Update README.md
Browse files
README.md
CHANGED
@@ -7,16 +7,62 @@ tags:
|
|
7 |
- transformers
|
8 |
- unsloth
|
9 |
- mistral
|
10 |
-
-
|
11 |
base_model: unsloth/mistral-7b-bnb-4bit
|
|
|
|
|
12 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
13 |
|
|
|
|
|
|
|
14 |
# Uploaded model
|
15 |
|
16 |
- **Developed by:** liminerity
|
17 |
- **License:** apache-2.0
|
18 |
- **Finetuned from model :** unsloth/mistral-7b-bnb-4bit
|
19 |
-
|
20 |
This mistral model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
|
21 |
|
22 |
-
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|
|
|
7 |
- transformers
|
8 |
- unsloth
|
9 |
- mistral
|
10 |
+
- trl
|
11 |
base_model: unsloth/mistral-7b-bnb-4bit
|
12 |
+
datasets:
|
13 |
+
- gate369/Alpaca-Star
|
14 |
---
|
15 |
+
- QSTAR
|
16 |
+
- I think this model is proof of my theory that you dont need a special architecture to train a llm to reason. The techniques i imployed to make this could
|
17 |
+
be greatly expanded on and coupled with a agent system to achieve a functioning low cost agi system.
|
18 |
+
-Steps: -Loss:
|
19 |
+
- 356 - 0.014300
|
20 |
+
- 357 - 0.012400
|
21 |
+
- 358 - 0.016800
|
22 |
+
- 359 - 0.022200
|
23 |
+
- 360 - 0.015000
|
24 |
+
- 361 - 0.018300
|
25 |
+
- 362 - 0.016000
|
26 |
+
- 363 - 0.019000
|
27 |
+
- 364 - 0.017600
|
28 |
+
- 365 - 0.015600
|
29 |
+
- 366 - 0.016700
|
30 |
+
- 367 - 0.016400
|
31 |
+
- 368 - 0.016600
|
32 |
+
- 369 - 0.017600
|
33 |
+
- heres a conversation i had with the model:
|
34 |
+
- user: "hi there. id like to build a time machine. how might i go about achieving this?"
|
35 |
+
- assistant: "|startthought| To build a time machine, I need to figure out how to move through time just like we move through space. That means finding a way to change my
|
36 |
+
frame of reference from the stationary Earth to one that's moving forward in time. |endthought| One approach is to use Einstein's theory of relativity and massive
|
37 |
+
objects with strong gravitational fields, like black holes or neutron stars. By warping spacetime, these objects can slow down time for an observer passing by.
|
38 |
+
Another idea is to explore quantum mechanics and the notion of entanglement between particles. If I could create a pair of entangled particles and keep one, the
|
39 |
+
other might appear elsewhere in space-time, effectively teleporting it through time. Yet another approach is to look at cosmic rays and high-energy particle
|
40 |
+
collisions, which can create short-lived particles that seem to violate the forward-in-time direction of time. Understanding these phenomena might lead to a
|
41 |
+
way to control time flow. Ultimately, building a functional time machine will require advancing our understanding of these fundamental physical principles and
|
42 |
+
finding a way to apply them technologically. It's a grand challenge that has captivated scientists and science fiction writers alike for centuries."
|
43 |
+
- user: "how might we make use of this phenomena to create a functioning time machine?"
|
44 |
+
- assistant: "|startthought| To make use of these phenomenas to create a funcitoning time machine, we need to find a way to control and harness them technologically.
|
45 |
+
That could mean developing advanced gravitational lensing techniques to manipulate space-time around massive objects, exploring quantum entanglement
|
46 |
+
in more complex systems, or finding a way to generate the high-energy particle collision conditions needed to create tachyons. It's likely that we'll need to
|
47 |
+
understand and combine multiple approaches to make a functional time machine a reality. |endthought| One approach might be to focus on developing advanced
|
48 |
+
gravitational lensing techniques. This could allow us to control the warping of space-time around massive objects like black holes or neutrino stars, creating
|
49 |
+
stable time vortexes that we can pass through. Another idea is to explore quantum entanglement in more complex systems. If we could create and maintain a
|
50 |
+
large-scale entangled state between two particles, we might be able to use one particle as a clock while the other appears elsewhere in space-time, effectively
|
51 |
+
teleporting it through time. Yet another approach is to look at high-energy particle collision phenomenas like those created in large hadron colliders or
|
52 |
+
supernova explosions. These events can generate short-lived particles called tachyons, which seem to move faster than the speed of light and violate the
|
53 |
+
forward-in-time direction of time. If we could understand and control this phenomena, we might be able to create a stable source of tachyons that could be
|
54 |
+
used to power a time machine. Ultimately, making a functional time machine will require advancing our understanding of these fundamental physical principles
|
55 |
+
and finding a way to apply them technologically. It's a grand challenge that has captivaed scientists and science fiction writers alike for centuries."
|
56 |
|
57 |
+
|
58 |
+
|
59 |
+
- the data set will need more work but this shows insane potential
|
60 |
# Uploaded model
|
61 |
|
62 |
- **Developed by:** liminerity
|
63 |
- **License:** apache-2.0
|
64 |
- **Finetuned from model :** unsloth/mistral-7b-bnb-4bit
|
65 |
+
This model was trained on a alpaca based dataset i made using perplexity and claude 3. The dataset is meant to encourage the llm the think before speaking
|
66 |
This mistral model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
|
67 |
|
68 |
+
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|