root
/
tabby
mirror of https://gitee.com/zhang_1334717033/tabby.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Add testdata for GPTNeoX

add-more-languages
Meng Zhang 2023-03-20 16:51:28 +08:00
parent beddfc0f7f
commit fe8e02aec6
217 changed files with 710 additions and 310 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

135
converter/huggingface_gptneox_convert.py
View File

@ -2,12 +2,13 @@ import argparse
import configparser
import multiprocessing
import os
import shutil
import sys
from pathlib import Path
import numpy as np
import torch
from transformers import GPTNeoXForCausalLM # 4.21.1
from transformers import GPTNeoXForCausalLM
def get_weight_data_type(data_type):
@ -19,51 +20,7 @@ def get_weight_data_type(data_type):
assert False, f"Invalid weight data type {data_type}"
def prefix_prompt_convert(args, config, weight_data_type):
saved_dir = args.saved_dir + "/%d-gpu/" % args.infer_gpu_num
prompt_in_file_list = args.prompt_in_file_list.split(",")
task_list = []
for idx, prompt_in_file in enumerate(prompt_in_file_list):
weights = torch.load(prompt_in_file)
task_name = prompt_in_file.split("/")[-1].split(".")[-3]
total_size = weights.nelement()
n_layers = config["num_hidden_layers"]
n_head = config["num_heads"]
size_per_head = config["hidden_size"] // n_head
prefix_prompt_len = total_size // (2 * n_layers * n_head * size_per_head)
task_list.append((task_name, prefix_prompt_len))
# GPT NeoX
weights = weights.view(
prefix_prompt_len, n_layers, 2, n_head, size_per_head
) ## prefix_seq_len, num_layers, 2, num_heads, size_per_head
# weights=weights.view(prefix_prompt_len,28,2,16,256) ## prefix_seq_len, num_layers, 2, num_heads, size_per_head
weights = weights.permute(
1, 2, 3, 0, 4
) ## num_layers, 2, num_heads, perfix_seq_len, size_per_head
local_head_num = n_head // args.infer_gpu_num
weights_split = torch.split(weights, local_head_num, dim=2)
for i in range(args.infer_gpu_num):
output_file_path = (
saved_dir
+ "/model.prefix_prompt."
+ task_name
+ ".weight."
+ str(i)
+ ".bin"
)
weights_split[i].detach().cpu().numpy().astype(weight_data_type).tofile(
output_file_path
)
return task_list
def split_and_convert_process(i, saved_dir, factor, key, args, config, val):
def split_and_convert_process(saved_dir, factor, key, args, config, val):
if (
key.find("input_layernorm.weight") != -1
@ -75,11 +32,8 @@ def split_and_convert_process(i, saved_dir, factor, key, args, config, val):
or key.find("final_layernorm.weight") != -1
or key.find("final_layernorm.bias") != -1
):
# shared weights, only need to convert the weights of rank 0
if i == 0:
saved_path = saved_dir + "/model." + key + ".bin"
val.tofile(saved_path)
saved_path = saved_dir + f"/model.{key}.bin"
val.tofile(saved_path)
elif (
key.find("attention.dense.weight") != -1
@ -87,7 +41,7 @@ def split_and_convert_process(i, saved_dir, factor, key, args, config, val):
):
split_vals = np.split(val, factor, axis=0)
for j in range(factor):
saved_path = saved_dir + "/model." + key + ".%d.bin" % (i * factor + j)
saved_path = saved_dir + f"/model.{key}.{j}.bin"
split_vals[j].tofile(saved_path)
elif (
@ -97,7 +51,7 @@ def split_and_convert_process(i, saved_dir, factor, key, args, config, val):
split_vals = np.split(val, factor, axis=-1)
for j in range(factor):
saved_path = saved_dir + "/model." + key + ".%d.bin" % (i * factor + j)
saved_path = saved_dir + f"/model.{key}.{j}.bin"
split_vals[j].tofile(saved_path)
elif key.find("attention.query_key_value.bias") != -1:
@ -109,7 +63,7 @@ def split_and_convert_process(i, saved_dir, factor, key, args, config, val):
split_vals = np.split(val, factor, axis=-1)
for j in range(factor):
saved_path = saved_dir + "/model." + key + ".%d.bin" % (i * factor + j)
saved_path = saved_dir + f"/model.{key}.{j}.bin"
split_vals[j].tofile(saved_path)
elif key.find("attention.query_key_value.weight") != -1:
@ -125,7 +79,7 @@ def split_and_convert_process(i, saved_dir, factor, key, args, config, val):
split_vals = np.split(val, factor, axis=-1)
for j in range(factor):
saved_path = saved_dir + "/model." + key + ".%d.bin" % (i * factor + j)
saved_path = saved_dir + f"/model.{key}.{j}.bin"
split_vals[j].tofile(saved_path)
else:
@ -149,45 +103,30 @@ def split_and_convert(args):
# model = torch.load(ckpt_name)
model = GPTNeoXForCausalLM.from_pretrained(args.in_file)
hf_config = vars(model.config)
if "gpt_j_residual" not in hf_config:
hf_config["gpt_j_residual"] = 0
np_weight_data_type = get_weight_data_type(args.weight_data_type)
