add libraries and how to
#2
by
MaziyarPanahi
- opened
README.md
CHANGED
@@ -5,6 +5,11 @@ language:
|
|
5 |
- en
|
6 |
base_model:
|
7 |
- Qwen/Qwen2.5-7B-Instruct
|
|
|
|
|
|
|
|
|
|
|
8 |
---
|
9 |
|
10 |
<div align="center">
|
@@ -39,6 +44,39 @@ Arcee Meraj Mini is capable of solving a wide range of language tasks, including
|
|
39 |
|
40 |
6. **Content Creation**: Arcee Meraj Mini generates high-quality Arabic content for various needs, from marketing materials and technical documentation to creative writing, ensuring impactful communication and engagement in the Arabic-speaking world.
|
41 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
42 |
|
43 |
## Evaluations
|
44 |
#### Open Arabic LLM Leaderboard (OALL) Benchmarks
|
@@ -87,5 +125,4 @@ We are grateful to the open-source AI community for their continuous contributio
|
|
87 |
|
88 |
## Future Directions
|
89 |
|
90 |
-
As we release the Arcee Meraj Mini to the public, we invite researchers, developers, and businesses to engage with the Arcee Meraj Mini model, particularly in enhancing support for the Arabic language and fostering domain adaptation. We are committed to advancing open-source AI technology and invite the community to explore, contribute, and build upon Arcee Meraj Mini.
|
91 |
-
|
|
|
5 |
- en
|
6 |
base_model:
|
7 |
- Qwen/Qwen2.5-7B-Instruct
|
8 |
+
pipeline_tag: text2text-generation
|
9 |
+
library_name: transformers
|
10 |
+
tags:
|
11 |
+
- qwen
|
12 |
+
- text-generation-inference
|
13 |
---
|
14 |
|
15 |
<div align="center">
|
|
|
44 |
|
45 |
6. **Content Creation**: Arcee Meraj Mini generates high-quality Arabic content for various needs, from marketing materials and technical documentation to creative writing, ensuring impactful communication and engagement in the Arabic-speaking world.
|
46 |
|
47 |
+
## How to
|
48 |
+
This model uses ChatML prompt template:
|
49 |
+
|
50 |
+
```
|
51 |
+
<|im_start|>system
|
52 |
+
{System}
|
53 |
+
<|im_end|>
|
54 |
+
<|im_start|>user
|
55 |
+
{User}
|
56 |
+
<|im_end|>
|
57 |
+
<|im_start|>assistant
|
58 |
+
{Assistant}
|
59 |
+
```
|
60 |
+
|
61 |
+
```python
|
62 |
+
# Use a pipeline as a high-level helper
|
63 |
+
|
64 |
+
from transformers import pipeline
|
65 |
+
|
66 |
+
messages = [
|
67 |
+
{"role": "user", "content": "مرحبا، كيف حالك؟"},
|
68 |
+
]
|
69 |
+
pipe = pipeline("text-generation", model="arcee-ai/Meraj-Mini")
|
70 |
+
pipe(messages)
|
71 |
+
|
72 |
+
|
73 |
+
# Load model directly
|
74 |
+
|
75 |
+
from transformers import AutoTokenizer, AutoModelForCausalLM
|
76 |
+
|
77 |
+
tokenizer = AutoTokenizer.from_pretrained("arcee-ai/Meraj-Mini")
|
78 |
+
model = AutoModelForCausalLM.from_pretrained("arcee-ai/Meraj-Mini")
|
79 |
+
```
|
80 |
|
81 |
## Evaluations
|
82 |
#### Open Arabic LLM Leaderboard (OALL) Benchmarks
|
|
|
125 |
|
126 |
## Future Directions
|
127 |
|
128 |
+
As we release the Arcee Meraj Mini to the public, we invite researchers, developers, and businesses to engage with the Arcee Meraj Mini model, particularly in enhancing support for the Arabic language and fostering domain adaptation. We are committed to advancing open-source AI technology and invite the community to explore, contribute, and build upon Arcee Meraj Mini.
|
|