Update README.md
Browse files
README.md
CHANGED
@@ -3,11 +3,14 @@ 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>
|
10 |
|
|
|
11 |
## Improvements from v1:
|
12 |
- Extended Training: Further refinement of the model, resulting in improved benchmark performance and overall text generation quality.
|
13 |
- Tokenizer changes.
|
@@ -15,65 +18,80 @@ This is a Lite series model based on the Mistral architecture, comprising approx
|
|
15 |
## How coherent is the 150M model?
|
16 |
Let's look at real-world examples:
|
17 |
|
18 |
-
|
19 |
-
|
20 |
-
|
21 |
-
|
22 |
-
|
23 |
-
<s>
|
24 |
-
|
25 |
-
<s>
|
26 |
-
|
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 |
-
Input:
|
58 |
-
<s>user
|
59 |
-
|
60 |
-
|
61 |
-
|
62 |
-
<s>
|
63 |
-
|
64 |
-
|
65 |
-
|
66 |
-
|
67 |
-
|
68 |
-
|
69 |
-
|
70 |
-
|
71 |
-
|
72 |
-
|
73 |
-
|
74 |
-
|
75 |
-
|
76 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
77 |
|
78 |
## Benchmarks:
|
79 |
|
|
|
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>
|
12 |
|
13 |
+
|
14 |
## Improvements from v1:
|
15 |
- Extended Training: Further refinement of the model, resulting in improved benchmark performance and overall text generation quality.
|
16 |
- Tokenizer changes.
|
|
|
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 |
|