github
/
InternLM
mirror of https://github.com/InternLM/InternLM
1
0
Fork 0
Code Issues Projects Releases Wiki Activity

[Doc] Add bitsandbytes to Readme,and support usage on low-resource devices. (#636)

pull/663/head
LYMDLUT 2024-01-24 16:06:45 +08:00 committed by GitHub
parent fe41bbc058
commit f395c4b5d1
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 22 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
README.md
View File

@ -138,7 +138,12 @@ import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("internlm/internlm2-chat-7b", trust_remote_code=True)
# Set `torch_dtype=torch.float16` to load model in float16, otherwise it will be loaded as float32 and might cause OOM Error.
model = AutoModelForCausalLM.from_pretrained("internlm/internlm2-chat-7b", trust_remote_code=True, torch_dtype=torch.float16).cuda()
model = AutoModelForCausalLM.from_pretrained("internlm/internlm2-chat-7b", device_map="auto", trust_remote_code=True, torch_dtype=torch.float16)
# (Optional) If on low resource devices, you can load model in 4-bit or 8-bit to further save GPU memory via bitsandbytes.
# InternLM 7B in 4bit will cost nearly 8GB GPU memory.
# pip install -U bitsandbytes
# 8-bit: model = AutoModelForCausalLM.from_pretrained(model_dir, device_map="auto", trust_remote_code=True, load_in_8bit=True)
# 4-bit: model = AutoModelForCausalLM.from_pretrained(model_dir, device_map="auto", trust_remote_code=True, load_in_4bit=True)
model = model.eval()
response, history = model.chat(tokenizer, "hello", history=[])
print(response)
@ -158,6 +163,11 @@ model_dir = snapshot_download('Shanghai_AI_Laboratory/internlm2-chat-7b')
tokenizer = AutoTokenizer.from_pretrained(model_dir, device_map="auto", trust_remote_code=True)
# Set `torch_dtype=torch.float16` to load model in float16, otherwise it will be loaded as float32 and might cause OOM Error.
model = AutoModelForCausalLM.from_pretrained(model_dir, device_map="auto", trust_remote_code=True, torch_dtype=torch.float16)
# (Optional) If on low resource devices, you can load model in 4-bit or 8-bit to further save GPU memory via bitsandbytes.
# InternLM 7B in 4bit will cost nearly 8GB GPU memory.
# pip install -U bitsandbytes
# 8-bit: model = AutoModelForCausalLM.from_pretrained(model_dir, device_map="auto", trust_remote_code=True, load_in_8bit=True)
# 4-bit: model = AutoModelForCausalLM.from_pretrained(model_dir, device_map="auto", trust_remote_code=True, load_in_4bit=True)
model = model.eval()
response, history = model.chat(tokenizer, "hello", history=[])
print(response)

12
README_zh-CN.md
View File

@ -136,7 +136,12 @@ import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("internlm/internlm2-chat-7b", trust_remote_code=True)
# 设置`torch_dtype=torch.float16`来将模型精度指定为torch.float16，否则可能会因为您的硬件原因造成显存不足的问题。
model = AutoModelForCausalLM.from_pretrained("internlm/internlm2-chat-7b", trust_remote_code=True, torch_dtype=torch.float16).cuda()
model = AutoModelForCausalLM.from_pretrained("internlm/internlm2-chat-7b", device_map="auto",trust_remote_code=True, torch_dtype=torch.float16)
# (可选) 如果在低资源设备上，可以通过bitsandbytes加载4-bit或8-bit量化的模型，进一步节省GPU显存.
# 4-bit 量化的 InternLM 7B 大约会消耗 8GB 显存.
# pip install -U bitsandbytes
# 8-bit: model = AutoModelForCausalLM.from_pretrained(model_dir, device_map="auto", trust_remote_code=True, load_in_8bit=True)
# 4-bit: model = AutoModelForCausalLM.from_pretrained(model_dir, device_map="auto", trust_remote_code=True, load_in_4bit=True)
model = model.eval()
response, history = model.chat(tokenizer, "你好", history=[])
print(response)
@ -155,6 +160,11 @@ from modelscope import snapshot_download, AutoTokenizer, AutoModelForCausalLM
model_dir = snapshot_download('Shanghai_AI_Laboratory/internlm2-chat-7b')
tokenizer = AutoTokenizer.from_pretrained(model_dir, device_map="auto", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(model_dir, device_map="auto", trust_remote_code=True, torch_dtype=torch.float16)
# (可选) 如果在低资源设备上，可以通过bitsandbytes加载4-bit或8-bit量化的模型，进一步节省GPU显存.
# 4-bit 量化的 InternLM 7B 大约会消耗 8GB 显存.
# pip install -U bitsandbytes
# 8-bit: model = AutoModelForCausalLM.from_pretrained(model_dir, device_map="auto", trust_remote_code=True, load_in_8bit=True)
# 4-bit: model = AutoModelForCausalLM.from_pretrained(model_dir, device_map="auto", trust_remote_code=True, load_in_4bit=True)
model = model.eval()
response, history = model.chat(tokenizer, "hello", history=[])
print(response)