task_list = []
if args.prompt_in_file_list is not None:
task_list = prefix_prompt_convert(args, hf_config, np_weight_data_type)
try:
model_name = args.model_name
n_heads = hf_config["num_attention_heads"]
head_size = hf_config["hidden_size"] // n_heads
rotary_dim = int(head_size * hf_config["rotary_pct"])
use_gptj_residual = int(hf_config["use_parallel_residual"])
config = configparser.ConfigParser()
config["gptneox"] = {}
config["gptneox"]["model_name"] = model_name
config["gptneox"]["head_num"] = str(hf_config["num_attention_heads"])
n_embd = hf_config["hidden_size"]
config["gptneox"]["size_per_head"] = str(
n_embd // hf_config["num_attention_heads"]
)
config["gptneox"]["inter_size"] = str(n_embd * 4)
config["gptneox"]["head_num"] = str(n_heads)
config["gptneox"]["size_per_head"] = str(head_size)
config["gptneox"]["inter_size"] = str(hf_config["intermediate_size"])
config["gptneox"]["num_layer"] = str(hf_config["num_hidden_layers"])
if "rotary_dim" in hf_config:
rotary_dim = hf_config["rotary_dim"]
else:
rotary_dim = n_embd // hf_config["num_attention_heads"]
config["gptneox"]["rotary_embedding"] = str(rotary_dim)
config["gptneox"]["vocab_size"] = str(hf_config["vocab_size"])
config["gptneox"]["start_id"] = str(hf_config["bos_token_id"])
config["gptneox"]["end_id"] = str(hf_config["eos_token_id"])
config["gptneox"]["use_gptj_residual"] = str(int(hf_config["gpt_j_residual"]))
config["gptneox"]["use_gptj_residual"] = str(use_gptj_residual)
config["gptneox"]["weight_data_type"] = args.weight_data_type
if len(task_list) > 0:
config["gptneox"]["num_tasks"] = str(len(task_list))
config["gptneox"]["prompt_learning_type"] = str(2)
for idx, (task_name, prompt_length) in enumerate(task_list):
config[f"task_{idx}"] = {}
config[f"task_{idx}"]["task_name"] = task_name
config[f"task_{idx}"]["prompt_length"] = str(prompt_length)
with open((Path(saved_dir) / f"config.ini").as_posix(), "w") as configfile:
config.write(configfile)
except Exception as e:
@ -211,24 +150,19 @@ def split_and_convert(args):
torch.multiprocessing.set_start_method("spawn")
pool = multiprocessing.Pool(args.processes)
for name, param in model.named_parameters():
array = param.detach().cpu().numpy().astype(np_weight_data_type)
# print("input shape", name, array.shape)
if name.find("weight") == -1 and name.find("bias") == -1:
print("skipped", name)
continue
elif name == "gpt_neox.embed_in.weight":
param.detach().cpu().numpy().astype(np_weight_data_type).tofile(
saved_dir + "model.wte.bin"
)
array.tofile(saved_dir + "model.wte.bin")
elif name == "gpt_neox.final_layer_norm.bias":
param.detach().cpu().numpy().astype(np_weight_data_type).tofile(
saved_dir + "model.final_layernorm.bias.bin"
)
array.tofile(saved_dir + "model.final_layernorm.bias.bin")
elif name == "gpt_neox.final_layer_norm.weight":
param.detach().cpu().numpy().astype(np_weight_data_type).tofile(
saved_dir + "model.final_layernorm.weight.bin"
)
array.tofile(saved_dir + "model.final_layernorm.weight.bin")
elif name == "embed_out.weight":
param.detach().cpu().numpy().astype(np_weight_data_type).tofile(
saved_dir + "model.lm_head.weight.bin"
)
array.tofile(saved_dir + "model.lm_head.weight.bin")
else:
processed = False
for i in range(len(ft_model_name_pattern)):
@ -238,17 +172,12 @@ def split_and_convert(args):
split_and_convert_process,
[
(
0,
saved_dir,
factor,
new_name,
args,
vars(model.config),
param.detach()
.cpu()
.numpy()
.astype(np_weight_data_type)
.T,
array.T,
)
],
)
@ -256,13 +185,13 @@ def split_and_convert(args):
break
if not processed:
raise Exception("Unused layer", name)
print("Unused layer", name)
pool.close()
pool.join()
# Post-process biases if use_gptj_residual is True
if hf_config["gpt_j_residual"]:
if use_gptj_residual:
for layer_idx in range(hf_config["n_layer"]):
attn_bias = np.fromfile(
saved_dir + f"/model.layers.{layer_idx}.attention.dense.bias.bin",
@ -290,13 +219,6 @@ if __name__ == "__main__":
help="file name of input checkpoint file",
required=True,
)
parser.add_argument(
"-prompt_in_file_list",
"-p_i_list",
type=str,
help="list of the prompt weight file path,"
"separate by (,). e.g. -prompt_in_file_list prefix_prompt.task0.weight,prefix_prompt.task1.weight",
)
parser.add_argument(
"-trained_gpu_num",
"-t_g",
@ -331,4 +253,5 @@ if __name__ == "__main__":
print("{}: {}".format(key, vars(args)[key]))
print("========================================")
shutil.rmtree(args.saved_dir, ignore_errors=True)
split_and_convert(args)

