Upload LlamaForCausalLM
Browse files- config.json +3 -1
- generation_config.json +1 -1
config.json
CHANGED
|
@@ -7,12 +7,14 @@
|
|
| 7 |
"attention_dropout": 0.0,
|
| 8 |
"bos_token_id": 1,
|
| 9 |
"eos_token_id": 2,
|
|
|
|
| 10 |
"hidden_act": "silu",
|
| 11 |
"hidden_size": 128,
|
| 12 |
"initializer_range": 0.02,
|
| 13 |
"intermediate_size": 128,
|
| 14 |
"is_decoder": true,
|
| 15 |
"max_position_embeddings": 4096,
|
|
|
|
| 16 |
"model_type": "llama",
|
| 17 |
"num_attention_heads": 32,
|
| 18 |
"num_hidden_layers": 4,
|
|
@@ -24,7 +26,7 @@
|
|
| 24 |
"rope_theta": 10000.0,
|
| 25 |
"tie_word_embeddings": false,
|
| 26 |
"torch_dtype": "float32",
|
| 27 |
-
"transformers_version": "4.
|
| 28 |
"use_cache": true,
|
| 29 |
"vocab_size": 32000
|
| 30 |
}
|
|
|
|
| 7 |
"attention_dropout": 0.0,
|
| 8 |
"bos_token_id": 1,
|
| 9 |
"eos_token_id": 2,
|
| 10 |
+
"head_dim": 4,
|
| 11 |
"hidden_act": "silu",
|
| 12 |
"hidden_size": 128,
|
| 13 |
"initializer_range": 0.02,
|
| 14 |
"intermediate_size": 128,
|
| 15 |
"is_decoder": true,
|
| 16 |
"max_position_embeddings": 4096,
|
| 17 |
+
"mlp_bias": false,
|
| 18 |
"model_type": "llama",
|
| 19 |
"num_attention_heads": 32,
|
| 20 |
"num_hidden_layers": 4,
|
|
|
|
| 26 |
"rope_theta": 10000.0,
|
| 27 |
"tie_word_embeddings": false,
|
| 28 |
"torch_dtype": "float32",
|
| 29 |
+
"transformers_version": "4.48.1",
|
| 30 |
"use_cache": true,
|
| 31 |
"vocab_size": 32000
|
| 32 |
}
|
generation_config.json
CHANGED
|
@@ -3,5 +3,5 @@
|
|
| 3 |
"bos_token_id": 1,
|
| 4 |
"eos_token_id": 2,
|
| 5 |
"pad_token_id": 0,
|
| 6 |
-
"transformers_version": "4.
|
| 7 |
}
|
|
|
|
| 3 |
"bos_token_id": 1,
|
| 4 |
"eos_token_id": 2,
|
| 5 |
"pad_token_id": 0,
|
| 6 |
+
"transformers_version": "4.48.1"
|
| 7 |
}
|