pseudotensor
commited on
Commit
•
dbccff2
1
Parent(s):
58833fb
Update README.md
Browse files
README.md
CHANGED
@@ -18,10 +18,8 @@ datasets:
|
|
18 |
|
19 |
H2O.ai's `h2oai/h2ogpt-research-oig-oasst1-512-30b` is a 30 billion parameter instruction-following large language model for research use only.
|
20 |
|
21 |
-
|
22 |
-
|
23 |
-
|
24 |
-
|
25 |
-
|
26 |
-
|
27 |
|
|
|
|
18 |
|
19 |
H2O.ai's `h2oai/h2ogpt-research-oig-oasst1-512-30b` is a 30 billion parameter instruction-following large language model for research use only.
|
20 |
|
21 |
+
- Base model [decapoda-research/llama-30b-hf](https://huggingface.co/decapoda-research/llama-30b-hf)
|
22 |
+
- LORA [h2oai/h2ogpt-research-oig-oasst1-512-30b-lora](https://huggingface.co/h2oai/h2ogpt-research-oig-oasst1-512-30b-lora)
|
23 |
+
- This HF version was built using [export script](https://huggingface.co/h2oai/h2ogpt-research-oig-oasst1-512-30b-lora#build-hf-model)
|
|
|
|
|
|
|
24 |
|
25 |
+
All details about performance etc. are provided in the [LORA Model Card](https://huggingface.co/h2oai/h2ogpt-research-oig-oasst1-512-30b-lora).
|