Add pipeline tag, library name, and paper link (#1)
Browse files- Add pipeline tag, library name, and paper link (986b5532785ad3122855604c742c60d8bd2cc419)
Co-authored-by: Niels Rogge <[email protected]>
README.md
CHANGED
@@ -1,25 +1,26 @@
|
|
1 |
---
|
2 |
-
license: mit
|
3 |
base_model:
|
4 |
- ai-sage/GigaChat-20B-A3B-instruct
|
5 |
language:
|
6 |
- ru
|
7 |
- en
|
|
|
|
|
|
|
8 |
---
|
9 |
-
# GigaChat-20B-A3B-instruct bf16
|
10 |
|
11 |
-
|
12 |
|
13 |
-
|
14 |
|
|
|
15 |
|
16 |
-
##
|
17 |
|
18 |
```bash
|
19 |
pip install --upgrade transformers torch accelerate bitsandbytes
|
20 |
```
|
21 |
|
22 |
-
|
23 |
```python
|
24 |
import torch
|
25 |
from transformers import AutoTokenizer, AutoModelForCausalLM, GenerationConfig
|
@@ -37,5 +38,4 @@ outputs = model.generate(input_tensor.to(model.device))
|
|
37 |
|
38 |
result = tokenizer.decode(outputs[0][input_tensor.shape[1]:], skip_special_tokens=False)
|
39 |
print(result)
|
40 |
-
```
|
41 |
-
|
|
|
1 |
---
|
|
|
2 |
base_model:
|
3 |
- ai-sage/GigaChat-20B-A3B-instruct
|
4 |
language:
|
5 |
- ru
|
6 |
- en
|
7 |
+
license: mit
|
8 |
+
pipeline_tag: text-generation
|
9 |
+
library_name: transformers
|
10 |
---
|
|
|
11 |
|
12 |
+
# GigaChat-20B-A3B-instruct bf16
|
13 |
|
14 |
+
This model is part of the GigaChat family of Russian LLMs, based on [ai-sage/GigaChat-20B-A3B-instruct](https://huggingface.co/ai-sage/GigaChat-20B-A3B-instruct). It supports a context length of 131,000 tokens.
|
15 |
|
16 |
+
More details are available in [this habr article](https://habr.com/en/companies/sberdevices/articles/865996/) and the original instruct model card. The model was presented in [GigaChat Family: Efficient Russian Language Modeling Through Mixture of Experts Architecture](https://huggingface.co/papers/2506.09440).
|
17 |
|
18 |
+
## Example Usage with Transformers
|
19 |
|
20 |
```bash
|
21 |
pip install --upgrade transformers torch accelerate bitsandbytes
|
22 |
```
|
23 |
|
|
|
24 |
```python
|
25 |
import torch
|
26 |
from transformers import AutoTokenizer, AutoModelForCausalLM, GenerationConfig
|
|
|
38 |
|
39 |
result = tokenizer.decode(outputs[0][input_tensor.shape[1]:], skip_special_tokens=False)
|
40 |
print(result)
|
41 |
+
```
|
|