Commit
•
3082b91
1
Parent(s):
4a5ef8a
更新Yi 1.5
Browse files- .gitignore +1 -0
- Yi-1.5-6B-Chat/bert4torch_config.json +316 -0
- Yi-1.5-6B/bert4torch_config.json +316 -0
- Yi-1.5-9B-32K/bert4torch_config.json +460 -0
- Yi-1.5-9B-Chat/bert4torch_config.json +460 -0
- Yi-1.5-9B/bert4torch_config.json +460 -0
.gitignore
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
config.json
|
Yi-1.5-6B-Chat/bert4torch_config.json
ADDED
|
@@ -0,0 +1,316 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 1,
|
| 3 |
+
"eos_token_id": 2,
|
| 4 |
+
"hidden_act": "silu",
|
| 5 |
+
"hidden_size": 4096,
|
| 6 |
+
"initializer_range": 0.02,
|
| 7 |
+
"intermediate_size": 11008,
|
| 8 |
+
"max_position_embeddings": 4096,
|
| 9 |
+
"model": "llama",
|
| 10 |
+
"num_attention_heads": 32,
|
| 11 |
+
"num_hidden_layers": 32,
|
| 12 |
+
"num_key_value_heads": 4,
|
| 13 |
+
"pad_token_id": 0,
|
| 14 |
+
"layer_norm_eps": 1e-06,
|
| 15 |
+
"rope_theta": 5000000.0,
|
| 16 |
+
"tie_word_embeddings": false,
|
| 17 |
+
"torch_dtype": "bfloat16",
|
| 18 |
+
"vocab_size": 64000,
|
| 19 |
+
"skip_init": true,
|
| 20 |
+
"rope_rank": "updown",
|
| 21 |
+
"segment_vocab_size": 0,
|
| 22 |
+
"generation_config": {"tokenizer_decode_config": {"skip_special_tokens": true}, "max_length": 4096, "eos_token_id": 2},
|
| 23 |
+
"mapping": {
|
| 24 |
+
"embeddings.word_embeddings.weight": "model.embed_tokens.weight",
|
| 25 |
+
"LayerNormFinal.weight": "model.norm.weight",
|
| 26 |
+
"lm_head.weight": "lm_head.weight",
|
| 27 |
+
"decoderLayer.0.multiHeadAttention.q.weight": "model.layers.0.self_attn.q_proj.weight",
|
| 28 |
+
"decoderLayer.0.multiHeadAttention.k.weight": "model.layers.0.self_attn.k_proj.weight",
|
| 29 |
+
"decoderLayer.0.multiHeadAttention.v.weight": "model.layers.0.self_attn.v_proj.weight",
|
| 30 |
+
"decoderLayer.0.multiHeadAttention.o.weight": "model.layers.0.self_attn.o_proj.weight",
|
| 31 |
+
"decoderLayer.0.attnLayerNorm.weight": "model.layers.0.ln1.weight",
|
| 32 |
+
"decoderLayer.0.feedForward.intermediateDense.weight": "model.layers.0.mlp.gate_proj.weight",
|
| 33 |
+
"decoderLayer.0.feedForward.outputDense.weight": "model.layers.0.mlp.down_proj.weight",
|
| 34 |
+
"decoderLayer.0.ffnLayerNorm.weight": "model.layers.0.ln2.weight",
|
| 35 |
+
"decoderLayer.0.feedForward.intermediateDense2.weight": "model.layers.0.mlp.up_proj.weight",
|
| 36 |
+
"decoderLayer.1.multiHeadAttention.q.weight": "model.layers.1.self_attn.q_proj.weight",
|
| 37 |
+
"decoderLayer.1.multiHeadAttention.k.weight": "model.layers.1.self_attn.k_proj.weight",
|
| 38 |
+
"decoderLayer.1.multiHeadAttention.v.weight": "model.layers.1.self_attn.v_proj.weight",
|
| 39 |
+
"decoderLayer.1.multiHeadAttention.o.weight": "model.layers.1.self_attn.o_proj.weight",
|
| 40 |
+
"decoderLayer.1.attnLayerNorm.weight": "model.layers.1.ln1.weight",
|
| 41 |
+
"decoderLayer.1.feedForward.intermediateDense.weight": "model.layers.1.mlp.gate_proj.weight",
|
| 42 |
+
"decoderLayer.1.feedForward.outputDense.weight": "model.layers.1.mlp.down_proj.weight",
|
| 43 |
+
"decoderLayer.1.ffnLayerNorm.weight": "model.layers.1.ln2.weight",
|
| 44 |
+
"decoderLayer.1.feedForward.intermediateDense2.weight": "model.layers.1.mlp.up_proj.weight",
|
| 45 |
+
"decoderLayer.2.multiHeadAttention.q.weight": "model.layers.2.self_attn.q_proj.weight",
|
| 46 |
+
"decoderLayer.2.multiHeadAttention.k.weight": "model.layers.2.self_attn.k_proj.weight",
|
| 47 |
+
"decoderLayer.2.multiHeadAttention.v.weight": "model.layers.2.self_attn.v_proj.weight",
|
| 48 |
+
"decoderLayer.2.multiHeadAttention.o.weight": "model.layers.2.self_attn.o_proj.weight",
|
| 49 |
+
"decoderLayer.2.attnLayerNorm.weight": "model.layers.2.ln1.weight",
|
| 50 |
+
"decoderLayer.2.feedForward.intermediateDense.weight": "model.layers.2.mlp.gate_proj.weight",
|
| 51 |
+
"decoderLayer.2.feedForward.outputDense.weight": "model.layers.2.mlp.down_proj.weight",
|
| 52 |
+
"decoderLayer.2.ffnLayerNorm.weight": "model.layers.2.ln2.weight",
|
| 53 |
+
"decoderLayer.2.feedForward.intermediateDense2.weight": "model.layers.2.mlp.up_proj.weight",
|
| 54 |
+
"decoderLayer.3.multiHeadAttention.q.weight": "model.layers.3.self_attn.q_proj.weight",
|
| 55 |
+
"decoderLayer.3.multiHeadAttention.k.weight": "model.layers.3.self_attn.k_proj.weight",
|
| 56 |
+
"decoderLayer.3.multiHeadAttention.v.weight": "model.layers.3.self_attn.v_proj.weight",
|
| 57 |
+
"decoderLayer.3.multiHeadAttention.o.weight": "model.layers.3.self_attn.o_proj.weight",
|
| 58 |
+
"decoderLayer.3.attnLayerNorm.weight": "model.layers.3.ln1.weight",
|
| 59 |
+
"decoderLayer.3.feedForward.intermediateDense.weight": "model.layers.3.mlp.gate_proj.weight",
|
| 60 |
+
"decoderLayer.3.feedForward.outputDense.weight": "model.layers.3.mlp.down_proj.weight",
|
| 61 |
+
"decoderLayer.3.ffnLayerNorm.weight": "model.layers.3.ln2.weight",
|
| 62 |
+
"decoderLayer.3.feedForward.intermediateDense2.weight": "model.layers.3.mlp.up_proj.weight",
|
| 63 |
+
"decoderLayer.4.multiHeadAttention.q.weight": "model.layers.4.self_attn.q_proj.weight",
|
| 64 |
+
"decoderLayer.4.multiHeadAttention.k.weight": "model.layers.4.self_attn.k_proj.weight",
|
| 65 |
+
"decoderLayer.4.multiHeadAttention.v.weight": "model.layers.4.self_attn.v_proj.weight",
|
| 66 |
+
"decoderLayer.4.multiHeadAttention.o.weight": "model.layers.4.self_attn.o_proj.weight",
|
| 67 |
+
"decoderLayer.4.attnLayerNorm.weight": "model.layers.4.ln1.weight",
|
| 68 |
+
"decoderLayer.4.feedForward.intermediateDense.weight": "model.layers.4.mlp.gate_proj.weight",
|
| 69 |
+
"decoderLayer.4.feedForward.outputDense.weight": "model.layers.4.mlp.down_proj.weight",
|
| 70 |
+
"decoderLayer.4.ffnLayerNorm.weight": "model.layers.4.ln2.weight",
|
| 71 |
+
"decoderLayer.4.feedForward.intermediateDense2.weight": "model.layers.4.mlp.up_proj.weight",
|
| 72 |
+
"decoderLayer.5.multiHeadAttention.q.weight": "model.layers.5.self_attn.q_proj.weight",
|
| 73 |
+
"decoderLayer.5.multiHeadAttention.k.weight": "model.layers.5.self_attn.k_proj.weight",
|
| 74 |
+
"decoderLayer.5.multiHeadAttention.v.weight": "model.layers.5.self_attn.v_proj.weight",
|
| 75 |
+
"decoderLayer.5.multiHeadAttention.o.weight": "model.layers.5.self_attn.o_proj.weight",
|
| 76 |
+
"decoderLayer.5.attnLayerNorm.weight": "model.layers.5.ln1.weight",
|
| 77 |
+
"decoderLayer.5.feedForward.intermediateDense.weight": "model.layers.5.mlp.gate_proj.weight",
|
| 78 |
+
"decoderLayer.5.feedForward.outputDense.weight": "model.layers.5.mlp.down_proj.weight",
|
| 79 |
+
"decoderLayer.5.ffnLayerNorm.weight": "model.layers.5.ln2.weight",
|
| 80 |
+
"decoderLayer.5.feedForward.intermediateDense2.weight": "model.layers.5.mlp.up_proj.weight",
|
| 81 |
+
"decoderLayer.6.multiHeadAttention.q.weight": "model.layers.6.self_attn.q_proj.weight",
|
| 82 |
+
"decoderLayer.6.multiHeadAttention.k.weight": "model.layers.6.self_attn.k_proj.weight",
|
| 83 |
+
"decoderLayer.6.multiHeadAttention.v.weight": "model.layers.6.self_attn.v_proj.weight",
|
| 84 |
+
"decoderLayer.6.multiHeadAttention.o.weight": "model.layers.6.self_attn.o_proj.weight",
|
| 85 |
+
"decoderLayer.6.attnLayerNorm.weight": "model.layers.6.ln1.weight",
|
| 86 |
+
"decoderLayer.6.feedForward.intermediateDense.weight": "model.layers.6.mlp.gate_proj.weight",
|
| 87 |
+
"decoderLayer.6.feedForward.outputDense.weight": "model.layers.6.mlp.down_proj.weight",
|
| 88 |
+
"decoderLayer.6.ffnLayerNorm.weight": "model.layers.6.ln2.weight",
|
| 89 |
+
"decoderLayer.6.feedForward.intermediateDense2.weight": "model.layers.6.mlp.up_proj.weight",
|
| 90 |
+
"decoderLayer.7.multiHeadAttention.q.weight": "model.layers.7.self_attn.q_proj.weight",
|
| 91 |
+
"decoderLayer.7.multiHeadAttention.k.weight": "model.layers.7.self_attn.k_proj.weight",
|
| 92 |
+
"decoderLayer.7.multiHeadAttention.v.weight": "model.layers.7.self_attn.v_proj.weight",
|
| 93 |
+
"decoderLayer.7.multiHeadAttention.o.weight": "model.layers.7.self_attn.o_proj.weight",
|
| 94 |
+
"decoderLayer.7.attnLayerNorm.weight": "model.layers.7.ln1.weight",
|
| 95 |
+
"decoderLayer.7.feedForward.intermediateDense.weight": "model.layers.7.mlp.gate_proj.weight",
|
| 96 |
+
"decoderLayer.7.feedForward.outputDense.weight": "model.layers.7.mlp.down_proj.weight",
|
| 97 |
+
"decoderLayer.7.ffnLayerNorm.weight": "model.layers.7.ln2.weight",
|
| 98 |
+
"decoderLayer.7.feedForward.intermediateDense2.weight": "model.layers.7.mlp.up_proj.weight",
|
| 99 |
+
"decoderLayer.8.multiHeadAttention.q.weight": "model.layers.8.self_attn.q_proj.weight",
|
| 100 |
+
"decoderLayer.8.multiHeadAttention.k.weight": "model.layers.8.self_attn.k_proj.weight",
|
| 101 |
+
"decoderLayer.8.multiHeadAttention.v.weight": "model.layers.8.self_attn.v_proj.weight",
|
| 102 |
+
"decoderLayer.8.multiHeadAttention.o.weight": "model.layers.8.self_attn.o_proj.weight",
|
| 103 |
+
"decoderLayer.8.attnLayerNorm.weight": "model.layers.8.ln1.weight",
|
| 104 |
+
"decoderLayer.8.feedForward.intermediateDense.weight": "model.layers.8.mlp.gate_proj.weight",
|
| 105 |
+
"decoderLayer.8.feedForward.outputDense.weight": "model.layers.8.mlp.down_proj.weight",
|
| 106 |
+
"decoderLayer.8.ffnLayerNorm.weight": "model.layers.8.ln2.weight",
|
| 107 |
+
"decoderLayer.8.feedForward.intermediateDense2.weight": "model.layers.8.mlp.up_proj.weight",
|
| 108 |
+
"decoderLayer.9.multiHeadAttention.q.weight": "model.layers.9.self_attn.q_proj.weight",
|
| 109 |
+
"decoderLayer.9.multiHeadAttention.k.weight": "model.layers.9.self_attn.k_proj.weight",
|
| 110 |
+
"decoderLayer.9.multiHeadAttention.v.weight": "model.layers.9.self_attn.v_proj.weight",
|
| 111 |
+
"decoderLayer.9.multiHeadAttention.o.weight": "model.layers.9.self_attn.o_proj.weight",
|
| 112 |
+
"decoderLayer.9.attnLayerNorm.weight": "model.layers.9.ln1.weight",
|
| 113 |
+
"decoderLayer.9.feedForward.intermediateDense.weight": "model.layers.9.mlp.gate_proj.weight",
|
| 114 |
+
"decoderLayer.9.feedForward.outputDense.weight": "model.layers.9.mlp.down_proj.weight",
|
| 115 |
+
"decoderLayer.9.ffnLayerNorm.weight": "model.layers.9.ln2.weight",
|
| 116 |
+
"decoderLayer.9.feedForward.intermediateDense2.weight": "model.layers.9.mlp.up_proj.weight",
|
| 117 |
+
"decoderLayer.10.multiHeadAttention.q.weight": "model.layers.10.self_attn.q_proj.weight",
|
| 118 |
+
"decoderLayer.10.multiHeadAttention.k.weight": "model.layers.10.self_attn.k_proj.weight",
|
| 119 |
+
"decoderLayer.10.multiHeadAttention.v.weight": "model.layers.10.self_attn.v_proj.weight",
|
| 120 |
+
"decoderLayer.10.multiHeadAttention.o.weight": "model.layers.10.self_attn.o_proj.weight",
|
| 121 |
+
"decoderLayer.10.attnLayerNorm.weight": "model.layers.10.ln1.weight",
|
| 122 |
+
"decoderLayer.10.feedForward.intermediateDense.weight": "model.layers.10.mlp.gate_proj.weight",
|
| 123 |
+
"decoderLayer.10.feedForward.outputDense.weight": "model.layers.10.mlp.down_proj.weight",
|
| 124 |
+
"decoderLayer.10.ffnLayerNorm.weight": "model.layers.10.ln2.weight",
|
| 125 |
+
"decoderLayer.10.feedForward.intermediateDense2.weight": "model.layers.10.mlp.up_proj.weight",
|
| 126 |
+
"decoderLayer.11.multiHeadAttention.q.weight": "model.layers.11.self_attn.q_proj.weight",
|
| 127 |
+
"decoderLayer.11.multiHeadAttention.k.weight": "model.layers.11.self_attn.k_proj.weight",
|
| 128 |
+
"decoderLayer.11.multiHeadAttention.v.weight": "model.layers.11.self_attn.v_proj.weight",
|
| 129 |
+
"decoderLayer.11.multiHeadAttention.o.weight": "model.layers.11.self_attn.o_proj.weight",
|
| 130 |
+
"decoderLayer.11.attnLayerNorm.weight": "model.layers.11.ln1.weight",
|
| 131 |
+
"decoderLayer.11.feedForward.intermediateDense.weight": "model.layers.11.mlp.gate_proj.weight",
|
| 132 |
+
"decoderLayer.11.feedForward.outputDense.weight": "model.layers.11.mlp.down_proj.weight",
|
| 133 |
+
"decoderLayer.11.ffnLayerNorm.weight": "model.layers.11.ln2.weight",
|
| 134 |
+
"decoderLayer.11.feedForward.intermediateDense2.weight": "model.layers.11.mlp.up_proj.weight",
|
| 135 |
+
"decoderLayer.12.multiHeadAttention.q.weight": "model.layers.12.self_attn.q_proj.weight",
|
| 136 |
+
"decoderLayer.12.multiHeadAttention.k.weight": "model.layers.12.self_attn.k_proj.weight",
|
| 137 |
+
"decoderLayer.12.multiHeadAttention.v.weight": "model.layers.12.self_attn.v_proj.weight",
|
| 138 |
+
"decoderLayer.12.multiHeadAttention.o.weight": "model.layers.12.self_attn.o_proj.weight",
|
| 139 |
+
"decoderLayer.12.attnLayerNorm.weight": "model.layers.12.ln1.weight",
|
| 140 |
+
"decoderLayer.12.feedForward.intermediateDense.weight": "model.layers.12.mlp.gate_proj.weight",
|
| 141 |
+
"decoderLayer.12.feedForward.outputDense.weight": "model.layers.12.mlp.down_proj.weight",
|
| 142 |
+
"decoderLayer.12.ffnLayerNorm.weight": "model.layers.12.ln2.weight",
|
| 143 |
+
"decoderLayer.12.feedForward.intermediateDense2.weight": "model.layers.12.mlp.up_proj.weight",
|
| 144 |
+
"decoderLayer.13.multiHeadAttention.q.weight": "model.layers.13.self_attn.q_proj.weight",
|
| 145 |
+
"decoderLayer.13.multiHeadAttention.k.weight": "model.layers.13.self_attn.k_proj.weight",
|
| 146 |
+
"decoderLayer.13.multiHeadAttention.v.weight": "model.layers.13.self_attn.v_proj.weight",
|
| 147 |
+
"decoderLayer.13.multiHeadAttention.o.weight": "model.layers.13.self_attn.o_proj.weight",
|
| 148 |
+
"decoderLayer.13.attnLayerNorm.weight": "model.layers.13.ln1.weight",
|
| 149 |
+
"decoderLayer.13.feedForward.intermediateDense.weight": "model.layers.13.mlp.gate_proj.weight",
|
| 150 |
+
"decoderLayer.13.feedForward.outputDense.weight": "model.layers.13.mlp.down_proj.weight",
|
| 151 |
+
"decoderLayer.13.ffnLayerNorm.weight": "model.layers.13.ln2.weight",
|
| 152 |
+
"decoderLayer.13.feedForward.intermediateDense2.weight": "model.layers.13.mlp.up_proj.weight",
|
| 153 |
+
"decoderLayer.14.multiHeadAttention.q.weight": "model.layers.14.self_attn.q_proj.weight",
|
| 154 |
+
"decoderLayer.14.multiHeadAttention.k.weight": "model.layers.14.self_attn.k_proj.weight",
|
| 155 |
+
"decoderLayer.14.multiHeadAttention.v.weight": "model.layers.14.self_attn.v_proj.weight",
|
| 156 |
+
"decoderLayer.14.multiHeadAttention.o.weight": "model.layers.14.self_attn.o_proj.weight",
|
| 157 |
+
"decoderLayer.14.attnLayerNorm.weight": "model.layers.14.ln1.weight",
|
| 158 |
+
"decoderLayer.14.feedForward.intermediateDense.weight": "model.layers.14.mlp.gate_proj.weight",
|
| 159 |
+
"decoderLayer.14.feedForward.outputDense.weight": "model.layers.14.mlp.down_proj.weight",
|
| 160 |
+
"decoderLayer.14.ffnLayerNorm.weight": "model.layers.14.ln2.weight",
|
| 161 |
+
"decoderLayer.14.feedForward.intermediateDense2.weight": "model.layers.14.mlp.up_proj.weight",
|
| 162 |
+
"decoderLayer.15.multiHeadAttention.q.weight": "model.layers.15.self_attn.q_proj.weight",
|
| 163 |
+
"decoderLayer.15.multiHeadAttention.k.weight": "model.layers.15.self_attn.k_proj.weight",
|
| 164 |
+
"decoderLayer.15.multiHeadAttention.v.weight": "model.layers.15.self_attn.v_proj.weight",
|
| 165 |
+
"decoderLayer.15.multiHeadAttention.o.weight": "model.layers.15.self_attn.o_proj.weight",
|
| 166 |
+
"decoderLayer.15.attnLayerNorm.weight": "model.layers.15.ln1.weight",
|
| 167 |
+
"decoderLayer.15.feedForward.intermediateDense.weight": "model.layers.15.mlp.gate_proj.weight",
|
| 168 |
+
"decoderLayer.15.feedForward.outputDense.weight": "model.layers.15.mlp.down_proj.weight",
|
| 169 |
+
"decoderLayer.15.ffnLayerNorm.weight": "model.layers.15.ln2.weight",
|
| 170 |
+
"decoderLayer.15.feedForward.intermediateDense2.weight": "model.layers.15.mlp.up_proj.weight",
|
| 171 |
+
"decoderLayer.16.multiHeadAttention.q.weight": "model.layers.16.self_attn.q_proj.weight",
|
| 172 |
