Upload 4 files
Browse files- config.json +6 -10
- tokenizer.json +0 -0
- tokenizer_config.json +5 -37
config.json
CHANGED
|
@@ -1,13 +1,7 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "/hpi/fs00/share/fg/meinel/nianhui.guo/01-ai/models--01-ai--Yi-6B/snapshots/5978aa81cd0fb25852004e7a86c71435b3f8de31/",
|
| 3 |
"architectures": [
|
| 4 |
-
"
|
| 5 |
],
|
| 6 |
-
"auto_map": {
|
| 7 |
-
"AutoConfig": "configuration_yi.YiConfig",
|
| 8 |
-
"AutoModel": "modeling_yi.YiModel",
|
| 9 |
-
"AutoModelForCausalLM": "modeling_yi.YiForCausalLM"
|
| 10 |
-
},
|
| 11 |
"bos_token_id": 1,
|
| 12 |
"eos_token_id": 2,
|
| 13 |
"hidden_act": "silu",
|
|
@@ -15,16 +9,18 @@
|
|
| 15 |
"initializer_range": 0.02,
|
| 16 |
"intermediate_size": 11008,
|
| 17 |
"max_position_embeddings": 4096,
|
| 18 |
-
"model_type": "
|
| 19 |
"num_attention_heads": 32,
|
| 20 |
"num_hidden_layers": 32,
|
| 21 |
"num_key_value_heads": 4,
|
| 22 |
"pad_token_id": 0,
|
|
|
|
| 23 |
"rms_norm_eps": 1e-05,
|
|
|
|
| 24 |
"rope_theta": 5000000.0,
|
| 25 |
"tie_word_embeddings": false,
|
| 26 |
-
"torch_dtype": "
|
| 27 |
-
"transformers_version": "4.
|
| 28 |
"use_cache": true,
|
| 29 |
"vocab_size": 64000
|
| 30 |
}
|
|
|
|
| 1 |
{
|
|
|
|
| 2 |
"architectures": [
|
| 3 |
+
"LlamaForCausalLM"
|
| 4 |
],
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
"bos_token_id": 1,
|
| 6 |
"eos_token_id": 2,
|
| 7 |
"hidden_act": "silu",
|
|
|
|
| 9 |
"initializer_range": 0.02,
|
| 10 |
"intermediate_size": 11008,
|
| 11 |
"max_position_embeddings": 4096,
|
| 12 |
+
"model_type": "llama",
|
| 13 |
"num_attention_heads": 32,
|
| 14 |
"num_hidden_layers": 32,
|
| 15 |
"num_key_value_heads": 4,
|
| 16 |
"pad_token_id": 0,
|
| 17 |
+
"pretraining_tp": 1,
|
| 18 |
"rms_norm_eps": 1e-05,
|
| 19 |
+
"rope_scaling": null,
|
| 20 |
"rope_theta": 5000000.0,
|
| 21 |
"tie_word_embeddings": false,
|
| 22 |
+
"torch_dtype": "bfloat16",
|
| 23 |
+
"transformers_version": "4.34.0",
|
| 24 |
"use_cache": true,
|
| 25 |
"vocab_size": 64000
|
| 26 |
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
CHANGED
|
@@ -1,45 +1,13 @@
|
|
| 1 |
{
|
| 2 |
"add_bos_token": false,
|
| 3 |
"add_eos_token": false,
|
| 4 |
-
"
|
| 5 |
-
|
| 6 |
-
"content": "<unk>",
|
| 7 |
-
"lstrip": false,
|
| 8 |
-
"normalized": true,
|
| 9 |
-
"rstrip": false,
|
| 10 |
-
"single_word": false,
|
| 11 |
-
"special": true
|
| 12 |
-
},
|
| 13 |
-
"1": {
|
| 14 |
-
"content": "<|startoftext|>",
|
| 15 |
-
"lstrip": false,
|
| 16 |
-
"normalized": true,
|
| 17 |
-
"rstrip": false,
|
| 18 |
-
"single_word": false,
|
| 19 |
-
"special": true
|
| 20 |
-
},
|
| 21 |
-
"2": {
|
| 22 |
-
"content": "<|endoftext|>",
|
| 23 |
-
"lstrip": false,
|
| 24 |
-
"normalized": true,
|
| 25 |
-
"rstrip": false,
|
| 26 |
-
"single_word": false,
|
| 27 |
-
"special": true
|
| 28 |
-
}
|
| 29 |
-
},
|
| 30 |
-
"auto_map": {
|
| 31 |
-
"AutoTokenizer": [
|
| 32 |
-
"tokenization_yi.YiTokenizer",
|
| 33 |
-
null
|
| 34 |
-
]
|
| 35 |
-
},
|
| 36 |
"bos_token": "<|startoftext|>",
|
| 37 |
-
"clean_up_tokenization_spaces": false,
|
| 38 |
"eos_token": "<|endoftext|>",
|
| 39 |
-
"legacy": false,
|
| 40 |
-
"model_max_length": 4096,
|
| 41 |
"pad_token": "<unk>",
|
| 42 |
"sp_model_kwargs": {},
|
| 43 |
-
"
|
| 44 |
-
"
|
|
|
|
| 45 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"add_bos_token": false,
|
| 3 |
"add_eos_token": false,
|
| 4 |
+
"model_max_length": 4096,
|
| 5 |
+
"unk_token": "<unk>",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6 |
"bos_token": "<|startoftext|>",
|
|
|
|
| 7 |
"eos_token": "<|endoftext|>",
|
|
|
|
|
|
|
| 8 |
"pad_token": "<unk>",
|
| 9 |
"sp_model_kwargs": {},
|
| 10 |
+
"clean_up_tokenization_spaces": false,
|
| 11 |
+
"legacy": true,
|
| 12 |
+
"tokenizer_class": "LlamaTokenizer"
|
| 13 |
}
|