12
converter/testdata/tiny-random-GPTNeoXModel/fastertransformer/1/1-gpu/config.ini vendored
View File

@ -1,12 +0,0 @@
[gptneox]
model_name = tiny-random-GPTNeoX
head_num = 4
size_per_head = 8
inter_size = 128
num_layer = 5
rotary_embedding = 8
vocab_size = 1024
start_id = 0
end_id = 0
use_gptj_residual = 0
weight_data_type = fp32

3
converter/testdata/tiny-random-GPTNeoXModel/fastertransformer/1/1-gpu/model.final_layernorm.bias.bin vendored
View File

@ -1,3 +0,0 @@
version https://git-lfs.github.com/spec/v1
oid sha256:38723a2e5e8a17aa7950dc008209944e898f69a7bd10a23c839d341e935fd5ca
size 128

3
converter/testdata/tiny-random-GPTNeoXModel/fastertransformer/1/1-gpu/model.final_layernorm.weight.bin vendored
View File

@ -1,3 +0,0 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b638277a8690e175a9137feff1e43c067f9faf4e2f600caf468fb05b0403b717
size 128

3
converter/testdata/tiny-random-GPTNeoXModel/fastertransformer/1/1-gpu/model.layers.0.attention.dense.bias.bin vendored
View File

@ -1,3 +0,0 @@
version https://git-lfs.github.com/spec/v1
oid sha256:38723a2e5e8a17aa7950dc008209944e898f69a7bd10a23c839d341e935fd5ca
size 128

3
converter/testdata/tiny-random-GPTNeoXModel/fastertransformer/1/1-gpu/model.layers.0.attention.dense.weight.0.bin vendored
View File

@ -1,3 +0,0 @@
version https://git-lfs.github.com/spec/v1
oid sha256:75ec999d1d55bc4af21e7ee8101f7540ff53f73725fc332f175bac14fda1b83a
size 4096

3
converter/testdata/tiny-random-GPTNeoXModel/fastertransformer/1/1-gpu/model.layers.0.attention.query_key_value.bias.0.bin vendored
View File

@ -1,3 +0,0 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a1a4f5721c1c4610af7f71078f3a68c330536d679803b0e0507ee8dc10c5dfca
size 384

3
converter/testdata/tiny-random-GPTNeoXModel/fastertransformer/1/1-gpu/model.layers.0.attention.query_key_value.weight.0.bin vendored
View File

@ -1,3 +0,0 @@
version https://git-lfs.github.com/spec/v1
oid sha256:8d0af572105f74f7711069438049a1b539af19b43e4d341fd314b5c67792ce28
size 12288

3
converter/testdata/tiny-random-GPTNeoXModel/fastertransformer/1/1-gpu/model.layers.0.input_layernorm.bias.bin vendored
View File

@ -1,3 +0,0 @@
version https://git-lfs.github.com/spec/v1
oid sha256:38723a2e5e8a17aa7950dc008209944e898f69a7bd10a23c839d341e935fd5ca
size 128

3
converter/testdata/tiny-random-GPTNeoXModel/fastertransformer/1/1-gpu/model.layers.0.input_layernorm.weight.bin vendored
View File

@ -1,3 +0,0 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b638277a8690e175a9137feff1e43c067f9faf4e2f600caf468fb05b0403b717
size 128

3
converter/testdata/tiny-random-GPTNeoXModel/fastertransformer/1/1-gpu/model.layers.0.mlp.dense_4h_to_h.bias.bin vendored
View File

@ -1,3 +0,0 @@
version https://git-lfs.github.com/spec/v1
oid sha256:38723a2e5e8a17aa7950dc008209944e898f69a7bd10a23c839d341e935fd5ca
size 128

3
converter/testdata/tiny-random-GPTNeoXModel/fastertransformer/1/1-gpu/model.layers.0.mlp.dense_4h_to_h.weight.0.bin vendored
View File

@ -1,3 +0,0 @@
version https://git-lfs.github.com/spec/v1
oid sha256:aca4617a559ee69fe7c96a62087f3b18700da03d5ad974ab8c58c01d32a5a65e
size 4736

3
converter/testdata/tiny-random-GPTNeoXModel/fastertransformer/1/1-gpu/model.layers.0.mlp.dense_h_to_4h.bias.0.bin vendored
View File

@ -1,3 +0,0 @@
version https://git-lfs.github.com/spec/v1
oid sha256:3b18c58c739716e76429634a61375c45b3b5cd470c22ab6d3e14cee23dd992e1
size 148

3
converter/testdata/tiny-random-GPTNeoXModel/fastertransformer/1/1-gpu/model.layers.0.mlp.dense_h_to_4h.weight.0.bin vendored
View File

@ -1,3 +0,0 @@
version https://git-lfs.github.com/spec/v1
oid sha256:8c7eae417acdf83e12125252829446e277269e3aeff2543148576a6b267934d3
size 4736

3
converter/testdata/tiny-random-GPTNeoXModel/fastertransformer/1/1-gpu/model.layers.0.post_attention_layernorm.bias.bin vendored
View File

@ -1,3 +0,0 @@
version https://git-lfs.github.com/spec/v1
oid sha256:38723a2e5e8a17aa7950dc008209944e898f69a7bd10a23c839d341e935fd5ca
size 128

3
converter/testdata/tiny-random-GPTNeoXModel/fastertransformer/1/1-gpu/model.layers.0.post_attention_layernorm.weight.bin vendored
View File

@ -1,3 +0,0 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b638277a8690e175a9137feff1e43c067f9faf4e2f600caf468fb05b0403b717
size 128

3
converter/testdata/tiny-random-GPTNeoXModel/fastertransformer/1/1-gpu/model.layers.1.attention.dense.bias.bin vendored
View File

@ -1,3 +0,0 @@
version https://git-lfs.github.com/spec/v1
oid sha256:38723a2e5e8a17aa7950dc008209944e898f69a7bd10a23c839d341e935fd5ca
size 128

3
converter/testdata/tiny-random-GPTNeoXModel/fastertransformer/1/1-gpu/model.layers.1.attention.dense.weight.0.bin vendored
View File

@ -1,3 +0,0 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b9e123291a9e860163e8e6acd45f4e46ab7f65a3da84767d9c45541ff2e61a27
size 4096