+
"decoderLayer.16.multiHeadAttention.k.weight": "model.layers.16.self_attn.k_proj.weight",
|
| 173 |
+
"decoderLayer.16.multiHeadAttention.v.weight": "model.layers.16.self_attn.v_proj.weight",
|
| 174 |
+
"decoderLayer.16.multiHeadAttention.o.weight": "model.layers.16.self_attn.o_proj.weight",
|
| 175 |
+
"decoderLayer.16.attnLayerNorm.weight": "model.layers.16.ln1.weight",
|
| 176 |
+
"decoderLayer.16.feedForward.intermediateDense.weight": "model.layers.16.mlp.gate_proj.weight",
|
| 177 |
+
"decoderLayer.16.feedForward.outputDense.weight": "model.layers.16.mlp.down_proj.weight",
|
| 178 |
+
"decoderLayer.16.ffnLayerNorm.weight": "model.layers.16.ln2.weight",
|
| 179 |
+
"decoderLayer.16.feedForward.intermediateDense2.weight": "model.layers.16.mlp.up_proj.weight",
|
| 180 |
+
"decoderLayer.17.multiHeadAttention.q.weight": "model.layers.17.self_attn.q_proj.weight",
|
| 181 |
+
"decoderLayer.17.multiHeadAttention.k.weight": "model.layers.17.self_attn.k_proj.weight",
|
| 182 |
+
"decoderLayer.17.multiHeadAttention.v.weight": "model.layers.17.self_attn.v_proj.weight",
|
| 183 |
+
"decoderLayer.17.multiHeadAttention.o.weight": "model.layers.17.self_attn.o_proj.weight",
|
| 184 |
+
"decoderLayer.17.attnLayerNorm.weight": "model.layers.17.ln1.weight",
|
| 185 |
+
"decoderLayer.17.feedForward.intermediateDense.weight": "model.layers.17.mlp.gate_proj.weight",
|
| 186 |
+
"decoderLayer.17.feedForward.outputDense.weight": "model.layers.17.mlp.down_proj.weight",
|
| 187 |
+
"decoderLayer.17.ffnLayerNorm.weight": "model.layers.17.ln2.weight",
|
| 188 |
+
"decoderLayer.17.feedForward.intermediateDense2.weight": "model.layers.17.mlp.up_proj.weight",
|
| 189 |
+
"decoderLayer.18.multiHeadAttention.q.weight": "model.layers.18.self_attn.q_proj.weight",
|
| 190 |
+
"decoderLayer.18.multiHeadAttention.k.weight": "model.layers.18.self_attn.k_proj.weight",
|
| 191 |
+
"decoderLayer.18.multiHeadAttention.v.weight": "model.layers.18.self_attn.v_proj.weight",
|
| 192 |
+
"decoderLayer.18.multiHeadAttention.o.weight": "model.layers.18.self_attn.o_proj.weight",
|
| 193 |
+
"decoderLayer.18.attnLayerNorm.weight": "model.layers.18.ln1.weight",
|
| 194 |
+
"decoderLayer.18.feedForward.intermediateDense.weight": "model.layers.18.mlp.gate_proj.weight",
|
| 195 |
+
"decoderLayer.18.feedForward.outputDense.weight": "model.layers.18.mlp.down_proj.weight",
|
| 196 |
+
"decoderLayer.18.ffnLayerNorm.weight": "model.layers.18.ln2.weight",
|
| 197 |
+
"decoderLayer.18.feedForward.intermediateDense2.weight": "model.layers.18.mlp.up_proj.weight",
|
| 198 |
+
"decoderLayer.19.multiHeadAttention.q.weight": "model.layers.19.self_attn.q_proj.weight",
|
| 199 |
+
"decoderLayer.19.multiHeadAttention.k.weight": "model.layers.19.self_attn.k_proj.weight",
|
| 200 |
+
"decoderLayer.19.multiHeadAttention.v.weight": "model.layers.19.self_attn.v_proj.weight",
|
| 201 |
+
"decoderLayer.19.multiHeadAttention.o.weight": "model.layers.19.self_attn.o_proj.weight",
|
| 202 |
+
"decoderLayer.19.attnLayerNorm.weight": "model.layers.19.ln1.weight",
|
| 203 |
+
"decoderLayer.19.feedForward.intermediateDense.weight": "model.layers.19.mlp.gate_proj.weight",
|
| 204 |
+
"decoderLayer.19.feedForward.outputDense.weight": "model.layers.19.mlp.down_proj.weight",
|
| 205 |
+
"decoderLayer.19.ffnLayerNorm.weight": "model.layers.19.ln2.weight",
|
| 206 |
+
"decoderLayer.19.feedForward.intermediateDense2.weight": "model.layers.19.mlp.up_proj.weight",
|
| 207 |
+
"decoderLayer.20.multiHeadAttention.q.weight": "model.layers.20.self_attn.q_proj.weight",
|
| 208 |
+
"decoderLayer.20.multiHeadAttention.k.weight": "model.layers.20.self_attn.k_proj.weight",
|
| 209 |
+
"decoderLayer.20.multiHeadAttention.v.weight": "model.layers.20.self_attn.v_proj.weight",
|
| 210 |
+
"decoderLayer.20.multiHeadAttention.o.weight": "model.layers.20.self_attn.o_proj.weight",
|
| 211 |
+
"decoderLayer.20.attnLayerNorm.weight": "model.layers.20.ln1.weight",
|
| 212 |
+
"decoderLayer.20.feedForward.intermediateDense.weight": "model.layers.20.mlp.gate_proj.weight",
|
| 213 |
+
"decoderLayer.20.feedForward.outputDense.weight": "model.layers.20.mlp.down_proj.weight",
|
| 214 |
+
"decoderLayer.20.ffnLayerNorm.weight": "model.layers.20.ln2.weight",
|
| 215 |
+
"decoderLayer.20.feedForward.intermediateDense2.weight": "model.layers.20.mlp.up_proj.weight",
|
| 216 |
+
"decoderLayer.21.multiHeadAttention.q.weight": "model.layers.21.self_attn.q_proj.weight",
|
| 217 |
+
"decoderLayer.21.multiHeadAttention.k.weight": "model.layers.21.self_attn.k_proj.weight",
|
| 218 |
+
"decoderLayer.21.multiHeadAttention.v.weight": "model.layers.21.self_attn.v_proj.weight",
|
| 219 |
+
"decoderLayer.21.multiHeadAttention.o.weight": "model.layers.21.self_attn.o_proj.weight",
|
| 220 |
+
"decoderLayer.21.attnLayerNorm.weight": "model.layers.21.ln1.weight",
|
| 221 |
+
"decoderLayer.21.feedForward.intermediateDense.weight": "model.layers.21.mlp.gate_proj.weight",
|
| 222 |
+
"decoderLayer.21.feedForward.outputDense.weight": "model.layers.21.mlp.down_proj.weight",
|
| 223 |
+
"decoderLayer.21.ffnLayerNorm.weight": "model.layers.21.ln2.weight",
|
| 224 |
+
"decoderLayer.21.feedForward.intermediateDense2.weight": "model.layers.21.mlp.up_proj.weight",
|
| 225 |
+
"decoderLayer.22.multiHeadAttention.q.weight": "model.layers.22.self_attn.q_proj.weight",
|
| 226 |
+
"decoderLayer.22.multiHeadAttention.k.weight": "model.layers.22.self_attn.k_proj.weight",
|
| 227 |
+
"decoderLayer.22.multiHeadAttention.v.weight": "model.layers.22.self_attn.v_proj.weight",
|
| 228 |
+
"decoderLayer.22.multiHeadAttention.o.weight": "model.layers.22.self_attn.o_proj.weight",
|
| 229 |
+
"decoderLayer.22.attnLayerNorm.weight": "model.layers.22.ln1.weight",
|
| 230 |
+
"decoderLayer.22.feedForward.intermediateDense.weight": "model.layers.22.mlp.gate_proj.weight",
|
| 231 |
+
"decoderLayer.22.feedForward.outputDense.weight": "model.layers.22.mlp.down_proj.weight",
|
| 232 |
+
"decoderLayer.22.ffnLayerNorm.weight": "model.layers.22.ln2.weight",
|
| 233 |
+
"decoderLayer.22.feedForward.intermediateDense2.weight": "model.layers.22.mlp.up_proj.weight",
|
| 234 |
+
"decoderLayer.23.multiHeadAttention.q.weight": "model.layers.23.self_attn.q_proj.weight",
|
| 235 |
+
"decoderLayer.23.multiHeadAttention.k.weight": "model.layers.23.self_attn.k_proj.weight",
|
| 236 |
+
"decoderLayer.23.multiHeadAttention.v.weight": "model.layers.23.self_attn.v_proj.weight",
|
| 237 |
+
"decoderLayer.23.multiHeadAttention.o.weight": "model.layers.23.self_attn.o_proj.weight",
|
| 238 |
+
"decoderLayer.23.attnLayerNorm.weight": "model.layers.23.ln1.weight",
|
| 239 |
+
"decoderLayer.23.feedForward.intermediateDense.weight": "model.layers.23.mlp.gate_proj.weight",
|
| 240 |
+
"decoderLayer.23.feedForward.outputDense.weight": "model.layers.23.mlp.down_proj.weight",
|
| 241 |
+
"decoderLayer.23.ffnLayerNorm.weight": "model.layers.23.ln2.weight",
|
| 242 |
+
"decoderLayer.23.feedForward.intermediateDense2.weight": "model.layers.23.mlp.up_proj.weight",
|
| 243 |
+
"decoderLayer.24.multiHeadAttention.q.weight": "model.layers.24.self_attn.q_proj.weight",
|
| 244 |
+
"decoderLayer.24.multiHeadAttention.k.weight": "model.layers.24.self_attn.k_proj.weight",
|
| 245 |
+
"decoderLayer.24.multiHeadAttention.v.weight": "model.layers.24.self_attn.v_proj.weight",
|
| 246 |
+
"decoderLayer.24.multiHeadAttention.o.weight": "model.layers.24.self_attn.o_proj.weight",
|
| 247 |
+
"decoderLayer.24.attnLayerNorm.weight": "model.layers.24.ln1.weight",
|
| 248 |
+
"decoderLayer.24.feedForward.intermediateDense.weight": "model.layers.24.mlp.gate_proj.weight",
|
| 249 |
+
"decoderLayer.24.feedForward.outputDense.weight": "model.layers.24.mlp.down_proj.weight",
|
| 250 |
+
"decoderLayer.24.ffnLayerNorm.weight": "model.layers.24.ln2.weight",
|
| 251 |
+
"decoderLayer.24.feedForward.intermediateDense2.weight": "model.layers.24.mlp.up_proj.weight",
|
| 252 |
+
"decoderLayer.25.multiHeadAttention.q.weight": "model.layers.25.self_attn.q_proj.weight",
|
| 253 |
+
"decoderLayer.25.multiHeadAttention.k.weight": "model.layers.25.self_attn.k_proj.weight",
|
| 254 |
+
"decoderLayer.25.multiHeadAttention.v.weight": "model.layers.25.self_attn.v_proj.weight",
|
| 255 |
+
"decoderLayer.25.multiHeadAttention.o.weight": "model.layers.25.self_attn.o_proj.weight",
|
| 256 |
+
"decoderLayer.25.attnLayerNorm.weight": "model.layers.25.ln1.weight",
|
| 257 |
+
"decoderLayer.25.feedForward.intermediateDense.weight": "model.layers.25.mlp.gate_proj.weight",
|
| 258 |
+
"decoderLayer.25.feedForward.outputDense.weight": "model.layers.25.mlp.down_proj.weight",
|
| 259 |
+
"decoderLayer.25.ffnLayerNorm.weight": "model.layers.25.ln2.weight",
|
| 260 |
+
"decoderLayer.25.feedForward.intermediateDense2.weight": "model.layers.25.mlp.up_proj.weight",
|
| 261 |
+
"decoderLayer.26.multiHeadAttention.q.weight": "model.layers.26.self_attn.q_proj.weight",
|
| 262 |
+
"decoderLayer.26.multiHeadAttention.k.weight": "model.layers.26.self_attn.k_proj.weight",
|
| 263 |
+
"decoderLayer.26.multiHeadAttention.v.weight": "model.layers.26.self_attn.v_proj.weight",
|
| 264 |
+
"decoderLayer.26.multiHeadAttention.o.weight": "model.layers.26.self_attn.o_proj.weight",
|
| 265 |
+
"decoderLayer.26.attnLayerNorm.weight": "model.layers.26.ln1.weight",
|
| 266 |
+
"decoderLayer.26.feedForward.intermediateDense.weight": "model.layers.26.mlp.gate_proj.weight",
|
| 267 |
+
"decoderLayer.26.feedForward.outputDense.weight": "model.layers.26.mlp.down_proj.weight",
|
| 268 |
+
"decoderLayer.26.ffnLayerNorm.weight": "model.layers.26.ln2.weight",
|
| 269 |
+
"decoderLayer.26.feedForward.intermediateDense2.weight": "model.layers.26.mlp.up_proj.weight",
|
| 270 |
+
"decoderLayer.27.multiHeadAttention.q.weight": "model.layers.27.self_attn.q_proj.weight",
|
| 271 |
+
"decoderLayer.27.multiHeadAttention.k.weight": "model.layers.27.self_attn.k_proj.weight",
|
| 272 |
+
"decoderLayer.27.multiHeadAttention.v.weight": "model.layers.27.self_attn.v_proj.weight",
|
| 273 |
+
"decoderLayer.27.multiHeadAttention.o.weight": "model.layers.27.self_attn.o_proj.weight",
|
| 274 |
+
"decoderLayer.27.attnLayerNorm.weight": "model.layers.27.ln1.weight",
|
| 275 |
+
"decoderLayer.27.feedForward.intermediateDense.weight": "model.layers.27.mlp.gate_proj.weight",
|
| 276 |
+
"decoderLayer.27.feedForward.outputDense.weight": "model.layers.27.mlp.down_proj.weight",
|
| 277 |
+
"decoderLayer.27.ffnLayerNorm.weight": "model.layers.27.ln2.weight",
|
| 278 |
+
"decoderLayer.27.feedForward.intermediateDense2.weight": "model.layers.27.mlp.up_proj.weight",
|
| 279 |
+
"decoderLayer.28.multiHeadAttention.q.weight": "model.layers.28.self_attn.q_proj.weight",
|
| 280 |
+
"decoderLayer.28.multiHeadAttention.k.weight": "model.layers.28.self_attn.k_proj.weight",
|
| 281 |
+
"decoderLayer.28.multiHeadAttention.v.weight": "model.layers.28.self_attn.v_proj.weight",
|
| 282 |
+
"decoderLayer.28.multiHeadAttention.o.weight": "model.layers.28.self_attn.o_proj.weight",
|
| 283 |
+
"decoderLayer.28.attnLayerNorm.weight": "model.layers.28.ln1.weight",
|
| 284 |
+
"decoderLayer.28.feedForward.intermediateDense.weight": "model.layers.28.mlp.gate_proj.weight",
|
| 285 |
+
"decoderLayer.28.feedForward.outputDense.weight": "model.layers.28.mlp.down_proj.weight",
|
| 286 |
+
"decoderLayer.28.ffnLayerNorm.weight": "model.layers.28.ln2.weight",
|
| 287 |
+
"decoderLayer.28.feedForward.intermediateDense2.weight": "model.layers.28.mlp.up_proj.weight",
|
| 288 |
+
"decoderLayer.29.multiHeadAttention.q.weight": "model.layers.29.self_attn.q_proj.weight",
|
| 289 |
+
"decoderLayer.29.multiHeadAttention.k.weight": "model.layers.29.self_attn.k_proj.weight",
|
| 290 |
+
"decoderLayer.29.multiHeadAttention.v.weight": "model.layers.29.self_attn.v_proj.weight",
|
| 291 |
+
"decoderLayer.29.multiHeadAttention.o.weight": "model.layers.29.self_attn.o_proj.weight",
|
| 292 |
+
"decoderLayer.29.attnLayerNorm.weight": "model.layers.29.ln1.weight",
|
| 293 |
+
"decoderLayer.29.feedForward.intermediateDense.weight": "model.layers.29.mlp.gate_proj.weight",
|
| 294 |
+
"decoderLayer.29.feedForward.outputDense.weight": "model.layers.29.mlp.down_proj.weight",
|
| 295 |
+
"decoderLayer.29.ffnLayerNorm.weight": "model.layers.29.ln2.weight",
|
| 296 |
+
"decoderLayer.29.feedForward.intermediateDense2.weight": "model.layers.29.mlp.up_proj.weight",
|
| 297 |
+
"decoderLayer.30.multiHeadAttention.q.weight": "model.layers.30.self_attn.q_proj.weight",
|
| 298 |
+
"decoderLayer.30.multiHeadAttention.k.weight": "model.layers.30.self_attn.k_proj.weight",
|
| 299 |
+
"decoderLayer.30.multiHeadAttention.v.weight": "model.layers.30.self_attn.v_proj.weight",
|
| 300 |
+
"decoderLayer.30.multiHeadAttention.o.weight": "model.layers.30.self_attn.o_proj.weight",
|
| 301 |
+
"decoderLayer.30.attnLayerNorm.weight": "model.layers.30.ln1.weight",
|
| 302 |
+
"decoderLayer.30.feedForward.intermediateDense.weight": "model.layers.30.mlp.gate_proj.weight",
|
| 303 |
+
"decoderLayer.30.feedForward.outputDense.weight": "model.layers.30.mlp.down_proj.weight",
|
| 304 |
+
"decoderLayer.30.ffnLayerNorm.weight": "model.layers.30.ln2.weight",
|
| 305 |
+
"decoderLayer.30.feedForward.intermediateDense2.weight": "model.layers.30.mlp.up_proj.weight",
|
| 306 |
+
"decoderLayer.31.multiHeadAttention.q.weight": "model.layers.31.self_attn.q_proj.weight",
|
| 307 |
+
"decoderLayer.31.multiHeadAttention.k.weight": "model.layers.31.self_attn.k_proj.weight",
|
| 308 |
+
"decoderLayer.31.multiHeadAttention.v.weight": "model.layers.31.self_attn.v_proj.weight",
|
| 309 |
+
"decoderLayer.31.multiHeadAttention.o.weight": "model.layers.31.self_attn.o_proj.weight",
|
| 310 |
+
"decoderLayer.31.attnLayerNorm.weight": "model.layers.31.ln1.weight",
|
| 311 |
+
"decoderLayer.31.feedForward.intermediateDense.weight": "model.layers.31.mlp.gate_proj.weight",
|
| 312 |
+
"decoderLayer.31.feedForward.outputDense.weight": "model.layers.31.mlp.down_proj.weight",
|
| 313 |
+
"decoderLayer.31.ffnLayerNorm.weight": "model.layers.31.ln2.weight",
|
| 314 |
+
"decoderLayer.31.feedForward.intermediateDense2.weight": "model.layers.31.mlp.up_proj.weight"
|
| 315 |
+
}
|
| 316 |
+
}
|
Yi-1.5-6B/bert4torch_config.json
ADDED
|
@@ -0,0 +1,316 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 1,
|
| 3 |
+
"eos_token_id": 2,
|
| 4 |
+
"hidden_act": "silu",
|
| 5 |
+
"hidden_size": 4096,
|
| 6 |
+
"initializer_range": 0.02,
|
| 7 |
+
"intermediate_size": 11008,
|
| 8 |
+
"max_position_embeddings": 4096,
|
| 9 |
+
"model": "llama",
|
| 10 |
+
"num_attention_heads": 32,
|
| 11 |
+
"num_hidden_layers": 32,
|
| 12 |
+
"num_key_value_heads": 4,
|
| 13 |
+
"pad_token_id": 0,
|
| 14 |
+
"layer_norm_eps": 1e-06,
|
| 15 |
+
"rope_theta": 5000000.0,
|
| 16 |
+
"tie_word_embeddings": false,
|
| 17 |
+
"torch_dtype": "bfloat16",
|
| 18 |
+
"vocab_size": 64000,
|
| 19 |
+
"skip_init": true,
|
| 20 |
+
"rope_rank": "updown",
|
| 21 |
+
"segment_vocab_size": 0,
|
| 22 |
+
"generation_config": {"tokenizer_decode_config": {"skip_special_tokens": true}, "max_length": 4096, "eos_token_id": 2},
|
| 23 |
+
"mapping": {
|
| 24 |
+
"embeddings.word_embeddings.weight": "model.embed_tokens.weight",
|
| 25 |
+
"LayerNormFinal.weight": "model.norm.weight",
|
| 26 |
+
"lm_head.weight": "lm_head.weight",
|
| 27 |
+
"decoderLayer.0.multiHeadAttention.q.weight": "model.layers.0.self_attn.q_proj.weight",
|
| 28 |
+
"decoderLayer.0.multiHeadAttention.k.weight": "model.layers.0.self_attn.k_proj.weight",
|
| 29 |
+
"decoderLayer.0.multiHeadAttention.v.weight": "model.layers.0.self_attn.v_proj.weight",
|
| 30 |
+
