Update README.md
Browse files
README.md
CHANGED
@@ -24,6 +24,38 @@ tags:
|
|
24 |
This model was converted to GGUF format from [`nbeerbower/Dumpling-Qwen2.5-32B-v2`](https://huggingface.co/nbeerbower/Dumpling-Qwen2.5-32B-v2) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
|
25 |
Refer to the [original model card](https://huggingface.co/nbeerbower/Dumpling-Qwen2.5-32B-v2) for more details on the model.
|
26 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
27 |
## Use with llama.cpp
|
28 |
Install llama.cpp through brew (works on Mac and Linux)
|
29 |
|
|
|
24 |
This model was converted to GGUF format from [`nbeerbower/Dumpling-Qwen2.5-32B-v2`](https://huggingface.co/nbeerbower/Dumpling-Qwen2.5-32B-v2) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
|
25 |
Refer to the [original model card](https://huggingface.co/nbeerbower/Dumpling-Qwen2.5-32B-v2) for more details on the model.
|
26 |
|
27 |
+
---
|
28 |
+
[nbeerbower/Rombos-EVAGutenberg-TIES-Qwen2.5-32B](https://huggingface.co/nbeerbower/Rombos-EVAGutenberg-TIES-Qwen2.5-32B) finetuned on:
|
29 |
+
|
30 |
+
* [nbeerbower/GreatFirewall-DPO](https://huggingface.co/datasets/nbeerbower/GreatFirewall-DPO)
|
31 |
+
|
32 |
+
* [nbeerbower/Schule-DPO](https://huggingface.co/datasets/nbeerbower/Schule-DPO)
|
33 |
+
|
34 |
+
* [nbeerbower/Purpura-DPO](https://huggingface.co/datasets/nbeerbower/Purpura-DPO)
|
35 |
+
|
36 |
+
* [nbeerbower/Arkhaios-DPO](https://huggingface.co/datasets/nbeerbower/Arkhaios-DPO)
|
37 |
+
|
38 |
+
* [jondurbin/truthy-dpo-v0.1](https://huggingface.co/datasets/jondurbin/truthy-dpo-v0.1)
|
39 |
+
|
40 |
+
* [antiven0m/physical-reasoning-dpo](https://huggingface.co/datasets/antiven0m/physical-reasoning-dpo)
|
41 |
+
|
42 |
+
* [flammenai/Date-DPO-NoAsterisks](https://huggingface.co/datasets/flammenai/Date-DPO-NoAsterisks)
|
43 |
+
|
44 |
+
* [flammenai/Prude-Phi3-DPO](https://huggingface.co/datasets/flammenai/Prude-Phi3-DPO)
|
45 |
+
|
46 |
+
* [Atsunori/HelpSteer2-DPO](https://huggingface.co/datasets/Atsunori/HelpSteer2-DPO)
|
47 |
+
|
48 |
+
* [jondurbin/gutenberg-dpo-v0.1](https://huggingface.co/datasets/jondurbin/gutenberg-dpo-v0.1)
|
49 |
+
|
50 |
+
* [nbeerbower/gutenberg2-dpo](https://huggingface.co/datasets/nbeerbower/gutenberg2-dpo)
|
51 |
+
|
52 |
+
* [nbeerbower/gutenberg-moderne-dpo](https://huggingface.co/datasets/nbeerbower/gutenberg-moderne-dpo).
|
53 |
+
|
54 |
+
### Method
|
55 |
+
|
56 |
+
[QLoRA ORPO tuned](https://mlabonne.github.io/blog/posts/2024-04-19_Fine_tune_Llama_3_with_ORPO.html) with 8x A100 for 2 epochs. Rank 64 LoRA, 2e-5 learning rate.
|
57 |
+
|
58 |
+
---
|
59 |
## Use with llama.cpp
|
60 |
Install llama.cpp through brew (works on Mac and Linux)
|
61 |
|