3
converter/testdata/tiny-random-GPTNeoXModel/fastertransformer/1/1-gpu/model.layers.1.attention.query_key_value.bias.0.bin vendored
View File

@ -1,3 +0,0 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a1a4f5721c1c4610af7f71078f3a68c330536d679803b0e0507ee8dc10c5dfca
size 384

3
converter/testdata/tiny-random-GPTNeoXModel/fastertransformer/1/1-gpu/model.layers.1.attention.query_key_value.weight.0.bin vendored
View File

@ -1,3 +0,0 @@
version https://git-lfs.github.com/spec/v1
oid sha256:3aa877cf3a9c6f51414a3773bf2036af613f999dff1d08966c84f5c0164be0bb
size 12288

3
converter/testdata/tiny-random-GPTNeoXModel/fastertransformer/1/1-gpu/model.layers.1.input_layernorm.bias.bin vendored
View File

@ -1,3 +0,0 @@
version https://git-lfs.github.com/spec/v1
oid sha256:38723a2e5e8a17aa7950dc008209944e898f69a7bd10a23c839d341e935fd5ca
size 128

3
converter/testdata/tiny-random-GPTNeoXModel/fastertransformer/1/1-gpu/model.layers.1.input_layernorm.weight.bin vendored
View File

@ -1,3 +0,0 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b638277a8690e175a9137feff1e43c067f9faf4e2f600caf468fb05b0403b717
size 128

3
converter/testdata/tiny-random-GPTNeoXModel/fastertransformer/1/1-gpu/model.layers.1.mlp.dense_4h_to_h.bias.bin vendored
View File

@ -1,3 +0,0 @@
version https://git-lfs.github.com/spec/v1
oid sha256:38723a2e5e8a17aa7950dc008209944e898f69a7bd10a23c839d341e935fd5ca
size 128

3
converter/testdata/tiny-random-GPTNeoXModel/fastertransformer/1/1-gpu/model.layers.1.mlp.dense_4h_to_h.weight.0.bin vendored
View File

@ -1,3 +0,0 @@
version https://git-lfs.github.com/spec/v1
oid sha256:0568057def9087e03b35fdcc8ed89ad88bcf672b9a8d3562d816e95b4de8b10f
size 4736

3
converter/testdata/tiny-random-GPTNeoXModel/fastertransformer/1/1-gpu/model.layers.1.mlp.dense_h_to_4h.bias.0.bin vendored
View File

@ -1,3 +0,0 @@
version https://git-lfs.github.com/spec/v1
oid sha256:3b18c58c739716e76429634a61375c45b3b5cd470c22ab6d3e14cee23dd992e1
size 148

3
converter/testdata/tiny-random-GPTNeoXModel/fastertransformer/1/1-gpu/model.layers.1.mlp.dense_h_to_4h.weight.0.bin vendored
View File

@ -1,3 +0,0 @@
version https://git-lfs.github.com/spec/v1
oid sha256:38d439b2f0ce9e61bdc56aaea018bac52ba20f5eb6a9af39f11b920afa98a74d
size 4736

3
converter/testdata/tiny-random-GPTNeoXModel/fastertransformer/1/1-gpu/model.layers.1.post_attention_layernorm.bias.bin vendored
View File

@ -1,3 +0,0 @@
version https://git-lfs.github.com/spec/v1
oid sha256:38723a2e5e8a17aa7950dc008209944e898f69a7bd10a23c839d341e935fd5ca
size 128

3
converter/testdata/tiny-random-GPTNeoXModel/fastertransformer/1/1-gpu/model.layers.1.post_attention_layernorm.weight.bin vendored
View File

@ -1,3 +0,0 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b638277a8690e175a9137feff1e43c067f9faf4e2f600caf468fb05b0403b717
size 128

3
converter/testdata/tiny-random-GPTNeoXModel/fastertransformer/1/1-gpu/model.layers.2.attention.dense.bias.bin vendored
View File

@ -1,3 +0,0 @@
version https://git-lfs.github.com/spec/v1
oid sha256:38723a2e5e8a17aa7950dc008209944e898f69a7bd10a23c839d341e935fd5ca
size 128

3
converter/testdata/tiny-random-GPTNeoXModel/fastertransformer/1/1-gpu/model.layers.2.attention.dense.weight.0.bin vendored
View File

@ -1,3 +0,0 @@
version https://git-lfs.github.com/spec/v1
oid sha256:439187a6e4a716b263062a0393e015944688d5ade8becc855b18b53799a1b9f4
size 4096

3
converter/testdata/tiny-random-GPTNeoXModel/fastertransformer/1/1-gpu/model.layers.2.attention.query_key_value.bias.0.bin vendored
View File

@ -1,3 +0,0 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a1a4f5721c1c4610af7f71078f3a68c330536d679803b0e0507ee8dc10c5dfca
size 384

3
converter/testdata/tiny-random-GPTNeoXModel/fastertransformer/1/1-gpu/model.layers.2.attention.query_key_value.weight.0.bin vendored
View File

@ -1,3 +0,0 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ff118539b509bc4d35473c1c4d2ecee86276a1b56f8b1c128fb343fbe7126b29
size 12288

3
converter/testdata/tiny-random-GPTNeoXModel/fastertransformer/1/1-gpu/model.layers.2.input_layernorm.bias.bin vendored
View File

@ -1,3 +0,0 @@
version https://git-lfs.github.com/spec/v1
oid sha256:38723a2e5e8a17aa7950dc008209944e898f69a7bd10a23c839d341e935fd5ca
size 128

3
converter/testdata/tiny-random-GPTNeoXModel/fastertransformer/1/1-gpu/model.layers.2.input_layernorm.weight.bin vendored
View File

