpenAssistant)
- Original model: [Llama2 70B SFT v10](https://huggingface.co/OpenAssistant/llama2-70b-oasst-sft-v10)
## Description
This repo contains GPTQ model files for [OpenAssistant's Llama2 70B SFT v10](https://huggingface.co/OpenAssistant/llama2-70b-oasst-sft-v10).
Multiple GPTQ parameter permutations are provided; see Provided Files below for details of the options provided, their parameters, and the software used to create them.
## Repositories available
* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/Llama2-70B-OASST-SFT-v10-GPTQ)
* [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/Llama2-70B-OASST-SFT-v10-GGUF)
* [2, 3, 4, 5, 6 and 8-bit GGML models for CPU+GPU inference (deprecated)](https://huggingface.co/TheBloke/Llama2-70B-OASST-SFT-v10-GGML)
* [OpenAssistant's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/OpenAssistant/llama2-70b-oasst-sft-v10)
## Prompt template: ChatML
```
<|im_start|>system
{system_message}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant
```
## Provided files and GPTQ parameters
Multiple quantisation parameters are provided, to allow you to choose the best one for your hardware and requirements.
Each separate quant is in a different branch. See below for instructions on fetching from different branches.
All GPTQ files are made with AutoGPTQ.
Explanation of GPTQ parameters
- Bits: The bit size of the quantised model.
- GS: GPTQ group size. Higher numbers use less VRAM, but have lower quantisation accuracy. "None" is the lowest possible value.
- Act Order: True or False. Also known as `desc_act`. True results in better quantisation accuracy. Some GPTQ clients have issues with models that use Act Order plus Group Size.
- Damp %: A GPTQ parameter that affects how samples are processed for quantisation. 0.01 is default, but 0.1 results in slightly better accuracy.
- GPTQ dataset: The dataset used for quantisation. Using a dataset more appropriate to the model's training can improve quantisation accuracy. Note that the GPTQ dataset is not the same as the dataset used to train the model - please refer to the original model repo for details of the training dataset(s).
- Sequence Length: The length of the dataset sequences used for quantisation. Ideally this is the same as the model sequence length. For some very long sequence models (16+K), a lower sequence length may have to be used. Note that a lower sequence length does not limit the sequence length of the quantised model. It only impacts the quantisation accuracy on longer inference sequences.
- ExLlama Compatibility: Whether this file can be loaded with ExLlama, which currently only supports Llama models in 4-bit.
| Branch | Bits | GS | Act Order | Damp % | GPTQ Dataset | Seq Len | Size | ExLlama | Desc |
| ------ | ---- | -- | --------- | ------ | ------------ | ------- | ---- | ------- | ---- |
| [main](https://huggingface.co/TheBloke/Llama2-70B-OASST-SFT-v10-GPTQ/tree/main) | 4 | None | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 35.33 GB | Yes | Most compatible option. Good inference speed in AutoGPTQ and GPTQ-for-LLaMa. Lower inference quality than other options. |
| [gptq-4bit-32g-actorder_True](https://huggingface.co/TheBloke/Llama2-70B-OASST-SFT-v10-GPTQ/tree/gptq-4bit-32g-actorder_True) | 4 | 32 | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 40.66 GB | Yes | 4-bit, with Act Order and group size 32g. Gives highest possible inference quality, with maximum VRAM usage. Poor AutoGPTQ CUDA speed. |
| [gptq-4bit-64g-actorder_True](https://huggingface.co/TheBloke/Llama2-70B-OASST-SFT-v10-GPTQ/tree/gptq-4bit-64g-actorder_True) | 4 | 64 | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 37.99 GB | Yes | 4-bit, with Act Order and group size 64g. Uses less VRAM than 32g, but with slightly lower accuracy. Poor AutoGPTQ CUDA speed. |
| [gptq-4bit-128g-actorder_True](https://huggingface.co/TheBloke/Llama2-70B-OASST-SFT-v10-GPTQ/tree/gptq-4bit-128g-actorder_True) | 4 | 128 | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 36.65 GB | Yes | 4-bit, with Act Order and group size 128g. Uses even less VRAM than 64g, but with slightly lower accuracy. Poor AutoGPTQ CUDA speed. |
| [gptq-3bit--1g-actorder_True](https://huggingface.co/TheBloke/Llama2-70B-OASST-SFT-v10-GPTQ/tree/gptq-3bit--1g-actorder_True) | 3 | None | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 26.78 GB | No | 3-bit, with Act Order and no group size. Lowest possible VRAM requirements. May be lower quality than 3-bit 128g. |
| [gptq-3bit-128g-actorder_True](https://huggingface.co/TheBloke/Llama2-70B-OASST-SFT-v10-GPTQ/tree/gptq-3bit-128g-actorder_True) | 3 | 128 | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 28.03 GB | No | 3-bit, with group size 128g and act-order. Higher quality than 128g-False but poor AutoGPTQ CUDA speed. |
## How to download from branches
- In text-generation-webui, you can add `:branch` to the end of the download name, eg `TheBloke/Llama2-70B-OASST-SFT-v10-GPTQ:gptq-4bit-32g-actorder_True`
- With Git, you can clone a branch with:
```
git clone --single-branch --branch gptq-4bit-32g-actorder_True https://huggingface.co/TheBloke/Llama2-70B-OASST-SFT-v10-GPTQ
```
- In Python Transformers code, the branch is the `revision` parameter; see below.
