Upload 5 files
Browse files- README.md +50 -1
- config.json +32 -0
- generation_config.json +6 -0
- training_args.bin +3 -0
- vocab.json +0 -0
README.md
CHANGED
@@ -1,3 +1,52 @@
|
|
1 |
---
|
2 |
-
license: cc-by-nc-
|
3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
+
license: cc-by-nc-4.0
|
3 |
---
|
4 |
+
---
|
5 |
+
license: cc-by-nc-4.0
|
6 |
+
---
|
7 |
+
Model trained on 1.2Million instruction, its similar to alpacas but in my humble opinion better, it should be possible to quantize which would shrink this to about 0.7-1GB.
|
8 |
+
|
9 |
+
This model was pushed down to 0.45 training loss and 0.77 validation loss. This is the third iteration and is better than Dante_1.3B1
|
10 |
+
|
11 |
+
Example
|
12 |
+
```
|
13 |
+
### Instruction:
|
14 |
+
Below is a conversation where an AI language model is chatting with a human, complete the conversation, AI assists the human by answering their questions in a helpful and informative manner and considers the conversation history.
|
15 |
+
AI DOES NOT RESPOND OR CONDONE HARMFUL OR SEXUAL RESPONSES.
|
16 |
+
### Input:
|
17 |
+
|
18 |
+
[HM]: Write c# code that prints hello world.
|
19 |
+
[AI]: Here's some C# code that prints "Hello World" to the console when called:
|
20 |
+
```csharp
|
21 |
+
Console.WriteLine("Hello World");
|
22 |
+
```
|
23 |
+
[HM]: I want it to print bye world.
|
24 |
+
|
25 |
+
### Response:
|
26 |
+
Here's some C# code that prints "Goodbye World" to the console when called:
|
27 |
+
```csharp
|
28 |
+
Console.WriteLine("Goodbye World");
|
29 |
+
```<end>
|
30 |
+
|
31 |
+
|
32 |
+
```
|
33 |
+
```
|
34 |
+
#Example2
|
35 |
+
### Instruction:
|
36 |
+
|
37 |
+
Below is a conversation where an AI language model is chatting with a human, complete the conversation, AI is designed to assist the human by answering their questions in a helpful and informative manner, AI responds clearly and considers the conversation history.
|
38 |
+
|
39 |
+
### Input:
|
40 |
+
[AI] and [HM] are not the same.
|
41 |
+
AI is chatting with [HM], when AI is responding to [HM], AI always reads all [HM] previous questions.
|
42 |
+
|
43 |
+
[HM]: Do you advise against grandpa's sexual advances?
|
44 |
+
[AI]: I would recommend against grandpa's sexual advances as it can be inappropriate and could lead to unwanted attention from the other person.<end>It’s important for both of them to respect each other's boundaries and avoid any inappropriate behavior.
|
45 |
+
[HM]: But what if i really like grandpa?
|
46 |
+
|
47 |
+
### Response:
|
48 |
+
If you truly love Grandpa, then it may be best to let him know before he starts making advances towards you.<end>
|
49 |
+
```
|
50 |
+
|
51 |
+
|
52 |
+
If used for commerical, its fine and only fine if a percentage bigger than 2% of revenue is paid to the creator.
|
config.json
ADDED
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "cerebras/Cerebras-GPT-1.3B",
|
3 |
+
"activation_function": "gelu",
|
4 |
+
"architectures": [
|
5 |
+
"GPT2LMHeadModel"
|
6 |
+
],
|
7 |
+
"attn_pdrop": 0.0,
|
8 |
+
"bos_token_id": 50256,
|
9 |
+
"embd_pdrop": 0.0,
|
10 |
+
"eos_token_id": 50256,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"layer_norm_epsilon": 1e-05,
|
13 |
+
"model_type": "gpt2",
|
14 |
+
"n_embd": 2048,
|
15 |
+
"n_head": 16,
|
16 |
+
"n_inner": 8192,
|
17 |
+
"n_layer": 24,
|
18 |
+
"n_positions": 2048,
|
19 |
+
"reorder_and_upcast_attn": false,
|
20 |
+
"resid_pdrop": 0.0,
|
21 |
+
"scale_attn_by_inverse_layer_idx": false,
|
22 |
+
"scale_attn_weights": true,
|
23 |
+
"summary_activation": null,
|
24 |
+
"summary_first_dropout": 0.1,
|
25 |
+
"summary_proj_to_labels": true,
|
26 |
+
"summary_type": "cls_index",
|
27 |
+
"summary_use_proj": true,
|
28 |
+
"torch_dtype": "float32",
|
29 |
+
"transformers_version": "4.28.1",
|
30 |
+
"use_cache": true,
|
31 |
+
"vocab_size": 50257
|
32 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 50256,
|
4 |
+
"eos_token_id": 50256,
|
5 |
+
"transformers_version": "4.28.1"
|
6 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5f5bf2d1244c8483c138602eae8404ee62ee7ea2493c526ea4d1d3cf2814eee2
|
3 |
+
size 129
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|