Upload config.json with huggingface_hub
Browse files- config.json +11 -6
config.json
CHANGED
|
@@ -5,27 +5,32 @@
|
|
| 5 |
"attention_bias": false,
|
| 6 |
"attention_dropout": 0.0,
|
| 7 |
"bos_token_id": 151643,
|
|
|
|
|
|
|
|
|
|
| 8 |
"eos_token_id": 151645,
|
| 9 |
-
"head_dim":
|
| 10 |
"hidden_act": "silu",
|
| 11 |
"hidden_size": 2048,
|
| 12 |
"initializer_range": 0.02,
|
| 13 |
"intermediate_size": 6144,
|
| 14 |
"max_position_embeddings": 40960,
|
| 15 |
"max_window_layers": 48,
|
|
|
|
| 16 |
"model_type": "llama",
|
| 17 |
"num_attention_heads": 32,
|
| 18 |
"num_hidden_layers": 1,
|
| 19 |
"num_key_value_heads": 4,
|
|
|
|
|
|
|
| 20 |
"rms_norm_eps": 1e-06,
|
| 21 |
"rope_scaling": null,
|
| 22 |
"rope_theta": 1000000.0,
|
|
|
|
| 23 |
"sliding_window": null,
|
| 24 |
"tie_word_embeddings": false,
|
| 25 |
-
"
|
| 26 |
-
"transformers_version": "4.51.0",
|
| 27 |
"use_cache": true,
|
| 28 |
"use_sliding_window": false,
|
| 29 |
-
"vocab_size": 151936
|
| 30 |
-
|
| 31 |
-
}
|
|
|
|
| 5 |
"attention_bias": false,
|
| 6 |
"attention_dropout": 0.0,
|
| 7 |
"bos_token_id": 151643,
|
| 8 |
+
"decoder_sparse_step": 1,
|
| 9 |
+
"draft_vocab_size": 32000,
|
| 10 |
+
"dtype": "bfloat16",
|
| 11 |
"eos_token_id": 151645,
|
| 12 |
+
"head_dim": 128,
|
| 13 |
"hidden_act": "silu",
|
| 14 |
"hidden_size": 2048,
|
| 15 |
"initializer_range": 0.02,
|
| 16 |
"intermediate_size": 6144,
|
| 17 |
"max_position_embeddings": 40960,
|
| 18 |
"max_window_layers": 48,
|
| 19 |
+
"mlp_bias": false,
|
| 20 |
"model_type": "llama",
|
| 21 |
"num_attention_heads": 32,
|
| 22 |
"num_hidden_layers": 1,
|
| 23 |
"num_key_value_heads": 4,
|
| 24 |
+
"output_router_logits": false,
|
| 25 |
+
"pretraining_tp": 1,
|
| 26 |
"rms_norm_eps": 1e-06,
|
| 27 |
"rope_scaling": null,
|
| 28 |
"rope_theta": 1000000.0,
|
| 29 |
+
"router_aux_loss_coef": 0.001,
|
| 30 |
"sliding_window": null,
|
| 31 |
"tie_word_embeddings": false,
|
| 32 |
+
"transformers_version": "4.57.3",
|
|
|
|
| 33 |
"use_cache": true,
|
| 34 |
"use_sliding_window": false,
|
| 35 |
+
"vocab_size": 151936
|
| 36 |
+
}
|
|
|