"decoderLayer.0.multiHeadAttention.o.weight": "model.layers.0.self_attn.o_proj.weight",
|
| 31 |
+
"decoderLayer.0.attnLayerNorm.weight": "model.layers.0.ln1.weight",
|
| 32 |
+
"decoderLayer.0.feedForward.intermediateDense.weight": "model.layers.0.mlp.gate_proj.weight",
|
| 33 |
+
"decoderLayer.0.feedForward.outputDense.weight": "model.layers.0.mlp.down_proj.weight",
|
| 34 |
+
"decoderLayer.0.ffnLayerNorm.weight": "model.layers.0.ln2.weight",
|
| 35 |
+
"decoderLayer.0.feedForward.intermediateDense2.weight": "model.layers.0.mlp.up_proj.weight",
|
| 36 |
+
"decoderLayer.1.multiHeadAttention.q.weight": "model.layers.1.self_attn.q_proj.weight",
|
| 37 |
+
"decoderLayer.1.multiHeadAttention.k.weight": "model.layers.1.self_attn.k_proj.weight",
|
| 38 |
+
"decoderLayer.1.multiHeadAttention.v.weight": "model.layers.1.self_attn.v_proj.weight",
|
| 39 |
+
"decoderLayer.1.multiHeadAttention.o.weight": "model.layers.1.self_attn.o_proj.weight",
|
| 40 |
+
"decoderLayer.1.attnLayerNorm.weight": "model.layers.1.ln1.weight",
|
| 41 |
+
"decoderLayer.1.feedForward.intermediateDense.weight": "model.layers.1.mlp.gate_proj.weight",
|
| 42 |
+
"decoderLayer.1.feedForward.outputDense.weight": "model.layers.1.mlp.down_proj.weight",
|
| 43 |
+
"decoderLayer.1.ffnLayerNorm.weight": "model.layers.1.ln2.weight",
|
| 44 |
+
"decoderLayer.1.feedForward.intermediateDense2.weight": "model.layers.1.mlp.up_proj.weight",
|
| 45 |
+
"decoderLayer.2.multiHeadAttention.q.weight": "model.layers.2.self_attn.q_proj.weight",
|
| 46 |
+
"decoderLayer.2.multiHeadAttention.k.weight": "model.layers.2.self_attn.k_proj.weight",
|
| 47 |
+
"decoderLayer.2.multiHeadAttention.v.weight": "model.layers.2.self_attn.v_proj.weight",
|
| 48 |
+
"decoderLayer.2.multiHeadAttention.o.weight": "model.layers.2.self_attn.o_proj.weight",
|
| 49 |
+
"decoderLayer.2.attnLayerNorm.weight": "model.layers.2.ln1.weight",
|
| 50 |
+
"decoderLayer.2.feedForward.intermediateDense.weight": "model.layers.2.mlp.gate_proj.weight",
|
| 51 |
+
"decoderLayer.2.feedForward.outputDense.weight": "model.layers.2.mlp.down_proj.weight",
|
| 52 |
+
"decoderLayer.2.ffnLayerNorm.weight": "model.layers.2.ln2.weight",
|
| 53 |
+
"decoderLayer.2.feedForward.intermediateDense2.weight": "model.layers.2.mlp.up_proj.weight",
|
| 54 |
+
"decoderLayer.3.multiHeadAttention.q.weight": "model.layers.3.self_attn.q_proj.weight",
|
| 55 |
+
"decoderLayer.3.multiHeadAttention.k.weight": "model.layers.3.self_attn.k_proj.weight",
|
| 56 |
+
"decoderLayer.3.multiHeadAttention.v.weight": "model.layers.3.self_attn.v_proj.weight",
|
| 57 |
+
"decoderLayer.3.multiHeadAttention.o.weight": "model.layers.3.self_attn.o_proj.weight",
|
| 58 |
+
"decoderLayer.3.attnLayerNorm.weight": "model.layers.3.ln1.weight",
|
| 59 |
+
"decoderLayer.3.feedForward.intermediateDense.weight": "model.layers.3.mlp.gate_proj.weight",
|
| 60 |
+
"decoderLayer.3.feedForward.outputDense.weight": "model.layers.3.mlp.down_proj.weight",
|
| 61 |
+
"decoderLayer.3.ffnLayerNorm.weight": "model.layers.3.ln2.weight",
|
| 62 |
+
"decoderLayer.3.feedForward.intermediateDense2.weight": "model.layers.3.mlp.up_proj.weight",
|
| 63 |
+
"decoderLayer.4.multiHeadAttention.q.weight": "model.layers.4.self_attn.q_proj.weight",
|
| 64 |
+
"decoderLayer.4.multiHeadAttention.k.weight": "model.layers.4.self_attn.k_proj.weight",
|
| 65 |
+
"decoderLayer.4.multiHeadAttention.v.weight": "model.layers.4.self_attn.v_proj.weight",
|
| 66 |
+
"decoderLayer.4.multiHeadAttention.o.weight": "model.layers.4.self_attn.o_proj.weight",
|
| 67 |
+
"decoderLayer.4.attnLayerNorm.weight": "model.layers.4.ln1.weight",
|
| 68 |
+
"decoderLayer.4.feedForward.intermediateDense.weight": "model.layers.4.mlp.gate_proj.weight",
|
| 69 |
+
"decoderLayer.4.feedForward.outputDense.weight": "model.layers.4.mlp.down_proj.weight",
|
| 70 |
+
"decoderLayer.4.ffnLayerNorm.weight": "model.layers.4.ln2.weight",
|
| 71 |
+
"decoderLayer.4.feedForward.intermediateDense2.weight": "model.layers.4.mlp.up_proj.weight",
|
| 72 |
+
"decoderLayer.5.multiHeadAttention.q.weight": "model.layers.5.self_attn.q_proj.weight",
|
| 73 |
+
"decoderLayer.5.multiHeadAttention.k.weight": "model.layers.5.self_attn.k_proj.weight",
|
| 74 |
+
"decoderLayer.5.multiHeadAttention.v.weight": "model.layers.5.self_attn.v_proj.weight",
|
| 75 |
+
"decoderLayer.5.multiHeadAttention.o.weight": "model.layers.5.self_attn.o_proj.weight",
|
| 76 |
+
"decoderLayer.5.attnLayerNorm.weight": "model.layers.5.ln1.weight",
|
| 77 |
+
"decoderLayer.5.feedForward.intermediateDense.weight": "model.layers.5.mlp.gate_proj.weight",
|
| 78 |
+
"decoderLayer.5.feedForward.outputDense.weight": "model.layers.5.mlp.down_proj.weight",
|
| 79 |
+
"decoderLayer.5.ffnLayerNorm.weight": "model.layers.5.ln2.weight",
|
| 80 |
+
"decoderLayer.5.feedForward.intermediateDense2.weight": "model.layers.5.mlp.up_proj.weight",
|
| 81 |
+
"decoderLayer.6.multiHeadAttention.q.weight": "model.layers.6.self_attn.q_proj.weight",
|
| 82 |
+
"decoderLayer.6.multiHeadAttention.k.weight": "model.layers.6.self_attn.k_proj.weight",
|
| 83 |
+
"decoderLayer.6.multiHeadAttention.v.weight": "model.layers.6.self_attn.v_proj.weight",
|
| 84 |
+
"decoderLayer.6.multiHeadAttention.o.weight": "model.layers.6.self_attn.o_proj.weight",
|
| 85 |
+
"decoderLayer.6.attnLayerNorm.weight": "model.layers.6.ln1.weight",
|
| 86 |
+
"decoderLayer.6.feedForward.intermediateDense.weight": "model.layers.6.mlp.gate_proj.weight",
|
| 87 |
+
"decoderLayer.6.feedForward.outputDense.weight": "model.layers.6.mlp.down_proj.weight",
|
| 88 |
+
"decoderLayer.6.ffnLayerNorm.weight": "model.layers.6.ln2.weight",
|
| 89 |
+
"decoderLayer.6.feedForward.intermediateDense2.weight": "model.layers.6.mlp.up_proj.weight",
|
| 90 |
+
"decoderLayer.7.multiHeadAttention.q.weight": "model.layers.7.self_attn.q_proj.weight",
|
| 91 |
+
"decoderLayer.7.multiHeadAttention.k.weight": "model.layers.7.self_attn.k_proj.weight",
|
| 92 |
+
"decoderLayer.7.multiHeadAttention.v.weight": "model.layers.7.self_attn.v_proj.weight",
|
| 93 |
+
"decoderLayer.7.multiHeadAttention.o.weight": "model.layers.7.self_attn.o_proj.weight",
|
| 94 |
+
"decoderLayer.7.attnLayerNorm.weight": "model.layers.7.ln1.weight",
|
| 95 |
+
"decoderLayer.7.feedForward.intermediateDense.weight": "model.layers.7.mlp.gate_proj.weight",
|
| 96 |
+
"decoderLayer.7.feedForward.outputDense.weight": "model.layers.7.mlp.down_proj.weight",
|
| 97 |
+
"decoderLayer.7.ffnLayerNorm.weight": "model.layers.7.ln2.weight",
|
| 98 |
+
"decoderLayer.7.feedForward.intermediateDense2.weight": "model.layers.7.mlp.up_proj.weight",
|
| 99 |
+
"decoderLayer.8.multiHeadAttention.q.weight": "model.layers.8.self_attn.q_proj.weight",
|
| 100 |
+
"decoderLayer.8.multiHeadAttention.k.weight": "model.layers.8.self_attn.k_proj.weight",
|
| 101 |
+
"decoderLayer.8.multiHeadAttention.v.weight": "model.layers.8.self_attn.v_proj.weight",
|
| 102 |
+
"decoderLayer.8.multiHeadAttention.o.weight": "model.layers.8.self_attn.o_proj.weight",
|
| 103 |
+
"decoderLayer.8.attnLayerNorm.weight": "model.layers.8.ln1.weight",
|
| 104 |
+
"decoderLayer.8.feedForward.intermediateDense.weight": "model.layers.8.mlp.gate_proj.weight",
|
| 105 |
+
"decoderLayer.8.feedForward.outputDense.weight": "model.layers.8.mlp.down_proj.weight",
|
| 106 |
+
"decoderLayer.8.ffnLayerNorm.weight": "model.layers.8.ln2.weight",
|
| 107 |
+
"decoderLayer.8.feedForward.intermediateDense2.weight": "model.layers.8.mlp.up_proj.weight",
|
| 108 |
+
"decoderLayer.9.multiHeadAttention.q.weight": "model.layers.9.self_attn.q_proj.weight",
|
| 109 |
+
"decoderLayer.9.multiHeadAttention.k.weight": "model.layers.9.self_attn.k_proj.weight",
|
| 110 |
+
"decoderLayer.9.multiHeadAttention.v.weight": "model.layers.9.self_attn.v_proj.weight",
|
| 111 |
+
"decoderLayer.9.multiHeadAttention.o.weight": "model.layers.9.self_attn.o_proj.weight",
|
| 112 |
+
"decoderLayer.9.attnLayerNorm.weight": "model.layers.9.ln1.weight",
|
| 113 |
+
"decoderLayer.9.feedForward.intermediateDense.weight": "model.layers.9.mlp.gate_proj.weight",
|
| 114 |
+
"decoderLayer.9.feedForward.outputDense.weight": "model.layers.9.mlp.down_proj.weight",
|
| 115 |
+
"decoderLayer.9.ffnLayerNorm.weight": "model.layers.9.ln2.weight",
|
| 116 |
+
"decoderLayer.9.feedForward.intermediateDense2.weight": "model.layers.9.mlp.up_proj.weight",
|
| 117 |
+
"decoderLayer.10.multiHeadAttention.q.weight": "model.layers.10.self_attn.q_proj.weight",
|
| 118 |
+
"decoderLayer.10.multiHeadAttention.k.weight": "model.layers.10.self_attn.k_proj.weight",
|
| 119 |
+
"decoderLayer.10.multiHeadAttention.v.weight": "model.layers.10.self_attn.v_proj.weight",
|
| 120 |
+
"decoderLayer.10.multiHeadAttention.o.weight": "model.layers.10.self_attn.o_proj.weight",
|
| 121 |
+
"decoderLayer.10.attnLayerNorm.weight": "model.layers.10.ln1.weight",
|
| 122 |
+
"decoderLayer.10.feedForward.intermediateDense.weight": "model.layers.10.mlp.gate_proj.weight",
|
| 123 |
+
"decoderLayer.10.feedForward.outputDense.weight": "model.layers.10.mlp.down_proj.weight",
|
| 124 |
+
"decoderLayer.10.ffnLayerNorm.weight": "model.layers.10.ln2.weight",
|
| 125 |
+
"decoderLayer.10.feedForward.intermediateDense2.weight": "model.layers.10.mlp.up_proj.weight",
|
| 126 |
+
"decoderLayer.11.multiHeadAttention.q.weight": "model.layers.11.self_attn.q_proj.weight",
|
| 127 |
+
"decoderLayer.11.multiHeadAttention.k.weight": "model.layers.11.self_attn.k_proj.weight",
|
| 128 |
+
"decoderLayer.11.multiHeadAttention.v.weight": "model.layers.11.self_attn.v_proj.weight",
|
| 129 |
+
"decoderLayer.11.multiHeadAttention.o.weight": "model.layers.11.self_attn.o_proj.weight",
|
| 130 |
+
"decoderLayer.11.attnLayerNorm.weight": "model.layers.11.ln1.weight",
|
| 131 |
+
"decoderLayer.11.feedForward.intermediateDense.weight": "model.layers.11.mlp.gate_proj.weight",
|
| 132 |
+
"decoderLayer.11.feedForward.outputDense.weight": "model.layers.11.mlp.down_proj.weight",
|
| 133 |
+
"decoderLayer.11.ffnLayerNorm.weight": "model.layers.11.ln2.weight",
|
| 134 |
+
"decoderLayer.11.feedForward.intermediateDense2.weight": "model.layers.11.mlp.up_proj.weight",
|
| 135 |
+
"decoderLayer.12.multiHeadAttention.q.weight": "model.layers.12.self_attn.q_proj.weight",
|
| 136 |
+
"decoderLayer.12.multiHeadAttention.k.weight": "model.layers.12.self_attn.k_proj.weight",
|
| 137 |
+
"decoderLayer.12.multiHeadAttention.v.weight": "model.layers.12.self_attn.v_proj.weight",
|
| 138 |
+
"decoderLayer.12.multiHeadAttention.o.weight": "model.layers.12.self_attn.o_proj.weight",
|
| 139 |
+
"decoderLayer.12.attnLayerNorm.weight": "model.layers.12.ln1.weight",
|
| 140 |
+
"decoderLayer.12.feedForward.intermediateDense.weight": "model.layers.12.mlp.gate_proj.weight",
|
| 141 |
+
"decoderLayer.12.feedForward.outputDense.weight": "model.layers.12.mlp.down_proj.weight",
|
| 142 |
+
"decoderLayer.12.ffnLayerNorm.weight": "model.layers.12.ln2.weight",
|
| 143 |
+
"decoderLayer.12.feedForward.intermediateDense2.weight": "model.layers.12.mlp.up_proj.weight",
|
| 144 |
+
"decoderLayer.13.multiHeadAttention.q.weight": "model.layers.13.self_attn.q_proj.weight",
|
| 145 |
+
"decoderLayer.13.multiHeadAttention.k.weight": "model.layers.13.self_attn.k_proj.weight",
|
| 146 |
+
"decoderLayer.13.multiHeadAttention.v.weight": "model.layers.13.self_attn.v_proj.weight",
|
| 147 |
+
"decoderLayer.13.multiHeadAttention.o.weight": "model.layers.13.self_attn.o_proj.weight",
|
| 148 |
+
"decoderLayer.13.attnLayerNorm.weight": "model.layers.13.ln1.weight",
|
| 149 |
+
"decoderLayer.13.feedForward.intermediateDense.weight": "model.layers.13.mlp.gate_proj.weight",
|
| 150 |
+
"decoderLayer.13.feedForward.outputDense.weight": "model.layers.13.mlp.down_proj.weight",
|
| 151 |
+
"decoderLayer.13.ffnLayerNorm.weight": "model.layers.13.ln2.weight",
|
| 152 |
+
"decoderLayer.13.feedForward.intermediateDense2.weight": "model.layers.13.mlp.up_proj.weight",
|
| 153 |
+
"decoderLayer.14.multiHeadAttention.q.weight": "model.layers.14.self_attn.q_proj.weight",
|
| 154 |
+
"decoderLayer.14.multiHeadAttention.k.weight": "model.layers.14.self_attn.k_proj.weight",
|
| 155 |
+
"decoderLayer.14.multiHeadAttention.v.weight": "model.layers.14.self_attn.v_proj.weight",
|
| 156 |
+
"decoderLayer.14.multiHeadAttention.o.weight": "model.layers.14.self_attn.o_proj.weight",
|
| 157 |
+
"decoderLayer.14.attnLayerNorm.weight": "model.layers.14.ln1.weight",
|
| 158 |
+
"decoderLayer.14.feedForward.intermediateDense.weight": "model.layers.14.mlp.gate_proj.weight",
|
| 159 |
+
"decoderLayer.14.feedForward.outputDense.weight": "model.layers.14.mlp.down_proj.weight",
|
| 160 |
+
"decoderLayer.14.ffnLayerNorm.weight": "model.layers.14.ln2.weight",
|
| 161 |
+
"decoderLayer.14.feedForward.intermediateDense2.weight": "model.layers.14.mlp.up_proj.weight",
|
| 162 |
+
"decoderLayer.15.multiHeadAttention.q.weight": "model.layers.15.self_attn.q_proj.weight",
|
| 163 |
+
"decoderLayer.15.multiHeadAttention.k.weight": "model.layers.15.self_attn.k_proj.weight",
|
| 164 |
+
"decoderLayer.15.multiHeadAttention.v.weight": "model.layers.15.self_attn.v_proj.weight",
|
| 165 |
+
"decoderLayer.15.multiHeadAttention.o.weight": "model.layers.15.self_attn.o_proj.weight",
|
| 166 |
+
"decoderLayer.15.attnLayerNorm.weight": "model.layers.15.ln1.weight",
|
| 167 |
+
"decoderLayer.15.feedForward.intermediateDense.weight": "model.layers.15.mlp.gate_proj.weight",
|
| 168 |
+
"decoderLayer.15.feedForward.outputDense.weight": "model.layers.15.mlp.down_proj.weight",
|
| 169 |
+
"decoderLayer.15.ffnLayerNorm.weight": "model.layers.15.ln2.weight",
|
| 170 |
+
"decoderLayer.15.feedForward.intermediateDense2.weight": "model.layers.15.mlp.up_proj.weight",
|
| 171 |
+
"decoderLayer.16.multiHeadAttention.q.weight": "model.layers.16.self_attn.q_proj.weight",
|
| 172 |
+
"decoderLayer.16.multiHeadAttention.k.weight": "model.layers.16.self_attn.k_proj.weight",
|
| 173 |
+
"decoderLayer.16.multiHeadAttention.v.weight": "model.layers.16.self_attn.v_proj.weight",
|
| 174 |
+
"decoderLayer.16.multiHeadAttention.o.weight": "model.layers.16.self_attn.o_proj.weight",
|
| 175 |
+
"decoderLayer.16.attnLayerNorm.weight": "model.layers.16.ln1.weight",
|
| 176 |
+
"decoderLayer.16.feedForward.intermediateDense.weight": "model.layers.16.mlp.gate_proj.weight",
|
| 177 |
+
"decoderLayer.16.feedForward.outputDense.weight": "model.layers.16.mlp.down_proj.weight",
|
| 178 |
+
"decoderLayer.16.ffnLayerNorm.weight": "model.layers.16.ln2.weight",
|
| 179 |
+
"decoderLayer.16.feedForward.intermediateDense2.weight": "model.layers.16.mlp.up_proj.weight",
|
| 180 |
+
"decoderLayer.17.multiHeadAttention.q.weight": "model.layers.17.self_attn.q_proj.weight",
|
| 181 |
+
"decoderLayer.17.multiHeadAttention.k.weight": "model.layers.17.self_attn.k_proj.weight",
|
| 182 |
+
"decoderLayer.17.multiHeadAttention.v.weight": "model.layers.17.self_attn.v_proj.weight",
|
| 183 |
+
"decoderLayer.17.multiHeadAttention.o.weight": "model.layers.17.self_attn.o_proj.weight",
|
| 184 |
+
"decoderLayer.17.attnLayerNorm.weight": "model.layers.17.ln1.weight",
|
| 185 |
+
"decoderLayer.17.feedForward.intermediateDense.weight": "model.layers.17.mlp.gate_proj.weight",
|
| 186 |
+
"decoderLayer.17.feedForward.outputDense.weight": "model.layers.17.mlp.down_proj.weight",
|
| 187 |
+
"decoderLayer.17.ffnLayerNorm.weight": "model.layers.17.ln2.weight",
|
| 188 |
+
"decoderLayer.17.feedForward.intermediateDense2.weight": "model.layers.17.mlp.up_proj.weight",
|
| 189 |
+
"decoderLayer.18.multiHeadAttention.q.weight": "model.layers.18.self_attn.q_proj.weight",
|
| 190 |
+
"decoderLayer.18.multiHeadAttention.k.weight": "model.layers.18.self_attn.k_proj.weight",
