Training in progress, step 5123
Browse files- README.md +17 -82
- model-00001-of-00004.safetensors +1 -1
- model-00002-of-00004.safetensors +1 -1
- model-00003-of-00004.safetensors +1 -1
- model-00004-of-00004.safetensors +1 -1
README.md
CHANGED
|
@@ -15,96 +15,31 @@ licence: license
|
|
| 15 |
This model is a fine-tuned version of [unsloth/Ministral-3-8B-Base-2512](https://huggingface.co/unsloth/Ministral-3-8B-Base-2512).
|
| 16 |
It has been trained using [TRL](https://github.com/huggingface/trl).
|
| 17 |
|
| 18 |
-
|
| 19 |
-
'Görev: Metni etiketle, özetle, trivia hazırla ve terimleri çevir.'
|
| 20 |
-
|
| 21 |
-
'Görev: Metni etiketle ve İngilizceye çevir.'
|
| 22 |
-
|
| 23 |
-
---
|
| 24 |
-
|
| 25 |
-
'Görev: Metinden soru ve cevaplar hazırla.
|
| 26 |
-
Hedef uzunluk: kısa'
|
| 27 |
-
|
| 28 |
-
'Görev: Metinden soru ve cevaplar hazırla.
|
| 29 |
-
Hedef uzunluk: orta'
|
| 30 |
-
|
| 31 |
-
'Görev: Metinden soru ve cevaplar hazırla.
|
| 32 |
-
Hedef uzunluk: uzun'
|
| 33 |
-
|
| 34 |
-
---
|
| 35 |
|
| 36 |
-
|
| 37 |
-
|
| 38 |
-
|
| 39 |
-
'Görev: Metni etiketle ve özetle.
|
| 40 |
-
Hedef uzunluk: orta'
|
| 41 |
-
|
| 42 |
-
'Görev: Metni etiketle ve özetle.
|
| 43 |
-
Hedef uzunluk: uzun'
|
| 44 |
-
|
| 45 |
-
---
|
| 46 |
-
|
| 47 |
-
'Görev: Metni etiketle ve bir makale oluştur.
|
| 48 |
-
Hedef uzunluk: kısa'
|
| 49 |
-
|
| 50 |
-
'Görev: Metni etiketle ve bir makale oluştur.
|
| 51 |
-
Hedef uzunluk: orta'
|
| 52 |
-
|
| 53 |
-
'Görev: Metni etiketle ve bir makale oluştur.
|
| 54 |
-
Hedef uzunluk: uzun'
|
| 55 |
-
|
| 56 |
-
---
|
| 57 |
|
| 58 |
-
|
| 59 |
-
|
| 60 |
-
|
| 61 |
-
|
| 62 |
-
|
| 63 |
-
|
| 64 |
-
'Görev: Metinden bir iç konuşma (monolog) hazırla.
|
| 65 |
-
Hedef uzunluk: uzun'
|
| 66 |
-
|
| 67 |
-
---
|
| 68 |
-
|
| 69 |
-
'Görev: Metinden bir diyalog hazırla.
|
| 70 |
-
Hedef uzunluk: kısa'
|
| 71 |
-
|
| 72 |
-
'Görev: Metinden bir diyalog hazırla.
|
| 73 |
-
Hedef uzunluk: orta'
|
| 74 |
-
|
| 75 |
-
'Görev: Metinden bir diyalog hazırla.
|
| 76 |
-
Hedef uzunluk: uzun'
|
| 77 |
-
|
| 78 |
-
---
|
| 79 |
-
|
| 80 |
-
'Görev: Metinden Kullanıcı/Asistan diyaloğu üret.
|
| 81 |
-
Hedef uzunluk: kısa'
|
| 82 |
-
|
| 83 |
-
'Görev: Metinden Kullanıcı/Asistan diyaloğu üret.
|
| 84 |
-
Hedef uzunluk: orta'
|
| 85 |
-
|
| 86 |
-
'Görev: Metinden Kullanıcı/Asistan diyaloğu üret.
|
| 87 |
-
Hedef uzunluk: uzun'
|
| 88 |
-
|
| 89 |
-
---
|
| 90 |
|
| 91 |
-
|
| 92 |
-
Hedef uzunluk: yok'
|
| 93 |
|
| 94 |
-
|
| 95 |
-
Hedef uzunluk: yok'
|
| 96 |
|
| 97 |
-
---
|
| 98 |
|
| 99 |
-
|
| 100 |
-
Hedef uzunluk: kısa'
|
| 101 |
|
| 102 |
-
|
| 103 |
-
Hedef uzunluk: orta'
|
| 104 |
|
| 105 |
-
|
| 106 |
-
|
| 107 |
-
|
|
|
|
|
|
|
| 108 |
|
| 109 |
## Citations
|
| 110 |
|
|
|
|
| 15 |
This model is a fine-tuned version of [unsloth/Ministral-3-8B-Base-2512](https://huggingface.co/unsloth/Ministral-3-8B-Base-2512).
|
| 16 |
It has been trained using [TRL](https://github.com/huggingface/trl).
|
| 17 |
|
| 18 |
+
## Quick start
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 19 |
|
| 20 |
+
```python
|
| 21 |
+
from transformers import pipeline
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 22 |
|
| 23 |
+
question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
|
| 24 |
+
generator = pipeline("text-generation", model="Ba2han/mistral_augment-multi-ft", device="cuda")
|
| 25 |
+
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
|
| 26 |
+
print(output["generated_text"])
|
| 27 |
+
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 28 |
|
| 29 |
+
## Training procedure
|
|
|
|
| 30 |
|
| 31 |
+
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/batuhan409/huggingface/runs/7gnkzia9)
|
|
|
|
| 32 |
|
|
|
|
| 33 |
|
| 34 |
+
This model was trained with SFT.
|
|
|
|
| 35 |
|
| 36 |
+
### Framework versions
|
|
|
|
| 37 |
|
| 38 |
+
- TRL: 0.24.0
|
| 39 |
+
- Transformers: 5.0.0.dev0
|
| 40 |
+
- Pytorch: 2.9.1
|
| 41 |
+
- Datasets: 4.3.0
|
| 42 |
+
- Tokenizers: 0.22.1
|
| 43 |
|
| 44 |
## Citations
|
| 45 |
|
model-00001-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4999724576
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c5884a2b2d0cb5f9f7ca81335e3b0d762d15b2252db21b4779820322b56e2f89
|
| 3 |
size 4999724576
|
model-00002-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4999820896
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:79ff0c366937267e75c580f2bea22c720ba07e29d85ee8f3ee4d640d862f0ded
|
| 3 |
size 4999820896
|
model-00003-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4915917688
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:42787d9c96a32b393520a969b248710e8e163537f516a09795a30a71fee21a8f
|
| 3 |
size 4915917688
|
model-00004-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2920659992
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ce62f63d3d702fc3e51d44d342fcda4fc690231d3b3e7f9eb9c2c5b6f38f0fb1
|
| 3 |
size 2920659992
|