@ -1,3 +0,0 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b638277a8690e175a9137feff1e43c067f9faf4e2f600caf468fb05b0403b717
size 128

3
converter/testdata/tiny-random-GPTNeoXModel/fastertransformer/1/1-gpu/model.layers.2.mlp.dense_4h_to_h.bias.bin vendored
View File

@ -1,3 +0,0 @@
version https://git-lfs.github.com/spec/v1
oid sha256:38723a2e5e8a17aa7950dc008209944e898f69a7bd10a23c839d341e935fd5ca
size 128

3
converter/testdata/tiny-random-GPTNeoXModel/fastertransformer/1/1-gpu/model.layers.2.mlp.dense_4h_to_h.weight.0.bin vendored
View File

@ -1,3 +0,0 @@
version https://git-lfs.github.com/spec/v1
oid sha256:373d0d807fe8142dc107c53ba616cc7735e391ccc99947143e9490abf56ab807
size 4736

3
converter/testdata/tiny-random-GPTNeoXModel/fastertransformer/1/1-gpu/model.layers.2.mlp.dense_h_to_4h.bias.0.bin vendored
View File

@ -1,3 +0,0 @@
version https://git-lfs.github.com/spec/v1
oid sha256:3b18c58c739716e76429634a61375c45b3b5cd470c22ab6d3e14cee23dd992e1
size 148

3
converter/testdata/tiny-random-GPTNeoXModel/fastertransformer/1/1-gpu/model.layers.2.mlp.dense_h_to_4h.weight.0.bin vendored
View File

@ -1,3 +0,0 @@
version https://git-lfs.github.com/spec/v1
oid sha256:0954135db648aa7945baaa5f861b1b8012188dd199b9b8bc7c8343757ded04fc
size 4736

3
converter/testdata/tiny-random-GPTNeoXModel/fastertransformer/1/1-gpu/model.layers.2.post_attention_layernorm.bias.bin vendored
View File

@ -1,3 +0,0 @@
version https://git-lfs.github.com/spec/v1
oid sha256:38723a2e5e8a17aa7950dc008209944e898f69a7bd10a23c839d341e935fd5ca
size 128

3
converter/testdata/tiny-random-GPTNeoXModel/fastertransformer/1/1-gpu/model.layers.2.post_attention_layernorm.weight.bin vendored
View File

@ -1,3 +0,0 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b638277a8690e175a9137feff1e43c067f9faf4e2f600caf468fb05b0403b717
size 128

3
converter/testdata/tiny-random-GPTNeoXModel/fastertransformer/1/1-gpu/model.layers.3.attention.dense.bias.bin vendored
View File

@ -1,3 +0,0 @@
version https://git-lfs.github.com/spec/v1
oid sha256:38723a2e5e8a17aa7950dc008209944e898f69a7bd10a23c839d341e935fd5ca
size 128

3
converter/testdata/tiny-random-GPTNeoXModel/fastertransformer/1/1-gpu/model.layers.3.attention.dense.weight.0.bin vendored
View File

@ -1,3 +0,0 @@
version https://git-lfs.github.com/spec/v1
oid sha256:8318d93f17e38918736e07b5b70f5148d4b28f8096190902477118700b0a762e
size 4096

3
converter/testdata/tiny-random-GPTNeoXModel/fastertransformer/1/1-gpu/model.layers.3.attention.query_key_value.bias.0.bin vendored
View File

@ -1,3 +0,0 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a1a4f5721c1c4610af7f71078f3a68c330536d679803b0e0507ee8dc10c5dfca
size 384

3
converter/testdata/tiny-random-GPTNeoXModel/fastertransformer/1/1-gpu/model.layers.3.attention.query_key_value.weight.0.bin vendored
View File

@ -1,3 +0,0 @@
version https://git-lfs.github.com/spec/v1
oid sha256:1d5b8deb13e270dea2c77ea5a9f3d65d375bb008d8820128bcfec3c6efb4a454
size 12288

3
converter/testdata/tiny-random-GPTNeoXModel/fastertransformer/1/1-gpu/model.layers.3.input_layernorm.bias.bin vendored
View File

@ -1,3 +0,0 @@
version https://git-lfs.github.com/spec/v1
oid sha256:38723a2e5e8a17aa7950dc008209944e898f69a7bd10a23c839d341e935fd5ca
size 128

3
converter/testdata/tiny-random-GPTNeoXModel/fastertransformer/1/1-gpu/model.layers.3.input_layernorm.weight.bin vendored
View File

@ -1,3 +0,0 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b638277a8690e175a9137feff1e43c067f9faf4e2f600caf468fb05b0403b717
size 128

3
converter/testdata/tiny-random-GPTNeoXModel/fastertransformer/1/1-gpu/model.layers.3.mlp.dense_4h_to_h.bias.bin vendored
View File

@ -1,3 +0,0 @@
version https://git-lfs.github.com/spec/v1
oid sha256:38723a2e5e8a17aa7950dc008209944e898f69a7bd10a23c839d341e935fd5ca
size 128

3
converter/testdata/tiny-random-GPTNeoXModel/fastertransformer/1/1-gpu/model.layers.3.mlp.dense_4h_to_h.weight.0.bin vendored
View File

@ -1,3 +0,0 @@
version https://git-lfs.github.com/spec/v1
oid sha256:d1a725384598dc3cf2889e659a0b136abd98def073ec1c632f36db3803a987a2
size 4736

3
converter/testdata/tiny-random-GPTNeoXModel/fastertransformer/1/1-gpu/model.layers.3.mlp.dense_h_to_4h.bias.0.bin vendored
View File