|
| 191 |
+
"decoderLayer.18.multiHeadAttention.v.weight": "model.layers.18.self_attn.v_proj.weight",
|
| 192 |
+
"decoderLayer.18.multiHeadAttention.o.weight": "model.layers.18.self_attn.o_proj.weight",
|
| 193 |
+
"decoderLayer.18.attnLayerNorm.weight": "model.layers.18.ln1.weight",
|
| 194 |
+
"decoderLayer.18.feedForward.intermediateDense.weight": "model.layers.18.mlp.gate_proj.weight",
|
| 195 |
+
"decoderLayer.18.feedForward.outputDense.weight": "model.layers.18.mlp.down_proj.weight",
|
| 196 |
+
"decoderLayer.18.ffnLayerNorm.weight": "model.layers.18.ln2.weight",
|
| 197 |
+
"decoderLayer.18.feedForward.intermediateDense2.weight": "model.layers.18.mlp.up_proj.weight",
|
| 198 |
+
"decoderLayer.19.multiHeadAttention.q.weight": "model.layers.19.self_attn.q_proj.weight",
|
| 199 |
+
"decoderLayer.19.multiHeadAttention.k.weight": "model.layers.19.self_attn.k_proj.weight",
|
| 200 |
+
"decoderLayer.19.multiHeadAttention.v.weight": "model.layers.19.self_attn.v_proj.weight",
|
| 201 |
+
"decoderLayer.19.multiHeadAttention.o.weight": "model.layers.19.self_attn.o_proj.weight",
|
| 202 |
+
"decoderLayer.19.attnLayerNorm.weight": "model.layers.19.ln1.weight",
|
| 203 |
+
"decoderLayer.19.feedForward.intermediateDense.weight": "model.layers.19.mlp.gate_proj.weight",
|
| 204 |
+
"decoderLayer.19.feedForward.outputDense.weight": "model.layers.19.mlp.down_proj.weight",
|
| 205 |
+
"decoderLayer.19.ffnLayerNorm.weight": "model.layers.19.ln2.weight",
|
| 206 |
+
"decoderLayer.19.feedForward.intermediateDense2.weight": "model.layers.19.mlp.up_proj.weight",
|
| 207 |
+
"decoderLayer.20.multiHeadAttention.q.weight": "model.layers.20.self_attn.q_proj.weight",
|
| 208 |
+
"decoderLayer.20.multiHeadAttention.k.weight": "model.layers.20.self_attn.k_proj.weight",
|
| 209 |
+
"decoderLayer.20.multiHeadAttention.v.weight": "model.layers.20.self_attn.v_proj.weight",
|
| 210 |
+
"decoderLayer.20.multiHeadAttention.o.weight": "model.layers.20.self_attn.o_proj.weight",
|
| 211 |
+
"decoderLayer.20.attnLayerNorm.weight": "model.layers.20.ln1.weight",
|
| 212 |
+
"decoderLayer.20.feedForward.intermediateDense.weight": "model.layers.20.mlp.gate_proj.weight",
|
| 213 |
+
"decoderLayer.20.feedForward.outputDense.weight": "model.layers.20.mlp.down_proj.weight",
|
| 214 |
+
"decoderLayer.20.ffnLayerNorm.weight": "model.layers.20.ln2.weight",
|
| 215 |
+
"decoderLayer.20.feedForward.intermediateDense2.weight": "model.layers.20.mlp.up_proj.weight",
|
| 216 |
+
"decoderLayer.21.multiHeadAttention.q.weight": "model.layers.21.self_attn.q_proj.weight",
|
| 217 |
+
"decoderLayer.21.multiHeadAttention.k.weight": "model.layers.21.self_attn.k_proj.weight",
|
| 218 |
+
"decoderLayer.21.multiHeadAttention.v.weight": "model.layers.21.self_attn.v_proj.weight",
|
| 219 |
+
"decoderLayer.21.multiHeadAttention.o.weight": "model.layers.21.self_attn.o_proj.weight",
|
| 220 |
+
"decoderLayer.21.attnLayerNorm.weight": "model.layers.21.ln1.weight",
|
| 221 |
+
"decoderLayer.21.feedForward.intermediateDense.weight": "model.layers.21.mlp.gate_proj.weight",
|
| 222 |
+
"decoderLayer.21.feedForward.outputDense.weight": "model.layers.21.mlp.down_proj.weight",
|
| 223 |
+
"decoderLayer.21.ffnLayerNorm.weight": "model.layers.21.ln2.weight",
|
| 224 |
+
"decoderLayer.21.feedForward.intermediateDense2.weight": "model.layers.21.mlp.up_proj.weight",
|
| 225 |
+
"decoderLayer.22.multiHeadAttention.q.weight": "model.layers.22.self_attn.q_proj.weight",
|
| 226 |
+
"decoderLayer.22.multiHeadAttention.k.weight": "model.layers.22.self_attn.k_proj.weight",
|
| 227 |
+
"decoderLayer.22.multiHeadAttention.v.weight": "model.layers.22.self_attn.v_proj.weight",
|
| 228 |
+
"decoderLayer.22.multiHeadAttention.o.weight": "model.layers.22.self_attn.o_proj.weight",
|
| 229 |
+
"decoderLayer.22.attnLayerNorm.weight": "model.layers.22.ln1.weight",
|
| 230 |
+
"decoderLayer.22.feedForward.intermediateDense.weight": "model.layers.22.mlp.gate_proj.weight",
|
| 231 |
+
"decoderLayer.22.feedForward.outputDense.weight": "model.layers.22.mlp.down_proj.weight",
|
| 232 |
+
"decoderLayer.22.ffnLayerNorm.weight": "model.layers.22.ln2.weight",
|
| 233 |
+
"decoderLayer.22.feedForward.intermediateDense2.weight": "model.layers.22.mlp.up_proj.weight",
|
| 234 |
+
"decoderLayer.23.multiHeadAttention.q.weight": "model.layers.23.self_attn.q_proj.weight",
|
| 235 |
+
"decoderLayer.23.multiHeadAttention.k.weight": "model.layers.23.self_attn.k_proj.weight",
|
| 236 |
+
"decoderLayer.23.multiHeadAttention.v.weight": "model.layers.23.self_attn.v_proj.weight",
|
| 237 |
+
"decoderLayer.23.multiHeadAttention.o.weight": "model.layers.23.self_attn.o_proj.weight",
|
| 238 |
+
"decoderLayer.23.attnLayerNorm.weight": "model.layers.23.ln1.weight",
|
| 239 |
+
"decoderLayer.23.feedForward.intermediateDense.weight": "model.layers.23.mlp.gate_proj.weight",
|
| 240 |
+
"decoderLayer.23.feedForward.outputDense.weight": "model.layers.23.mlp.down_proj.weight",
|
| 241 |
+
"decoderLayer.23.ffnLayerNorm.weight": "model.layers.23.ln2.weight",
|
| 242 |
+
"decoderLayer.23.feedForward.intermediateDense2.weight": "model.layers.23.mlp.up_proj.weight",
|
| 243 |
+
"decoderLayer.24.multiHeadAttention.q.weight": "model.layers.24.self_attn.q_proj.weight",
|
| 244 |
+
"decoderLayer.24.multiHeadAttention.k.weight": "model.layers.24.self_attn.k_proj.weight",
|
| 245 |
+
"decoderLayer.24.multiHeadAttention.v.weight": "model.layers.24.self_attn.v_proj.weight",
|
| 246 |
+
"decoderLayer.24.multiHeadAttention.o.weight": "model.layers.24.self_attn.o_proj.weight",
|
| 247 |
+
"decoderLayer.24.attnLayerNorm.weight": "model.layers.24.ln1.weight",
|
| 248 |
+
"decoderLayer.24.feedForward.intermediateDense.weight": "model.layers.24.mlp.gate_proj.weight",
|
| 249 |
+
"decoderLayer.24.feedForward.outputDense.weight": "model.layers.24.mlp.down_proj.weight",
|
| 250 |
+
"decoderLayer.24.ffnLayerNorm.weight": "model.layers.24.ln2.weight",
|
| 251 |
+
"decoderLayer.24.feedForward.intermediateDense2.weight": "model.layers.24.mlp.up_proj.weight",
|
| 252 |
+
"decoderLayer.25.multiHeadAttention.q.weight": "model.layers.25.self_attn.q_proj.weight",
|
| 253 |
+
"decoderLayer.25.multiHeadAttention.k.weight": "model.layers.25.self_attn.k_proj.weight",
|
| 254 |
+
"decoderLayer.25.multiHeadAttention.v.weight": "model.layers.25.self_attn.v_proj.weight",
|
| 255 |
+
"decoderLayer.25.multiHeadAttention.o.weight": "model.layers.25.self_attn.o_proj.weight",
|
| 256 |
+
"decoderLayer.25.attnLayerNorm.weight": "model.layers.25.ln1.weight",
|
| 257 |
+
"decoderLayer.25.feedForward.intermediateDense.weight": "model.layers.25.mlp.gate_proj.weight",
|
| 258 |
+
"decoderLayer.25.feedForward.outputDense.weight": "model.layers.25.mlp.down_proj.weight",
|
| 259 |
+
"decoderLayer.25.ffnLayerNorm.weight": "model.layers.25.ln2.weight",
|
| 260 |
+
"decoderLayer.25.feedForward.intermediateDense2.weight": "model.layers.25.mlp.up_proj.weight",
|
| 261 |
+
"decoderLayer.26.multiHeadAttention.q.weight": "model.layers.26.self_attn.q_proj.weight",
|
| 262 |
+
"decoderLayer.26.multiHeadAttention.k.weight": "model.layers.26.self_attn.k_proj.weight",
|
| 263 |
+
"decoderLayer.26.multiHeadAttention.v.weight": "model.layers.26.self_attn.v_proj.weight",
|
| 264 |
+
"decoderLayer.26.multiHeadAttention.o.weight": "model.layers.26.self_attn.o_proj.weight",
|
| 265 |
+
"decoderLayer.26.attnLayerNorm.weight": "model.layers.26.ln1.weight",
|
| 266 |
+
"decoderLayer.26.feedForward.intermediateDense.weight": "model.layers.26.mlp.gate_proj.weight",
|
| 267 |
+
"decoderLayer.26.feedForward.outputDense.weight": "model.layers.26.mlp.down_proj.weight",
|
| 268 |
+
"decoderLayer.26.ffnLayerNorm.weight": "model.layers.26.ln2.weight",
|
| 269 |
+
"decoderLayer.26.feedForward.intermediateDense2.weight": "model.layers.26.mlp.up_proj.weight",
|
| 270 |
+
"decoderLayer.27.multiHeadAttention.q.weight": "model.layers.27.self_attn.q_proj.weight",
|
| 271 |
+
"decoderLayer.27.multiHeadAttention.k.weight": "model.layers.27.self_attn.k_proj.weight",
|
| 272 |
+
"decoderLayer.27.multiHeadAttention.v.weight": "model.layers.27.self_attn.v_proj.weight",
|
| 273 |
+
"decoderLayer.27.multiHeadAttention.o.weight": "model.layers.27.self_attn.o_proj.weight",
|
| 274 |
+
"decoderLayer.27.attnLayerNorm.weight": "model.layers.27.ln1.weight",
|
| 275 |
+
"decoderLayer.27.feedForward.intermediateDense.weight": "model.layers.27.mlp.gate_proj.weight",
|
| 276 |
+
"decoderLayer.27.feedForward.outputDense.weight": "model.layers.27.mlp.down_proj.weight",
|
| 277 |
+
"decoderLayer.27.ffnLayerNorm.weight": "model.layers.27.ln2.weight",
|
| 278 |
+
"decoderLayer.27.feedForward.intermediateDense2.weight": "model.layers.27.mlp.up_proj.weight",
|
| 279 |
+
"decoderLayer.28.multiHeadAttention.q.weight": "model.layers.28.self_attn.q_proj.weight",
|
| 280 |
+
"decoderLayer.28.multiHeadAttention.k.weight": "model.layers.28.self_attn.k_proj.weight",
|
| 281 |
+
"decoderLayer.28.multiHeadAttention.v.weight": "model.layers.28.self_attn.v_proj.weight",
|
| 282 |
+
"decoderLayer.28.multiHeadAttention.o.weight": "model.layers.28.self_attn.o_proj.weight",
|
| 283 |
+
"decoderLayer.28.attnLayerNorm.weight": "model.layers.28.ln1.weight",
|
| 284 |
+
"decoderLayer.28.feedForward.intermediateDense.weight": "model.layers.28.mlp.gate_proj.weight",
|
| 285 |
+
"decoderLayer.28.feedForward.outputDense.weight": "model.layers.28.mlp.down_proj.weight",
|
| 286 |
+
"decoderLayer.28.ffnLayerNorm.weight": "model.layers.28.ln2.weight",
|
| 287 |
+
"decoderLayer.28.feedForward.intermediateDense2.weight": "model.layers.28.mlp.up_proj.weight",
|
| 288 |
+
"decoderLayer.29.multiHeadAttention.q.weight": "model.layers.29.self_attn.q_proj.weight",
|
| 289 |
+
"decoderLayer.29.multiHeadAttention.k.weight": "model.layers.29.self_attn.k_proj.weight",
|
| 290 |
+
"decoderLayer.29.multiHeadAttention.v.weight": "model.layers.29.self_attn.v_proj.weight",
|
| 291 |
+
"decoderLayer.29.multiHeadAttention.o.weight": "model.layers.29.self_attn.o_proj.weight",
|
| 292 |
+
"decoderLayer.29.attnLayerNorm.weight": "model.layers.29.ln1.weight",
|
| 293 |
+
"decoderLayer.29.feedForward.intermediateDense.weight": "model.layers.29.mlp.gate_proj.weight",
|
| 294 |
+
"decoderLayer.29.feedForward.outputDense.weight": "model.layers.29.mlp.down_proj.weight",
|
| 295 |
+
"decoderLayer.29.ffnLayerNorm.weight": "model.layers.29.ln2.weight",
|
| 296 |
+
"decoderLayer.29.feedForward.intermediateDense2.weight": "model.layers.29.mlp.up_proj.weight",
|
| 297 |
+
"decoderLayer.30.multiHeadAttention.q.weight": "model.layers.30.self_attn.q_proj.weight",
|
| 298 |
+
"decoderLayer.30.multiHeadAttention.k.weight": "model.layers.30.self_attn.k_proj.weight",
|
| 299 |
+
"decoderLayer.30.multiHeadAttention.v.weight": "model.layers.30.self_attn.v_proj.weight",
|
| 300 |
+
"decoderLayer.30.multiHeadAttention.o.weight": "model.layers.30.self_attn.o_proj.weight",
|
| 301 |
+
"decoderLayer.30.attnLayerNorm.weight": "model.layers.30.ln1.weight",
|
| 302 |
+
"decoderLayer.30.feedForward.intermediateDense.weight": "model.layers.30.mlp.gate_proj.weight",
|
| 303 |
+
"decoderLayer.30.feedForward.outputDense.weight": "model.layers.30.mlp.down_proj.weight",
|
| 304 |
+
"decoderLayer.30.ffnLayerNorm.weight": "model.layers.30.ln2.weight",
|
| 305 |
+
"decoderLayer.30.feedForward.intermediateDense2.weight": "model.layers.30.mlp.up_proj.weight",
|
| 306 |
+
"decoderLayer.31.multiHeadAttention.q.weight": "model.layers.31.self_attn.q_proj.weight",
|
| 307 |
+
"decoderLayer.31.multiHeadAttention.k.weight": "model.layers.31.self_attn.k_proj.weight",
|
| 308 |
+
"decoderLayer.31.multiHeadAttention.v.weight": "model.layers.31.self_attn.v_proj.weight",
|
| 309 |
+
"decoderLayer.31.multiHeadAttention.o.weight": "model.layers.31.self_attn.o_proj.weight",
|
| 310 |
+
"decoderLayer.31.attnLayerNorm.weight": "model.layers.31.ln1.weight",
|
| 311 |
+
"decoderLayer.31.feedForward.intermediateDense.weight": "model.layers.31.mlp.gate_proj.weight",
|
| 312 |
+
"decoderLayer.31.feedForward.outputDense.weight": "model.layers.31.mlp.down_proj.weight",
|
| 313 |
+
"decoderLayer.31.ffnLayerNorm.weight": "model.layers.31.ln2.weight",
|
| 314 |
+
"decoderLayer.31.feedForward.intermediateDense2.weight": "model.layers.31.mlp.up_proj.weight"
|
| 315 |
+
}
|
| 316 |
+
}
|
Yi-1.5-9B-32K/bert4torch_config.json
ADDED
|
@@ -0,0 +1,460 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 1,
|
| 3 |
+
"eos_token_id": 2,
|
| 4 |
+
"hidden_act": "silu",
|
| 5 |
+
"hidden_size": 4096,
|
| 6 |
+
"initializer_range": 0.02,
|
| 7 |
+
"intermediate_size": 11008,
|
| 8 |
+
"max_position_embeddings": 32768,
|
| 9 |
+
"model": "llama",
|
| 10 |
+
"num_attention_heads": 32,
|
| 11 |
+
"num_hidden_layers": 48,
|
| 12 |
+
"num_key_value_heads": 4,
|
| 13 |
+
"pad_token_id": 0,
|
| 14 |
+
"layer_norm_eps": 1e-06,
|
| 15 |
+
"rope_theta": 5000000.0,
|
| 16 |
+
"tie_word_embeddings": false,
|
| 17 |
+
"torch_dtype": "bfloat16",
|
| 18 |
+
"vocab_size": 64000,
|
| 19 |
+
"skip_init": true,
|
| 20 |
+
"rope_rank": "updown",
|
| 21 |
+
"segment_vocab_size": 0,
|
| 22 |
+
"generation_config": {"tokenizer_decode_config": {"skip_special_tokens": true}, "max_length": 32768, "eos_token_id": 2},
|
| 23 |
+
"mapping": {
|
| 24 |
+
"embeddings.word_embeddings.weight": "model.embed_tokens.weight",
|
| 25 |
+
"LayerNormFinal.weight": "model.norm.weight",
|
| 26 |
+
"lm_head.weight": "lm_head.weight",
|
| 27 |
+
"decoderLayer.0.multiHeadAttention.q.weight": "model.layers.0.self_attn.q_proj.weight",
|
| 28 |
+
"decoderLayer.0.multiHeadAttention.k.weight": "model.layers.0.self_attn.k_proj.weight",
|
| 29 |
+
"decoderLayer.0.multiHeadAttention.v.weight": "model.layers.0.self_attn.v_proj.weight",
|
| 30 |
+
"decoderLayer.0.multiHeadAttention.o.weight": "model.layers.0.self_attn.o_proj.weight",
|
| 31 |
+
"decoderLayer.0.attnLayerNorm.weight": "model.layers.0.ln1.weight",
|
| 32 |
+
"decoderLayer.0.feedForward.intermediateDense.weight": "model.layers.0.mlp.gate_proj.weight",
|
| 33 |
+
"decoderLayer.0.feedForward.outputDense.weight": "model.layers.0.mlp.down_proj.weight",
|
| 34 |
+
"decoderLayer.0.ffnLayerNorm.weight": "model.layers.0.ln2.weight",
|
| 35 |
+
"decoderLayer.0.feedForward.intermediateDense2.weight": "model.layers.0.mlp.up_proj.weight",
|
| 36 |
+
"decoderLayer.1.multiHeadAttention.q.weight": "model.layers.1.self_attn.q_proj.weight",
|
| 37 |
+
"decoderLayer.1.multiHeadAttention.k.weight": "model.layers.1.self_attn.k_proj.weight",
|
| 38 |
+
"decoderLayer.1.multiHeadAttention.v.weight": "model.layers.1.self_attn.v_proj.weight",
|
| 39 |
+
"decoderLayer.1.multiHeadAttention.o.weight": "model.layers.1.self_attn.o_proj.weight",
|
| 40 |
+
"decoderLayer.1.attnLayerNorm.weight": "model.layers.1.ln1.weight",
|
| 41 |
+
"decoderLayer.1.feedForward.intermediateDense.weight": "model.layers.1.mlp.gate_proj.weight",
|
| 42 |
+
"decoderLayer.1.feedForward.outputDense.weight": "model.layers.1.mlp.down_proj.weight",
|
| 43 |
+
"decoderLayer.1.ffnLayerNorm.weight": "model.layers.1.ln2.weight",
|
| 44 |
+
"decoderLayer.1.feedForward.intermediateDense2.weight": "model.layers.1.mlp.up_proj.weight",
|
| 45 |
+
"decoderLayer.2.multiHeadAttention.q.weight": "model.layers.2.self_attn.q_proj.weight",
|
| 46 |
+
"decoderLayer.2.multiHeadAttention.k.weight": "model.layers.2.self_attn.k_proj.weight",
|
| 47 |
+
"decoderLayer.2.multiHeadAttention.v.weight": "model.layers.2.self_attn.v_proj.weight",
|
| 48 |
+
"decoderLayer.2.multiHeadAttention.o.weight": "model.layers.2.self_attn.o_proj.weight",
|
| 49 |
+
