Initial GPTQ model commit
Browse files- config.json +3 -3
config.json
CHANGED
|
@@ -14,16 +14,16 @@
|
|
| 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,
|
| 21 |
"tie_word_embeddings": false,
|
| 22 |
-
"torch_dtype": "
|
| 23 |
-
"transformers_version": "4.
|
| 24 |
"use_cache": true,
|
| 25 |
"vocab_size": 32000,
|
| 26 |
-
"pad_token_id": 0,
|
| 27 |
"quantization_config": {
|
| 28 |
"bits": 4,
|
| 29 |
"group_size": -1,
|
|
|
|
| 14 |
"num_attention_heads": 64,
|
| 15 |
"num_hidden_layers": 48,
|
| 16 |
"num_key_value_heads": 8,
|
| 17 |
+
"pad_token_id": 0,
|
| 18 |
"pretraining_tp": 1,
|
| 19 |
"rms_norm_eps": 1e-05,
|
| 20 |
"rope_scaling": null,
|
| 21 |
"rope_theta": 1000000,
|
| 22 |
"tie_word_embeddings": false,
|
| 23 |
+
"torch_dtype": "bfloat16",
|
| 24 |
+
"transformers_version": "4.31.0",
|
| 25 |
"use_cache": true,
|
| 26 |
"vocab_size": 32000,
|
|
|
|
| 27 |
"quantization_config": {
|
| 28 |
"bits": 4,
|
| 29 |
"group_size": -1,
|