Update README.md
Browse files
README.md
CHANGED
@@ -2,7 +2,7 @@
|
|
2 |
license: apache-2.0
|
3 |
---
|
4 |
# ✨ Orion-7B
|
5 |
-
**Orion is based on
|
6 |
*Paper coming soon 😊.*
|
7 |
|
8 |
|
@@ -13,7 +13,7 @@ license: apache-2.0
|
|
13 |
*
|
14 |
⚠️ **This is a raw, fine-tuned model, which should be further instruction-tuned for production level performance.**
|
15 |
|
16 |
-
💥 **Orion LLM
|
17 |
|
18 |
You will need **at least 20-25GB of memory** to swiftly run inference with Orion-7B.
|
19 |
|
@@ -21,7 +21,7 @@ You will need **at least 20-25GB of memory** to swiftly run inference with Orion
|
|
21 |
|
22 |
### Model Description
|
23 |
- **Developed by:** [AttentionX](https://atttentionx.github.io);
|
24 |
-
- **Base model:**
|
25 |
- **Training method: LoRA, llama-adapter, llama-adapterV2, full fine-tuning**
|
26 |
- **Language(s) (NLP):** English;
|
27 |
- **License:** Apache 2.0 license.
|
|
|
2 |
license: apache-2.0
|
3 |
---
|
4 |
# ✨ Orion-7B
|
5 |
+
**Orion is based on alpaca-7B, further trained on the latest deep learning papers published at notable conferences with various PEFT methods. It is made available under the Apache 2.0 license.**
|
6 |
*Paper coming soon 😊.*
|
7 |
|
8 |
|
|
|
13 |
*
|
14 |
⚠️ **This is a raw, fine-tuned model, which should be further instruction-tuned for production level performance.**
|
15 |
|
16 |
+
💥 **Orion LLM requires PyTorch 2.0**
|
17 |
|
18 |
You will need **at least 20-25GB of memory** to swiftly run inference with Orion-7B.
|
19 |
|
|
|
21 |
|
22 |
### Model Description
|
23 |
- **Developed by:** [AttentionX](https://atttentionx.github.io);
|
24 |
+
- **Base model:** alpaca-7B;
|
25 |
- **Training method: LoRA, llama-adapter, llama-adapterV2, full fine-tuning**
|
26 |
- **Language(s) (NLP):** English;
|
27 |
- **License:** Apache 2.0 license.
|