Update Nemotron-Cascade-8B-SFT/config.json
Browse files
Nemotron-Cascade-8B-SFT/config.json
CHANGED
|
@@ -4,32 +4,65 @@
|
|
| 4 |
],
|
| 5 |
"attention_bias": false,
|
| 6 |
"attention_dropout": 0.0,
|
| 7 |
-
"
|
| 8 |
-
"eos_token_id": 151643,
|
| 9 |
"head_dim": 128,
|
| 10 |
"hidden_act": "silu",
|
| 11 |
"hidden_size": 4096,
|
| 12 |
"initializer_range": 0.02,
|
| 13 |
"intermediate_size": 12288,
|
| 14 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 15 |
"max_window_layers": 36,
|
| 16 |
"model_type": "qwen3",
|
| 17 |
"num_attention_heads": 32,
|
| 18 |
"num_hidden_layers": 36,
|
| 19 |
"num_key_value_heads": 8,
|
|
|
|
| 20 |
"rms_norm_eps": 1e-06,
|
| 21 |
-
"rope_scaling":
|
| 22 |
-
"attention_factor": 0.8782488562869419,
|
| 23 |
-
"factor": 2.0,
|
| 24 |
-
"original_max_position_embeddings": 32768,
|
| 25 |
-
"rope_type": "yarn"
|
| 26 |
-
},
|
| 27 |
"rope_theta": 1000000,
|
| 28 |
"sliding_window": null,
|
| 29 |
"tie_word_embeddings": false,
|
| 30 |
"torch_dtype": "bfloat16",
|
| 31 |
-
"transformers_version": "4.
|
| 32 |
"use_cache": true,
|
| 33 |
"use_sliding_window": false,
|
| 34 |
"vocab_size": 151936
|
| 35 |
-
}
|
|
|
|
| 4 |
],
|
| 5 |
"attention_bias": false,
|
| 6 |
"attention_dropout": 0.0,
|
| 7 |
+
"eos_token_id": 151645,
|
|
|
|
| 8 |
"head_dim": 128,
|
| 9 |
"hidden_act": "silu",
|
| 10 |
"hidden_size": 4096,
|
| 11 |
"initializer_range": 0.02,
|
| 12 |
"intermediate_size": 12288,
|
| 13 |
+
"layer_types": [
|
| 14 |
+
"full_attention",
|
| 15 |
+
"full_attention",
|
| 16 |
+
"full_attention",
|
| 17 |
+
"full_attention",
|
| 18 |
+
"full_attention",
|
| 19 |
+
"full_attention",
|
| 20 |
+
"full_attention",
|
| 21 |
+
"full_attention",
|
| 22 |
+
"full_attention",
|
| 23 |
+
"full_attention",
|
| 24 |
+
"full_attention",
|
| 25 |
+
"full_attention",
|
| 26 |
+
"full_attention",
|
| 27 |
+
"full_attention",
|
| 28 |
+
"full_attention",
|
| 29 |
+
"full_attention",
|
| 30 |
+
"full_attention",
|
| 31 |
+
"full_attention",
|
| 32 |
+
"full_attention",
|
| 33 |
+
"full_attention",
|
| 34 |
+
"full_attention",
|
| 35 |
+
"full_attention",
|
| 36 |
+
"full_attention",
|
| 37 |
+
"full_attention",
|
| 38 |
+
"full_attention",
|
| 39 |
+
"full_attention",
|
| 40 |
+
"full_attention",
|
| 41 |
+
"full_attention",
|
| 42 |
+
"full_attention",
|
| 43 |
+
"full_attention",
|
| 44 |
+
"full_attention",
|
| 45 |
+
"full_attention",
|
| 46 |
+
"full_attention",
|
| 47 |
+
"full_attention",
|
| 48 |
+
"full_attention",
|
| 49 |
+
"full_attention"
|
| 50 |
+
],
|
| 51 |
+
"max_position_embeddings": 32768,
|
| 52 |
"max_window_layers": 36,
|
| 53 |
"model_type": "qwen3",
|
| 54 |
"num_attention_heads": 32,
|
| 55 |
"num_hidden_layers": 36,
|
| 56 |
"num_key_value_heads": 8,
|
| 57 |
+
"pad_token_id": 151643,
|
| 58 |
"rms_norm_eps": 1e-06,
|
| 59 |
+
"rope_scaling": null,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 60 |
"rope_theta": 1000000,
|
| 61 |
"sliding_window": null,
|
| 62 |
"tie_word_embeddings": false,
|
| 63 |
"torch_dtype": "bfloat16",
|
| 64 |
+
"transformers_version": "4.53.3",
|
| 65 |
"use_cache": true,
|
| 66 |
"use_sliding_window": false,
|
| 67 |
"vocab_size": 151936
|
| 68 |
+
}
|