## How to easily download and use this model in [text-generation-webui](https://github.com/oobabooga/text-generation-webui).
Please make sure you're using the latest version of [text-generation-webui](https://github.com/oobabooga/text-generation-webui).
It is strongly recommended to use the text-generation-webui one-click-installers unless you know how to make a manual install.
1. Click the **Model tab**.
2. Under **Download custom model or LoRA**, enter `TheBloke/Llama2-70B-OASST-SFT-v10-GPTQ`.
- To download from a specific branch, enter for example `TheBloke/Llama2-70B-OASST-SFT-v10-GPTQ:gptq-4bit-32g-actorder_True`
- see Provided Files above for the list of branches for each option.
3. Click **Download**.
4. The model will start downloading. Once it's finished it will say "Done"
5. In the top left, click the refresh icon next to **Model**.
6. In the **Model** dropdown, choose the model you just downloaded: `Llama2-70B-OASST-SFT-v10-GPTQ`
7. The model will automatically load, and is now ready for use!
8. If you want any custom settings, set them and then click **Save settings for this model** followed by **Reload the Model** in the top right.
* Note that you do not need to set GPTQ parameters any more. These are set automatically from the file `quantize_config.json`.
9. Once you're ready, click the **Text Generation tab** and enter a prompt to get started!
## How to use this GPTQ model from Python code
First make sure you have [AutoGPTQ](https://github.com/PanQiWei/AutoGPTQ) 0.3.1 or later installed:
```
pip3 install auto-gptq
```
If you have problems installing AutoGPTQ, please build from source instead:
```
pip3 uninstall -y auto-gptq
git clone https://github.com/PanQiWei/AutoGPTQ
cd AutoGPTQ
pip3 install .
```
Then try the following example code:
```python
from transformers import AutoTokenizer, pipeline, logging
from auto_gptq import AutoGPTQForCausalLM, BaseQuantizeConfig
model_name_or_path = "TheBloke/Llama2-70B-OASST-SFT-v10-GPTQ"
use_triton = False
tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=True)
model = AutoGPTQForCausalLM.from_quantized(model_name_or_path,
use_safetensors=True,
trust_remote_code=False,
device="cuda:0",
use_triton=use_triton,
quantize_config=None)
"""
# To download from a specific branch, use the revision parameter, as in this example:
# Note that `revision` requires AutoGPTQ 0.3.1 or later!
model = AutoGPTQForCausalLM.from_quantized(model_name_or_path,
revision="gptq-4bit-32g-actorder_True",
use_safetensors=True,
trust_remote_code=False,
device="cuda:0",
quantize_config=None)
"""
prompt = "Tell me about AI"
prompt_template=f'''<|im_start|>system
{system_message}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant
'''
print("\n\n*** Generate:")
input_ids = tokenizer(prompt_template, return_tensors='pt').input_ids.cuda()
output = model.generate(inputs=input_ids, temperature=0.7, max_new_tokens=512)
print(tokenizer.decode(output[0]))
# Inference can also be done using transformers' pipeline
# Prevent printing spurious transformers error when using pipeline with AutoGPTQ
logging.set_verbosity(logging.CRITICAL)
print("*** Pipeline:")
pipe = pipeline(
"text-generation",
model=model,
tokenizer=tokenizer,
max_new_tokens=512,
temperature=0.7,
top_p=0.95,
repetition_penalty=1.15
)
print(pipe(prompt_template)[0]['generated_text'])
```
## Compatibility
The files provided will work with AutoGPTQ (CUDA and Triton modes), GPTQ-for-LLaMa (only CUDA has been tested), and Occ4m's GPTQ-for-LLaMa fork.
ExLlama works with Llama models in 4-bit. Please see the Provided Files table above for per-file compatibility.