"decoderLayer.2.attnLayerNorm.weight": "model.layers.2.ln1.weight",
|
| 50 |
+
"decoderLayer.2.feedForward.intermediateDense.weight": "model.layers.2.mlp.gate_proj.weight",
|
| 51 |
+
"decoderLayer.2.feedForward.outputDense.weight": "model.layers.2.mlp.down_proj.weight",
|
| 52 |
+
"decoderLayer.2.ffnLayerNorm.weight": "model.layers.2.ln2.weight",
|
| 53 |
+
"decoderLayer.2.feedForward.intermediateDense2.weight": "model.layers.2.mlp.up_proj.weight",
|
| 54 |
+
"decoderLayer.3.multiHeadAttention.q.weight": "model.layers.3.self_attn.q_proj.weight",
|
| 55 |
+
"decoderLayer.3.multiHeadAttention.k.weight": "model.layers.3.self_attn.k_proj.weight",
|
| 56 |
+
"decoderLayer.3.multiHeadAttention.v.weight": "model.layers.3.self_attn.v_proj.weight",
|
| 57 |
+
"decoderLayer.3.multiHeadAttention.o.weight": "model.layers.3.self_attn.o_proj.weight",
|
| 58 |
+
"decoderLayer.3.attnLayerNorm.weight": "model.layers.3.ln1.weight",
|
| 59 |
+
"decoderLayer.3.feedForward.intermediateDense.weight": "model.layers.3.mlp.gate_proj.weight",
|
| 60 |
+
"decoderLayer.3.feedForward.outputDense.weight": "model.layers.3.mlp.down_proj.weight",
|
| 61 |
+
"decoderLayer.3.ffnLayerNorm.weight": "model.layers.3.ln2.weight",
|
| 62 |
+
"decoderLayer.3.feedForward.intermediateDense2.weight": "model.layers.3.mlp.up_proj.weight",
|
| 63 |
+
"decoderLayer.4.multiHeadAttention.q.weight": "model.layers.4.self_attn.q_proj.weight",
|
| 64 |
+
"decoderLayer.4.multiHeadAttention.k.weight": "model.layers.4.self_attn.k_proj.weight",
|
| 65 |
+
"decoderLayer.4.multiHeadAttention.v.weight": "model.layers.4.self_attn.v_proj.weight",
|
| 66 |
+
"decoderLayer.4.multiHeadAttention.o.weight": "model.layers.4.self_attn.o_proj.weight",
|
| 67 |
+
"decoderLayer.4.attnLayerNorm.weight": "model.layers.4.ln1.weight",
|
| 68 |
+
"decoderLayer.4.feedForward.intermediateDense.weight": "model.layers.4.mlp.gate_proj.weight",
|
| 69 |
+
"decoderLayer.4.feedForward.outputDense.weight": "model.layers.4.mlp.down_proj.weight",
|
| 70 |
+
"decoderLayer.4.ffnLayerNorm.weight": "model.layers.4.ln2.weight",
|
| 71 |
+
"decoderLayer.4.feedForward.intermediateDense2.weight": "model.layers.4.mlp.up_proj.weight",
|
| 72 |
+
"decoderLayer.5.multiHeadAttention.q.weight": "model.layers.5.self_attn.q_proj.weight",
|
| 73 |
+
"decoderLayer.5.multiHeadAttention.k.weight": "model.layers.5.self_attn.k_proj.weight",
|
| 74 |
+
"decoderLayer.5.multiHeadAttention.v.weight": "model.layers.5.self_attn.v_proj.weight",
|
| 75 |
+
"decoderLayer.5.multiHeadAttention.o.weight": "model.layers.5.self_attn.o_proj.weight",
|
| 76 |
+
"decoderLayer.5.attnLayerNorm.weight": "model.layers.5.ln1.weight",
|
| 77 |
+
"decoderLayer.5.feedForward.intermediateDense.weight": "model.layers.5.mlp.gate_proj.weight",
|
| 78 |
+
"decoderLayer.5.feedForward.outputDense.weight": "model.layers.5.mlp.down_proj.weight",
|
| 79 |
+
"decoderLayer.5.ffnLayerNorm.weight": "model.layers.5.ln2.weight",
|
| 80 |
+
"decoderLayer.5.feedForward.intermediateDense2.weight": "model.layers.5.mlp.up_proj.weight",
|
| 81 |
+
"decoderLayer.6.multiHeadAttention.q.weight": "model.layers.6.self_attn.q_proj.weight",
|
| 82 |
+
"decoderLayer.6.multiHeadAttention.k.weight": "model.layers.6.self_attn.k_proj.weight",
|
| 83 |
+
"decoderLayer.6.multiHeadAttention.v.weight": "model.layers.6.self_attn.v_proj.weight",
|
| 84 |
+
"decoderLayer.6.multiHeadAttention.o.weight": "model.layers.6.self_attn.o_proj.weight",
|
| 85 |
+
"decoderLayer.6.attnLayerNorm.weight": "model.layers.6.ln1.weight",
|
| 86 |
+
"decoderLayer.6.feedForward.intermediateDense.weight": "model.layers.6.mlp.gate_proj.weight",
|
| 87 |
+
"decoderLayer.6.feedForward.outputDense.weight": "model.layers.6.mlp.down_proj.weight",
|
| 88 |
+
"decoderLayer.6.ffnLayerNorm.weight": "model.layers.6.ln2.weight",
|
| 89 |
+
"decoderLayer.6.feedForward.intermediateDense2.weight": "model.layers.6.mlp.up_proj.weight",
|
| 90 |
+
"decoderLayer.7.multiHeadAttention.q.weight": "model.layers.7.self_attn.q_proj.weight",
|
| 91 |
+
"decoderLayer.7.multiHeadAttention.k.weight": "model.layers.7.self_attn.k_proj.weight",
|
| 92 |
+
"decoderLayer.7.multiHeadAttention.v.weight": "model.layers.7.self_attn.v_proj.weight",
|
| 93 |
+
"decoderLayer.7.multiHeadAttention.o.weight": "model.layers.7.self_attn.o_proj.weight",
|
| 94 |
+
"decoderLayer.7.attnLayerNorm.weight": "model.layers.7.ln1.weight",
|
| 95 |
+
"decoderLayer.7.feedForward.intermediateDense.weight": "model.layers.7.mlp.gate_proj.weight",
|
| 96 |
+
"decoderLayer.7.feedForward.outputDense.weight": "model.layers.7.mlp.down_proj.weight",
|
| 97 |
+
"decoderLayer.7.ffnLayerNorm.weight": "model.layers.7.ln2.weight",
|
| 98 |
+
"decoderLayer.7.feedForward.intermediateDense2.weight": "model.layers.7.mlp.up_proj.weight",
|
| 99 |
+
"decoderLayer.8.multiHeadAttention.q.weight": "model.layers.8.self_attn.q_proj.weight",
|
| 100 |
+
"decoderLayer.8.multiHeadAttention.k.weight": "model.layers.8.self_attn.k_proj.weight",
|
| 101 |
+
"decoderLayer.8.multiHeadAttention.v.weight": "model.layers.8.self_attn.v_proj.weight",
|
| 102 |
+
"decoderLayer.8.multiHeadAttention.o.weight": "model.layers.8.self_attn.o_proj.weight",
|
| 103 |
+
"decoderLayer.8.attnLayerNorm.weight": "model.layers.8.ln1.weight",
|
| 104 |
+
"decoderLayer.8.feedForward.intermediateDense.weight": "model.layers.8.mlp.gate_proj.weight",
|
| 105 |
+
"decoderLayer.8.feedForward.outputDense.weight": "model.layers.8.mlp.down_proj.weight",
|
| 106 |
+
"decoderLayer.8.ffnLayerNorm.weight": "model.layers.8.ln2.weight",
|
| 107 |
+
"decoderLayer.8.feedForward.intermediateDense2.weight": "model.layers.8.mlp.up_proj.weight",
|
| 108 |
+
"decoderLayer.9.multiHeadAttention.q.weight": "model.layers.9.self_attn.q_proj.weight",
|
| 109 |
+
"decoderLayer.9.multiHeadAttention.k.weight": "model.layers.9.self_attn.k_proj.weight",
|
| 110 |
+
"decoderLayer.9.multiHeadAttention.v.weight": "model.layers.9.self_attn.v_proj.weight",
|
| 111 |
+
"decoderLayer.9.multiHeadAttention.o.weight": "model.layers.9.self_attn.o_proj.weight",
|
| 112 |
+
"decoderLayer.9.attnLayerNorm.weight": "model.layers.9.ln1.weight",
|
| 113 |
+
"decoderLayer.9.feedForward.intermediateDense.weight": "model.layers.9.mlp.gate_proj.weight",
|
| 114 |
+
"decoderLayer.9.feedForward.outputDense.weight": "model.layers.9.mlp.down_proj.weight",
|
| 115 |
+
"decoderLayer.9.ffnLayerNorm.weight": "model.layers.9.ln2.weight",
|
| 116 |
+
"decoderLayer.9.feedForward.intermediateDense2.weight": "model.layers.9.mlp.up_proj.weight",
|
| 117 |
+
"decoderLayer.10.multiHeadAttention.q.weight": "model.layers.10.self_attn.q_proj.weight",
|
| 118 |
+
"decoderLayer.10.multiHeadAttention.k.weight": "model.layers.10.self_attn.k_proj.weight",
|
| 119 |
+
"decoderLayer.10.multiHeadAttention.v.weight": "model.layers.10.self_attn.v_proj.weight",
|
| 120 |
+
"decoderLayer.10.multiHeadAttention.o.weight": "model.layers.10.self_attn.o_proj.weight",
|
| 121 |
+
"decoderLayer.10.attnLayerNorm.weight": "model.layers.10.ln1.weight",
|
| 122 |
+
"decoderLayer.10.feedForward.intermediateDense.weight": "model.layers.10.mlp.gate_proj.weight",
|
| 123 |
+
"decoderLayer.10.feedForward.outputDense.weight": "model.layers.10.mlp.down_proj.weight",
|
| 124 |
+
"decoderLayer.10.ffnLayerNorm.weight": "model.layers.10.ln2.weight",
|
| 125 |
+
"decoderLayer.10.feedForward.intermediateDense2.weight": "model.layers.10.mlp.up_proj.weight",
|
| 126 |
+
"decoderLayer.11.multiHeadAttention.q.weight": "model.layers.11.self_attn.q_proj.weight",
|
| 127 |
+
"decoderLayer.11.multiHeadAttention.k.weight": "model.layers.11.self_attn.k_proj.weight",
|
| 128 |
+
"decoderLayer.11.multiHeadAttention.v.weight": "model.layers.11.self_attn.v_proj.weight",
|
| 129 |
+
"decoderLayer.11.multiHeadAttention.o.weight": "model.layers.11.self_attn.o_proj.weight",
|
| 130 |
+
"decoderLayer.11.attnLayerNorm.weight": "model.layers.11.ln1.weight",
|
| 131 |
+
"decoderLayer.11.feedForward.intermediateDense.weight": "model.layers.11.mlp.gate_proj.weight",
|
| 132 |
+
"decoderLayer.11.feedForward.outputDense.weight": "model.layers.11.mlp.down_proj.weight",
|
| 133 |
+
"decoderLayer.11.ffnLayerNorm.weight": "model.layers.11.ln2.weight",
|
| 134 |
+
"decoderLayer.11.feedForward.intermediateDense2.weight": "model.layers.11.mlp.up_proj.weight",
|
| 135 |
+
"decoderLayer.12.multiHeadAttention.q.weight": "model.layers.12.self_attn.q_proj.weight",
|
| 136 |
+
"decoderLayer.12.multiHeadAttention.k.weight": "model.layers.12.self_attn.k_proj.weight",
|
| 137 |
+
"decoderLayer.12.multiHeadAttention.v.weight": "model.layers.12.self_attn.v_proj.weight",
|
| 138 |
+
"decoderLayer.12.multiHeadAttention.o.weight": "model.layers.12.self_attn.o_proj.weight",
|
| 139 |
+
"decoderLayer.12.attnLayerNorm.weight": "model.layers.12.ln1.weight",
|
| 140 |
+
"decoderLayer.12.feedForward.intermediateDense.weight": "model.layers.12.mlp.gate_proj.weight",
|
| 141 |
+
"decoderLayer.12.feedForward.outputDense.weight": "model.layers.12.mlp.down_proj.weight",
|
| 142 |
+
"decoderLayer.12.ffnLayerNorm.weight": "model.layers.12.ln2.weight",
|
| 143 |
+
"decoderLayer.12.feedForward.intermediateDense2.weight": "model.layers.12.mlp.up_proj.weight",
|
| 144 |
+
"decoderLayer.13.multiHeadAttention.q.weight": "model.layers.13.self_attn.q_proj.weight",
|
| 145 |
+
"decoderLayer.13.multiHeadAttention.k.weight": "model.layers.13.self_attn.k_proj.weight",
|
| 146 |
+
"decoderLayer.13.multiHeadAttention.v.weight": "model.layers.13.self_attn.v_proj.weight",
|
| 147 |
+
"decoderLayer.13.multiHeadAttention.o.weight": "model.layers.13.self_attn.o_proj.weight",
|
| 148 |
+
"decoderLayer.13.attnLayerNorm.weight": "model.layers.13.ln1.weight",
|
| 149 |
+
"decoderLayer.13.feedForward.intermediateDense.weight": "model.layers.13.mlp.gate_proj.weight",
|
| 150 |
+
"decoderLayer.13.feedForward.outputDense.weight": "model.layers.13.mlp.down_proj.weight",
|
| 151 |
+
"decoderLayer.13.ffnLayerNorm.weight": "model.layers.13.ln2.weight",
|
| 152 |
+
"decoderLayer.13.feedForward.intermediateDense2.weight": "model.layers.13.mlp.up_proj.weight",
|
| 153 |
+
"decoderLayer.14.multiHeadAttention.q.weight": "model.layers.14.self_attn.q_proj.weight",
|
| 154 |
+
"decoderLayer.14.multiHeadAttention.k.weight": "model.layers.14.self_attn.k_proj.weight",
|
| 155 |
+
"decoderLayer.14.multiHeadAttention.v.weight": "model.layers.14.self_attn.v_proj.weight",
|
| 156 |
+
"decoderLayer.14.multiHeadAttention.o.weight": "model.layers.14.self_attn.o_proj.weight",
|
| 157 |
+
"decoderLayer.14.attnLayerNorm.weight": "model.layers.14.ln1.weight",
|
| 158 |
+
"decoderLayer.14.feedForward.intermediateDense.weight": "model.layers.14.mlp.gate_proj.weight",
|
| 159 |
+
"decoderLayer.14.feedForward.outputDense.weight": "model.layers.14.mlp.down_proj.weight",
|
| 160 |
+
"decoderLayer.14.ffnLayerNorm.weight": "model.layers.14.ln2.weight",
|
| 161 |
+
"decoderLayer.14.feedForward.intermediateDense2.weight": "model.layers.14.mlp.up_proj.weight",
|
| 162 |
+
"decoderLayer.15.multiHeadAttention.q.weight": "model.layers.15.self_attn.q_proj.weight",
|
| 163 |
+
"decoderLayer.15.multiHeadAttention.k.weight": "model.layers.15.self_attn.k_proj.weight",
|
| 164 |
+
"decoderLayer.15.multiHeadAttention.v.weight": "model.layers.15.self_attn.v_proj.weight",
|
| 165 |
+
"decoderLayer.15.multiHeadAttention.o.weight": "model.layers.15.self_attn.o_proj.weight",
|
| 166 |
+
"decoderLayer.15.attnLayerNorm.weight": "model.layers.15.ln1.weight",
|
| 167 |
+
"decoderLayer.15.feedForward.intermediateDense.weight": "model.layers.15.mlp.gate_proj.weight",
|
| 168 |
+
"decoderLayer.15.feedForward.outputDense.weight": "model.layers.15.mlp.down_proj.weight",
|
| 169 |
+
"decoderLayer.15.ffnLayerNorm.weight": "model.layers.15.ln2.weight",
|
| 170 |
+
"decoderLayer.15.feedForward.intermediateDense2.weight": "model.layers.15.mlp.up_proj.weight",
|
| 171 |
+
"decoderLayer.16.multiHeadAttention.q.weight": "model.layers.16.self_attn.q_proj.weight",
|
| 172 |
+
"decoderLayer.16.multiHeadAttention.k.weight": "model.layers.16.self_attn.k_proj.weight",
|
| 173 |
+
"decoderLayer.16.multiHeadAttention.v.weight": "model.layers.16.self_attn.v_proj.weight",
|
| 174 |
+
"decoderLayer.16.multiHeadAttention.o.weight": "model.layers.16.self_attn.o_proj.weight",
|
| 175 |
+
"decoderLayer.16.attnLayerNorm.weight": "model.layers.16.ln1.weight",
|
| 176 |
+
"decoderLayer.16.feedForward.intermediateDense.weight": "model.layers.16.mlp.gate_proj.weight",
|
| 177 |
+
"decoderLayer.16.feedForward.outputDense.weight": "model.layers.16.mlp.down_proj.weight",
|
| 178 |
+
"decoderLayer.16.ffnLayerNorm.weight": "model.layers.16.ln2.weight",
|
| 179 |
+
"decoderLayer.16.feedForward.intermediateDense2.weight": "model.layers.16.mlp.up_proj.weight",
|
| 180 |
+
"decoderLayer.17.multiHeadAttention.q.weight": "model.layers.17.self_attn.q_proj.weight",
|
| 181 |
+
"decoderLayer.17.multiHeadAttention.k.weight": "model.layers.17.self_attn.k_proj.weight",
|
| 182 |
+
"decoderLayer.17.multiHeadAttention.v.weight": "model.layers.17.self_attn.v_proj.weight",
|
| 183 |
+
"decoderLayer.17.multiHeadAttention.o.weight": "model.layers.17.self_attn.o_proj.weight",
|
| 184 |
+
"decoderLayer.17.attnLayerNorm.weight": "model.layers.17.ln1.weight",
|
| 185 |
+
"decoderLayer.17.feedForward.intermediateDense.weight": "model.layers.17.mlp.gate_proj.weight",
|
| 186 |
+
"decoderLayer.17.feedForward.outputDense.weight": "model.layers.17.mlp.down_proj.weight",
|
| 187 |
+
"decoderLayer.17.ffnLayerNorm.weight": "model.layers.17.ln2.weight",
|
| 188 |
+
"decoderLayer.17.feedForward.intermediateDense2.weight": "model.layers.17.mlp.up_proj.weight",
|
| 189 |
+
"decoderLayer.18.multiHeadAttention.q.weight": "model.layers.18.self_attn.q_proj.weight",
|
| 190 |
+
"decoderLayer.18.multiHeadAttention.k.weight": "model.layers.18.self_attn.k_proj.weight",
|
| 191 |
+
"decoderLayer.18.multiHeadAttention.v.weight": "model.layers.18.self_attn.v_proj.weight",
|
| 192 |
+
"decoderLayer.18.multiHeadAttention.o.weight": "model.layers.18.self_attn.o_proj.weight",
|
| 193 |
+
"decoderLayer.18.attnLayerNorm.weight": "model.layers.18.ln1.weight",
|
| 194 |
+
"decoderLayer.18.feedForward.intermediateDense.weight": "model.layers.18.mlp.gate_proj.weight",
|
| 195 |
+
"decoderLayer.18.feedForward.outputDense.weight": "model.layers.18.mlp.down_proj.weight",
|
| 196 |
+
"decoderLayer.18.ffnLayerNorm.weight": "model.layers.18.ln2.weight",
|
| 197 |
+
"decoderLayer.18.feedForward.intermediateDense2.weight": "model.layers.18.mlp.up_proj.weight",
|
| 198 |
+
"decoderLayer.19.multiHeadAttention.q.weight": "model.layers.19.self_attn.q_proj.weight",
|
| 199 |
+
"decoderLayer.19.multiHeadAttention.k.weight": "model.layers.19.self_attn.k_proj.weight",
|
| 200 |
+
"decoderLayer.19.multiHeadAttention.v.weight": "model.layers.19.self_attn.v_proj.weight",
|
| 201 |
+
"decoderLayer.19.multiHeadAttention.o.weight": "model.layers.19.self_attn.o_proj.weight",
|
| 202 |
+
"decoderLayer.19.attnLayerNorm.weight": "model.layers.19.ln1.weight",
|
| 203 |
+
"decoderLayer.19.feedForward.intermediateDense.weight": "model.layers.19.mlp.gate_proj.weight",
|
| 204 |
+
"decoderLayer.19.feedForward.outputDense.weight": "model.layers.19.mlp.down_proj.weight",
|
| 205 |
+
"decoderLayer.19.ffnLayerNorm.weight": "model.layers.19.ln2.weight",
|
| 206 |
+
"decoderLayer.19.feedForward.intermediateDense2.weight": "model.layers.19.mlp.up_proj.weight",
|
| 207 |
+
"decoderLayer.20.multiHeadAttention.q.weight": "model.layers.20.self_attn.q_proj.weight",
|
| 208 |
+
"decoderLayer.20.multiHeadAttention.k.weight": "model.layers.20.self_attn.k_proj.weight",
|
| 209 |
+
