Upload config_3b.json
Browse files- config_3b.json +25 -0
config_3b.json
ADDED
|
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Rwkv6ForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"auto_map": {
|
| 6 |
+
"AutoConfig": "configuration_rwkv6.Rwkv6Config",
|
| 7 |
+
"AutoModelForCausalLM": "modeling_rwkv6.Rwkv6ForCausalLM"
|
| 8 |
+
},
|
| 9 |
+
"attention_hidden_size": 2560,
|
| 10 |
+
"bos_token_id": 0,
|
| 11 |
+
"eos_token_id": 0,
|
| 12 |
+
"head_size": 64,
|
| 13 |
+
"head_size_divisor": 8,
|
| 14 |
+
"hidden_size": 2560,
|
| 15 |
+
"intermediate_size": null,
|
| 16 |
+
"layer_norm_epsilon": 1e-05,
|
| 17 |
+
"model_type": "rwkv6",
|
| 18 |
+
"num_attention_heads": 64,
|
| 19 |
+
"num_hidden_layers": 32,
|
| 20 |
+
"rescale_every": 6,
|
| 21 |
+
"tie_word_embeddings": false,
|
| 22 |
+
"transformers_version": "4.34.0",
|
| 23 |
+
"use_cache": true,
|
| 24 |
+
"vocab_size": 65536
|
| 25 |
+
}
|