Instructions to use stanrom/internlm-xcomposer-7b-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use stanrom/internlm-xcomposer-7b-4bit with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="stanrom/internlm-xcomposer-7b-4bit", trust_remote_code=True, device_map="auto")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("stanrom/internlm-xcomposer-7b-4bit", trust_remote_code=True, dtype="auto", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update configuration_InternLM_XComposer.py
Browse files
configuration_InternLM_XComposer.py
CHANGED
|
@@ -32,8 +32,8 @@ class InternLMXComposerConfig(PretrainedConfig):
|
|
| 32 |
num_quant=32,
|
| 33 |
intern_converted_llm=True,
|
| 34 |
kqvo_bias=True,
|
| 35 |
-
|
| 36 |
-
device='cpu',
|
| 37 |
internlm_lora=None,
|
| 38 |
**kwargs,
|
| 39 |
):
|
|
|
|
| 32 |
num_quant=32,
|
| 33 |
intern_converted_llm=True,
|
| 34 |
kqvo_bias=True,
|
| 35 |
+
device='cuda:0',
|
| 36 |
+
# device='cpu',
|
| 37 |
internlm_lora=None,
|
| 38 |
**kwargs,
|
| 39 |
):
|