@ -1,3 +0,0 @@
version https://git-lfs.github.com/spec/v1
oid sha256:3b18c58c739716e76429634a61375c45b3b5cd470c22ab6d3e14cee23dd992e1
size 148

3
converter/testdata/tiny-random-GPTNeoXModel/fastertransformer/1/1-gpu/model.layers.3.mlp.dense_h_to_4h.weight.0.bin vendored
View File

@ -1,3 +0,0 @@
version https://git-lfs.github.com/spec/v1
oid sha256:3dccd82f3a3e32ea7619e48b972c77ff9def1b3fee58a2df924092a707e30152
size 4736

3
converter/testdata/tiny-random-GPTNeoXModel/fastertransformer/1/1-gpu/model.layers.3.post_attention_layernorm.bias.bin vendored
View File

@ -1,3 +0,0 @@
version https://git-lfs.github.com/spec/v1
oid sha256:38723a2e5e8a17aa7950dc008209944e898f69a7bd10a23c839d341e935fd5ca
size 128

3
converter/testdata/tiny-random-GPTNeoXModel/fastertransformer/1/1-gpu/model.layers.3.post_attention_layernorm.weight.bin vendored
View File

@ -1,3 +0,0 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b638277a8690e175a9137feff1e43c067f9faf4e2f600caf468fb05b0403b717
size 128

3
converter/testdata/tiny-random-GPTNeoXModel/fastertransformer/1/1-gpu/model.layers.4.attention.dense.bias.bin vendored
View File

@ -1,3 +0,0 @@
version https://git-lfs.github.com/spec/v1
oid sha256:38723a2e5e8a17aa7950dc008209944e898f69a7bd10a23c839d341e935fd5ca
size 128

3
converter/testdata/tiny-random-GPTNeoXModel/fastertransformer/1/1-gpu/model.layers.4.attention.dense.weight.0.bin vendored
View File

@ -1,3 +0,0 @@
version https://git-lfs.github.com/spec/v1
oid sha256:43e013e9d9ddfc3f604562e7136e02ef97bcc40ecd42f94a236945b6e05e014a
size 4096

3
converter/testdata/tiny-random-GPTNeoXModel/fastertransformer/1/1-gpu/model.layers.4.attention.query_key_value.bias.0.bin vendored
View File

@ -1,3 +0,0 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a1a4f5721c1c4610af7f71078f3a68c330536d679803b0e0507ee8dc10c5dfca
size 384

3
converter/testdata/tiny-random-GPTNeoXModel/fastertransformer/1/1-gpu/model.layers.4.attention.query_key_value.weight.0.bin vendored
View File

@ -1,3 +0,0 @@
version https://git-lfs.github.com/spec/v1
oid sha256:202256fec152abace918bd2da29d3eb9a9213920622756bee56f11162903f043
size 12288

3
converter/testdata/tiny-random-GPTNeoXModel/fastertransformer/1/1-gpu/model.layers.4.input_layernorm.bias.bin vendored
View File

@ -1,3 +0,0 @@
version https://git-lfs.github.com/spec/v1
oid sha256:38723a2e5e8a17aa7950dc008209944e898f69a7bd10a23c839d341e935fd5ca
size 128

3
converter/testdata/tiny-random-GPTNeoXModel/fastertransformer/1/1-gpu/model.layers.4.input_layernorm.weight.bin vendored
View File

@ -1,3 +0,0 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b638277a8690e175a9137feff1e43c067f9faf4e2f600caf468fb05b0403b717
size 128

3
converter/testdata/tiny-random-GPTNeoXModel/fastertransformer/1/1-gpu/model.layers.4.mlp.dense_4h_to_h.bias.bin vendored
View File

@ -1,3 +0,0 @@
version https://git-lfs.github.com/spec/v1
oid sha256:38723a2e5e8a17aa7950dc008209944e898f69a7bd10a23c839d341e935fd5ca
size 128

3
converter/testdata/tiny-random-GPTNeoXModel/fastertransformer/1/1-gpu/model.layers.4.mlp.dense_4h_to_h.weight.0.bin vendored
View File

@ -1,3 +0,0 @@
version https://git-lfs.github.com/spec/v1
oid sha256:1715bf310c65c00750acacf5247186e3422f4c85fde6f056ba21b380a8097b80
size 4736

3
converter/testdata/tiny-random-GPTNeoXModel/fastertransformer/1/1-gpu/model.layers.4.mlp.dense_h_to_4h.bias.0.bin vendored
View File

@ -1,3 +0,0 @@
version https://git-lfs.github.com/spec/v1
oid sha256:3b18c58c739716e76429634a61375c45b3b5cd470c22ab6d3e14cee23dd992e1
size 148

3
converter/testdata/tiny-random-GPTNeoXModel/fastertransformer/1/1-gpu/model.layers.4.mlp.dense_h_to_4h.weight.0.bin vendored
View File

@ -1,3 +0,0 @@
version https://git-lfs.github.com/spec/v1
oid sha256:482a3307809bfb1eb7a34fc3780ed76e2dc4ba51536eef4d9d616d846db729e6
size 4736

3
converter/testdata/tiny-random-GPTNeoXModel/fastertransformer/1/1-gpu/model.layers.4.post_attention_layernorm.bias.bin vendored
View File

@ -1,3 +0,0 @@
version https://git-lfs.github.com/spec/v1
oid sha256:38723a2e5e8a17aa7950dc008209944e898f69a7bd10a23c839d341e935fd5ca
size 128