"decoderLayer.20.multiHeadAttention.v.weight": "model.layers.20.self_attn.v_proj.weight",
|
| 210 |
+
"decoderLayer.20.multiHeadAttention.o.weight": "model.layers.20.self_attn.o_proj.weight",
|
| 211 |
+
"decoderLayer.20.attnLayerNorm.weight": "model.layers.20.ln1.weight",
|
| 212 |
+
"decoderLayer.20.feedForward.intermediateDense.weight": "model.layers.20.mlp.gate_proj.weight",
|
| 213 |
+
"decoderLayer.20.feedForward.outputDense.weight": "model.layers.20.mlp.down_proj.weight",
|
| 214 |
+
"decoderLayer.20.ffnLayerNorm.weight": "model.layers.20.ln2.weight",
|
| 215 |
+
"decoderLayer.20.feedForward.intermediateDense2.weight": "model.layers.20.mlp.up_proj.weight",
|
| 216 |
+
"decoderLayer.21.multiHeadAttention.q.weight": "model.layers.21.self_attn.q_proj.weight",
|
| 217 |
+
"decoderLayer.21.multiHeadAttention.k.weight": "model.layers.21.self_attn.k_proj.weight",
|
| 218 |
+
"decoderLayer.21.multiHeadAttention.v.weight": "model.layers.21.self_attn.v_proj.weight",
|
| 219 |
+
"decoderLayer.21.multiHeadAttention.o.weight": "model.layers.21.self_attn.o_proj.weight",
|
| 220 |
+
"decoderLayer.21.attnLayerNorm.weight": "model.layers.21.ln1.weight",
|
| 221 |
+
"decoderLayer.21.feedForward.intermediateDense.weight": "model.layers.21.mlp.gate_proj.weight",
|
| 222 |
+
"decoderLayer.21.feedForward.outputDense.weight": "model.layers.21.mlp.down_proj.weight",
|
| 223 |
+
"decoderLayer.21.ffnLayerNorm.weight": "model.layers.21.ln2.weight",
|
| 224 |
+
"decoderLayer.21.feedForward.intermediateDense2.weight": "model.layers.21.mlp.up_proj.weight",
|
| 225 |
+
"decoderLayer.22.multiHeadAttention.q.weight": "model.layers.22.self_attn.q_proj.weight",
|
| 226 |
+
"decoderLayer.22.multiHeadAttention.k.weight": "model.layers.22.self_attn.k_proj.weight",
|
| 227 |
+
"decoderLayer.22.multiHeadAttention.v.weight": "model.layers.22.self_attn.v_proj.weight",
|
| 228 |
+
"decoderLayer.22.multiHeadAttention.o.weight": "model.layers.22.self_attn.o_proj.weight",
|
| 229 |
+
"decoderLayer.22.attnLayerNorm.weight": "model.layers.22.ln1.weight",
|
| 230 |
+
"decoderLayer.22.feedForward.intermediateDense.weight": "model.layers.22.mlp.gate_proj.weight",
|
| 231 |
+
"decoderLayer.22.feedForward.outputDense.weight": "model.layers.22.mlp.down_proj.weight",
|
| 232 |
+
"decoderLayer.22.ffnLayerNorm.weight": "model.layers.22.ln2.weight",
|
| 233 |
+
"decoderLayer.22.feedForward.intermediateDense2.weight": "model.layers.22.mlp.up_proj.weight",
|
| 234 |
+
"decoderLayer.23.multiHeadAttention.q.weight": "model.layers.23.self_attn.q_proj.weight",
|
| 235 |
+
"decoderLayer.23.multiHeadAttention.k.weight": "model.layers.23.self_attn.k_proj.weight",
|
| 236 |
+
"decoderLayer.23.multiHeadAttention.v.weight": "model.layers.23.self_attn.v_proj.weight",
|
| 237 |
+
"decoderLayer.23.multiHeadAttention.o.weight": "model.layers.23.self_attn.o_proj.weight",
|
| 238 |
+
"decoderLayer.23.attnLayerNorm.weight": "model.layers.23.ln1.weight",
|
| 239 |
+
"decoderLayer.23.feedForward.intermediateDense.weight": "model.layers.23.mlp.gate_proj.weight",
|
| 240 |
+
"decoderLayer.23.feedForward.outputDense.weight": "model.layers.23.mlp.down_proj.weight",
|
| 241 |
+
"decoderLayer.23.ffnLayerNorm.weight": "model.layers.23.ln2.weight",
|
| 242 |
+
"decoderLayer.23.feedForward.intermediateDense2.weight": "model.layers.23.mlp.up_proj.weight",
|
| 243 |
+
"decoderLayer.24.multiHeadAttention.q.weight": "model.layers.24.self_attn.q_proj.weight",
|
| 244 |
+
"decoderLayer.24.multiHeadAttention.k.weight": "model.layers.24.self_attn.k_proj.weight",
|
| 245 |
+
"decoderLayer.24.multiHeadAttention.v.weight": "model.layers.24.self_attn.v_proj.weight",
|
| 246 |
+
"decoderLayer.24.multiHeadAttention.o.weight": "model.layers.24.self_attn.o_proj.weight",
|
| 247 |
+
"decoderLayer.24.attnLayerNorm.weight": "model.layers.24.ln1.weight",
|
| 248 |
+
"decoderLayer.24.feedForward.intermediateDense.weight": "model.layers.24.mlp.gate_proj.weight",
|
| 249 |
+
"decoderLayer.24.feedForward.outputDense.weight": "model.layers.24.mlp.down_proj.weight",
|
| 250 |
+
"decoderLayer.24.ffnLayerNorm.weight": "model.layers.24.ln2.weight",
|
| 251 |
+
"decoderLayer.24.feedForward.intermediateDense2.weight": "model.layers.24.mlp.up_proj.weight",
|
| 252 |
+
"decoderLayer.25.multiHeadAttention.q.weight": "model.layers.25.self_attn.q_proj.weight",
|
| 253 |
+
"decoderLayer.25.multiHeadAttention.k.weight": "model.layers.25.self_attn.k_proj.weight",
|
| 254 |
+
"decoderLayer.25.multiHeadAttention.v.weight": "model.layers.25.self_attn.v_proj.weight",
|
| 255 |
+
"decoderLayer.25.multiHeadAttention.o.weight": "model.layers.25.self_attn.o_proj.weight",
|
| 256 |
+
"decoderLayer.25.attnLayerNorm.weight": "model.layers.25.ln1.weight",
|
| 257 |
+
"decoderLayer.25.feedForward.intermediateDense.weight": "model.layers.25.mlp.gate_proj.weight",
|
| 258 |
+
"decoderLayer.25.feedForward.outputDense.weight": "model.layers.25.mlp.down_proj.weight",
|
| 259 |
+
"decoderLayer.25.ffnLayerNorm.weight": "model.layers.25.ln2.weight",
|
| 260 |
+
"decoderLayer.25.feedForward.intermediateDense2.weight": "model.layers.25.mlp.up_proj.weight",
|
| 261 |
+
"decoderLayer.26.multiHeadAttention.q.weight": "model.layers.26.self_attn.q_proj.weight",
|
| 262 |
+
"decoderLayer.26.multiHeadAttention.k.weight": "model.layers.26.self_attn.k_proj.weight",
|
| 263 |
+
"decoderLayer.26.multiHeadAttention.v.weight": "model.layers.26.self_attn.v_proj.weight",
|
| 264 |
+
"decoderLayer.26.multiHeadAttention.o.weight": "model.layers.26.self_attn.o_proj.weight",
|
| 265 |
+
"decoderLayer.26.attnLayerNorm.weight": "model.layers.26.ln1.weight",
|
| 266 |
+
"decoderLayer.26.feedForward.intermediateDense.weight": "model.layers.26.mlp.gate_proj.weight",
|
| 267 |
+
"decoderLayer.26.feedForward.outputDense.weight": "model.layers.26.mlp.down_proj.weight",
|
| 268 |
+
"decoderLayer.26.ffnLayerNorm.weight": "model.layers.26.ln2.weight",
|
| 269 |
+
"decoderLayer.26.feedForward.intermediateDense2.weight": "model.layers.26.mlp.up_proj.weight",
|
| 270 |
+
"decoderLayer.27.multiHeadAttention.q.weight": "model.layers.27.self_attn.q_proj.weight",
|
| 271 |
+
"decoderLayer.27.multiHeadAttention.k.weight": "model.layers.27.self_attn.k_proj.weight",
|
| 272 |
+
"decoderLayer.27.multiHeadAttention.v.weight": "model.layers.27.self_attn.v_proj.weight",
|
| 273 |
+
"decoderLayer.27.multiHeadAttention.o.weight": "model.layers.27.self_attn.o_proj.weight",
|
| 274 |
+
"decoderLayer.27.attnLayerNorm.weight": "model.layers.27.ln1.weight",
|
| 275 |
+
"decoderLayer.27.feedForward.intermediateDense.weight": "model.layers.27.mlp.gate_proj.weight",
|
| 276 |
+
"decoderLayer.27.feedForward.outputDense.weight": "model.layers.27.mlp.down_proj.weight",
|
| 277 |
+
"decoderLayer.27.ffnLayerNorm.weight": "model.layers.27.ln2.weight",
|
| 278 |
+
"decoderLayer.27.feedForward.intermediateDense2.weight": "model.layers.27.mlp.up_proj.weight",
|
| 279 |
+
"decoderLayer.28.multiHeadAttention.q.weight": "model.layers.28.self_attn.q_proj.weight",
|
| 280 |
+
"decoderLayer.28.multiHeadAttention.k.weight": "model.layers.28.self_attn.k_proj.weight",
|
| 281 |
+
"decoderLayer.28.multiHeadAttention.v.weight": "model.layers.28.self_attn.v_proj.weight",
|
| 282 |
+
"decoderLayer.28.multiHeadAttention.o.weight": "model.layers.28.self_attn.o_proj.weight",
|
| 283 |
+
"decoderLayer.28.attnLayerNorm.weight": "model.layers.28.ln1.weight",
|
| 284 |
+
"decoderLayer.28.feedForward.intermediateDense.weight": "model.layers.28.mlp.gate_proj.weight",
|
| 285 |
+
"decoderLayer.28.feedForward.outputDense.weight": "model.layers.28.mlp.down_proj.weight",
|
| 286 |
+
"decoderLayer.28.ffnLayerNorm.weight": "model.layers.28.ln2.weight",
|
| 287 |
+
"decoderLayer.28.feedForward.intermediateDense2.weight": "model.layers.28.mlp.up_proj.weight",
|
| 288 |
+
"decoderLayer.29.multiHeadAttention.q.weight": "model.layers.29.self_attn.q_proj.weight",
|
| 289 |
+
"decoderLayer.29.multiHeadAttention.k.weight": "model.layers.29.self_attn.k_proj.weight",
|
| 290 |
+
"decoderLayer.29.multiHeadAttention.v.weight": "model.layers.29.self_attn.v_proj.weight",
|
| 291 |
+
"decoderLayer.29.multiHeadAttention.o.weight": "model.layers.29.self_attn.o_proj.weight",
|
| 292 |
+
"decoderLayer.29.attnLayerNorm.weight": "model.layers.29.ln1.weight",
|
| 293 |
+
"decoderLayer.29.feedForward.intermediateDense.weight": "model.layers.29.mlp.gate_proj.weight",
|
| 294 |
+
"decoderLayer.29.feedForward.outputDense.weight": "model.layers.29.mlp.down_proj.weight",
|
| 295 |
+
"decoderLayer.29.ffnLayerNorm.weight": "model.layers.29.ln2.weight",
|
| 296 |
+
"decoderLayer.29.feedForward.intermediateDense2.weight": "model.layers.29.mlp.up_proj.weight",
|
| 297 |
+
"decoderLayer.30.multiHeadAttention.q.weight": "model.layers.30.self_attn.q_proj.weight",
|
| 298 |
+
"decoderLayer.30.multiHeadAttention.k.weight": "model.layers.30.self_attn.k_proj.weight",
|
| 299 |
+
"decoderLayer.30.multiHeadAttention.v.weight": "model.layers.30.self_attn.v_proj.weight",
|
| 300 |
+
"decoderLayer.30.multiHeadAttention.o.weight": "model.layers.30.self_attn.o_proj.weight",
|
| 301 |
+
"decoderLayer.30.attnLayerNorm.weight": "model.layers.30.ln1.weight",
|
| 302 |
+
"decoderLayer.30.feedForward.intermediateDense.weight": "model.layers.30.mlp.gate_proj.weight",
|
| 303 |
+
"decoderLayer.30.feedForward.outputDense.weight": "model.layers.30.mlp.down_proj.weight",
|
| 304 |
+
"decoderLayer.30.ffnLayerNorm.weight": "model.layers.30.ln2.weight",
|
| 305 |
+
"decoderLayer.30.feedForward.intermediateDense2.weight": "model.layers.30.mlp.up_proj.weight",
|
| 306 |
+
"decoderLayer.31.multiHeadAttention.q.weight": "model.layers.31.self_attn.q_proj.weight",
|
| 307 |
+
"decoderLayer.31.multiHeadAttention.k.weight": "model.layers.31.self_attn.k_proj.weight",
|
| 308 |
+
"decoderLayer.31.multiHeadAttention.v.weight": "model.layers.31.self_attn.v_proj.weight",
|
| 309 |
+
"decoderLayer.31.multiHeadAttention.o.weight": "model.layers.31.self_attn.o_proj.weight",
|
| 310 |
+
"decoderLayer.31.attnLayerNorm.weight": "model.layers.31.ln1.weight",
|
| 311 |
+
"decoderLayer.31.feedForward.intermediateDense.weight": "model.layers.31.mlp.gate_proj.weight",
|
| 312 |
+
"decoderLayer.31.feedForward.outputDense.weight": "model.layers.31.mlp.down_proj.weight",
|
| 313 |
+
"decoderLayer.31.ffnLayerNorm.weight": "model.layers.31.ln2.weight",
|
| 314 |
+
"decoderLayer.31.feedForward.intermediateDense2.weight": "model.layers.31.mlp.up_proj.weight",
|
| 315 |
+
"decoderLayer.32.multiHeadAttention.q.weight": "model.layers.32.self_attn.q_proj.weight",
|
| 316 |
+
"decoderLayer.32.multiHeadAttention.k.weight": "model.layers.32.self_attn.k_proj.weight",
|
| 317 |
+
"decoderLayer.32.multiHeadAttention.v.weight": "model.layers.32.self_attn.v_proj.weight",
|
| 318 |
+
"decoderLayer.32.multiHeadAttention.o.weight": "model.layers.32.self_attn.o_proj.weight",
|
| 319 |
+
"decoderLayer.32.attnLayerNorm.weight": "model.layers.32.ln1.weight",
|
| 320 |
+
"decoderLayer.32.feedForward.intermediateDense.weight": "model.layers.32.mlp.gate_proj.weight",
|
| 321 |
+
"decoderLayer.32.feedForward.outputDense.weight": "model.layers.32.mlp.down_proj.weight",
|
| 322 |
+
"decoderLayer.32.ffnLayerNorm.weight": "model.layers.32.ln2.weight",
|
| 323 |
+
"decoderLayer.32.feedForward.intermediateDense2.weight": "model.layers.32.mlp.up_proj.weight",
|
| 324 |
+
"decoderLayer.33.multiHeadAttention.q.weight": "model.layers.33.self_attn.q_proj.weight",
|
| 325 |
+
"decoderLayer.33.multiHeadAttention.k.weight": "model.layers.33.self_attn.k_proj.weight",
|
| 326 |
+
"decoderLayer.33.multiHeadAttention.v.weight": "model.layers.33.self_attn.v_proj.weight",
|
| 327 |
+
"decoderLayer.33.multiHeadAttention.o.weight": "model.layers.33.self_attn.o_proj.weight",
|
| 328 |
+
"decoderLayer.33.attnLayerNorm.weight": "model.layers.33.ln1.weight",
|
| 329 |
+
"decoderLayer.33.feedForward.intermediateDense.weight": "model.layers.33.mlp.gate_proj.weight",
|
| 330 |
+
"decoderLayer.33.feedForward.outputDense.weight": "model.layers.33.mlp.down_proj.weight",
|
| 331 |
+
"decoderLayer.33.ffnLayerNorm.weight": "model.layers.33.ln2.weight",
|
| 332 |
+
"decoderLayer.33.feedForward.intermediateDense2.weight": "model.layers.33.mlp.up_proj.weight",
|
| 333 |
+
"decoderLayer.34.multiHeadAttention.q.weight": "model.layers.34.self_attn.q_proj.weight",
|
| 334 |
+
"decoderLayer.34.multiHeadAttention.k.weight": "model.layers.34.self_attn.k_proj.weight",
|
| 335 |
+
"decoderLayer.34.multiHeadAttention.v.weight": "model.layers.34.self_attn.v_proj.weight",
|
| 336 |
+
"decoderLayer.34.multiHeadAttention.o.weight": "model.layers.34.self_attn.o_proj.weight",
|
| 337 |
+
"decoderLayer.34.attnLayerNorm.weight": "model.layers.34.ln1.weight",
|
| 338 |
+
"decoderLayer.34.feedForward.intermediateDense.weight": "model.layers.34.mlp.gate_proj.weight",
|
| 339 |
+
"decoderLayer.34.feedForward.outputDense.weight": "model.layers.34.mlp.down_proj.weight",
|
| 340 |
+
"decoderLayer.34.ffnLayerNorm.weight": "model.layers.34.ln2.weight",
|
| 341 |
+
"decoderLayer.34.feedForward.intermediateDense2.weight": "model.layers.34.mlp.up_proj.weight",
|
| 342 |
+
"decoderLayer.35.multiHeadAttention.q.weight": "model.layers.35.self_attn.q_proj.weight",
|
| 343 |
+
"decoderLayer.35.multiHeadAttention.k.weight": "model.layers.35.self_attn.k_proj.weight",
|
| 344 |
+
"decoderLayer.35.multiHeadAttention.v.weight": "model.layers.35.self_attn.v_proj.weight",
|
| 345 |
+
"decoderLayer.35.multiHeadAttention.o.weight": "model.layers.35.self_attn.o_proj.weight",
|
| 346 |
+
"decoderLayer.35.attnLayerNorm.weight": "model.layers.35.ln1.weight",
|
| 347 |
+
"decoderLayer.35.feedForward.intermediateDense.weight": "model.layers.35.mlp.gate_proj.weight",
|
| 348 |
+
"decoderLayer.35.feedForward.outputDense.weight": "model.layers.35.mlp.down_proj.weight",
|
| 349 |
+
"decoderLayer.35.ffnLayerNorm.weight": "model.layers.35.ln2.weight",
|
| 350 |
+
"decoderLayer.35.feedForward.intermediateDense2.weight": "model.layers.35.mlp.up_proj.weight",
|
| 351 |
+
"decoderLayer.36.multiHeadAttention.q.weight": "model.layers.36.self_attn.q_proj.weight",
|
| 352 |
+
"decoderLayer.36.multiHeadAttention.k.weight": "model.layers.36.self_attn.k_proj.weight",
|
| 353 |
+
"decoderLayer.36.multiHeadAttention.v.weight": "model.layers.36.self_attn.v_proj.weight",
|
| 354 |
+
"decoderLayer.36.multiHeadAttention.o.weight": "model.layers.36.self_attn.o_proj.weight",
|
| 355 |
+
"decoderLayer.36.attnLayerNorm.weight": "model.layers.36.ln1.weight",
|
| 356 |
+
"decoderLayer.36.feedForward.intermediateDense.weight": "model.layers.36.mlp.gate_proj.weight",
|
| 357 |
+
"decoderLayer.36.feedForward.outputDense.weight": "model.layers.36.mlp.down_proj.weight",
|
| 358 |
+
"decoderLayer.36.ffnLayerNorm.weight": "model.layers.36.ln2.weight",
|
| 359 |
+
"decoderLayer.36.feedForward.intermediateDense2.weight": "model.layers.36.mlp.up_proj.weight",
|
| 360 |
+
"decoderLayer.37.multiHeadAttention.q.weight": "model.layers.37.self_attn.q_proj.weight",
|
| 361 |
+
"decoderLayer.37.multiHeadAttention.k.weight": "model.layers.37.self_attn.k_proj.weight",
|
| 362 |
+
"decoderLayer.37.multiHeadAttention.v.weight": "model.layers.37.self_attn.v_proj.weight",
|
| 363 |
+
"decoderLayer.37.multiHeadAttention.o.weight": "model.layers.37.self_attn.o_proj.weight",
|
| 364 |
+
"decoderLayer.37.attnLayerNorm.weight": "model.layers.37.ln1.weight",
|
| 365 |
+
"decoderLayer.37.feedForward.intermediateDense.weight": "model.layers.37.mlp.gate_proj.weight",
|
| 366 |
+
"decoderLayer.37.feedForward.outputDense.weight": "model.layers.37.mlp.down_proj.weight",