## Discord
For further support, and discussions on these models and AI in general, join us at:
[TheBloke AI's Discord server](https://discord.gg/theblokeai)
## Thanks, and how to contribute.
Thanks to the [chirper.ai](https://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**: 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](https://huggingface.co/meta-llama/Llama-2-70b) 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](https://open-assistant.io/) up to July 23, 2023 (see [Configuration Details](#configuration-details) below).
## Model Details
- **Finetuned from:** [meta-llama/Llama-2-70b](https://huggingface.co/meta-llama/Llama-2-70b) via [epfLLM/Megatron-LLM](https://github.com/epfLLM/Megatron-LLM)
- **Model type:** Causal decoder-only transformer language model
- **Language:** English (and limited capabilities in German, Spanish, French, Italian, Portuguese, Polish, Dutch, Romanian, Czech, Swedish)
- **Weights & Biases training logs:** [Stage 1](https://wandb.ai/open-assistant/public-sft/runs/run45_oasst_pre10_llama2_70b) (1 epoch pretrain-mix, 12k steps), [Stage 2](https://wandb.ai/open-assistant/public-sft/runs/run46_oasst_sft10_llama2_70b) (3 epochs oasst top-1, 519 steps)
- **Demo:** [Continuations for 250 random prompts (TGI, 4bit nf4 quantization)](https://open-assistant.github.io/oasst-model-eval/?f=https%3A%2F%2Fraw.githubusercontent.com%2FOpen-Assistant%2Foasst-model-eval%2Fmain%2Fsampling_reports%2Foasst-sft%2F2023-08-22_OpenAssistant_llama2-70b-oasst-sft-v10_sampling_noprefix2_nf4.json%0A)
- **Evaluation** [FastEval-OpenAssistant Overview](https://tju01.github.io/FastEval-OpenAssistant/) (using [FastEval](https://github.com/FastEval/FastEval) & [vLLM](https://github.com/vllm-project/vllm))
- **License:** [LLAMA 2 COMMUNITY LICENSE AGREEMENT](https://huggingface.co/meta-llama/Llama-2-70b/raw/main/LICENSE.txt)
- **Contact:** [Open-Assistant Discord](https://ykilcher.com/open-assistant-discord)
## Prompting / Prompt Template
Due to public demand (see [survey](https://twitter.com/erhartford/status/1682403597525430272)) we changed the prompt-template for this model from custom prompter/assistant tokens to OpenAI's [chatml](https://github.com/openai/openai-python/blob/main/chatml.md) 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](https://github.com/facebookresearch/llama/blob/ea9f33d6d3ea8ed7d560d270986407fd6c2e52b7/example_chat_completion.py#L57-L61):
```
<|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
- Thanks to [Meta AI](https://ai.meta.com/) for training and releasing the Llama2 model.
- Distributed training support was provided by EPFL's [Machine Learning and Optimization Laboratory](https://www.epfl.ch/labs/mlo/), and [Natural Language Processing Lab](https://nlp.epfl.ch/).
- The open-source [epfLLM/Megatron-LLM](https://github.com/epfLLM/Megatron-LLM) trainer was used for fine-tuning.
- [rombodawg](https://huggingface.co/rombodawg) curated the [LosslessMegaCodeTrainingV2_1m_Evol_Uncensored](https://huggingface.co/datasets/rombodawg/LosslessMegaCodeTrainingV2_1m_Evol_Uncensored) dataset.
- [ehartford](https://huggingface.co/ehartford) generated and published the [ehartford/dolphin](https://huggingface.co/datasets/ehartford/dolphin) and the [ehartford/oa_leet10k](https://huggingface.co/datasets/ehartford/oa_leet10k) datasets.
- [Argilla](https://huggingface.co/argilla) curated and published the [argilla/databricks-dolly-15k-curated-multilingual](https://huggingface.co/datasets/argilla/databricks-dolly-15k-curated-multilingual) dataset.
- [shahules786](https://github.com/shahules786) de-duped and filtered the Dolphin dataset with a cluster-center approach and generated the orca-best (ocra-chat) dataset.
- [andreaskoepf](https://github.com/andreaskoepf/) prepared & orchestrated the training.
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](https://ai.meta.com/llama/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](https://github.com/huggingface/text-generation-inference).
In contrast the model could be evaluated without problem using [vLLM](https://github.com/vllm-project/vllm).
The model also worked decently well when loaded with TGI on a single GPPU nf4 quantized via [TimDettmers/bitsandbytes](https://github.com/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](https://github.com/LAION-AI/Open-Assistant/tree/main/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
```