Upload folder using huggingface_hub
Browse files- README.md +21 -9
- model-1.safetensors +1 -1
README.md
CHANGED
@@ -4,9 +4,11 @@ tags:
|
|
4 |
- mergekit
|
5 |
- lazymergekit
|
6 |
- abhishek/autotrain-llama3-8b-open-hermes-sft
|
|
|
7 |
- DiscoResearch/Llama3_DiscoLM_German_8b_v0.1_experimental
|
8 |
base_model:
|
9 |
- abhishek/autotrain-llama3-8b-open-hermes-sft
|
|
|
10 |
- DiscoResearch/Llama3_DiscoLM_German_8b_v0.1_experimental
|
11 |
---
|
12 |
|
@@ -14,24 +16,34 @@ base_model:
|
|
14 |
|
15 |
llama3-discolm-orpo-t2 is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
|
16 |
* [abhishek/autotrain-llama3-8b-open-hermes-sft](https://huggingface.co/abhishek/autotrain-llama3-8b-open-hermes-sft)
|
|
|
17 |
* [DiscoResearch/Llama3_DiscoLM_German_8b_v0.1_experimental](https://huggingface.co/DiscoResearch/Llama3_DiscoLM_German_8b_v0.1_experimental)
|
18 |
|
19 |
## 🧩 Configuration
|
20 |
|
21 |
```yaml
|
22 |
models:
|
23 |
-
-
|
24 |
-
model: abhishek/autotrain-llama3-8b-open-hermes-sft
|
25 |
parameters:
|
26 |
-
|
27 |
-
|
28 |
-
|
29 |
parameters:
|
30 |
-
|
31 |
-
|
32 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
33 |
dtype: bfloat16
|
34 |
-
random_seed: 0
|
35 |
```
|
36 |
|
37 |
## 💻 Usage
|
|
|
4 |
- mergekit
|
5 |
- lazymergekit
|
6 |
- abhishek/autotrain-llama3-8b-open-hermes-sft
|
7 |
+
- cognitivecomputations/dolphin-2.9-llama3-8b
|
8 |
- DiscoResearch/Llama3_DiscoLM_German_8b_v0.1_experimental
|
9 |
base_model:
|
10 |
- abhishek/autotrain-llama3-8b-open-hermes-sft
|
11 |
+
- cognitivecomputations/dolphin-2.9-llama3-8b
|
12 |
- DiscoResearch/Llama3_DiscoLM_German_8b_v0.1_experimental
|
13 |
---
|
14 |
|
|
|
16 |
|
17 |
llama3-discolm-orpo-t2 is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
|
18 |
* [abhishek/autotrain-llama3-8b-open-hermes-sft](https://huggingface.co/abhishek/autotrain-llama3-8b-open-hermes-sft)
|
19 |
+
* [cognitivecomputations/dolphin-2.9-llama3-8b](https://huggingface.co/cognitivecomputations/dolphin-2.9-llama3-8b)
|
20 |
* [DiscoResearch/Llama3_DiscoLM_German_8b_v0.1_experimental](https://huggingface.co/DiscoResearch/Llama3_DiscoLM_German_8b_v0.1_experimental)
|
21 |
|
22 |
## 🧩 Configuration
|
23 |
|
24 |
```yaml
|
25 |
models:
|
26 |
+
- model: abhishek/autotrain-llama3-8b-open-hermes-sft
|
|
|
27 |
parameters:
|
28 |
+
density: 0.5
|
29 |
+
weight: 0.4
|
30 |
+
- model: cognitivecomputations/dolphin-2.9-llama3-8b
|
31 |
parameters:
|
32 |
+
density: 0.5
|
33 |
+
weight: 0.3
|
34 |
+
- model: DiscoResearch/Llama3_DiscoLM_German_8b_v0.1_experimental
|
35 |
+
parameters:
|
36 |
+
density: 0.6
|
37 |
+
weight: [0, 0.3, 0.7, 1]
|
38 |
+
# - filter: mlp
|
39 |
+
# value: 0.5
|
40 |
+
# - value: 0.3
|
41 |
+
merge_method: ties
|
42 |
+
base_model: mlabonne/OrpoLlama-3-8B
|
43 |
+
parameters:
|
44 |
+
normalize: true
|
45 |
+
int8_mask: true
|
46 |
dtype: bfloat16
|
|
|
47 |
```
|
48 |
|
49 |
## 💻 Usage
|
model-1.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1979781432
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1d4176e7db405441843d00a3105c3a50e180c584b0676a7542a4987c1aeb7c9d
|
3 |
size 1979781432
|