Add pipeline tag and library name
Browse filesThis PR ensures the "how to use" button appears on the top right and the model can be found at https://huggingface.co/models?pipeline_tag=text-generation.
README.md
CHANGED
|
@@ -1,6 +1,9 @@
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
|
|
|
|
|
|
| 3 |
---
|
|
|
|
| 4 |
# lmarena-ai/p2l-360m-bt-01132025
|
| 5 |
|
| 6 |
Large language model (LLM) evaluations typically rely on aggregated metrics like accuracy or human preference, averaging across users and prompts. This averaging obscures user- and prompt-specific variations in model performance.
|
|
@@ -33,7 +36,6 @@ To serve a P2L model, please see our documentation on GitHub: [Serving P2L](http
|
|
| 33 |
|
| 34 |
Note: the P2L model outputs with this structure:
|
| 35 |
|
| 36 |
-
|
| 37 |
```python
|
| 38 |
class P2LOutputs(ModelOutput):
|
| 39 |
coefs: torch.FloatTensor = None # "betas" as described above
|
|
@@ -57,8 +59,6 @@ with open(fname) as fin:
|
|
| 57 |
model_list = json.load(fin)
|
| 58 |
```
|
| 59 |
|
| 60 |
-
|
| 61 |
-
|
| 62 |
### Loading from Pretrained
|
| 63 |
|
| 64 |
To define and load the model:
|
|
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
| 3 |
+
library_name: transformers
|
| 4 |
+
pipeline_tag: text-generation
|
| 5 |
---
|
| 6 |
+
|
| 7 |
# lmarena-ai/p2l-360m-bt-01132025
|
| 8 |
|
| 9 |
Large language model (LLM) evaluations typically rely on aggregated metrics like accuracy or human preference, averaging across users and prompts. This averaging obscures user- and prompt-specific variations in model performance.
|
|
|
|
| 36 |
|
| 37 |
Note: the P2L model outputs with this structure:
|
| 38 |
|
|
|
|
| 39 |
```python
|
| 40 |
class P2LOutputs(ModelOutput):
|
| 41 |
coefs: torch.FloatTensor = None # "betas" as described above
|
|
|
|
| 59 |
model_list = json.load(fin)
|
| 60 |
```
|
| 61 |
|
|
|
|
|
|
|
| 62 |
### Loading from Pretrained
|
| 63 |
|
| 64 |
To define and load the model:
|