vltnmmdv nielsr HF Staff commited on
Commit
bc459c9
·
verified ·
1 Parent(s): d676181

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]>

Files changed (1) hide show
  1. README.md +8 -8
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
- Диалоговая модель из семейства моделей GigaChat, основная на [ai-sage/GigaChat-20B-A3B-instruct](https://huggingface.co/ai-sage/GigaChat-20B-A3B-instruct). Поддерживает контекст в 131 тысячу токенов.
12
 
13
- Больше подробностей в [хабр статье](https://habr.com/en/companies/sberdevices/articles/865996/) и в карточке оригинальной instruct модели.
14
 
 
15
 
16
- ## Пример использования через transformers
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
+ ```