(Trained with Unsloth)
Browse files- config.json +15 -7
- tokenizer_config.json +1 -0
config.json
CHANGED
|
@@ -7,13 +7,14 @@
|
|
| 7 |
"attention_dropout": 0.0,
|
| 8 |
"attn_logit_softcapping": null,
|
| 9 |
"bos_token_id": 2,
|
|
|
|
| 10 |
"eos_token_id": 106,
|
| 11 |
"final_logit_softcapping": null,
|
| 12 |
"head_dim": 256,
|
| 13 |
"hidden_activation": "gelu_pytorch_tanh",
|
| 14 |
-
"hidden_size":
|
| 15 |
"initializer_range": 0.02,
|
| 16 |
-
"intermediate_size":
|
| 17 |
"layer_types": [
|
| 18 |
"sliding_attention",
|
| 19 |
"sliding_attention",
|
|
@@ -32,25 +33,32 @@
|
|
| 32 |
"sliding_attention",
|
| 33 |
"sliding_attention",
|
| 34 |
"sliding_attention",
|
| 35 |
-
"full_attention"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 36 |
],
|
| 37 |
"max_position_embeddings": 32768,
|
| 38 |
"model_type": "gemma3_text",
|
| 39 |
"num_attention_heads": 4,
|
| 40 |
-
"num_hidden_layers":
|
| 41 |
"num_key_value_heads": 1,
|
| 42 |
"pad_token_id": 0,
|
| 43 |
"query_pre_attn_scalar": 256,
|
| 44 |
"rms_norm_eps": 1e-06,
|
| 45 |
-
"rope_local_base_freq": 10000
|
| 46 |
"rope_scaling": null,
|
| 47 |
-
"rope_theta": 1000000
|
| 48 |
"sliding_window": 512,
|
| 49 |
"torch_dtype": "bfloat16",
|
| 50 |
"transformers_version": "4.55.4",
|
| 51 |
"unsloth_fixed": true,
|
| 52 |
"unsloth_version": "2025.8.10",
|
| 53 |
-
"use_bidirectional_attention": false,
|
| 54 |
"use_cache": true,
|
| 55 |
"vocab_size": 262144
|
| 56 |
}
|
|
|
|
| 7 |
"attention_dropout": 0.0,
|
| 8 |
"attn_logit_softcapping": null,
|
| 9 |
"bos_token_id": 2,
|
| 10 |
+
"cache_implementation": "hybrid",
|
| 11 |
"eos_token_id": 106,
|
| 12 |
"final_logit_softcapping": null,
|
| 13 |
"head_dim": 256,
|
| 14 |
"hidden_activation": "gelu_pytorch_tanh",
|
| 15 |
+
"hidden_size": 1152,
|
| 16 |
"initializer_range": 0.02,
|
| 17 |
+
"intermediate_size": 6912,
|
| 18 |
"layer_types": [
|
| 19 |
"sliding_attention",
|
| 20 |
"sliding_attention",
|
|
|
|
| 33 |
"sliding_attention",
|
| 34 |
"sliding_attention",
|
| 35 |
"sliding_attention",
|
| 36 |
+
"full_attention",
|
| 37 |
+
"sliding_attention",
|
| 38 |
+
"sliding_attention",
|
| 39 |
+
"sliding_attention",
|
| 40 |
+
"sliding_attention",
|
| 41 |
+
"sliding_attention",
|
| 42 |
+
"full_attention",
|
| 43 |
+
"sliding_attention",
|
| 44 |
+
"sliding_attention"
|
| 45 |
],
|
| 46 |
"max_position_embeddings": 32768,
|
| 47 |
"model_type": "gemma3_text",
|
| 48 |
"num_attention_heads": 4,
|
| 49 |
+
"num_hidden_layers": 26,
|
| 50 |
"num_key_value_heads": 1,
|
| 51 |
"pad_token_id": 0,
|
| 52 |
"query_pre_attn_scalar": 256,
|
| 53 |
"rms_norm_eps": 1e-06,
|
| 54 |
+
"rope_local_base_freq": 10000,
|
| 55 |
"rope_scaling": null,
|
| 56 |
+
"rope_theta": 1000000,
|
| 57 |
"sliding_window": 512,
|
| 58 |
"torch_dtype": "bfloat16",
|
| 59 |
"transformers_version": "4.55.4",
|
| 60 |
"unsloth_fixed": true,
|
| 61 |
"unsloth_version": "2025.8.10",
|
|
|
|
| 62 |
"use_cache": true,
|
| 63 |
"vocab_size": 262144
|
| 64 |
}
|
tokenizer_config.json
CHANGED
|
@@ -51337,6 +51337,7 @@
|
|
| 51337 |
"model_max_length": 32768,
|
| 51338 |
"pad_token": "<pad>",
|
| 51339 |
"padding_side": "right",
|
|
|
|
| 51340 |
"sp_model_kwargs": null,
|
| 51341 |
"spaces_between_special_tokens": false,
|
| 51342 |
"tokenizer_class": "GemmaTokenizer",
|
|
|
|
| 51337 |
"model_max_length": 32768,
|
| 51338 |
"pad_token": "<pad>",
|
| 51339 |
"padding_side": "right",
|
| 51340 |
+
"processor_class": "Gemma3Processor",
|
| 51341 |
"sp_model_kwargs": null,
|
| 51342 |
"spaces_between_special_tokens": false,
|
| 51343 |
"tokenizer_class": "GemmaTokenizer",
|