3
converter/testdata/tiny-random-GPTNeoXModel/fastertransformer/1/1-gpu/model.layers.4.post_attention_layernorm.weight.bin vendored
View File

@ -1,3 +0,0 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b638277a8690e175a9137feff1e43c067f9faf4e2f600caf468fb05b0403b717
size 128

3
converter/testdata/tiny-random-GPTNeoXModel/fastertransformer/1/1-gpu/model.lm_head.weight.bin vendored
View File

@ -1,3 +0,0 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b2d2ae19f874eb46f4c94c8c58930a9df564bdb9205aedcc47f0daadc14ae9a5
size 131072

3
converter/testdata/tiny-random-GPTNeoXModel/fastertransformer/1/1-gpu/model.wte.bin vendored
View File

@ -1,3 +0,0 @@
version https://git-lfs.github.com/spec/v1
oid sha256:51a808360ffa74213dcbfac40776866c50b1bc18fc3d6993e856ae2ffa92e0d0
size 131072

17
converter/tests/gptneox/docker-compose.yaml Normal file
View File

@ -0,0 +1,17 @@
version: '3.3'
services:
triton:
image: ghcr.io/tabbyml/fastertransformer_backend:main
command: mpirun -n 1 --allow-run-as-root /opt/tritonserver/bin/tritonserver --model-repository=/model
shm_size: 1gb
ports:
- "8001:8001"
volumes:
- ./testdata:/model
deploy:
resources:
reservations:
devices:
- driver: nvidia
count: all
capabilities: [gpu]

12
converter/tests/gptneox/testdata/fastertransformer/1/1-gpu/config.ini vendored Normal file
View File

@ -0,0 +1,12 @@
[gptneox]
model_name = gptneox
head_num = 12
size_per_head = 64
inter_size = 3072
num_layer = 12
rotary_embedding = 64
vocab_size = 50304
start_id = 0
end_id = 0
use_gptj_residual = 0
weight_data_type = fp32

3
converter/tests/gptneox/testdata/fastertransformer/1/1-gpu/model.final_layernorm.bias.bin vendored Normal file
View File

@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:c8e8e6b531dabfeff987975cc6c937428139beb7f5699b8b938545716d8eeca7
size 3072

3
converter/tests/gptneox/testdata/fastertransformer/1/1-gpu/model.final_layernorm.weight.bin vendored Normal file
View File

@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a20104b8a794c5dfa02c2847d25a2697ae60971ea296192dc88a9eaaa479f606
size 3072

3
converter/tests/gptneox/testdata/fastertransformer/1/1-gpu/model.layers.0.attention.dense.bias.bin vendored Normal file
View File

@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:3df9dbc92f1617b447db1aa855da24d07660a12c41b22dee002696813b3ebbba
size 3072

3
converter/tests/gptneox/testdata/fastertransformer/1/1-gpu/model.layers.0.attention.dense.weight.0.bin vendored Normal file
View File

@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:5eba16ee6fe2391cf2efcb7162e4662dd905a58cb8610ff32d07813e7575d6fc
size 2359296

3
converter/tests/gptneox/testdata/fastertransformer/1/1-gpu/model.layers.0.attention.query_key_value.bias.0.bin vendored Normal file
View File

@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:93fb9545a9c7ba88f8927bb1929a3d1d74962d18909ee21225e6b9756c77c332
size 9216

3
converter/tests/gptneox/testdata/fastertransformer/1/1-gpu/model.layers.0.attention.query_key_value.weight.0.bin vendored Normal file
View File

@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:35a3c434d0af69813352edd06e29e671e8e160de1221a90abe6f308cd6b624ab
size 7077888

3
converter/tests/gptneox/testdata/fastertransformer/1/1-gpu/model.layers.0.input_layernorm.bias.bin vendored Normal file
View File

@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:f324b52b78c5e245f0b68559ac1b40c7c54aa1d48005ca2d12887cb53dbbc9b2
size 3072

3
converter/tests/gptneox/testdata/fastertransformer/1/1-gpu/model.layers.0.input_layernorm.weight.bin vendored Normal file
View File

@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:1c632d0534e7e7e4eab3d843a0a1f0d0f3843aa9b1aefd6b706ad71cf3de08ed
size 3072

3
converter/tests/gptneox/testdata/fastertransformer/1/1-gpu/model.layers.0.mlp.dense_4h_to_h.bias.bin vendored Normal file
View File

@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:7e2b220335cce206b3928380f069259c01e382937189f1d86d40641bea319a27
size 3072

3
converter/tests/gptneox/testdata/fastertransformer/1/1-gpu/model.layers.0.mlp.dense_4h_to_h.weight.0.bin vendored Normal file
View File

@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:2d59fe9d26e5a6b5bf67a2d631bf012cb67e30a8aee34d5a8b5589a1a3b767d0
size 9437184

3
converter/tests/gptneox/testdata/fastertransformer/1/1-gpu/model.layers.0.mlp.dense_h_to_4h.bias.0.bin vendored Normal file
View File

@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:1fb0620b893fc6c19a0d99f7b0b19fcbc81262b7de48532a0cfd74a6c2ceb11e
size 12288

3
converter/tests/gptneox/testdata/fastertransformer/1/1-gpu/model.layers.0.mlp.dense_h_to_4h.weight.0.bin vendored Normal file
View File

@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ea4b2ed74e487155f748f4ad057070db5a1ef9bbe18f155caf05f1889a7db0e4
size 9437184

3
converter/tests/gptneox/testdata/fastertransformer/1/1-gpu/model.layers.0.post_attention_layernorm.bias.bin vendored Normal file
View File

