update readme
Browse files
README.md
CHANGED
@@ -1,23 +1,21 @@
|
|
1 |
---
|
2 |
-
|
3 |
language:
|
4 |
- de
|
5 |
library_name: transformers
|
6 |
-
|
7 |
-
inference: false
|
8 |
model_creator: jphme
|
9 |
model_name: EM German
|
10 |
model_type: llama
|
11 |
-
|
12 |
-
|
13 |
tags:
|
14 |
-
|
15 |
-
|
16 |
-
|
17 |
-
|
18 |
-
|
19 |
-
|
20 |
-
- deutsch
|
21 |
---
|
22 |
![EM Logo](em_model_logo_web.jpeg)
|
23 |
|
@@ -35,18 +33,19 @@ tags:
|
|
35 |
|
36 |
# Introduction
|
37 |
|
38 |
-
**EM German
|
39 |
-
|
40 |
-
Please find all Informations, Example Outputs, the special RAG prompt format, output examples and eval results for the EM German Model family in [our Github Repository](https://github.com/jphme/EM_German).
|
41 |
|
|
|
42 |
|
43 |
-
|
44 |
|
45 |
|
46 |
# Links & Demos
|
47 |
|
48 |
## Model Links
|
49 |
|
|
|
|
|
50 |
| Base Model | HF | GPTQ | GGUF | AWQ |
|
51 |
|-------|-------|-------|-------|-------|
|
52 |
| Llama2 7b | [Link](https://huggingface.co/jphme/em_german_7b_v01) | [Link](https://huggingface.co/TheBloke/em_german_7b_v01-GPTQ) | [Link](https://huggingface.co/TheBloke/em_german_7b_v01-GGUF) | [Link](https://huggingface.co/TheBloke/em_german_7b_v01-AWQ) |
|
@@ -54,10 +53,11 @@ Please find all Informations, Example Outputs, the special RAG prompt format, ou
|
|
54 |
| Llama2 70b | [Link](https://huggingface.co/jphme/em_german_70b_v01) | [Link](https://huggingface.co/TheBloke/em_german_70b_v01-GPTQ) | [Link](https://huggingface.co/TheBloke/em_german_70b_v01-GGUF) | [Link](https://huggingface.co/TheBloke/em_german_70b_v01-AWQ) |
|
55 |
| [Mistral 7b](https://huggingface.co/mistralai/Mistral-7B-v0.1) | [Link](https://huggingface.co/jphme/em_german_mistral_v01) | [Link](https://huggingface.co/TheBloke/em_german_mistral_v01-GPTQ) | [Link](https://huggingface.co/TheBloke/em_german_mistral_v01-GGUF) | [Link](https://huggingface.co/TheBloke/em_german_mistral_v01-AWQ) |
|
56 |
| [LeoLM 7b](https://huggingface.co/LeoLM/leo-hessianai-7b) | [Link](https://huggingface.co/jphme/em_german_7b_leo) | [Link](https://huggingface.co/jphme/em_german_7b_leo_gptq) | [Link](hhttps://huggingface.co/jphme/em_german_7b_leo_gguf) | tbc |
|
57 |
-
| LeoLM 13b | soon | soon |
|
|
|
58 |
|
59 |
### Notes about the different versions:
|
60 |
-
|
61 |
|
62 |
If you get unsatisfying results with one or another EM German version, please try a different (and/or larger) model or version for your usecase.
|
63 |
|
@@ -68,7 +68,7 @@ You can use some of the models with **free** google Colab instances (e.g. the 7b
|
|
68 |
|
69 |
* [Example Colab Notebook for 13b with GPTQ](https://colab.research.google.com/drive/1IJfJdVwGkfe5MYOqHptystR3FBeEUdGn?usp=sharing)
|
70 |
* [Example Colab Notebook for 7b with 8bit-Loading](https://colab.research.google.com/drive/1bsv6vkLM4AlCpSyXA6ol9P32zxZmf7Zu?usp=sharing)
|
71 |
-
*
|
72 |
|
73 |
|
74 |
# Prompt Format
|
@@ -83,30 +83,40 @@ You can swap the standard system prompt for a better suited one (see below for R
|
|
83 |
|
84 |
# Example Output
|
85 |
|
86 |
-
|
87 |
|
88 |
**Prompt:**
|
89 |
-
>
|
90 |
|
91 |
-
**Antwort EM German 7b
|
92 |
```
|
93 |
-
|
|
|
|
|
94 |
|
95 |
-
|
96 |
|
97 |
-
|
|
|
98 |
|
99 |
-
|
|
|
100 |
|
101 |
-
|
|
|
|
|
102 |
|
103 |
-
|
|
|
|
|
104 |
|
105 |
-
|
106 |
|
107 |
-
|
|
|
|
|
108 |
|
109 |
-
|
110 |
```
|
111 |
(For more examples, please visit [our Github Repository](https://github.com/jphme/EM_German).)
