artificialguybr
commited on
Create README.md
Browse files
README.md
ADDED
@@ -0,0 +1,68 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- GEMMA
|
4 |
+
- instruct
|
5 |
+
- finetune
|
6 |
+
- chatml
|
7 |
+
- gpt4
|
8 |
+
- synthetic data
|
9 |
+
- distillation
|
10 |
+
model-index:
|
11 |
+
- name: google/gemma-2-2b
|
12 |
+
results: []
|
13 |
+
license: apache-2.0
|
14 |
+
language:
|
15 |
+
- en
|
16 |
+
library_name: transformers
|
17 |
+
datasets:
|
18 |
+
- teknium/OpenHermes-2.5
|
19 |
+
---
|
20 |
+
|
21 |
+
# Model Card for Meta-Llama-3.1-8B-openhermes-2.5
|
22 |
+
|
23 |
+
This model is a fine-tuned version of Gemma 2 -2B on the OpenHermes-2.5 dataset.
|
24 |
+
|
25 |
+
## Model Details
|
26 |
+
|
27 |
+
### Model Description
|
28 |
+
|
29 |
+
This is a fine-tuned version of the google/gemma-2-2b model, trained on the OpenHermes-2.5 dataset. It is designed for instruction following and general language tasks.
|
30 |
+
|
31 |
+
- **Developed by:** artificialguybr
|
32 |
+
- **Model type:** Causal Language Model
|
33 |
+
- **Language(s):** English
|
34 |
+
- **License:** apache-2.0
|
35 |
+
- **Finetuned from model:** google/gemma-2-2b
|
36 |
+
|
37 |
+
### Model Sources
|
38 |
+
|
39 |
+
- **Repository:** https://huggingface.co/artificialguybr/Gemma2-2B-OpenHermes2.5
|
40 |
+
|
41 |
+
## Uses
|
42 |
+
|
43 |
+
This model can be used for various natural language processing tasks, particularly those involving instruction following and general language understanding.
|
44 |
+
|
45 |
+
### Direct Use
|
46 |
+
|
47 |
+
The model can be used for tasks such as text generation, question answering, and other language-related applications.
|
48 |
+
|
49 |
+
### Out-of-Scope Use
|
50 |
+
|
51 |
+
The model should not be used for generating harmful or biased content. Users should be aware of potential biases in the training data.
|
52 |
+
|
53 |
+
## Training Details
|
54 |
+
|
55 |
+
### Training Data
|
56 |
+
|
57 |
+
The model was fine-tuned on the teknium/OpenHermes-2.5 dataset.
|
58 |
+
|
59 |
+
### Training Procedure
|
60 |
+
|
61 |
+
#### Hardware and Software
|
62 |
+
|
63 |
+
- **Hardware:** NVIDIA A100-SXM4-80GB (1 GPU)
|
64 |
+
- **Software Framework:** 🤗 Transformers, Axolotl
|
65 |
+
|
66 |
+
## Limitations and Biases
|
67 |
+
|
68 |
+
More information is needed about specific limitations and biases of this model.
|