Commit
•
47b1cd2
1
Parent(s):
7754b1e
Update README.md
Browse files
README.md
CHANGED
|
@@ -1,6 +1,6 @@
|
|
| 1 |
# llama2-7B-Chat-hf-8bit-guanaco-pico-finetuned
|
| 2 |
|
| 3 |
-
This is a 8bit quanitzed fine tuned adapter merged with fp16 llama2-7b-chat-hf checkpoint.
|
| 4 |
Fine tuning has been performed on a very small/pico Guanaco dataset: manojkumarvohra/guanaco-pico-100-samples
|
| 5 |
https://huggingface.co/datasets/manojkumarvohra/guanaco-pico-100-samples
|
| 6 |
with 100 training samples and 20 validation samples.
|
|
|
|
| 1 |
# llama2-7B-Chat-hf-8bit-guanaco-pico-finetuned
|
| 2 |
|
| 3 |
+
This is a 8bit quanitzed fine tuned adapter (https://huggingface.co/manojkumarvohra/llama2-7B-Chat-8bit-guanaco-pico-adapter-hf) merged with fp16 llama2-7b-chat-hf checkpoint.
|
| 4 |
Fine tuning has been performed on a very small/pico Guanaco dataset: manojkumarvohra/guanaco-pico-100-samples
|
| 5 |
https://huggingface.co/datasets/manojkumarvohra/guanaco-pico-100-samples
|
| 6 |
with 100 training samples and 20 validation samples.
|