Upload README (1).md
Browse files- README (1).md +96 -0
README (1).md
ADDED
@@ -0,0 +1,96 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: transformers
|
3 |
+
tags:
|
4 |
+
- llama-factory
|
5 |
+
- merge
|
6 |
+
license: llama3
|
7 |
+
language:
|
8 |
+
- en
|
9 |
+
---
|
10 |
+
|
11 |
+
# Model Card for Model ID
|
12 |
+
|
13 |
+
![image/webp](https://cdn-uploads.huggingface.co/production/uploads/643eab4f05a395e2b1c727e3/TciPHbHULFVgClbNaw0hY.webp)
|
14 |
+
|
15 |
+
This is a fine tune of a merged model using the [DARE](https://arxiv.org/abs/2311.03099) [TIES](https://arxiv.org/abs/2306.01708) merge method using [cognitivecomputations/dolphin-2.9-llama3-8b](https://huggingface.co/cognitivecomputations/dolphin-2.9-llama3-8b) as a base.
|
16 |
+
The following models were included in the merge:
|
17 |
+
* [Weyaxi/Einstein-v6.1-Llama3-8B](https://huggingface.co/Weyaxi/Einstein-v6.1-Llama3-8B)
|
18 |
+
|
19 |
+
|
20 |
+
|
21 |
+
|
22 |
+
## Model Details
|
23 |
+
Quant [Q8_0 GGUF](https://huggingface.co/giannisan/penny5-dolphin-einstein-llama3-dare-ties-chatml.gguf)
|
24 |
+
|
25 |
+
### Model Description
|
26 |
+
|
27 |
+
<!-- Provide a longer summary of what this model is. -->
|
28 |
+
|
29 |
+
This is the model card of a 🤗 transformers model that has been pushed on the Hub.
|
30 |
+
|
31 |
+
- **Developed by:** [Gianni Sanrochman](https://x.com/Giannisanii)
|
32 |
+
- **Funded by:** [Merildo Sanrochman]
|
33 |
+
- **Model type:** [LLaMA-3](https://ai.meta.com/blog/meta-llama-3)
|
34 |
+
- **Language(s) (NLP):** [English]
|
35 |
+
- **License:** [llama3](https://huggingface.co/meta-llama/Meta-Llama-3-8B/blob/main/LICENSE)
|
36 |
+
- **Finetuned from model:** [giannisan/dolphin-einstein-llama3-dare-ties](https://huggingface.co/giannisan/dolphin-einstein-llama3-dare-ties) using the PENNY dataset
|
37 |
+
|
38 |
+
|
39 |
+
## Training Details
|
40 |
+
|
41 |
+
### Training Data
|
42 |
+
|
43 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
44 |
+
|
45 |
+
[More Information Needed]
|
46 |
+
|
47 |
+
### Training Procedure
|
48 |
+
|
49 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
50 |
+
|
51 |
+
#### Training Hyperparameters
|
52 |
+
|
53 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
54 |
+
|
55 |
+
#### Speeds, Sizes, Times [optional]
|
56 |
+
|
57 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
58 |
+
|
59 |
+
[More Information Needed]
|
60 |
+
|
61 |
+
## Evaluation
|
62 |
+
|
63 |
+
|
64 |
+
| Metric | Value |
|
65 |
+
|----------------------|---------|
|
66 |
+
| Avg. | 66.72 |
|
67 |
+
| ARC (25-shot) | 61.01 |
|
68 |
+
| HellaSwag (10-shot) | 82.50 |
|
69 |
+
| MMLU (5-shot) | 64.48 |
|
70 |
+
| TruthfulQA (0-shot) | 50.73 |
|
71 |
+
| Winogrande (5-shot) | 74.11 |
|
72 |
+
| GSM8K (5-shot) | 67.48 |
|
73 |
+
|
74 |
+
full results [here](https://huggingface.co/datasets/open-llm-leaderboard/details_giannisan__penny5-dolphin-einstein-llama3-dare-ties-chatml/blob/main/results_2024-05-30T05-14-11.958453.json)
|
75 |
+
|
76 |
+
|
77 |
+
## Environmental Impact
|
78 |
+
|
79 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
80 |
+
|
81 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
82 |
+
|
83 |
+
- **Hardware Type:** [Nvidia RTX A100]
|
84 |
+
- **Hours used:** [2]
|
85 |
+
- **Cloud Provider:** [RunPod]
|
86 |
+
- **Compute Region:** [Europe]
|
87 |
+
- **Carbon Emitted:** [More Information Needed]
|
88 |
+
|
89 |
+
|
90 |
+
## Model Card Authors [optional]
|
91 |
+
|
92 |
+
[Gianni Sanrochman]
|
93 |
+
|
94 |
+
## Model Card Contact
|
95 |
+
|
96 |
+
[More Information Needed]
|