Changes made to model
Browse files- LLM/config.json +6 -3
- LLM/generation_config.json +8 -0
LLM/config.json
CHANGED
|
@@ -15,13 +15,16 @@
|
|
| 15 |
"num_attention_heads": 14,
|
| 16 |
"num_hidden_layers": 24,
|
| 17 |
"num_key_value_heads": 2,
|
|
|
|
| 18 |
"rms_norm_eps": 1e-06,
|
|
|
|
| 19 |
"rope_theta": 1000000.0,
|
| 20 |
"sliding_window": 32768,
|
| 21 |
"tie_word_embeddings": true,
|
| 22 |
-
"torch_dtype": "
|
| 23 |
-
"transformers_version": "4.
|
|
|
|
| 24 |
"use_cache": true,
|
| 25 |
"use_sliding_window": false,
|
| 26 |
"vocab_size": 166000
|
| 27 |
-
}
|
|
|
|
| 15 |
"num_attention_heads": 14,
|
| 16 |
"num_hidden_layers": 24,
|
| 17 |
"num_key_value_heads": 2,
|
| 18 |
+
"pad_token_id": 151643,
|
| 19 |
"rms_norm_eps": 1e-06,
|
| 20 |
+
"rope_scaling": null,
|
| 21 |
"rope_theta": 1000000.0,
|
| 22 |
"sliding_window": 32768,
|
| 23 |
"tie_word_embeddings": true,
|
| 24 |
+
"torch_dtype": "float32",
|
| 25 |
+
"transformers_version": "4.52.0.dev0",
|
| 26 |
+
"unsloth_version": "2025.5.7",
|
| 27 |
"use_cache": true,
|
| 28 |
"use_sliding_window": false,
|
| 29 |
"vocab_size": 166000
|
| 30 |
+
}
|
LLM/generation_config.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 151643,
|
| 4 |
+
"eos_token_id": 151645,
|
| 5 |
+
"max_length": 32768,
|
| 6 |
+
"pad_token_id": 151643,
|
| 7 |
+
"transformers_version": "4.52.0.dev0"
|
| 8 |
+
}
|