|
112 |
|
@@ -120,7 +130,7 @@ The 70b model was trained with support of the [OVH Cloud Startup Program](https:
|
|
120 |
|
121 |
I you are interested in customized LLMs for business applications, please get in contact with me via [my website](https://www.jph.me). I am also always happy about suggestions and feedback.
|
122 |
|
123 |
-
*PS: We are also always interested in support for our startup ellamind, which will offer customized models for business applications in the future (currently still in stealth mode).
|
124 |
|
125 |
# Disclaimer:
|
126 |
|
|
|
1 |
---
|
2 |
+
inference: false
|
3 |
language:
|
4 |
- de
|
5 |
library_name: transformers
|
6 |
+
license: llama2
|
|
|
7 |
model_creator: jphme
|
8 |
model_name: EM German
|
9 |
model_type: llama
|
10 |
+
pipeline_tag: text-generation
|
11 |
+
prompt_template: 'Du bist ein hilfreicher Assistent. USER: Was ist 1+1? ASSISTANT:'
|
12 |
tags:
|
13 |
+
- pytorch
|
14 |
+
- german
|
15 |
+
- deutsch
|
16 |
+
- llama2
|
17 |
+
- meta
|
18 |
+
- facebook
|
|
|
19 |
---
|
20 |
![EM Logo](em_model_logo_web.jpeg)
|
21 |
|
|
|
33 |
|
34 |
# Introduction
|
35 |
|
36 |
+
**EM German** is a Llama2/Mistral/LeoLM-based model family, finetuned on a large dataset of various instructions in German language. The models are optimized for German text, providing proficiency in understanding, generating, and interacting with German language content.
|
|
|
|
|
37 |
|
38 |
+
We offer versions based on 7b, 13b and 70b Llama-2, Mistral and LeoLM (Llama-2/Mistral with continued pretraining on German texts) models.
|
39 |
|
40 |
+
Please find all Informations, Example Outputs, the special RAG prompt format, output examples and eval results for the EM German Model family in [our Github Repository](https://github.com/jphme/EM_German). ([Deutsche Version](https://github.com/jphme/EM_German/blob/main/README_DE.md))
|
41 |
|
42 |
|
43 |
# Links & Demos
|
44 |
|
45 |
## Model Links
|
46 |
|
47 |
+
Should you try only one model version, I strongly recommend the **LeoLM Mistral** model which offers by far the best combination of performance and computing requirements!
|
48 |
+
|
49 |
| Base Model | HF | GPTQ | GGUF | AWQ |
|
50 |
|-------|-------|-------|-------|-------|
|
51 |
| Llama2 7b | [Link](https://huggingface.co/jphme/em_german_7b_v01) | [Link](https://huggingface.co/TheBloke/em_german_7b_v01-GPTQ) | [Link](https://huggingface.co/TheBloke/em_german_7b_v01-GGUF) | [Link](https://huggingface.co/TheBloke/em_german_7b_v01-AWQ) |
|
|
|
53 |
| Llama2 70b | [Link](https://huggingface.co/jphme/em_german_70b_v01) | [Link](https://huggingface.co/TheBloke/em_german_70b_v01-GPTQ) | [Link](https://huggingface.co/TheBloke/em_german_70b_v01-GGUF) | [Link](https://huggingface.co/TheBloke/em_german_70b_v01-AWQ) |
|
54 |
| [Mistral 7b](https://huggingface.co/mistralai/Mistral-7B-v0.1) | [Link](https://huggingface.co/jphme/em_german_mistral_v01) | [Link](https://huggingface.co/TheBloke/em_german_mistral_v01-GPTQ) | [Link](https://huggingface.co/TheBloke/em_german_mistral_v01-GGUF) | [Link](https://huggingface.co/TheBloke/em_german_mistral_v01-AWQ) |
|
55 |
| [LeoLM 7b](https://huggingface.co/LeoLM/leo-hessianai-7b) | [Link](https://huggingface.co/jphme/em_german_7b_leo) | [Link](https://huggingface.co/jphme/em_german_7b_leo_gptq) | [Link](hhttps://huggingface.co/jphme/em_german_7b_leo_gguf) | tbc |
|
56 |
+
| [LeoLM 13b](https://huggingface.co/LeoLM/leo-hessianai-13b) | soon | soon | [Link](https://huggingface.co/jphme/em_german_13b_leo_gguf) | tbc |
|
57 |
+
| [LeoLM Mistral 7b](tbc) | [Link](https://huggingface.co/jphme/em_german_leo_mistral) | soon | [Link](https://huggingface.co/jphme/em_german_leo_mistral_gguf) | tbc |
|
58 |
|
59 |
### Notes about the different versions:
|
60 |
+
See also the [comparison of example outputs](https://github.com/jphme/EM_German/blob/main/example_output_comparison.md) for a comparison of (7b) model capabilities.
|
61 |
|
62 |
If you get unsatisfying results with one or another EM German version, please try a different (and/or larger) model or version for your usecase.
