WHATEVER420
commited on
Commit
•
21f45da
1
Parent(s):
8e98956
:no_mouth:
Browse files
README.md
CHANGED
@@ -16,21 +16,45 @@ model-index:
|
|
16 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
17 |
should probably proofread and complete it, then remove this comment. -->
|
18 |
|
19 |
-
#
|
20 |
|
21 |
This model is a fine-tuned version of [cognitivecomputations/dolphin-2.2.1-mistral-7b](https://huggingface.co/cognitivecomputations/dolphin-2.2.1-mistral-7b) on the generator dataset.
|
22 |
|
23 |
## Model description
|
24 |
|
25 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
26 |
|
27 |
-
## Intended
|
28 |
|
29 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
30 |
|
31 |
## Training and evaluation data
|
32 |
|
33 |
-
|
34 |
|
35 |
## Training procedure
|
36 |
|
@@ -52,4 +76,4 @@ The following hyperparameters were used during training:
|
|
52 |
- Transformers 4.40.1
|
53 |
- Pytorch 2.3.0+cu121
|
54 |
- Datasets 2.19.0
|
55 |
-
- Tokenizers 0.19.1
|
|
|
16 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
17 |
should probably proofread and complete it, then remove this comment. -->
|
18 |
|
19 |
+
# chain-texts-0.1-dolphin-mixtral-8x7b
|
20 |
|
21 |
This model is a fine-tuned version of [cognitivecomputations/dolphin-2.2.1-mistral-7b](https://huggingface.co/cognitivecomputations/dolphin-2.2.1-mistral-7b) on the generator dataset.
|
22 |
|
23 |
## Model description
|
24 |
|
25 |
+
- **Developed by:** Matt Owen
|
26 |
+
- **Funded by [optional]:** Matt Owen
|
27 |
+
- **Shared by [optional]:** Matt Owen
|
28 |
+
- **Model type:** Sparse Mixture-of-Experts (SMoE)
|
29 |
+
- **Language(s) (NLP):** English
|
30 |
+
- **License:** The Unlicense
|
31 |
+
- **Finetuned from model [optional]:** Dolphin 2.6 Mixtral 8x7b
|
32 |
|
33 |
+
## Intended Uses & Limitations
|
34 |
|
35 |
+
Easy your day-to-day workload by:
|
36 |
+
* Generate horny chain text message threads for any holiday
|
37 |
+
* Other things
|
38 |
+
|
39 |
+
### Direct Use
|
40 |
+
|
41 |
+
This can be used directly to make semi-spot-on, humorous, risqué chain text messages.
|
42 |
+
|
43 |
+
### Out-of-Scope Use
|
44 |
+
|
45 |
+
Do not use this model to send unsolicited, creepy messages.
|
46 |
+
|
47 |
+
## Bias, Risks, and Limitations
|
48 |
+
|
49 |
+
Source data was compiled from message boards, and - as a result - carries all the biases of anonymous internet users.
|
50 |
+
|
51 |
+
### Recommendations
|
52 |
+
|
53 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
54 |
|
55 |
## Training and evaluation data
|
56 |
|
57 |
+
Chain texts scraped from the world wide web.
|
58 |
|
59 |
## Training procedure
|
60 |
|
|
|
76 |
- Transformers 4.40.1
|
77 |
- Pytorch 2.3.0+cu121
|
78 |
- Datasets 2.19.0
|
79 |
+
- Tokenizers 0.19.1
|