Create config.json
Browse files- config.json +42 -0
config.json
ADDED
|
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "THUDM/chatglm3-6b",
|
| 3 |
+
"model_type": "chatglm",
|
| 4 |
+
"architectures": [
|
| 5 |
+
"ChatGLMModel"
|
| 6 |
+
],
|
| 7 |
+
"auto_map": {
|
| 8 |
+
"AutoConfig": "configuration_chatglm.ChatGLMConfig",
|
| 9 |
+
"AutoModel": "modeling_chatglm.ChatGLMForConditionalGeneration",
|
| 10 |
+
"AutoModelForCausalLM": "modeling_chatglm.ChatGLMForConditionalGeneration",
|
| 11 |
+
"AutoModelForSeq2SeqLM": "modeling_chatglm.ChatGLMForConditionalGeneration",
|
| 12 |
+
"AutoModelForSequenceClassification": "modeling_chatglm.ChatGLMForSequenceClassification"
|
| 13 |
+
},
|
| 14 |
+
"add_bias_linear": false,
|
| 15 |
+
"add_qkv_bias": true,
|
| 16 |
+
"apply_query_key_layer_scaling": true,
|
| 17 |
+
"apply_residual_connection_post_layernorm": false,
|
| 18 |
+
"attention_dropout": 0.0,
|
| 19 |
+
"attention_softmax_in_fp32": true,
|
| 20 |
+
"bias_dropout_fusion": true,
|
| 21 |
+
"ffn_hidden_size": 13696,
|
| 22 |
+
"fp32_residual_connection": false,
|
| 23 |
+
"hidden_dropout": 0.0,
|
| 24 |
+
"hidden_size": 4096,
|
| 25 |
+
"kv_channels": 128,
|
| 26 |
+
"layernorm_epsilon": 1e-05,
|
| 27 |
+
"multi_query_attention": true,
|
| 28 |
+
"multi_query_group_num": 2,
|
| 29 |
+
"num_attention_heads": 32,
|
| 30 |
+
"num_layers": 28,
|
| 31 |
+
"original_rope": true,
|
| 32 |
+
"padded_vocab_size": 65024,
|
| 33 |
+
"post_layer_norm": true,
|
| 34 |
+
"rmsnorm": true,
|
| 35 |
+
"seq_length": 8192,
|
| 36 |
+
"use_cache": true,
|
| 37 |
+
"torch_dtype": "float16",
|
| 38 |
+
"transformers_version": "4.30.2",
|
| 39 |
+
"tie_word_embeddings": false,
|
| 40 |
+
"eos_token_id": 2,
|
| 41 |
+
"pad_token_id": 0
|
| 42 |
+
}
|