Update model
Browse files- README.md +13 -9
- model-00001-of-00003.safetensors +1 -1
- model-00002-of-00003.safetensors +1 -1
- model-00003-of-00003.safetensors +1 -1
README.md
CHANGED
@@ -16,7 +16,7 @@ This model was finetuned using the [german-news-titles](https://huggingface.co/d
|
|
16 |
|
17 |
Use the following prompt instruction that was used during the training process:
|
18 |
|
19 |
-
`Erstelle einen Titelvorschlag für folgenden Artikel:`
|
20 |
|
21 |
## Example
|
22 |
|
@@ -37,18 +37,22 @@ Training sources: https://github.com/Jotschi/mistral-7b_german-news-titles
|
|
37 |
|
38 |
Hyperparams used to train this model:
|
39 |
|
40 |
-
| Parameter
|
41 |
-
|
42 |
-
| gradient_accumulation_steps
|
43 |
-
| learning_rate
|
44 |
-
| epochs
|
45 |
-
|
|
|
|
|
46 |
|
47 |
Training template:
|
48 |
|
49 |
```python
|
50 |
-
|
51 |
-
|
|
|
|
|
52 |
{"role": "assistant", "content": "Titelvorschlag: " + title},
|
53 |
]
|
54 |
```
|
|
|
16 |
|
17 |
Use the following prompt instruction that was used during the training process:
|
18 |
|
19 |
+
`Erstelle einen 14 Wörter langen Titelvorschlag für folgenden Artikel:`
|
20 |
|
21 |
## Example
|
22 |
|
|
|
37 |
|
38 |
Hyperparams used to train this model:
|
39 |
|
40 |
+
| Parameter | Value |
|
41 |
+
|--------------------------------|-------|
|
42 |
+
| gradient_accumulation_steps | 2 |
|
43 |
+
| learning_rate | 2e-4 |
|
44 |
+
| epochs | 3 |
|
45 |
+
| lora_r | 64 |
|
46 |
+
| lora_alpha | 16 |
|
47 |
+
| max_seq_length | 256 |
|
48 |
|
49 |
Training template:
|
50 |
|
51 |
```python
|
52 |
+
count=count_words(title)
|
53 |
+
prompt="Erstelle einen " + str(count) + " Wörter langen Titelvorschlag für folgenden Artikel:\n" + text
|
54 |
+
chat = [
|
55 |
+
{"role": "user", "content": prompt},
|
56 |
{"role": "assistant", "content": "Titelvorschlag: " + title},
|
57 |
]
|
58 |
```
|
model-00001-of-00003.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4943162240
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cda88c4e1528832ef5b62da01091ff2c8d6ebb564acb36248721a82d3951e368
|
3 |
size 4943162240
|
model-00002-of-00003.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4999819232
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:eca927d08d7ed8cb694925ecb756e10554f5175593f8f6f115c22d2a48acd463
|
3 |
size 4999819232
|
model-00003-of-00003.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4540516256
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4f632dc4a94c34d5ade434dca81ef3e3d7432b3a56db5f635fc1860ba72c8239
|
3 |
size 4540516256
|