upload
Browse files- config.json +17 -59
config.json
CHANGED
|
@@ -1,69 +1,27 @@
|
|
| 1 |
{
|
| 2 |
"architectures": [
|
| 3 |
-
"
|
| 4 |
],
|
| 5 |
-
"attention_bias": true,
|
| 6 |
"attention_dropout": 0.0,
|
| 7 |
-
"bos_token_id":
|
| 8 |
-
"
|
| 9 |
-
"eos_token_id": 200002,
|
| 10 |
-
"experts_per_token": 4,
|
| 11 |
-
"head_dim": 64,
|
| 12 |
"hidden_act": "silu",
|
| 13 |
-
"hidden_size":
|
| 14 |
-
"initial_context_length": 4096,
|
| 15 |
"initializer_range": 0.02,
|
| 16 |
-
"intermediate_size":
|
| 17 |
-
"
|
| 18 |
-
|
| 19 |
-
|
| 20 |
-
|
| 21 |
-
|
| 22 |
-
"sliding_attention",
|
| 23 |
-
"full_attention",
|
| 24 |
-
"sliding_attention",
|
| 25 |
-
"full_attention",
|
| 26 |
-
"sliding_attention",
|
| 27 |
-
"full_attention",
|
| 28 |
-
"sliding_attention",
|
| 29 |
-
"full_attention",
|
| 30 |
-
"sliding_attention",
|
| 31 |
-
"full_attention",
|
| 32 |
-
"sliding_attention",
|
| 33 |
-
"full_attention",
|
| 34 |
-
"sliding_attention",
|
| 35 |
-
"full_attention",
|
| 36 |
-
"sliding_attention",
|
| 37 |
-
"full_attention",
|
| 38 |
-
"sliding_attention",
|
| 39 |
-
"full_attention",
|
| 40 |
-
"sliding_attention",
|
| 41 |
-
"full_attention"
|
| 42 |
-
],
|
| 43 |
-
"max_position_embeddings": 131072,
|
| 44 |
-
"model_type": "gpt_oss",
|
| 45 |
-
"num_attention_heads": 64,
|
| 46 |
-
"num_experts_per_tok": 4,
|
| 47 |
-
"num_hidden_layers": 24,
|
| 48 |
"num_key_value_heads": 8,
|
| 49 |
-
"num_local_experts": 32,
|
| 50 |
-
"output_router_logits": false,
|
| 51 |
-
"pad_token_id": 199999,
|
| 52 |
"rms_norm_eps": 1e-05,
|
| 53 |
-
"
|
| 54 |
-
|
| 55 |
-
"beta_slow": 1.0,
|
| 56 |
-
"factor": 32.0,
|
| 57 |
-
"original_max_position_embeddings": 4096,
|
| 58 |
-
"rope_type": "yarn",
|
| 59 |
-
"truncate": false
|
| 60 |
-
},
|
| 61 |
-
"rope_theta": 150000,
|
| 62 |
-
"router_aux_loss_coef": 0.9,
|
| 63 |
-
"sliding_window": 128,
|
| 64 |
-
"swiglu_limit": 7.0,
|
| 65 |
"tie_word_embeddings": false,
|
| 66 |
-
"
|
| 67 |
-
"
|
| 68 |
-
"
|
|
|
|
|
|
|
| 69 |
}
|
|
|
|
| 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": 27648,
|
| 12 |
+
"max_position_embeddings": 40960,
|
| 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-05,
|
| 19 |
+
"rope_theta": 1000000.0,
|
| 20 |
+
"sliding_window": 32768,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 21 |
"tie_word_embeddings": false,
|
| 22 |
+
"torch_dtype": "bfloat16",
|
| 23 |
+
"transformers_version": "4.43.1",
|
| 24 |
+
"use_cache": true,
|
| 25 |
+
"use_sliding_window": false,
|
| 26 |
+
"vocab_size": 152064
|
| 27 |
}
|