|
63 |
|
|
|
68 |
|
69 |
* [Example Colab Notebook for 13b with GPTQ](https://colab.research.google.com/drive/1IJfJdVwGkfe5MYOqHptystR3FBeEUdGn?usp=sharing)
|
70 |
* [Example Colab Notebook for 7b with 8bit-Loading](https://colab.research.google.com/drive/1bsv6vkLM4AlCpSyXA6ol9P32zxZmf7Zu?usp=sharing)
|
71 |
+
* [Example Colab Notebook for 7b Mistral GGUF with Grammar-based structured output](https://colab.research.google.com/drive/17O-a3D4BnVc_V9Of3dFfed18v1ULu1Sv?usp=sharing)
|
72 |
|
73 |
|
74 |
# Prompt Format
|
|
|
83 |
|
84 |
# Example Output
|
85 |
|
86 |
+
Please find a selection of various example outputs for all 7b versions of EM German [here](https://github.com/jphme/EM_German/blob/main/example_output_comparison.md).
|
87 |
|
88 |
**Prompt:**
|
89 |
+
> Erkläre die Bedeutung von drei wesentlichen Elementen der Bilanzierung und des Accountings nach IFRS für Unternehmen, die auf internationaler Ebene tätig sind.
|
90 |
|
91 |
+
**Antwort EM German Leo Mistral 7b:**
|
92 |
```
|
93 |
+
Die International Financial Reporting Standards (IFRS) sind eine Reihe von internationalen Rechnungslegungsstandards, die von der International Accounting Standards Board (IASB) entwickelt wurden. Sie sollen dazu beitragen, dass Finanzberichte vergleichbar, zuverlässig und relevant sind.
|
94 |
+
|
95 |
+
1. Fair Value: Dieses Konzept ist ein zentraler Bestandteil der IFRS. Es besagt, dass Vermögenswerte und Schulden zum fairen Wert bilanziert werden sollten, was dem Preis entspricht, zu dem sie zwischen Marktteilnehmern gehandelt werden könnten. Dadurch wird sichergestellt, dass das Unternehmen eine genaue Darstellung seiner finanziellen Lage liefert.
|
96 |
|
97 |
+
2. Konsolidierung: Die IFRS verlangen von Unternehmen, ihre Finanzergebnisse auf konsolidierter Basis darzustellen. Das bedeutet, dass alle Tochtergesellschaften und verbundenen Unternehmen in die Bilanz des Mutterunternehmens aufgenommen werden. Dadurch wird ein klareres Bild von der finanziellen Situation des Konzerns geschaffen.
|
98 |
|
99 |
+
3. Vollständigkeitsprinzip: Die IFRS verlangen von Unternehmen, alle relevanten Informationen offenzulegen. Dies umfasst sowohl positive als auch negative Faktoren, wie zum Beispiel Gewinne und Verluste, Einnahmen und Ausgaben sowie Risiken und Unsicherheiten. Durch dieses Prinzip wird sichergestellt, dass Investoren, Kreditgeber und andere Stakeholder eine umfassende Einschätzung der finanziellen Lage des Unternehmens vornehmen können.
|
100 |
+
```
|
101 |
|
102 |
+
**Prompt:**
|
103 |
+
> Ein Mensch atmet durchschnittlich 16 Mal pro Minute. Wie oft atmet er an einem Tag?
|
104 |
|
105 |
+
**Antwort EM German Leo Mistral 7b:**
|
106 |
+
```
|
107 |
+
Zuerst berechnen wir, wie oft eine Person in einer Stunde atmet. Wir wissen, dass eine Stunde 60 Minuten hat, also:
|
108 |
|
109 |
+
Atemzüge pro Stunde = Atemfrequenz * Minuten pro Stunde
|
110 |
+
= 16 Atemzüge pro Minute * 60 Minuten
|
111 |
+
= 960 Atemzüge
|
112 |
|
113 |
+
Um herauszufinden, wie viele Atemzüge eine Person an einem Tag macht, müssen wir diese stündliche Rate mit der Anzahl der Stunden an einem Tag multiplizieren, also 24:
|
114 |
|
115 |
+
Atemzüge pro Tag = Atemzüge pro Stunde * Stunden pro Tag
|
116 |
+
= 960 Atemzüge * 24 Stunden
|
117 |
+
= 23.040 Atemzüge
|
118 |
|
119 |
+
Also macht ein durchschnittlicher Mensch etwa 23.040 Atemzüge an einem Tag.
|
120 |
```
|
121 |
(For more examples, please visit [our Github Repository](https://github.com/jphme/EM_German).)
|
122 |
|
|
|
130 |
|
131 |
I you are interested in customized LLMs for business applications, please get in contact with me via [my website](https://www.jph.me). I am also always happy about suggestions and feedback.
|
132 |
|
133 |
+
*PS: We are also always interested in support for our startup [ellamind](https://ellamind.com), which will offer customized models for business applications in the future (we are currently still in stealth mode). If you use our models for business applications and have advanced needs for specialized capabilities, please get in touch.*
|
134 |
|
135 |
# Disclaimer:
|
136 |
|