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

Update README.md

pull/636/head
LYMDLUT 2024-01-19 15:08:05 +08:00 committed by GitHub
parent 4fd9391594
commit c4bd50bcb9
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 11 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
README.md
View File

@ -132,7 +132,12 @@ 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)
@ -152,6 +157,11 @@ 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)