tahauzumcu
commited on
Commit
•
f6b1b9c
1
Parent(s):
8fc3926
Update README.md
Browse files
README.md
CHANGED
@@ -13,7 +13,7 @@ Base Model: unsloth/llama-3-8b-bnb-4bit
|
|
13 |
|
14 |
Training Dataset: A combined dataset of alpaca, dolly and bactrainx which is translated to turkish.
|
15 |
|
16 |
-
Training Method: Fine-tuned with Unsloth,
|
17 |
|
18 |
#TrainingArguments\
|
19 |
PER_DEVICE_BATCH_SIZE: 2\
|
@@ -52,12 +52,11 @@ How to load with unsloth:
|
|
52 |
```commandline
|
53 |
from unsloth import FastLanguageModel
|
54 |
|
55 |
-
max_seq_len =
|
56 |
model, tokenizer = FastLanguageModel.from_pretrained(
|
57 |
model_name="VeriUs/VeriUS-LLM-8b-v0.2",
|
58 |
max_seq_length=max_seq_len,
|
59 |
-
dtype=None
|
60 |
-
load_in_4bit=True
|
61 |
)
|
62 |
FastLanguageModel.for_inference(model) # Enable native 2x faster inference
|
63 |
|
|
|
13 |
|
14 |
Training Dataset: A combined dataset of alpaca, dolly and bactrainx which is translated to turkish.
|
15 |
|
16 |
+
Training Method: Fine-tuned with Unsloth, QLoRA and ORPO
|
17 |
|
18 |
#TrainingArguments\
|
19 |
PER_DEVICE_BATCH_SIZE: 2\
|
|
|
52 |
```commandline
|
53 |
from unsloth import FastLanguageModel
|
54 |
|
55 |
+
max_seq_len = 1024
|
56 |
model, tokenizer = FastLanguageModel.from_pretrained(
|
57 |
model_name="VeriUs/VeriUS-LLM-8b-v0.2",
|
58 |
max_seq_length=max_seq_len,
|
59 |
+
dtype=None
|
|
|
60 |
)
|
61 |
FastLanguageModel.for_inference(model) # Enable native 2x faster inference
|
62 |
|