Triangle104
commited on
Update README.md
Browse files
README.md
CHANGED
@@ -13,6 +13,102 @@ base_model: caedencode/Caeden-o1
|
|
13 |
This model was converted to GGUF format from [`caedencode/Caeden-o1`](https://huggingface.co/caedencode/Caeden-o1) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
|
14 |
Refer to the [original model card](https://huggingface.co/caedencode/Caeden-o1) for more details on the model.
|
15 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
16 |
## Use with llama.cpp
|
17 |
Install llama.cpp through brew (works on Mac and Linux)
|
18 |
|
|
|
13 |
This model was converted to GGUF format from [`caedencode/Caeden-o1`](https://huggingface.co/caedencode/Caeden-o1) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
|
14 |
Refer to the [original model card](https://huggingface.co/caedencode/Caeden-o1) for more details on the model.
|
15 |
|
16 |
+
---
|
17 |
+
Model details
|
18 |
+
-
|
19 |
+
CaedenAI is a conversational AI model fine-tuned to provide detailed
|
20 |
+
reasoning in its responses using the Chain-of-Thought (CoT) methodology.
|
21 |
+
It is designed for educational use, enabling users to understand the
|
22 |
+
reasoning process behind answers.
|
23 |
+
|
24 |
+
Developed by: Caeden Rajoo
|
25 |
+
Model type: Conversational AI with CoT reasoning
|
26 |
+
License: Apache 2
|
27 |
+
Finetuned from model: Qwen/Qwen2.5-1.5B
|
28 |
+
Primary Use Case: Education and knowledge expansion
|
29 |
+
|
30 |
+
|
31 |
+
This model is fine-tuned for generating step-by-step reasoning for
|
32 |
+
queries, making it an excellent tool for educational environments and
|
33 |
+
learning applications.
|
34 |
+
|
35 |
+
Uses
|
36 |
+
|
37 |
+
|
38 |
+
|
39 |
+
|
40 |
+
|
41 |
+
|
42 |
+
|
43 |
+
|
44 |
+
|
45 |
+
Direct Use
|
46 |
+
|
47 |
+
|
48 |
+
|
49 |
+
|
50 |
+
This model can be directly applied in:
|
51 |
+
|
52 |
+
|
53 |
+
Educational environments to help students learn with explanations.
|
54 |
+
Applications where detailed reasoning is required for understanding answers.
|
55 |
+
Conversational AI systems that prioritize reasoning over simple answers.
|
56 |
+
|
57 |
+
Out-of-Scope Use
|
58 |
+
|
59 |
+
|
60 |
+
|
61 |
+
|
62 |
+
This model may not be suitable for:
|
63 |
+
|
64 |
+
Scenarios requiring highly specialized domain knowledge not covered in the training data.
|
65 |
+
Tasks requiring real-time response for critical systems (e.g., healthcare, safety).
|
66 |
+
|
67 |
+
Bias, Risks, and Limitations
|
68 |
+
|
69 |
+
|
70 |
+
|
71 |
+
|
72 |
+
The model inherits limitations from its training data and base model.
|
73 |
+
Users should consider potential biases or incomplete information in
|
74 |
+
responses.
|
75 |
+
|
76 |
+
Recommendations
|
77 |
+
|
78 |
+
|
79 |
+
|
80 |
+
|
81 |
+
The model's output should be reviewed for accuracy in critical use cases.
|
82 |
+
Users should ensure that ethical considerations are met when using the model in sensitive environments.
|
83 |
+
|
84 |
+
How to Get Started with the Model
|
85 |
+
|
86 |
+
|
87 |
+
|
88 |
+
|
89 |
+
Here’s how you can load and use CaedenAI:
|
90 |
+
|
91 |
+
|
92 |
+
import torch
|
93 |
+
from transformers import AutoTokenizer, AutoModelForCausalLM
|
94 |
+
|
95 |
+
model = AutoModelForCausalLM.from_pretrained("caedencode/Caeden-o1")
|
96 |
+
tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen2.5-1.5B")
|
97 |
+
|
98 |
+
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
|
99 |
+
model = model.to(device)
|
100 |
+
|
101 |
+
def generate_answer(question):
|
102 |
+
prompt = f"Question: {question}\nReasoning:\n"
|
103 |
+
inputs = tokenizer(prompt, return_tensors="pt").to(device)
|
104 |
+
outputs = model.generate(**inputs, max_length=200, num_beams=5, early_stopping=True)
|
105 |
+
return tokenizer.decode(outputs[0], skip_special_tokens=True)
|
106 |
+
|
107 |
+
question = "What is the largest planet in our solar system?"
|
108 |
+
answer = generate_answer(question)
|
109 |
+
print(answer)
|
110 |
+
|
111 |
+
---
|
112 |
## Use with llama.cpp
|
113 |
Install llama.cpp through brew (works on Mac and Linux)
|
114 |
|