|
| 367 |
+
"decoderLayer.37.ffnLayerNorm.weight": "model.layers.37.ln2.weight",
|
| 368 |
+
"decoderLayer.37.feedForward.intermediateDense2.weight": "model.layers.37.mlp.up_proj.weight",
|
| 369 |
+
"decoderLayer.38.multiHeadAttention.q.weight": "model.layers.38.self_attn.q_proj.weight",
|
| 370 |
+
"decoderLayer.38.multiHeadAttention.k.weight": "model.layers.38.self_attn.k_proj.weight",
|
| 371 |
+
"decoderLayer.38.multiHeadAttention.v.weight": "model.layers.38.self_attn.v_proj.weight",
|
| 372 |
+
"decoderLayer.38.multiHeadAttention.o.weight": "model.layers.38.self_attn.o_proj.weight",
|
| 373 |
+
"decoderLayer.38.attnLayerNorm.weight": "model.layers.38.ln1.weight",
|
| 374 |
+
"decoderLayer.38.feedForward.intermediateDense.weight": "model.layers.38.mlp.gate_proj.weight",
|
| 375 |
+
"decoderLayer.38.feedForward.outputDense.weight": "model.layers.38.mlp.down_proj.weight",
|
| 376 |
+
"decoderLayer.38.ffnLayerNorm.weight": "model.layers.38.ln2.weight",
|
| 377 |
+
"decoderLayer.38.feedForward.intermediateDense2.weight": "model.layers.38.mlp.up_proj.weight",
|
| 378 |
+
"decoderLayer.39.multiHeadAttention.q.weight": "model.layers.39.self_attn.q_proj.weight",
|
| 379 |
+
"decoderLayer.39.multiHeadAttention.k.weight": "model.layers.39.self_attn.k_proj.weight",
|
| 380 |
+
"decoderLayer.39.multiHeadAttention.v.weight": "model.layers.39.self_attn.v_proj.weight",
|
| 381 |
+
"decoderLayer.39.multiHeadAttention.o.weight": "model.layers.39.self_attn.o_proj.weight",
|
| 382 |
+
"decoderLayer.39.attnLayerNorm.weight": "model.layers.39.ln1.weight",
|
| 383 |
+
"decoderLayer.39.feedForward.intermediateDense.weight": "model.layers.39.mlp.gate_proj.weight",
|
| 384 |
+
"decoderLayer.39.feedForward.outputDense.weight": "model.layers.39.mlp.down_proj.weight",
|
| 385 |
+
"decoderLayer.39.ffnLayerNorm.weight": "model.layers.39.ln2.weight",
|
| 386 |
+
"decoderLayer.39.feedForward.intermediateDense2.weight": "model.layers.39.mlp.up_proj.weight",
|
| 387 |
+
"decoderLayer.40.multiHeadAttention.q.weight": "model.layers.40.self_attn.q_proj.weight",
|
| 388 |
+
"decoderLayer.40.multiHeadAttention.k.weight": "model.layers.40.self_attn.k_proj.weight",
|
| 389 |
+
"decoderLayer.40.multiHeadAttention.v.weight": "model.layers.40.self_attn.v_proj.weight",
|
| 390 |
+
"decoderLayer.40.multiHeadAttention.o.weight": "model.layers.40.self_attn.o_proj.weight",
|
| 391 |
+
"decoderLayer.40.attnLayerNorm.weight": "model.layers.40.ln1.weight",
|
| 392 |
+
"decoderLayer.40.feedForward.intermediateDense.weight": "model.layers.40.mlp.gate_proj.weight",
|
| 393 |
+
"decoderLayer.40.feedForward.outputDense.weight": "model.layers.40.mlp.down_proj.weight",
|
| 394 |
+
"decoderLayer.40.ffnLayerNorm.weight": "model.layers.40.ln2.weight",
|
| 395 |
+
"decoderLayer.40.feedForward.intermediateDense2.weight": "model.layers.40.mlp.up_proj.weight",
|
| 396 |
+
"decoderLayer.41.multiHeadAttention.q.weight": "model.layers.41.self_attn.q_proj.weight",
|
| 397 |
+
"decoderLayer.41.multiHeadAttention.k.weight": "model.layers.41.self_attn.k_proj.weight",
|
| 398 |
+
"decoderLayer.41.multiHeadAttention.v.weight": "model.layers.41.self_attn.v_proj.weight",
|
| 399 |
+
"decoderLayer.41.multiHeadAttention.o.weight": "model.layers.41.self_attn.o_proj.weight",
|
| 400 |
+
"decoderLayer.41.attnLayerNorm.weight": "model.layers.41.ln1.weight",
|
| 401 |
+
"decoderLayer.41.feedForward.intermediateDense.weight": "model.layers.41.mlp.gate_proj.weight",
|
| 402 |
+
"decoderLayer.41.feedForward.outputDense.weight": "model.layers.41.mlp.down_proj.weight",
|
| 403 |
+
"decoderLayer.41.ffnLayerNorm.weight": "model.layers.41.ln2.weight",
|
| 404 |
+
"decoderLayer.41.feedForward.intermediateDense2.weight": "model.layers.41.mlp.up_proj.weight",
|
| 405 |
+
"decoderLayer.42.multiHeadAttention.q.weight": "model.layers.42.self_attn.q_proj.weight",
|
| 406 |
+
"decoderLayer.42.multiHeadAttention.k.weight": "model.layers.42.self_attn.k_proj.weight",
|
| 407 |
+
"decoderLayer.42.multiHeadAttention.v.weight": "model.layers.42.self_attn.v_proj.weight",
|
| 408 |
+
"decoderLayer.42.multiHeadAttention.o.weight": "model.layers.42.self_attn.o_proj.weight",
|
| 409 |
+
"decoderLayer.42.attnLayerNorm.weight": "model.layers.42.ln1.weight",
|
| 410 |
+
"decoderLayer.42.feedForward.intermediateDense.weight": "model.layers.42.mlp.gate_proj.weight",
|
| 411 |
+
"decoderLayer.42.feedForward.outputDense.weight": "model.layers.42.mlp.down_proj.weight",
|
| 412 |
+
"decoderLayer.42.ffnLayerNorm.weight": "model.layers.42.ln2.weight",
|
| 413 |
+
"decoderLayer.42.feedForward.intermediateDense2.weight": "model.layers.42.mlp.up_proj.weight",
|
| 414 |
+
"decoderLayer.43.multiHeadAttention.q.weight": "model.layers.43.self_attn.q_proj.weight",
|
| 415 |
+
"decoderLayer.43.multiHeadAttention.k.weight": "model.layers.43.self_attn.k_proj.weight",
|
| 416 |
+
"decoderLayer.43.multiHeadAttention.v.weight": "model.layers.43.self_attn.v_proj.weight",
|
| 417 |
+
"decoderLayer.43.multiHeadAttention.o.weight": "model.layers.43.self_attn.o_proj.weight",
|
| 418 |
+
"decoderLayer.43.attnLayerNorm.weight": "model.layers.43.ln1.weight",
|
| 419 |
+
"decoderLayer.43.feedForward.intermediateDense.weight": "model.layers.43.mlp.gate_proj.weight",
|
| 420 |
+
"decoderLayer.43.feedForward.outputDense.weight": "model.layers.43.mlp.down_proj.weight",
|
| 421 |
+
"decoderLayer.43.ffnLayerNorm.weight": "model.layers.43.ln2.weight",
|
| 422 |
+
"decoderLayer.43.feedForward.intermediateDense2.weight": "model.layers.43.mlp.up_proj.weight",
|
| 423 |
+
"decoderLayer.44.multiHeadAttention.q.weight": "model.layers.44.self_attn.q_proj.weight",
|
| 424 |
+
"decoderLayer.44.multiHeadAttention.k.weight": "model.layers.44.self_attn.k_proj.weight",
|
| 425 |
+
"decoderLayer.44.multiHeadAttention.v.weight": "model.layers.44.self_attn.v_proj.weight",
|
| 426 |
+
"decoderLayer.44.multiHeadAttention.o.weight": "model.layers.44.self_attn.o_proj.weight",
|
| 427 |
+
"decoderLayer.44.attnLayerNorm.weight": "model.layers.44.ln1.weight",
|
| 428 |
+
"decoderLayer.44.feedForward.intermediateDense.weight": "model.layers.44.mlp.gate_proj.weight",
|
| 429 |
+
"decoderLayer.44.feedForward.outputDense.weight": "model.layers.44.mlp.down_proj.weight",
|
| 430 |
+
"decoderLayer.44.ffnLayerNorm.weight": "model.layers.44.ln2.weight",
|
| 431 |
+
"decoderLayer.44.feedForward.intermediateDense2.weight": "model.layers.44.mlp.up_proj.weight",
|
| 432 |
+
"decoderLayer.45.multiHeadAttention.q.weight": "model.layers.45.self_attn.q_proj.weight",
|
| 433 |
+
"decoderLayer.45.multiHeadAttention.k.weight": "model.layers.45.self_attn.k_proj.weight",
|
| 434 |
+
"decoderLayer.45.multiHeadAttention.v.weight": "model.layers.45.self_attn.v_proj.weight",
|
| 435 |
+
"decoderLayer.45.multiHeadAttention.o.weight": "model.layers.45.self_attn.o_proj.weight",
|
| 436 |
+
"decoderLayer.45.attnLayerNorm.weight": "model.layers.45.ln1.weight",
|
| 437 |
+
"decoderLayer.45.feedForward.intermediateDense.weight": "model.layers.45.mlp.gate_proj.weight",
|
| 438 |
+
"decoderLayer.45.feedForward.outputDense.weight": "model.layers.45.mlp.down_proj.weight",
|
| 439 |
+
"decoderLayer.45.ffnLayerNorm.weight": "model.layers.45.ln2.weight",
|
| 440 |
+
"decoderLayer.45.feedForward.intermediateDense2.weight": "model.layers.45.mlp.up_proj.weight",
|
| 441 |
+
"decoderLayer.46.multiHeadAttention.q.weight": "model.layers.46.self_attn.q_proj.weight",
|
| 442 |
+
"decoderLayer.46.multiHeadAttention.k.weight": "model.layers.46.self_attn.k_proj.weight",
|
| 443 |
+
"decoderLayer.46.multiHeadAttention.v.weight": "model.layers.46.self_attn.v_proj.weight",
|
| 444 |
+
"decoderLayer.46.multiHeadAttention.o.weight": "model.layers.46.self_attn.o_proj.weight",
|
| 445 |
+
"decoderLayer.46.attnLayerNorm.weight": "model.layers.46.ln1.weight",
|
| 446 |
+
"decoderLayer.46.feedForward.intermediateDense.weight": "model.layers.46.mlp.gate_proj.weight",
|
| 447 |
+
"decoderLayer.46.feedForward.outputDense.weight": "model.layers.46.mlp.down_proj.weight",
|
| 448 |
+
"decoderLayer.46.ffnLayerNorm.weight": "model.layers.46.ln2.weight",
|
| 449 |
+
"decoderLayer.46.feedForward.intermediateDense2.weight": "model.layers.46.mlp.up_proj.weight",
|
| 450 |
+
"decoderLayer.47.multiHeadAttention.q.weight": "model.layers.47.self_attn.q_proj.weight",
|
| 451 |
+
"decoderLayer.47.multiHeadAttention.k.weight": "model.layers.47.self_attn.k_proj.weight",
|
| 452 |
+
"decoderLayer.47.multiHeadAttention.v.weight": "model.layers.47.self_attn.v_proj.weight",
|
| 453 |
+
"decoderLayer.47.multiHeadAttention.o.weight": "model.layers.47.self_attn.o_proj.weight",
|
| 454 |
+
"decoderLayer.47.attnLayerNorm.weight": "model.layers.47.ln1.weight",
|
| 455 |
+
"decoderLayer.47.feedForward.intermediateDense.weight": "model.layers.47.mlp.gate_proj.weight",
|
| 456 |
+
"decoderLayer.47.feedForward.outputDense.weight": "model.layers.47.mlp.down_proj.weight",
|
| 457 |
+
"decoderLayer.47.ffnLayerNorm.weight": "model.layers.47.ln2.weight",
|
| 458 |
+
"decoderLayer.47.feedForward.intermediateDense2.weight": "model.layers.47.mlp.up_proj.weight"
|
| 459 |
+
}
|
| 460 |
+
}
|
Yi-1.5-9B-Chat/bert4torch_config.json
ADDED
|
@@ -0,0 +1,460 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 1,
|
| 3 |
+
"eos_token_id": 2,
|
| 4 |
+
"hidden_act": "silu",
|
| 5 |
+
"hidden_size": 4096,
|
| 6 |
+
"initializer_range": 0.02,
|
| 7 |
+
"intermediate_size": 11008,
|
| 8 |
+
"max_position_embeddings": 16384,
|
| 9 |
+
"model": "llama",
|
| 10 |
+
"num_attention_heads": 32,
|
| 11 |
+
"num_hidden_layers": 48,
|
| 12 |
+
"num_key_value_heads": 4,
|
| 13 |
+
"pad_token_id": 0,
|
| 14 |
+
"layer_norm_eps": 1e-06,
|
| 15 |
+
"rope_theta": 5000000.0,
|
| 16 |
+
"tie_word_embeddings": false,
|
| 17 |
+
"torch_dtype": "bfloat16",
|
| 18 |
+
"vocab_size": 64000,
|
| 19 |
+
"skip_init": true,
|
| 20 |
+
"rope_rank": "updown",
|
| 21 |
+
"segment_vocab_size": 0,
|
| 22 |
+
"generation_config": {"tokenizer_decode_config": {"skip_special_tokens": true}, "max_length": 16384, "eos_token_id": 2},
|
| 23 |
+
"mapping": {
|
| 24 |
+
"embeddings.word_embeddings.weight": "model.embed_tokens.weight",
|
| 25 |
+
"LayerNormFinal.weight": "model.norm.weight",
|
| 26 |
+
"lm_head.weight": "lm_head.weight",
|
| 27 |
+
"decoderLayer.0.multiHeadAttention.q.weight": "model.layers.0.self_attn.q_proj.weight",
|
| 28 |
+
"decoderLayer.0.multiHeadAttention.k.weight": "model.layers.0.self_attn.k_proj.weight",
|
| 29 |
+
"decoderLayer.0.multiHeadAttention.v.weight": "model.layers.0.self_attn.v_proj.weight",
|
| 30 |
+
"decoderLayer.0.multiHeadAttention.o.weight": "model.layers.0.self_attn.o_proj.weight",
|
| 31 |
+
"decoderLayer.0.attnLayerNorm.weight": "model.layers.0.ln1.weight",
|
| 32 |
+
"decoderLayer.0.feedForward.intermediateDense.weight": "model.layers.0.mlp.gate_proj.weight",
|
| 33 |
+
"decoderLayer.0.feedForward.outputDense.weight": "model.layers.0.mlp.down_proj.weight",
|
| 34 |
+
"decoderLayer.0.ffnLayerNorm.weight": "model.layers.0.ln2.weight",
|
| 35 |
+
"decoderLayer.0.feedForward.intermediateDense2.weight": "model.layers.0.mlp.up_proj.weight",
|
| 36 |
+
"decoderLayer.1.multiHeadAttention.q.weight": "model.layers.1.self_attn.q_proj.weight",
|
| 37 |
+
"decoderLayer.1.multiHeadAttention.k.weight": "model.layers.1.self_attn.k_proj.weight",
|
| 38 |
+
"decoderLayer.1.multiHeadAttention.v.weight": "model.layers.1.self_attn.v_proj.weight",
|
| 39 |
+
"decoderLayer.1.multiHeadAttention.o.weight": "model.layers.1.self_attn.o_proj.weight",
|
| 40 |
+
"decoderLayer.1.attnLayerNorm.weight": "model.layers.1.ln1.weight",
|
| 41 |
+
"decoderLayer.1.feedForward.intermediateDense.weight": "model.layers.1.mlp.gate_proj.weight",
|
| 42 |
+
"decoderLayer.1.feedForward.outputDense.weight": "model.layers.1.mlp.down_proj.weight",
|
| 43 |
+
"decoderLayer.1.ffnLayerNorm.weight": "model.layers.1.ln2.weight",
|
| 44 |
+
"decoderLayer.1.feedForward.intermediateDense2.weight": "model.layers.1.mlp.up_proj.weight",
|
| 45 |
+
"decoderLayer.2.multiHeadAttention.q.weight": "model.layers.2.self_attn.q_proj.weight",
|
| 46 |
+
"decoderLayer.2.multiHeadAttention.k.weight": "model.layers.2.self_attn.k_proj.weight",
|
| 47 |
+
"decoderLayer.2.multiHeadAttention.v.weight": "model.layers.2.self_attn.v_proj.weight",
|
| 48 |
+
"decoderLayer.2.multiHeadAttention.o.weight": "model.layers.2.self_attn.o_proj.weight",
|
| 49 |
+
"decoderLayer.2.attnLayerNorm.weight": "model.layers.2.ln1.weight",
|
| 50 |
+
"decoderLayer.2.feedForward.intermediateDense.weight": "model.layers.2.mlp.gate_proj.weight",
|
| 51 |
+
"decoderLayer.2.feedForward.outputDense.weight": "model.layers.2.mlp.down_proj.weight",
|
| 52 |
+
"decoderLayer.2.ffnLayerNorm.weight": "model.layers.2.ln2.weight",
|
| 53 |
+
"decoderLayer.2.feedForward.intermediateDense2.weight": "model.layers.2.mlp.up_proj.weight",
|
| 54 |
+
"decoderLayer.3.multiHeadAttention.q.weight": "model.layers.3.self_attn.q_proj.weight",
|
| 55 |
+
"decoderLayer.3.multiHeadAttention.k.weight": "model.layers.3.self_attn.k_proj.weight",
|
| 56 |
+
"decoderLayer.3.multiHeadAttention.v.weight": "model.layers.3.self_attn.v_proj.weight",
|
| 57 |
+
"decoderLayer.3.multiHeadAttention.o.weight": "model.layers.3.self_attn.o_proj.weight",
|
| 58 |
+
"decoderLayer.3.attnLayerNorm.weight": "model.layers.3.ln1.weight",
|
| 59 |
+
"decoderLayer.3.feedForward.intermediateDense.weight": "model.layers.3.mlp.gate_proj.weight",
|
| 60 |
+
"decoderLayer.3.feedForward.outputDense.weight": "model.layers.3.mlp.down_proj.weight",
|
| 61 |
+
"decoderLayer.3.ffnLayerNorm.weight": "model.layers.3.ln2.weight",
|
| 62 |
+
"decoderLayer.3.feedForward.intermediateDense2.weight": "model.layers.3.mlp.up_proj.weight",
|
| 63 |
+
"decoderLayer.4.multiHeadAttention.q.weight": "model.layers.4.self_attn.q_proj.weight",
|
| 64 |
+
"decoderLayer.4.multiHeadAttention.k.weight": "model.layers.4.self_attn.k_proj.weight",
|
| 65 |
+
"decoderLayer.4.multiHeadAttention.v.weight": "model.layers.4.self_attn.v_proj.weight",
|
| 66 |
+
"decoderLayer.4.multiHeadAttention.o.weight": "model.layers.4.self_attn.o_proj.weight",
|
| 67 |
+
"decoderLayer.4.attnLayerNorm.weight": "model.layers.4.ln1.weight",
|
| 68 |
+
"decoderLayer.4.feedForward.intermediateDense.weight": "model.layers.4.mlp.gate_proj.weight",
|
| 69 |
+
"decoderLayer.4.feedForward.outputDense.weight": "model.layers.4.mlp.down_proj.weight",
|
| 70 |
+
"decoderLayer.4.ffnLayerNorm.weight": "model.layers.4.ln2.weight",
|
| 71 |
+
"decoderLayer.4.feedForward.intermediateDense2.weight": "model.layers.4.mlp.up_proj.weight",
|
| 72 |
+
"decoderLayer.5.multiHeadAttention.q.weight": "model.layers.5.self_attn.q_proj.weight",
|
| 73 |
+
"decoderLayer.5.multiHeadAttention.k.weight": "model.layers.5.self_attn.k_proj.weight",
|
| 74 |
+
"decoderLayer.5.multiHeadAttention.v.weight": "model.layers.5.self_attn.v_proj.weight",
|
| 75 |
+
"decoderLayer.5.multiHeadAttention.o.weight": "model.layers.5.self_attn.o_proj.weight",
|
| 76 |
+
"decoderLayer.5.attnLayerNorm.weight": "model.layers.5.ln1.weight",
|
| 77 |
+
"decoderLayer.5.feedForward.intermediateDense.weight": "model.layers.5.mlp.gate_proj.weight",
|
| 78 |
+
"decoderLayer.5.feedForward.outputDense.weight": "model.layers.5.mlp.down_proj.weight",
|
| 79 |
+
"decoderLayer.5.ffnLayerNorm.weight": "model.layers.5.ln2.weight",
|
| 80 |
+
"decoderLayer.5.feedForward.intermediateDense2.weight": "model.layers.5.mlp.up_proj.weight",
|
| 81 |
+
"decoderLayer.6.multiHeadAttention.q.weight": "model.layers.6.self_attn.q_proj.weight",
|
| 82 |
+
"decoderLayer.6.multiHeadAttention.k.weight": "model.layers.6.self_attn.k_proj.weight",
