Update README.md
Browse files
README.md
CHANGED
@@ -7,9 +7,11 @@ datasets:
|
|
7 |
This is a modified version of the original LLaMA model that incorporates Scaled Rotary Embeddings first proposed by [kaiokendev](https://kaiokendev.github.io/). By default, the model is configured to be equivalent to the original OpenLLaMA model (2048 context length). To modify, instantiate the LLaMA configuration and set `max_position_embeddings` to the desired context length. The value should be a power of 2, e.g. 2048, 4096, 8192, etc.
|
8 |
|
9 |
```python
|
10 |
-
config = AutoConfig.from_pretrained("emozilla/open_llama_7b-scaled",
|
|
|
11 |
config.max_position_embeddings = 8192
|
12 |
-
model = AutoModelForCausalLM.from_pretrained("emozilla/open_llama_7b-scaled",
|
|
|
13 |
```
|
14 |
|
15 |
You should also set `max_model_length` on your tokenizer.
|
|
|
7 |
This is a modified version of the original LLaMA model that incorporates Scaled Rotary Embeddings first proposed by [kaiokendev](https://kaiokendev.github.io/). By default, the model is configured to be equivalent to the original OpenLLaMA model (2048 context length). To modify, instantiate the LLaMA configuration and set `max_position_embeddings` to the desired context length. The value should be a power of 2, e.g. 2048, 4096, 8192, etc.
|
8 |
|
9 |
```python
|
10 |
+
config = AutoConfig.from_pretrained("emozilla/open_llama_7b-scaled", \
|
11 |
+
trust_remote_code=True)
|
12 |
config.max_position_embeddings = 8192
|
13 |
+
model = AutoModelForCausalLM.from_pretrained("emozilla/open_llama_7b-scaled", \
|
14 |
+
config=config, trust_remote_code=True)
|
15 |
```
|
16 |
|
17 |
You should also set `max_model_length` on your tokenizer.
|