Spaces:
Running
Running
rename leaderboard
Browse files- README.md +2 -2
- src/about.py +2 -32
README.md
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
---
|
2 |
-
title:
|
3 |
emoji: 🥇
|
4 |
colorFrom: green
|
5 |
colorTo: indigo
|
@@ -9,4 +9,4 @@ pinned: true
|
|
9 |
license: apache-2.0
|
10 |
---
|
11 |
|
12 |
-
#
|
|
|
1 |
---
|
2 |
+
title: LLM Leaderboard for CRM
|
3 |
emoji: 🥇
|
4 |
colorFrom: green
|
5 |
colorTo: indigo
|
|
|
9 |
license: apache-2.0
|
10 |
---
|
11 |
|
12 |
+
# LLM Leaderboard for CRM
|
src/about.py
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
# Your leaderboard name
|
2 |
-
TITLE = """<h1 align="center" id="space-title">
|
3 |
<h3>Assess which LLMs are accurate enough or need fine-tuning, and weigh this versus tradeoffs of speed, costs, and trust and safety. This is based on human manual and automated evaluation with real operational CRM data per use case.</h3>
|
4 |
"""
|
5 |
|
@@ -26,41 +26,11 @@ LLM_BENCHMARKS_TEXT = """
|
|
26 |
13) Cost per request for self-hosted models assume a minimal frequency of calling the model, since the costs are per hour. All latencies / cost assume a single user at a time.
|
27 |
"""
|
28 |
|
29 |
-
EVALUATION_QUEUE_TEXT = """
|
30 |
-
## Some good practices before submitting a model
|
31 |
-
|
32 |
-
### 1) Make sure you can load your model and tokenizer using AutoClasses:
|
33 |
-
```python
|
34 |
-
from transformers import AutoConfig, AutoModel, AutoTokenizer
|
35 |
-
config = AutoConfig.from_pretrained("your model name", revision=revision)
|
36 |
-
model = AutoModel.from_pretrained("your model name", revision=revision)
|
37 |
-
tokenizer = AutoTokenizer.from_pretrained("your model name", revision=revision)
|
38 |
-
```
|
39 |
-
If this step fails, follow the error messages to debug your model before submitting it. It's likely your model has been improperly uploaded.
|
40 |
-
|
41 |
-
Note: make sure your model is public!
|
42 |
-
Note: if your model needs `use_remote_code=True`, we do not support this option yet but we are working on adding it, stay posted!
|
43 |
-
|
44 |
-
### 2) Convert your model weights to [safetensors](https://huggingface.co/docs/safetensors/index)
|
45 |
-
It's a new format for storing weights which is safer and faster to load and use. It will also allow us to add the number of parameters of your model to the `Extended Viewer`!
|
46 |
-
|
47 |
-
### 3) Make sure your model has an open license!
|
48 |
-
This is a leaderboard for Open LLMs, and we'd love for as many people as possible to know they can use your model 🤗
|
49 |
-
|
50 |
-
### 4) Fill up your model card
|
51 |
-
When we add extra information about models to the leaderboard, it will be automatically taken from the model card
|
52 |
-
|
53 |
-
## In case of model failure
|
54 |
-
If your model is displayed in the `FAILED` category, its execution stopped.
|
55 |
-
Make sure you have followed the above steps first.
|
56 |
-
If everything is done, check you can launch the EleutherAIHarness on your model locally, using the above command without modifications (you can add `--limit` to limit the number of examples per task).
|
57 |
-
"""
|
58 |
-
|
59 |
CITATION_BUTTON_LABEL = "Copy the following snippet to cite these results"
|
60 |
CITATION_BUTTON_TEXT = r"""
|
61 |
@misc{crm-llm-leaderboard,
|
62 |
author = {Salesforce AI},
|
63 |
-
title = {
|
64 |
year = {2024},
|
65 |
publisher = {Salesforce AI},
|
66 |
howpublished = "\url{https://https://huggingface.co/spaces/Salesforce/crm_llm_leaderboard}"
|
|
|
1 |
# Your leaderboard name
|
2 |
+
TITLE = """<h1 align="center" id="space-title">LLM Leaderboard for CRM</h1>
|
3 |
<h3>Assess which LLMs are accurate enough or need fine-tuning, and weigh this versus tradeoffs of speed, costs, and trust and safety. This is based on human manual and automated evaluation with real operational CRM data per use case.</h3>
|
4 |
"""
|
5 |
|
|
|
26 |
13) Cost per request for self-hosted models assume a minimal frequency of calling the model, since the costs are per hour. All latencies / cost assume a single user at a time.
|
27 |
"""
|
28 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
29 |
CITATION_BUTTON_LABEL = "Copy the following snippet to cite these results"
|
30 |
CITATION_BUTTON_TEXT = r"""
|
31 |
@misc{crm-llm-leaderboard,
|
32 |
author = {Salesforce AI},
|
33 |
+
title = {LLM Leaderboard for CRM},
|
34 |
year = {2024},
|
35 |
publisher = {Salesforce AI},
|
36 |
howpublished = "\url{https://https://huggingface.co/spaces/Salesforce/crm_llm_leaderboard}"
|