Upload folder using huggingface_hub
Browse files
README.md
ADDED
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
tags:
|
4 |
+
- Gemma Sprint
|
5 |
+
- GDE
|
6 |
+
- Google Cloud Champions Innovator
|
7 |
+
- Google Cloud Research Innovator
|
8 |
+
creator: Rabimba
|
9 |
+
---
|
10 |
+
|
11 |
+
# Gemma-rk-master1
|
12 |
+
|
13 |
+
The strength of this model is
|
14 |
+
- Coding
|
15 |
+
- Poetic
|
16 |
+
- DPO Trained
|
17 |
+
|
18 |
+
## 💻 Usage
|
19 |
+
|
20 |
+
```python
|
21 |
+
!pip install -qU transformers bitsandbytes accelerate
|
22 |
+
|
23 |
+
from transformers import AutoTokenizer
|
24 |
+
import transformers
|
25 |
+
import torch
|
26 |
+
|
27 |
+
model = "rabimba/Gemma-rk-master1"
|
28 |
+
|
29 |
+
tokenizer = AutoTokenizer.from_pretrained(model)
|
30 |
+
pipeline = transformers.pipeline(
|
31 |
+
"text-generation",
|
32 |
+
model=model,
|
33 |
+
model_kwargs={"torch_dtype": torch.float16, "load_in_4bit": True},
|
34 |
+
)
|
35 |
+
|
36 |
+
messages = [{"role": "user", "content": "Explain what a LLM is in less than 100 words."}]
|
37 |
+
prompt = pipeline.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
|
38 |
+
outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
|
39 |
+
print(outputs[0]["generated_text"])
|
40 |
+
```
|