AI/internlm3-8b-instruct
1
0
Fork 0
mirror of https://www.modelscope.cn/Shanghai_AI_Laboratory/internlm3-8b-instruct.git synced 2025-08-14 04:35:53 +08:00
Code Issues Packages Projects Releases Wiki Activity

Update README.md

Browse Source
This commit is contained in:
haijunlv 2025-01-15 06:28:58 +00:00
parent d085e29bbc
commit 667e0de63d
1 changed files with 9 additions and 13 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

22
README.md
View File

@ -80,15 +80,14 @@ transformers >= 4.48
### Conversation Mode
#### Transformers inference
#### Modelscope inference
To load the InternLM3 8B Instruct model using Transformers, use the following code:
```python
import torch
from modelscope import AutoTokenizer, AutoModelForCausalLM
model_dir = "internlm/internlm3-8b-instruct"
from modelscope import snapshot_download, AutoTokenizer, AutoModelForCausalLM
model_dir = snapshot_download('Shanghai_AI_Laboratory/internlm3-8b-instruct')
tokenizer = AutoTokenizer.from_pretrained(model_dir, 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, trust_remote_code=True, torch_dtype=torch.float16)
@ -272,9 +271,8 @@ Focus on clear, logical progression of ideas and thorough explanation of your ma
```python
import torch
from modelscope import AutoTokenizer, AutoModelForCausalLM
model_dir = "internlm/internlm3-8b-instruct"
from modelscope import snapshot_download, AutoTokenizer, AutoModelForCausalLM
model_dir = snapshot_download('Shanghai_AI_Laboratory/internlm3-8b-instruct')
tokenizer = AutoTokenizer.from_pretrained(model_dir, 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, trust_remote_code=True, torch_dtype=torch.float16)
@ -442,9 +440,8 @@ transformers >= 4.48
```python
import torch
from modelscope import AutoTokenizer, AutoModelForCausalLM
model_dir = "internlm/internlm3-8b-instruct"
from modelscope import snapshot_download, AutoTokenizer, AutoModelForCausalLM
model_dir = snapshot_download('Shanghai_AI_Laboratory/internlm3-8b-instruct')
tokenizer = AutoTokenizer.from_pretrained(model_dir, 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, trust_remote_code=True, torch_dtype=torch.float16)
@ -623,9 +620,8 @@ Focus on clear, logical progression of ideas and thorough explanation of your ma
```python
import torch
from modelscope import AutoTokenizer, AutoModelForCausalLM
model_dir = "internlm/internlm3-8b-instruct"
from modelscope import snapshot_download, AutoTokenizer, AutoModelForCausalLM
model_dir = snapshot_download('Shanghai_AI_Laboratory/internlm3-8b-instruct')
tokenizer = AutoTokenizer.from_pretrained(model_dir, 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, trust_remote_code=True, torch_dtype=torch.float16)