Update README.md
Browse files
README.md
CHANGED
|
@@ -11,7 +11,7 @@ library_name: transformers
|
|
| 11 |
<!-- Provide a quick summary of what the model is/does. -->
|
| 12 |
|
| 13 |
Llama-3-KoEn-8B-xtuner-llava-preview 🌋 is Korean based MutliModal based on Llava architecture, merged with [ChatVector](https://arxiv.org/abs/2310.04799) methods leveraging 2 models:
|
| 14 |
-
1) [beomi/Llama-3-KoEn-8B-preview](https://huggingface.co/beomi/Llama-3-KoEn-8B-preview)
|
| 15 |
2) [xtuner/llava-llama-3-8b-transformers](https://huggingface.co/xtuner/llava-llama-3-8b-transformers)
|
| 16 |
|
| 17 |
## Model Details
|
|
@@ -22,7 +22,7 @@ Llama-3-KoEn-8B-xtuner-llava-preview 🌋 is Korean based MutliModal based on Ll
|
|
| 22 |
- **Model type:** HuggingFace Llava 🌋
|
| 23 |
- **Language(s) (NLP):** Korean, English
|
| 24 |
- **License:** cc-by-nc-sa-4.0 under Llama3 License
|
| 25 |
-
- **Merged from model:** [beomi/Llama-3-KoEn-8B-preview](https://huggingface.co/beomi/Llama-3-KoEn-8B-preview)
|
| 26 |
|
| 27 |
### Direct Use
|
| 28 |
|
|
@@ -32,9 +32,11 @@ Llama-3-KoEn-8B-xtuner-llava-preview 🌋 is Korean based MutliModal based on Ll
|
|
| 32 |
|
| 33 |
> Two version recommended
|
| 34 |
>
|
| 35 |
-
> v1. `revision='a38aac3'`: Basic ChatVector
|
|
|
|
|
|
|
| 36 |
>
|
| 37 |
-
> v2. `revision='4f04d1e'`: Model diff based merging(ref. https://huggingface.co/blog/maywell/llm-feature-transfer)
|
| 38 |
|
| 39 |
```python
|
| 40 |
import requests
|
|
|
|
| 11 |
<!-- Provide a quick summary of what the model is/does. -->
|
| 12 |
|
| 13 |
Llama-3-KoEn-8B-xtuner-llava-preview 🌋 is Korean based MutliModal based on Llava architecture, merged with [ChatVector](https://arxiv.org/abs/2310.04799) methods leveraging 2 models:
|
| 14 |
+
1) [beomi/Llama-3-KoEn-8B-preview](https://huggingface.co/beomi/Llama-3-KoEn-8B-preview)
|
| 15 |
2) [xtuner/llava-llama-3-8b-transformers](https://huggingface.co/xtuner/llava-llama-3-8b-transformers)
|
| 16 |
|
| 17 |
## Model Details
|
|
|
|
| 22 |
- **Model type:** HuggingFace Llava 🌋
|
| 23 |
- **Language(s) (NLP):** Korean, English
|
| 24 |
- **License:** cc-by-nc-sa-4.0 under Llama3 License
|
| 25 |
+
- **Merged from model:** [beomi/Llama-3-KoEn-8B-preview](https://huggingface.co/beomi/Llama-3-KoEn-8B-preview) & [xtuner/llava-llama-3-8b-transformers](https://huggingface.co/xtuner/llava-llama-3-8b-transformers)
|
| 26 |
|
| 27 |
### Direct Use
|
| 28 |
|
|
|
|
| 32 |
|
| 33 |
> Two version recommended
|
| 34 |
>
|
| 35 |
+
> v1. `revision='a38aac3'`: Basic ChatVector, with [25B+ trained KoEn ckpt(rev. d4d25a2)](https://huggingface.co/beomi/Llama-3-KoEn-8B-preview/commit/d4d25a2).
|
| 36 |
+
>
|
| 37 |
+
> v1-1. `revision='0224971'`: Basic ChatVector, with [40B+ trained KoEn ckpt(rev. ad39b32)](https://huggingface.co/beomi/Llama-3-KoEn-8B-preview/commit/ad39b32cd4207f37f61f16e79d3f4020c5b744ef).
|
| 38 |
>
|
| 39 |
+
> v2. `revision='4f04d1e'`: Model diff based merging(ref. https://huggingface.co/blog/maywell/llm-feature-transfer), with [25B+ trained KoEn ckpt(rev. d4d25a2)](https://huggingface.co/beomi/Llama-3-KoEn-8B-preview/commit/d4d25a2).
|
| 40 |
|
| 41 |
```python
|
| 42 |
import requests
|