Jacob Louis Hoover commited on
Update README.md
Browse files
README.md
CHANGED
|
@@ -1,13 +1,13 @@
|
|
| 1 |
---
|
| 2 |
library_name: transformers
|
| 3 |
-
|
| 4 |
---
|
| 5 |
|
| 6 |
# Model Card for Model ID
|
| 7 |
|
| 8 |
-
Just a 4bit quantized version of `meta-llama/Llama-2-70b-hf`. Made as:
|
| 9 |
|
| 10 |
-
```
|
| 11 |
from transformers import AutoModelForCausalLM
|
| 12 |
|
| 13 |
model = AutoModelForCausalLM.from_pretrained(
|
|
@@ -15,6 +15,7 @@ model = AutoModelForCausalLM.from_pretrained(
|
|
| 15 |
device_map="auto",
|
| 16 |
load_in_4bit=True
|
| 17 |
)
|
|
|
|
| 18 |
```
|
| 19 |
|
| 20 |
saved for later use (to save 30mins)
|
|
@@ -208,6 +209,4 @@ Carbon emissions can be estimated using the [Machine Learning Impact calculator]
|
|
| 208 |
|
| 209 |
## Model Card Contact
|
| 210 |
|
| 211 |
-
[More Information Needed]
|
| 212 |
-
|
| 213 |
-
|
|
|
|
| 1 |
---
|
| 2 |
library_name: transformers
|
| 3 |
+
pipeline_tag: text-generation
|
| 4 |
---
|
| 5 |
|
| 6 |
# Model Card for Model ID
|
| 7 |
|
| 8 |
+
Just a 4bit quantized version of [`meta-llama/Llama-2-70b-hf`](https://huggingface.co/meta-llama/Llama-2-70b-hf). Made as:
|
| 9 |
|
| 10 |
+
```python
|
| 11 |
from transformers import AutoModelForCausalLM
|
| 12 |
|
| 13 |
model = AutoModelForCausalLM.from_pretrained(
|
|
|
|
| 15 |
device_map="auto",
|
| 16 |
load_in_4bit=True
|
| 17 |
)
|
| 18 |
+
model.push_to_hub('Llama-2-70b-hf-4bit')
|
| 19 |
```
|
| 20 |
|
| 21 |
saved for later use (to save 30mins)
|
|
|
|
| 209 |
|
| 210 |
## Model Card Contact
|
| 211 |
|
| 212 |
+
[More Information Needed]
|
|
|
|
|
|