Instructions to use Chaitanya14/Financial_Agent with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use Chaitanya14/Financial_Agent with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("bigscience/bloom-7b1") model = PeftModel.from_pretrained(base_model, "Chaitanya14/Financial_Agent") - Notebooks
- Google Colab
- Kaggle
Delete adapter_config.json
Browse files- adapter_config.json +0 -18
adapter_config.json
DELETED
|
@@ -1,18 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"auto_mapping": null,
|
| 3 |
-
"base_model_name_or_path": "bigscience/bloom-7b1",
|
| 4 |
-
"inference_mode": true,
|
| 5 |
-
"modules_to_save": null,
|
| 6 |
-
"num_attention_heads": 32,
|
| 7 |
-
"num_layers": 30,
|
| 8 |
-
"num_transformer_submodules": 1,
|
| 9 |
-
"num_virtual_tokens": 64,
|
| 10 |
-
"peft_type": "PROMPT_TUNING",
|
| 11 |
-
"prompt_tuning_init": "TEXT",
|
| 12 |
-
"prompt_tuning_init_text": "Analyse the query and provide the names of the companies, the relevant information and their related concepts, and the dates for which the information is required:",
|
| 13 |
-
"revision": null,
|
| 14 |
-
"task_type": "CAUSAL_LM",
|
| 15 |
-
"token_dim": 4096,
|
| 16 |
-
"tokenizer_kwargs": null,
|
| 17 |
-
"tokenizer_name_or_path": "bigscience/bloom-7b1"
|
| 18 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|