@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:0e949431800d44dc72725fb2a14c1b6257df33a087c89a5363504b2796f033ef
size 3072

3
converter/tests/gptneox/testdata/fastertransformer/1/1-gpu/model.layers.0.post_attention_layernorm.weight.bin vendored Normal file
View File

@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:e63fbed352f174592299da93e92c5652b45d4d439aea92867c30bc292d2d8891
size 3072

3
converter/tests/gptneox/testdata/fastertransformer/1/1-gpu/model.layers.1.attention.dense.bias.bin vendored Normal file
View File

@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ca3de5c5d037abd4ba67b56fca3fd35e11f2d3355313684066188424579295f0
size 3072

3
converter/tests/gptneox/testdata/fastertransformer/1/1-gpu/model.layers.1.attention.dense.weight.0.bin vendored Normal file
View File

@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:3bfab993d3877ea0dcdbb35f1bfbe371cf03dee47e23a124e1a3004c9abde182
size 2359296

3
converter/tests/gptneox/testdata/fastertransformer/1/1-gpu/model.layers.1.attention.query_key_value.bias.0.bin vendored Normal file
View File

@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ef2961811f9b09add00d1acf68bbb0d983b2a266415bcf4167c108cf0af2b162
size 9216

3
converter/tests/gptneox/testdata/fastertransformer/1/1-gpu/model.layers.1.attention.query_key_value.weight.0.bin vendored Normal file
View File

@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:678d7bdfff7a580935c141a3c8d56121925ad5688ca4839150f7c38aa07b3816
size 7077888

3
converter/tests/gptneox/testdata/fastertransformer/1/1-gpu/model.layers.1.input_layernorm.bias.bin vendored Normal file
View File

@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:22ee83ada70710e37e74558e042db460e1264b2373ad2272891f8681dd32992f
size 3072

3
converter/tests/gptneox/testdata/fastertransformer/1/1-gpu/model.layers.1.input_layernorm.weight.bin vendored Normal file
View File

@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ea7f1c9586a26d8b4c7db214c5e036691d24a6aaa0700434e34fb89789e8413d
size 3072

3
converter/tests/gptneox/testdata/fastertransformer/1/1-gpu/model.layers.1.mlp.dense_4h_to_h.bias.bin vendored Normal file
View File

@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ea6d9660941b2258411fa5a95bc2efae46f9b37b2c2677dbfd15fc4bfa97b7d8
size 3072

3
converter/tests/gptneox/testdata/fastertransformer/1/1-gpu/model.layers.1.mlp.dense_4h_to_h.weight.0.bin vendored Normal file
View File

@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:df394855b5b83e6cef0b009b66d75bc6ad9536f63ea81c118821269ddb389811
size 9437184

3
converter/tests/gptneox/testdata/fastertransformer/1/1-gpu/model.layers.1.mlp.dense_h_to_4h.bias.0.bin vendored Normal file
View File

@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:970ccc870e06e091619acffcd71eec44e61ea4e38490094850dea049a55ee4d4
size 12288

3
converter/tests/gptneox/testdata/fastertransformer/1/1-gpu/model.layers.1.mlp.dense_h_to_4h.weight.0.bin vendored Normal file
View File

@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:669ab6458f06db05c0310bf04a4c6681b00faa5ad498d144552ddc8b0ebcad1c
size 9437184

3
converter/tests/gptneox/testdata/fastertransformer/1/1-gpu/model.layers.1.post_attention_layernorm.bias.bin vendored Normal file
View File

@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:d77f19d5997955ea3d639595ca6d0a1d94f16eb0a54e6ed9256d151e84a32160
size 3072

3
converter/tests/gptneox/testdata/fastertransformer/1/1-gpu/model.layers.1.post_attention_layernorm.weight.bin vendored Normal file
View File

@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a208323db32e45ec21cb6fa92754862a2d8db9dc32a148ede730567e1b53ea6d
size 3072

3
converter/tests/gptneox/testdata/fastertransformer/1/1-gpu/model.layers.10.attention.dense.bias.bin vendored Normal file
View File

@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:9a991d95e2e3a0c716990227c3fca9617a3762963404bd1bbb1649d6031476d7
size 3072

3
converter/tests/gptneox/testdata/fastertransformer/1/1-gpu/model.layers.10.attention.dense.weight.0.bin vendored Normal file
View File

@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:0948b6eb35b6e388e7ad4cdf315abdf943960d7952dfebbebb4897023cc9a278
size 2359296

3
converter/tests/gptneox/testdata/fastertransformer/1/1-gpu/model.layers.10.attention.query_key_value.bias.0.bin vendored Normal file
View File

@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:4755cff515205a9072c5f00b4e592939e5359f7b535d447bc1f7da44830ce011
size 9216

3
converter/tests/gptneox/testdata/fastertransformer/1/1-gpu/model.layers.10.attention.query_key_value.weight.0.bin vendored Normal file
View File

@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:4b52cdfe8cd07b6f604cd3d848c7ab44efaa5a260441b7da057c42488992b3d6
size 7077888

3
converter/tests/gptneox/testdata/fastertransformer/1/1-gpu/model.layers.10.input_layernorm.bias.bin vendored Normal file
View File

@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:21b95c5b59d5a99b5f833825f620ddde882036901fda433046d6047a2ad90b51
size 3072

3
converter/tests/gptneox/testdata/fastertransformer/1/1-gpu/model.layers.10.input_layernorm.weight.bin vendored Normal file
View File

@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:2e927894a15e7a284be51655cb46338d98d4ca77378d9f865dc00707ae62758b
size 3072

Some files were not shown because too many files have changed in this diff Show More