Hugging Face's logo

Jotschi
/
Mistral-7B-v0.1_german-news-titles-v1

Text Generation
Transformers
Safetensors
mistral
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
Jotschi commited on
Commit
0c9e136
•
1 Parent(s): 4b70c2f

Update model

Browse files
Files changed (4) hide show
  1. README.md +13 -9
  2. model-00001-of-00003.safetensors +1 -1
  3. model-00002-of-00003.safetensors +1 -1
  4. 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 | Value |
41
- |----------------|-------|
42
- | gradient_accumulation_steps | 2 |
43
- | learning_rate | 2e-4 |
44
- | epochs | 1 |
45
-
 
 
46
 
47
  Training template:
48
 
49
  ```python
50
- chat = [
51
- {"role": "user", "content": "Erstelle einen Titelvorschlag für folgenden Artikel:\n" + text},
 
 
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:ded43a454ff29074edb53ae31497f48361cae80ac020f58d4f8bd47a2dfb511b
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:a7ec221429be20615a20521f5e920c04098f0d1350b414ee27d38a9f8ee74e13
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:d34b7ce4331520b7e4b9245729625dd6053d74d7986ef5378cb4ad53112e96c1
3
  size 4540516256
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f632dc4a94c34d5ade434dca81ef3e3d7432b3a56db5f635fc1860ba72c8239
3
  size 4540516256