[Coati] first commit (#3283)

applications/Chat/examples/train_dummy.sh

+set_n_least_used_CUDA_VISIBLE_DEVICES() {
+    local n=${1:-"9999"}
+    echo "GPU Memory Usage:"
+    local FIRST_N_GPU_IDS=$(nvidia-smi --query-gpu=memory.used --format=csv \
+        | tail -n +2 \
+        | nl -v 0 \
+        | tee /dev/tty \
+        | sort -g -k 2 \
+        | awk '{print $1}' \
+        | head -n $n)
+    export CUDA_VISIBLE_DEVICES=$(echo $FIRST_N_GPU_IDS | sed 's/ /,/g')
+    echo "Now CUDA_VISIBLE_DEVICES is set to:"
+    echo "CUDA_VISIBLE_DEVICES=$CUDA_VISIBLE_DEVICES"
+}
+
+set_n_least_used_CUDA_VISIBLE_DEVICES 2
+
+torchrun --standalone --nproc_per_node=2 train_dummy.py --strategy colossalai_zero2

applications/Chat/examples/train_prompts.sh

+set_n_least_used_CUDA_VISIBLE_DEVICES() {
+    local n=${1:-"9999"}
+    echo "GPU Memory Usage:"
+    local FIRST_N_GPU_IDS=$(nvidia-smi --query-gpu=memory.used --format=csv \
+        | tail -n +2 \
+        | nl -v 0 \
+        | tee /dev/tty \
+        | sort -g -k 2 \
+        | awk '{print $1}' \
+        | head -n $n)
+    export CUDA_VISIBLE_DEVICES=$(echo $FIRST_N_GPU_IDS | sed 's/ /,/g')
+    echo "Now CUDA_VISIBLE_DEVICES is set to:"
+    echo "CUDA_VISIBLE_DEVICES=$CUDA_VISIBLE_DEVICES"
+}
+
+set_n_least_used_CUDA_VISIBLE_DEVICES 2
+
+torchrun --standalone --nproc_per_node=2 train_prompts.py prompts.csv --strategy colossalai_zero2

applications/Chat/examples/train_rm.sh

+set_n_least_used_CUDA_VISIBLE_DEVICES 1
+
+python train_reward_model.py --pretrain 'microsoft/deberta-v3-large' \
+                             --model 'deberta' \
+                             --strategy naive \
+                             --loss_fn 'log_exp'\
+                             --save_path 'rmstatic.pt' \
+                             --test True

applications/Chat/examples/train_sft.sh

+torchrun --standalone --nproc_per_node=4 train_sft.py \
+    --pretrain "/path/to/LLaMa-7B/" \
+    --model 'llama' \
+    --strategy colossalai_zero2 \
+    --log_interval 10 \
+    --save_path  /path/to/Coati-7B \
+    --dataset /path/to/data.json \
+    --batch_size 4 \
+    --accimulation_steps 8 \
+    --lr 2e-5 \
+    --max_datasets_size 512 \
+    --max_epochs 1 \

applications/Chat/inference/llama_gptq/__init__.py

+from .loader import load_quant
+
+__all__ = [
+    'load_quant',
+]

applications/Chat/inference/llama_gptq/model_utils.py

+# copied from https://github.com/qwopqwop200/GPTQ-for-LLaMa/blob/past/modelutils.py
+
+import torch
+import torch.nn as nn
+
+
+def find_layers(module, layers=[nn.Conv2d, nn.Linear], name=''):
+    if type(module) in layers:
+        return {name: module}
+    res = {}
+    for name1, child in module.named_children():
+        res.update(find_layers(child, layers=layers, name=name + '.' + name1 if name != '' else name1))
+    return res

applications/Chat/requirements-test.txt

+pytest