GPTQ model commit
Browse files- config.json +2 -2
config.json
CHANGED
|
@@ -9,11 +9,12 @@
|
|
| 9 |
"hidden_size": 8192,
|
| 10 |
"initializer_range": 0.02,
|
| 11 |
"intermediate_size": 22016,
|
| 12 |
-
"max_position_embeddings":
|
| 13 |
"model_type": "llama",
|
| 14 |
"num_attention_heads": 64,
|
| 15 |
"num_hidden_layers": 48,
|
| 16 |
"num_key_value_heads": 8,
|
|
|
|
| 17 |
"rms_norm_eps": 1e-05,
|
| 18 |
"rope_scaling": null,
|
| 19 |
"rope_theta": 1000000,
|
|
@@ -22,7 +23,6 @@
|
|
| 22 |
"transformers_version": "4.33.1",
|
| 23 |
"use_cache": true,
|
| 24 |
"vocab_size": 32000,
|
| 25 |
-
"pretraining_tp": 1,
|
| 26 |
"pad_token_id": 0,
|
| 27 |
"quantization_config": {
|
| 28 |
"bits": 4,
|
|
|
|
| 9 |
"hidden_size": 8192,
|
| 10 |
"initializer_range": 0.02,
|
| 11 |
"intermediate_size": 22016,
|
| 12 |
+
"max_position_embeddings": 4096,
|
| 13 |
"model_type": "llama",
|
| 14 |
"num_attention_heads": 64,
|
| 15 |
"num_hidden_layers": 48,
|
| 16 |
"num_key_value_heads": 8,
|
| 17 |
+
"pretraining_tp": 1,
|
| 18 |
"rms_norm_eps": 1e-05,
|
| 19 |
"rope_scaling": null,
|
| 20 |
"rope_theta": 1000000,
|
|
|
|
| 23 |
"transformers_version": "4.33.1",
|
| 24 |
"use_cache": true,
|
| 25 |
"vocab_size": 32000,
|
|
|
|
| 26 |
"pad_token_id": 0,
|
| 27 |
"quantization_config": {
|
| 28 |
"bits": 4,
|