bafifi4972
commited on
Update README.md
Browse files
README.md
CHANGED
@@ -2,19 +2,8 @@
|
|
2 |
license: gpl-3.0
|
3 |
---
|
4 |
|
5 |
-
|
6 |
-
|
7 |
-
**Architecture:** Nvom-preview-4b has 3.8B parameters and is a dense decoder-only Transformer model using the same tokenizer as Phi-3 Mini.<br>
|
8 |
-
**Inputs:** Text. It is best suited for prompts using chat format.<br>
|
9 |
-
**Context length:** 128K tokens<br>
|
10 |
-
**GPUs:** 512 H100-80G<br>
|
11 |
-
**Training time:** 10 days<br>
|
12 |
-
**Training data:** 3.4T tokens<br>
|
13 |
-
**Outputs:** Generated text in response to the input<br>
|
14 |
-
**Dates:** Trained between June and August 2024<br>
|
15 |
-
**Status:** This is a static model trained on an offline dataset with cutoff date October 2023 for publicly available data. Future versions of the tuned models may be released as we improve models.<br>
|
16 |
-
**Supported languages:** Arabic, Chinese, Czech, Danish, Dutch, English, Finnish, French, German, Hebrew, Hungarian, Italian, Japanese, Korean, Norwegian, Polish, Portuguese, Russian, Spanish, Swedish, Thai, Turkish, Ukrainian<br>
|
17 |
-
**Release date:** August 2024<br>
|
18 |
|
19 |
q4_k_m to more optimize!
|
20 |
|
|
|
2 |
license: gpl-3.0
|
3 |
---
|
4 |
|
5 |
+
# Testing model
|
6 |
+
You can test the model on https://huggingface.co/spaces/nvomai/nvom-phi-3.5-mini-3b
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
7 |
|
8 |
q4_k_m to more optimize!
|
9 |
|