metadata

license: apache-2.0
language:
  - en
tags:
  - sft
pipeline_tag: text-generation
widget:
  - text: >-
      <prefix>You are a helpful assistant model trained by LAION called
      Aki</prefix><human>Hi, how are you?<bot>
  - text: <human>What's the Earth total population<bot>
  - text: <human>Write a story about future of AI development<bot>

Pythia 1.4B SFT model revision 1

Model Details

Model Description

Model was supervised fine tuned on only Open Assistant crowd souce platform.

Developed by: Open Assistant
Model type: Pythia
Language(s) (NLP): English
License: Apache-2.0

Model Sources [optional]

Repository: Open Assistant

Uses

Direct Use

See the example on the right

Bias, Risks, and Limitations

just read pythia

Recommendations

Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.

How to Get Started with the Model

Use the code below to get started with the model.

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "theblackcat102/pythia-1.4b-deduped-sft-r1"

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name).half().eval().cuda()

input_text = "<human>What's the earth population?<bot>"
inputs = tokenizer(input_text, return_tensors="pt", padding=True).to(0)
outputs = model.generate(
    **inputs,
    early_stopping=True,
    max_new_tokens=args.max_new_tokens,
    do_sample=True,
    top_k=args.top_k,
    temperature=args.temperature,
    pad_token_id=tokenizer.eos_token_id,
    # dialogue_collator.py line 36
)
output = tokenizer.decode(outputs[0], truncate_before_pattern=[r"\n\n^#", "^'''", "\n\n\n"])
print(output)

Training Details

Training Data

Training Procedure

deepspeed trainer_sft.py --configs defaults pythia-1b --deepspeed

This model was trained for 1000 iterations.

Training Hyperparameters

defaults:
  learning_rate: 1e-5
  gradient_checkpointing: false
  gradient_accumulation_steps: 32
  per_device_train_batch_size: 2
  per_device_eval_batch_size: 2
  weight_decay: 0.00
  warmup_steps: 600
  eval_steps: 250
  save_steps: 250
  max_length: 512
  num_train_epochs: 2
  logging_steps: 10
  max_grad_norm: 2.0
  save_total_limit: 4
  fp16: true
  eval_accumulation_steps:
  freeze_layer:
  datasets:
    - oa_private:
        data_path: .cache
        split: sft
        val_split: 0.01
        fraction: 1
        file: 2023-02-26_oasst_default.jsonl
  cache_dir: .cache
  loss_fn: CrossEntropyLoss
  eval_size:
  log_dir: "base"
  quantization: false
  seq2seqmodel: false
  poly_eps: 1.0
  fuse_gelu: false
  log_wandb: true
  samples_mixing: true # uses collator that mixes samples in the batch to create a single sample with possible multiple tasks within
  verbose: false


pythia-1-4b-ost:
  learning_rate: 1e-6
  model_name: EleutherAI/pythia-1.4b-deduped
  weight_decay: 0.01
  max_length: 1024
  warmup_steps: 100
  gradient_checkpointing: false
  gradient_accumulation_steps: 12
  per_device_train_batch_size: 5
  per_device_eval_batch_size: 6
  eval_steps: 100
  save_steps: 100
  num_train_epochs: 50
  save_total_limit: 4

Evaluation

Testing Data, Factors & Metrics

Testing Data

[More Information Needed]

Factors

[More Information Needed]

Metrics

[More Information Needed]

Results

Summary

Model Examination [optional]

[More Information Needed]

Environmental Impact

Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).

Hardware Type: [More Information Needed]
Hours used: [More Information Needed]
Cloud Provider: [More Information Needed]
Compute Region: [More Information Needed]
Carbon Emitted: [More Information Needed]

Technical Specifications [optional]

Model Architecture and Objective

[More Information Needed]

Compute Infrastructure

[More Information Needed]

Hardware

[More Information Needed]

Software

[More Information Needed]

Citation [optional]

BibTeX:

[More Information Needed]

APA:

[More Information Needed]

Glossary [optional]

[More Information Needed]

Acknowledgements

LAION & EleutherAI
Stability.ai : this project wouldn't be possible without their compute resource
Teams and contributors at Open Assistant : who put their time after their day job or whatever into this project
Huggingface : For the storage and spaces here

Model Card Authors [optional]

[More Information Needed]

Model Card Contact

[More Information Needed]