Update README.md
Browse files
README.md
CHANGED
|
@@ -9,11 +9,18 @@ library_name: transformers
|
|
| 9 |
tags:
|
| 10 |
- llama-factory
|
| 11 |
- unsloth
|
|
|
|
| 12 |
---
|
| 13 |
# h2o-danube2 with ChatML template
|
| 14 |
|
| 15 |
This model was first fine-tuned with [BAdam](https://arxiv.org/abs/2404.02827 "BAdam: A Memory Efficient Full Parameter Optimization Method for Large Language Models") on [m-a-p/CodeFeedback-Filtered-Instruction](https://huggingface.co/datasets/m-a-p/CodeFeedback-Filtered-Instruction) and [m-a-p/Code-Feedback](https://huggingface.co/datasets/m-a-p/Code-Feedback), unfiltered from the latest [dolphin dataset](https://huggingface.co/datasets/cognitivecomputations/dolphin-2.9.3), using LLama-Factory.
|
| 16 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 17 |
## Template
|
| 18 |
|
| 19 |
```jinja
|
|
|
|
| 9 |
tags:
|
| 10 |
- llama-factory
|
| 11 |
- unsloth
|
| 12 |
+
base_model: h2oai/h2o-danube2-1.8b-base
|
| 13 |
---
|
| 14 |
# h2o-danube2 with ChatML template
|
| 15 |
|
| 16 |
This model was first fine-tuned with [BAdam](https://arxiv.org/abs/2404.02827 "BAdam: A Memory Efficient Full Parameter Optimization Method for Large Language Models") on [m-a-p/CodeFeedback-Filtered-Instruction](https://huggingface.co/datasets/m-a-p/CodeFeedback-Filtered-Instruction) and [m-a-p/Code-Feedback](https://huggingface.co/datasets/m-a-p/Code-Feedback), unfiltered from the latest [dolphin dataset](https://huggingface.co/datasets/cognitivecomputations/dolphin-2.9.3), using LLama-Factory.
|
| 17 |
|
| 18 |
+
## Quants
|
| 19 |
+
|
| 20 |
+
Thanks to [mradermacher](https://huggingface.co/mradermacher)!
|
| 21 |
+
|
| 22 |
+
- [mradermacher/danube2-1.8b-CodeFeedback-GGUF](https://huggingface.co/mradermacher/danube2-1.8b-CodeFeedback-GGUF)
|
| 23 |
+
|
| 24 |
## Template
|
| 25 |
|
| 26 |
```jinja
|