maziyarpanahi

#!/bin/sh

log() {
  format="$1"; shift
  # shellcheck disable=SC2059
  >&2 printf "$format\n" "$@"
}

usage() {
  >&2 cat <<EOF

maziyarpanahi

from transformers import LlamaConfig as LC, LlamaForCausalLM as LLM, LlamaTokenizer as LT
from accelerate import init_empty_weights, load_checkpoint_and_dispatch
import torch
lt = LT.from_pretrained("NousResearch/Llama-2-7b-hf")
c = LC.from_pretrained("NousResearch/Llama-2-70b-hf")
c.max_position_embeddings = 32764
c.rope_theta = 1000000
with init_empty_weights(): m = LLM(c)
m = m.half().eval()
m.requires_grad_(False)

maziyarpanahi

Let's checkout the PR:

git fetch origin pull/625/head:dbrx
git switch dbrx
pip install -vvv --no-build-isolation -e .

Download the model:

maziyarpanahi

      File "/root/miniconda3/envs/py3.10/lib/python3.10/site-packages/trl/trainer/utils.py", line 338, in __call__
to_pad = [torch.LongTensor(ex[k]) for ex in features]
  File "/root/miniconda3/envs/py3.10/lib/python3.10/site-packages/trl/trainer/utils.py", line 338, in <listcomp>
    to_pad = [torch.LongTensor(ex[k]) for ex in features]
  File "/root/miniconda3/envs/py3.10/lib/python3.10/site-packages/trl/trainer/utils.py", line 338, in <listcomp>
    to_pad = [torch.LongTensor(ex[k]) for ex in features]
TypeError: 'NoneType' object cannot be interpreted as an integer
    to_pad = [torch.LongTensor(ex[k]) for ex in features]
TypeError: 'NoneType' object cannot be interpreted as an integer
    return inner_training_loop(