Update config.json
Browse files- config.json +7 -9
config.json
CHANGED
|
@@ -1,29 +1,27 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "/sailor2/sealm_share/cy_repo/pref_tuned/release/sailor2-v2/offpolicy/sailor2-20b-dpo-offpolicy",
|
| 3 |
"architectures": [
|
| 4 |
"Qwen2ForCausalLM"
|
| 5 |
],
|
| 6 |
"attention_dropout": 0.0,
|
| 7 |
"bos_token_id": 151643,
|
| 8 |
-
"eos_token_id":
|
| 9 |
"hidden_act": "silu",
|
| 10 |
"hidden_size": 5120,
|
| 11 |
"initializer_range": 0.02,
|
| 12 |
"intermediate_size": 13824,
|
| 13 |
-
"max_position_embeddings":
|
| 14 |
-
"max_window_layers":
|
| 15 |
"model_type": "qwen2",
|
| 16 |
"num_attention_heads": 40,
|
| 17 |
"num_hidden_layers": 64,
|
| 18 |
"num_key_value_heads": 8,
|
| 19 |
"rms_norm_eps": 1e-06,
|
| 20 |
-
"rope_scaling": null,
|
| 21 |
"rope_theta": 1000000.0,
|
| 22 |
-
"sliding_window":
|
| 23 |
"tie_word_embeddings": false,
|
| 24 |
"torch_dtype": "bfloat16",
|
| 25 |
-
"transformers_version": "4.
|
| 26 |
-
"use_cache":
|
| 27 |
"use_sliding_window": false,
|
| 28 |
"vocab_size": 151936
|
| 29 |
-
}
|
|
|
|
| 1 |
{
|
|
|
|
| 2 |
"architectures": [
|
| 3 |
"Qwen2ForCausalLM"
|
| 4 |
],
|
| 5 |
"attention_dropout": 0.0,
|
| 6 |
"bos_token_id": 151643,
|
| 7 |
+
"eos_token_id": 151645,
|
| 8 |
"hidden_act": "silu",
|
| 9 |
"hidden_size": 5120,
|
| 10 |
"initializer_range": 0.02,
|
| 11 |
"intermediate_size": 13824,
|
| 12 |
+
"max_position_embeddings": 4096,
|
| 13 |
+
"max_window_layers": 64,
|
| 14 |
"model_type": "qwen2",
|
| 15 |
"num_attention_heads": 40,
|
| 16 |
"num_hidden_layers": 64,
|
| 17 |
"num_key_value_heads": 8,
|
| 18 |
"rms_norm_eps": 1e-06,
|
|
|
|
| 19 |
"rope_theta": 1000000.0,
|
| 20 |
+
"sliding_window": 131072,
|
| 21 |
"tie_word_embeddings": false,
|
| 22 |
"torch_dtype": "bfloat16",
|
| 23 |
+
"transformers_version": "4.46.3",
|
| 24 |
+
"use_cache": true,
|
| 25 |
"use_sliding_window": false,
|
| 26 |
"vocab_size": 151936
|
| 27 |
+
}
|