Instructions to use agilan1102/sql_model with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use agilan1102/sql_model with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("unsloth/llama-3.2-3b-instruct-bnb-4bit") model = PeftModel.from_pretrained(base_model, "agilan1102/sql_model") - Notebooks
- Google Colab
- Kaggle
Create config.json
Browse files- config.json +14 -0
config.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"model_type": "llama",
|
| 3 |
+
"hidden_size": 3200,
|
| 4 |
+
"num_attention_heads": 32,
|
| 5 |
+
"num_hidden_layers": 32,
|
| 6 |
+
"vocab_size": 32000,
|
| 7 |
+
"intermediate_size": 8640,
|
| 8 |
+
"max_position_embeddings": 2048,
|
| 9 |
+
"initializer_range": 0.02,
|
| 10 |
+
"layer_norm_eps": 1e-5,
|
| 11 |
+
"bos_token_id": 1,
|
| 12 |
+
"eos_token_id": 2,
|
| 13 |
+
"pad_token_id": 0
|
| 14 |
+
}
|