Update README.md
Browse files
README.md
CHANGED
@@ -1,3 +1,72 @@
|
|
1 |
-
---
|
2 |
-
license: mit
|
3 |
-
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
---
|
4 |
+
|
5 |
+
This is a new kind of model optimization. This model is based on Meta's Llama-3 70B Instruct.
|
6 |
+
|
7 |
+
This research was supported with hardware from the [appliedAI Institute](https://www.appliedai-institute.de/en/), who's goal is to generate and communicate high-quality knowledge about trustworthy AI.
|
8 |
+
|
9 |
+
#### Usage with Transformers AutoModelForCausalLM
|
10 |
+
|
11 |
+
```python
|
12 |
+
from transformers import AutoTokenizer, AutoModelForCausalLM
|
13 |
+
import torch
|
14 |
+
|
15 |
+
model_id = "dnhkng/RYS-Llama3.1-Large"
|
16 |
+
|
17 |
+
tokenizer = AutoTokenizer.from_pretrained(model_id)
|
18 |
+
model = AutoModelForCausalLM.from_pretrained(
|
19 |
+
model_id,
|
20 |
+
torch_dtype=torch.bfloat16,
|
21 |
+
device_map="auto",
|
22 |
+
)
|
23 |
+
|
24 |
+
messages = [
|
25 |
+
{"role": "system", "content": "You are a pirate chatbot who always responds in pirate speak!"},
|
26 |
+
{"role": "user", "content": "Who are you?"},
|
27 |
+
]
|
28 |
+
|
29 |
+
input_ids = tokenizer.apply_chat_template(
|
30 |
+
messages,
|
31 |
+
add_generation_prompt=True,
|
32 |
+
return_tensors="pt"
|
33 |
+
).to(model.device)
|
34 |
+
|
35 |
+
terminators = [
|
36 |
+
tokenizer.eos_token_id,
|
37 |
+
tokenizer.convert_tokens_to_ids("<|eot_id|>")
|
38 |
+
]
|
39 |
+
|
40 |
+
outputs = model.generate(
|
41 |
+
input_ids,
|
42 |
+
max_new_tokens=256,
|
43 |
+
eos_token_id=terminators,
|
44 |
+
do_sample=True,
|
45 |
+
temperature=0.6,
|
46 |
+
top_p=0.9,
|
47 |
+
)
|
48 |
+
response = outputs[0][input_ids.shape[-1]:]
|
49 |
+
print(tokenizer.decode(response, skip_special_tokens=True))
|
50 |
+
```
|
51 |
+
|
52 |
+
|
53 |
+
___________________________________
|
54 |
+
# *ADVERTISING BREAK*
|
55 |
+
|
56 |
+
I’m on the hunt for new challenges and a chance to dive into some exciting research opportunities. Oh, and did I mention I just snagged a top spot on the Open LLM leaderboard? 🎉
|
57 |
+
|
58 |
+
|
59 |
+
|
60 |
+
## CV - Dr David Noel Ng
|
61 |
+
|
62 |
+
|
63 |
+
#### Profile
|
64 |
+
Innovation enthusiast, AI-strategist, and interdisciplinary-tech nerd – that's me! With over a decade of experience in research and project management, my professional journey has been largely shaped by my passion for artificial intelligence and its potential to transform various industries. With a solid background in artificial intelligence and machine learning, coupled with a knack for innovation and problem-solving (and a healthy dose of curiosity), I'm excited to bring my skills to a new team.
|
65 |
+
|
66 |
+
Originally from Australia, where I earned my degrees in Organic Chemistry and Biochemistry, I moved to Germany in 2004. My academic pursuit continued with a Ph.D. in Chemistry at the Max Planck Institute of Biochemistry. Today, I leverage my robust educational background and diverse industry experience to drive AI innovations in a wide range of applications. Hobbies? Lots: I've also built the world's most powerful espresso machine and am working to bring [GLaDOS to life](https://github.com/dnhkng/GlaDOS).
|
67 |
+
|
68 |
+
|
69 |
+
___________________________________
|
70 |
+
I'm based out of Munich, Germany, but I would be interested in working remotely for a team with more compute than my 2x 4090s 🚀
|
71 |
+
|
72 |
+
#### Reach out via [LinkedIn](https://www.linkedin.com/in/dnhkng)
|