Update README.md
Browse files
README.md
CHANGED
|
@@ -3,7 +3,9 @@ license: apache-2.0
|
|
| 3 |
---
|
| 4 |
# Lite-Mistral-150M-v2-Instruct
|
| 5 |
|
| 6 |
-
This is a Lite series model based on the Mistral architecture, comprising approximately 157 million parameters.
|
|
|
|
|
|
|
| 7 |
|
| 8 |
<a href="https://huggingface.co/OuteAI/Lite-Mistral-150M-v2-Instruct">Lite-Mistral-150M-v2-Instruct</a> <br>
|
| 9 |
<a href="https://huggingface.co/OuteAI/Lite-Mistral-150M-v2-Instruct-GGUF">Lite-Mistral-150M-v2-Instruct-GGUF</a> <br>
|
|
@@ -16,65 +18,80 @@ This is a Lite series model based on the Mistral architecture, comprising approx
|
|
| 16 |
## How coherent is the 150M model?
|
| 17 |
Let's look at real-world examples:
|
| 18 |
|
| 19 |
-
|
| 20 |
-
|
| 21 |
-
|
| 22 |
-
|
| 23 |
-
|
| 24 |
-
<s>
|
| 25 |
-
|
| 26 |
-
<s>
|
| 27 |
-
|
| 28 |
-
|
| 29 |
-
|
| 30 |
-
|
| 31 |
-
|
| 32 |
-
|
| 33 |
-
|
| 34 |
-
|
| 35 |
-
|
| 36 |
-
|
| 37 |
-
|
| 38 |
-
|
| 39 |
-
|
| 40 |
-
|
| 41 |
-
|
| 42 |
-
|
| 43 |
-
|
| 44 |
-
|
| 45 |
-
|
| 46 |
-
|
| 47 |
-
|
| 48 |
-
|
| 49 |
-
|
| 50 |
-
|
| 51 |
-
|
| 52 |
-
|
| 53 |
-
|
| 54 |
-
|
| 55 |
-
|
| 56 |
-
|
| 57 |
-
```
|
| 58 |
-
Input:
|
| 59 |
-
<s>user
|
| 60 |
-
|
| 61 |
-
|
| 62 |
-
|
| 63 |
-
<s>
|
| 64 |
-
|
| 65 |
-
|
| 66 |
-
|
| 67 |
-
|
| 68 |
-
|
| 69 |
-
|
| 70 |
-
|
| 71 |
-
|
| 72 |
-
|
| 73 |
-
|
| 74 |
-
|
| 75 |
-
|
| 76 |
-
|
| 77 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 78 |
|
| 79 |
## Benchmarks:
|
| 80 |
|
|
|
|
| 3 |
---
|
| 4 |
# Lite-Mistral-150M-v2-Instruct
|
| 5 |
|
| 6 |
+
This is a Lite series model based on the Mistral architecture, comprising approximately 157 million parameters. <br>
|
| 7 |
+
The primary goal of this 150-million parameter model was to develop a compact and efficient model capable of operating on a wide range of devices, while maintaining a reasonable level of functionality and coherence for its small size. <br>
|
| 8 |
+
A smaller model scale may lead to challenges in preserving context over multi-turn conversations. Consequently, there is a risk of inconsistent or inaccurate responses.
|
| 9 |
|
| 10 |
<a href="https://huggingface.co/OuteAI/Lite-Mistral-150M-v2-Instruct">Lite-Mistral-150M-v2-Instruct</a> <br>
|
| 11 |
<a href="https://huggingface.co/OuteAI/Lite-Mistral-150M-v2-Instruct-GGUF">Lite-Mistral-150M-v2-Instruct-GGUF</a> <br>
|
|
|
|
| 18 |
## How coherent is the 150M model?
|
| 19 |
Let's look at real-world examples:
|
| 20 |
|
| 21 |
+
<details open>
|
| 22 |
+
<summary>Example 1</summary>
|
| 23 |
+
|
| 24 |
+
```
|
| 25 |
+
Input:
|
| 26 |
+
<s>user
|
| 27 |
+
What is the capital of France?</s>
|
| 28 |
+
<s>assistant
|
| 29 |
+
The capital of France is Paris.</s>
|
| 30 |
+
<s>user
|
| 31 |
+
What is the capital of Spain?</s>
|
| 32 |
+
|
| 33 |
+
Response:
|
| 34 |
+
<s>assistant
|
| 35 |
+
The capital of Spain is Madrid, which is known for its beautiful architecture and rich history.</s>
|
| 36 |
+
```
|
| 37 |
+
|
| 38 |
+
</details>
|
| 39 |
+
|
| 40 |
+
<details open>
|
| 41 |
+
<summary>Example 2</summary>
|
| 42 |
+
|
| 43 |
+
```
|
| 44 |
+
Input:
|
| 45 |
+
<s>user
|
| 46 |
+
Who wrote the play "Romeo and Juliet"?</s>
|
| 47 |
+
|
| 48 |
+
Response:
|
| 49 |
+
<s>assistant
|
| 50 |
+
The play "Romeo and Juliet" was written by William Shakespeare.</s>
|
| 51 |
+
```
|
| 52 |
+
|
| 53 |
+
</details>
|
| 54 |
+
|
| 55 |
+
|
| 56 |
+
<details>
|
| 57 |
+
<summary>Example 3</summary>
|
| 58 |
+
|
| 59 |
+
```
|
| 60 |
+
Input:
|
| 61 |
+
<s>user
|
| 62 |
+
Tell me a joke</s>
|
| 63 |
+
|
| 64 |
+
Response:
|
| 65 |
+
<s>assistant
|
| 66 |
+
Why did the chicken cross the playground? Because it wanted to see who could get the ball!</s>
|
| 67 |
+
```
|
| 68 |
+
|
| 69 |
+
</details>
|
| 70 |
+
|
| 71 |
+
<details>
|
| 72 |
+
<summary>Example 4 (RP)</summary>
|
| 73 |
+
|
| 74 |
+
```
|
| 75 |
+
Input:
|
| 76 |
+
<s>user
|
| 77 |
+
Let's roleplay. I'll be a customer at a restaurant, and you be the waiter. Ready?</s>
|
| 78 |
+
<s>assistant
|
| 79 |
+
Certainly! I'll play the role of a waiter. Please go ahead and start the roleplay when you're ready.</s>
|
| 80 |
+
<s>user
|
| 81 |
+
Hello, I'd like to see the menu please.</s>
|
| 82 |
+
<s>assistant
|
| 83 |
+
Good evening, sir! Welcome to our restaurant. Here's our menu for today. May I recommend our chef's special, the grilled salmon with lemon butter sauce? Let me know if you have any questions about our dishes.</s>
|
| 84 |
+
<s>user
|
| 85 |
+
I'll have the salmon. What wines do you recommend to go with it?</s>
|
| 86 |
+
|
| 87 |
+
Response:
|
| 88 |
+
<s> assistant
|
| 89 |
+
To go with your salmon, we suggest a pair of red-tailed or white-tailed jackfights. The grilled salmon is creamy and has a nice acidity. The lemon butter sauce is a great addition to this dish.</s>
|
| 90 |
+
```
|
| 91 |
+
|
| 92 |
+
</details>
|
| 93 |
+
|
| 94 |
+
The model shows some promise in understanding context related to simple requests, but it's clear that it still struggles with more complex or nuanced situations.
|
| 95 |
|
| 96 |
## Benchmarks:
|
| 97 |
|