|
| 83 |
+
"decoderLayer.6.multiHeadAttention.v.weight": "model.layers.6.self_attn.v_proj.weight",
|
| 84 |
+
"decoderLayer.6.multiHeadAttention.o.weight": "model.layers.6.self_attn.o_proj.weight",
|
| 85 |
+
"decoderLayer.6.attnLayerNorm.weight": "model.layers.6.ln1.weight",
|
| 86 |
+
"decoderLayer.6.feedForward.intermediateDense.weight": "model.layers.6.mlp.gate_proj.weight",
|
| 87 |
+
"decoderLayer.6.feedForward.outputDense.weight": "model.layers.6.mlp.down_proj.weight",
|
| 88 |
+
"decoderLayer.6.ffnLayerNorm.weight": "model.layers.6.ln2.weight",
|
| 89 |
+
"decoderLayer.6.feedForward.intermediateDense2.weight": "model.layers.6.mlp.up_proj.weight",
|
| 90 |
+
"decoderLayer.7.multiHeadAttention.q.weight": "model.layers.7.self_attn.q_proj.weight",
|
| 91 |
+
"decoderLayer.7.multiHeadAttention.k.weight": "model.layers.7.self_attn.k_proj.weight",
|
| 92 |
+
"decoderLayer.7.multiHeadAttention.v.weight": "model.layers.7.self_attn.v_proj.weight",
|
| 93 |
+
"decoderLayer.7.multiHeadAttention.o.weight": "model.layers.7.self_attn.o_proj.weight",
|
| 94 |
+
"decoderLayer.7.attnLayerNorm.weight": "model.layers.7.ln1.weight",
|
| 95 |
+
"decoderLayer.7.feedForward.intermediateDense.weight": "model.layers.7.mlp.gate_proj.weight",
|
| 96 |
+
"decoderLayer.7.feedForward.outputDense.weight": "model.layers.7.mlp.down_proj.weight",
|
| 97 |
+
"decoderLayer.7.ffnLayerNorm.weight": "model.layers.7.ln2.weight",
|
| 98 |
+
"decoderLayer.7.feedForward.intermediateDense2.weight": "model.layers.7.mlp.up_proj.weight",
|
| 99 |
+
"decoderLayer.8.multiHeadAttention.q.weight": "model.layers.8.self_attn.q_proj.weight",
|
| 100 |
+
"decoderLayer.8.multiHeadAttention.k.weight": "model.layers.8.self_attn.k_proj.weight",
|
| 101 |
+
"decoderLayer.8.multiHeadAttention.v.weight": "model.layers.8.self_attn.v_proj.weight",
|
| 102 |
+
"decoderLayer.8.multiHeadAttention.o.weight": "model.layers.8.self_attn.o_proj.weight",
|
| 103 |
+
"decoderLayer.8.attnLayerNorm.weight": "model.layers.8.ln1.weight",
|
| 104 |
+
"decoderLayer.8.feedForward.intermediateDense.weight": "model.layers.8.mlp.gate_proj.weight",
|
| 105 |
+
"decoderLayer.8.feedForward.outputDense.weight": "model.layers.8.mlp.down_proj.weight",
|
| 106 |
+
"decoderLayer.8.ffnLayerNorm.weight": "model.layers.8.ln2.weight",
|
| 107 |
+
"decoderLayer.8.feedForward.intermediateDense2.weight": "model.layers.8.mlp.up_proj.weight",
|
| 108 |
+
"decoderLayer.9.multiHeadAttention.q.weight": "model.layers.9.self_attn.q_proj.weight",
|
| 109 |
+
"decoderLayer.9.multiHeadAttention.k.weight": "model.layers.9.self_attn.k_proj.weight",
|
| 110 |
+
"decoderLayer.9.multiHeadAttention.v.weight": "model.layers.9.self_attn.v_proj.weight",
|
| 111 |
+
"decoderLayer.9.multiHeadAttention.o.weight": "model.layers.9.self_attn.o_proj.weight",
|
| 112 |
+
"decoderLayer.9.attnLayerNorm.weight": "model.layers.9.ln1.weight",
|
| 113 |
+
"decoderLayer.9.feedForward.intermediateDense.weight": "model.layers.9.mlp.gate_proj.weight",
|
| 114 |
+
"decoderLayer.9.feedForward.outputDense.weight": "model.layers.9.mlp.down_proj.weight",
|
| 115 |
+
"decoderLayer.9.ffnLayerNorm.weight": "model.layers.9.ln2.weight",
|
| 116 |
+
"decoderLayer.9.feedForward.intermediateDense2.weight": "model.layers.9.mlp.up_proj.weight",
|
| 117 |
+
"decoderLayer.10.multiHeadAttention.q.weight": "model.layers.10.self_attn.q_proj.weight",
|
| 118 |
+
"decoderLayer.10.multiHeadAttention.k.weight": "model.layers.10.self_attn.k_proj.weight",
|
| 119 |
+
"decoderLayer.10.multiHeadAttention.v.weight": "model.layers.10.self_attn.v_proj.weight",
|
| 120 |
+
"decoderLayer.10.multiHeadAttention.o.weight": "model.layers.10.self_attn.o_proj.weight",
|
| 121 |
+
"decoderLayer.10.attnLayerNorm.weight": "model.layers.10.ln1.weight",
|
| 122 |
+
"decoderLayer.10.feedForward.intermediateDense.weight": "model.layers.10.mlp.gate_proj.weight",
|
| 123 |
+
"decoderLayer.10.feedForward.outputDense.weight": "model.layers.10.mlp.down_proj.weight",
|
| 124 |
+
"decoderLayer.10.ffnLayerNorm.weight": "model.layers.10.ln2.weight",
|
| 125 |
+
"decoderLayer.10.feedForward.intermediateDense2.weight": "model.layers.10.mlp.up_proj.weight",
|
| 126 |
+
"decoderLayer.11.multiHeadAttention.q.weight": "model.layers.11.self_attn.q_proj.weight",
|
| 127 |
+
"decoderLayer.11.multiHeadAttention.k.weight": "model.layers.11.self_attn.k_proj.weight",
|
| 128 |
+
"decoderLayer.11.multiHeadAttention.v.weight": "model.layers.11.self_attn.v_proj.weight",
|
| 129 |
+
"decoderLayer.11.multiHeadAttention.o.weight": "model.layers.11.self_attn.o_proj.weight",
|
| 130 |
+
"decoderLayer.11.attnLayerNorm.weight": "model.layers.11.ln1.weight",
|
| 131 |
+
"decoderLayer.11.feedForward.intermediateDense.weight": "model.layers.11.mlp.gate_proj.weight",
|
| 132 |
+
"decoderLayer.11.feedForward.outputDense.weight": "model.layers.11.mlp.down_proj.weight",
|
| 133 |
+
"decoderLayer.11.ffnLayerNorm.weight": "model.layers.11.ln2.weight",
|
| 134 |
+
"decoderLayer.11.feedForward.intermediateDense2.weight": "model.layers.11.mlp.up_proj.weight",
|
| 135 |
+
"decoderLayer.12.multiHeadAttention.q.weight": "model.layers.12.self_attn.q_proj.weight",
|
| 136 |
+
"decoderLayer.12.multiHeadAttention.k.weight": "model.layers.12.self_attn.k_proj.weight",
|
| 137 |
+
"decoderLayer.12.multiHeadAttention.v.weight": "model.layers.12.self_attn.v_proj.weight",
|
| 138 |
+
"decoderLayer.12.multiHeadAttention.o.weight": "model.layers.12.self_attn.o_proj.weight",
|
| 139 |
+
"decoderLayer.12.attnLayerNorm.weight": "model.layers.12.ln1.weight",
|
| 140 |
+
"decoderLayer.12.feedForward.intermediateDense.weight": "model.layers.12.mlp.gate_proj.weight",
|
| 141 |
+
"decoderLayer.12.feedForward.outputDense.weight": "model.layers.12.mlp.down_proj.weight",
|
| 142 |
+
"decoderLayer.12.ffnLayerNorm.weight": "model.layers.12.ln2.weight",
|
| 143 |
+
"decoderLayer.12.feedForward.intermediateDense2.weight": "model.layers.12.mlp.up_proj.weight",
|
| 144 |
+
"decoderLayer.13.multiHeadAttention.q.weight": "model.layers.13.self_attn.q_proj.weight",
|
| 145 |
+
"decoderLayer.13.multiHeadAttention.k.weight": "model.layers.13.self_attn.k_proj.weight",
|
| 146 |
+
"decoderLayer.13.multiHeadAttention.v.weight": "model.layers.13.self_attn.v_proj.weight",
|
| 147 |
+
"decoderLayer.13.multiHeadAttention.o.weight": "model.layers.13.self_attn.o_proj.weight",
|
| 148 |
+
"decoderLayer.13.attnLayerNorm.weight": "model.layers.13.ln1.weight",
|
| 149 |
+
"decoderLayer.13.feedForward.intermediateDense.weight": "model.layers.13.mlp.gate_proj.weight",
|
| 150 |
+
"decoderLayer.13.feedForward.outputDense.weight": "model.layers.13.mlp.down_proj.weight",
|
| 151 |
+
"decoderLayer.13.ffnLayerNorm.weight": "model.layers.13.ln2.weight",
|
| 152 |
+
"decoderLayer.13.feedForward.intermediateDense2.weight": "model.layers.13.mlp.up_proj.weight",
|
| 153 |
+
"decoderLayer.14.multiHeadAttention.q.weight": "model.layers.14.self_attn.q_proj.weight",
|
| 154 |
+
"decoderLayer.14.multiHeadAttention.k.weight": "model.layers.14.self_attn.k_proj.weight",
|
| 155 |
+
"decoderLayer.14.multiHeadAttention.v.weight": "model.layers.14.self_attn.v_proj.weight",
|
| 156 |
+
"decoderLayer.14.multiHeadAttention.o.weight": "model.layers.14.self_attn.o_proj.weight",
|
| 157 |
+
"decoderLayer.14.attnLayerNorm.weight": "model.layers.14.ln1.weight",
|
| 158 |
+
"decoderLayer.14.feedForward.intermediateDense.weight": "model.layers.14.mlp.gate_proj.weight",
|
| 159 |
+
"decoderLayer.14.feedForward.outputDense.weight": "model.layers.14.mlp.down_proj.weight",
|
| 160 |
+
"decoderLayer.14.ffnLayerNorm.weight": "model.layers.14.ln2.weight",
|
| 161 |
+
"decoderLayer.14.feedForward.intermediateDense2.weight": "model.layers.14.mlp.up_proj.weight",
|
| 162 |
+
"decoderLayer.15.multiHeadAttention.q.weight": "model.layers.15.self_attn.q_proj.weight",
|
| 163 |
+
"decoderLayer.15.multiHeadAttention.k.weight": "model.layers.15.self_attn.k_proj.weight",
|
| 164 |
+
"decoderLayer.15.multiHeadAttention.v.weight": "model.layers.15.self_attn.v_proj.weight",
|
| 165 |
+
"decoderLayer.15.multiHeadAttention.o.weight": "model.layers.15.self_attn.o_proj.weight",
|
| 166 |
+
"decoderLayer.15.attnLayerNorm.weight": "model.layers.15.ln1.weight",
|
| 167 |
+
"decoderLayer.15.feedForward.intermediateDense.weight": "model.layers.15.mlp.gate_proj.weight",
|
| 168 |
+
"decoderLayer.15.feedForward.outputDense.weight": "model.layers.15.mlp.down_proj.weight",
|
| 169 |
+
"decoderLayer.15.ffnLayerNorm.weight": "model.layers.15.ln2.weight",
|
| 170 |
+
"decoderLayer.15.feedForward.intermediateDense2.weight": "model.layers.15.mlp.up_proj.weight",
|
| 171 |
+
"decoderLayer.16.multiHeadAttention.q.weight": "model.layers.16.self_attn.q_proj.weight",
|
| 172 |
+
"decoderLayer.16.multiHeadAttention.k.weight": "model.layers.16.self_attn.k_proj.weight",
|
| 173 |
+
"decoderLayer.16.multiHeadAttention.v.weight": "model.layers.16.self_attn.v_proj.weight",
|
| 174 |
+
"decoderLayer.16.multiHeadAttention.o.weight": "model.layers.16.self_attn.o_proj.weight",
|
| 175 |
+
"decoderLayer.16.attnLayerNorm.weight": "model.layers.16.ln1.weight",
|
| 176 |
+
"decoderLayer.16.feedForward.intermediateDense.weight": "model.layers.16.mlp.gate_proj.weight",
|
| 177 |
+
"decoderLayer.16.feedForward.outputDense.weight": "model.layers.16.mlp.down_proj.weight",
|
| 178 |
+
"decoderLayer.16.ffnLayerNorm.weight": "model.layers.16.ln2.weight",
|
| 179 |
+
"decoderLayer.16.feedForward.intermediateDense2.weight": "model.layers.16.mlp.up_proj.weight",
|
| 180 |
+
"decoderLayer.17.multiHeadAttention.q.weight": "model.layers.17.self_attn.q_proj.weight",
|
| 181 |
+
"decoderLayer.17.multiHeadAttention.k.weight": "model.layers.17.self_attn.k_proj.weight",
|
| 182 |
+
"decoderLayer.17.multiHeadAttention.v.weight": "model.layers.17.self_attn.v_proj.weight",
|
| 183 |
+
"decoderLayer.17.multiHeadAttention.o.weight": "model.layers.17.self_attn.o_proj.weight",
|
| 184 |
+
"decoderLayer.17.attnLayerNorm.weight": "model.layers.17.ln1.weight",
|
| 185 |
+
"decoderLayer.17.feedForward.intermediateDense.weight": "model.layers.17.mlp.gate_proj.weight",
|
| 186 |
+
"decoderLayer.17.feedForward.outputDense.weight": "model.layers.17.mlp.down_proj.weight",
|
| 187 |
+
"decoderLayer.17.ffnLayerNorm.weight": "model.layers.17.ln2.weight",
|
| 188 |
+
"decoderLayer.17.feedForward.intermediateDense2.weight": "model.layers.17.mlp.up_proj.weight",
|
| 189 |
+
"decoderLayer.18.multiHeadAttention.q.weight": "model.layers.18.self_attn.q_proj.weight",
|
| 190 |
+
"decoderLayer.18.multiHeadAttention.k.weight": "model.layers.18.self_attn.k_proj.weight",
|
| 191 |
+
"decoderLayer.18.multiHeadAttention.v.weight": "model.layers.18.self_attn.v_proj.weight",
|
| 192 |
+
"decoderLayer.18.multiHeadAttention.o.weight": "model.layers.18.self_attn.o_proj.weight",
|
| 193 |
+
"decoderLayer.18.attnLayerNorm.weight": "model.layers.18.ln1.weight",
|
| 194 |
+
"decoderLayer.18.feedForward.intermediateDense.weight": "model.layers.18.mlp.gate_proj.weight",
|
| 195 |
+
"decoderLayer.18.feedForward.outputDense.weight": "model.layers.18.mlp.down_proj.weight",
|
| 196 |
+
"decoderLayer.18.ffnLayerNorm.weight": "model.layers.18.ln2.weight",
|
| 197 |
+
"decoderLayer.18.feedForward.intermediateDense2.weight": "model.layers.18.mlp.up_proj.weight",
|
| 198 |
+
"decoderLayer.19.multiHeadAttention.q.weight": "model.layers.19.self_attn.q_proj.weight",
|
| 199 |
+
"decoderLayer.19.multiHeadAttention.k.weight": "model.layers.19.self_attn.k_proj.weight",
|
| 200 |
+
"decoderLayer.19.multiHeadAttention.v.weight": "model.layers.19.self_attn.v_proj.weight",
|
| 201 |
+
"decoderLayer.19.multiHeadAttention.o.weight": "model.layers.19.self_attn.o_proj.weight",
|
| 202 |
+
"decoderLayer.19.attnLayerNorm.weight": "model.layers.19.ln1.weight",
|
| 203 |
+
"decoderLayer.19.feedForward.intermediateDense.weight": "model.layers.19.mlp.gate_proj.weight",
|
| 204 |
+
"decoderLayer.19.feedForward.outputDense.weight": "model.layers.19.mlp.down_proj.weight",
|
| 205 |
+
"decoderLayer.19.ffnLayerNorm.weight": "model.layers.19.ln2.weight",
|
| 206 |
+
"decoderLayer.19.feedForward.intermediateDense2.weight": "model.layers.19.mlp.up_proj.weight",
|
| 207 |
+
"decoderLayer.20.multiHeadAttention.q.weight": "model.layers.20.self_attn.q_proj.weight",
|
| 208 |
+
"decoderLayer.20.multiHeadAttention.k.weight": "model.layers.20.self_attn.k_proj.weight",
|
| 209 |
+
"decoderLayer.20.multiHeadAttention.v.weight": "model.layers.20.self_attn.v_proj.weight",
|
| 210 |
+
"decoderLayer.20.multiHeadAttention.o.weight": "model.layers.20.self_attn.o_proj.weight",
|
| 211 |
+
"decoderLayer.20.attnLayerNorm.weight": "model.layers.20.ln1.weight",
|
| 212 |
+
"decoderLayer.20.feedForward.intermediateDense.weight": "model.layers.20.mlp.gate_proj.weight",
|
| 213 |
+
"decoderLayer.20.feedForward.outputDense.weight": "model.layers.20.mlp.down_proj.weight",
|
| 214 |
+
"decoderLayer.20.ffnLayerNorm.weight": "model.layers.20.ln2.weight",
|
| 215 |
+
"decoderLayer.20.feedForward.intermediateDense2.weight": "model.layers.20.mlp.up_proj.weight",
|
| 216 |
+
"decoderLayer.21.multiHeadAttention.q.weight": "model.layers.21.self_attn.q_proj.weight",
|
| 217 |
+
"decoderLayer.21.multiHeadAttention.k.weight": "model.layers.21.self_attn.k_proj.weight",
|
| 218 |
+
"decoderLayer.21.multiHeadAttention.v.weight": "model.layers.21.self_attn.v_proj.weight",
|
| 219 |
+
"decoderLayer.21.multiHeadAttention.o.weight": "model.layers.21.self_attn.o_proj.weight",
|
| 220 |
+
"decoderLayer.21.attnLayerNorm.weight": "model.layers.21.ln1.weight",
|
| 221 |
+
"decoderLayer.21.feedForward.intermediateDense.weight": "model.layers.21.mlp.gate_proj.weight",
|
| 222 |
+
"decoderLayer.21.feedForward.outputDense.weight": "model.layers.21.mlp.down_proj.weight",
|
| 223 |
+
"decoderLayer.21.ffnLayerNorm.weight": "model.layers.21.ln2.weight",
|
| 224 |
+
"decoderLayer.21.feedForward.intermediateDense2.weight": "model.layers.21.mlp.up_proj.weight",
|
| 225 |
+
"decoderLayer.22.multiHeadAttention.q.weight": "model.layers.22.self_attn.q_proj.weight",
|
| 226 |
+
"decoderLayer.22.multiHeadAttention.k.weight": "model.layers.22.self_attn.k_proj.weight",
|
| 227 |
+
"decoderLayer.22.multiHeadAttention.v.weight": "model.layers.22.self_attn.v_proj.weight",
|
| 228 |
+
"decoderLayer.22.multiHeadAttention.o.weight": "model.layers.22.self_attn.o_proj.weight",
|
| 229 |
+
"decoderLayer.22.attnLayerNorm.weight": "model.layers.22.ln1.weight",
|
| 230 |
+
"decoderLayer.22.feedForward.intermediateDense.weight": "model.layers.22.mlp.gate_proj.weight",
|
| 231 |
+
"decoderLayer.22.feedForward.outputDense.weight": "model.layers.22.mlp.down_proj.weight",
|
| 232 |
+
"decoderLayer.22.ffnLayerNorm.weight": "model.layers.22.ln2.weight",
|
| 233 |
+
"decoderLayer.22.feedForward.intermediateDense2.weight": "model.layers.22.mlp.up_proj.weight",
|
| 234 |
+
"decoderLayer.23.multiHeadAttention.q.weight": "model.layers.23.self_attn.q_proj.weight",
|
| 235 |
+
"decoderLayer.23.multiHeadAttention.k.weight": "model.layers.23.self_attn.k_proj.weight",
|
| 236 |
+
"decoderLayer.23.multiHeadAttention.v.weight": "model.layers.23.self_attn.v_proj.weight",
|
| 237 |
+
"decoderLayer.23.multiHeadAttention.o.weight": "model.layers.23.self_attn.o_proj.weight",
|
| 238 |
+
"decoderLayer.23.attnLayerNorm.weight": "model.layers.23.ln1.weight",
|
| 239 |
+
"decoderLayer.23.feedForward.intermediateDense.weight": "model.layers.23.mlp.gate_proj.weight",
|
| 240 |
+
"decoderLayer.23.feedForward.outputDense.weight": "model.layers.23.mlp.down_proj.weight",
|
| 241 |
+
"decoderLayer.23.ffnLayerNorm.weight": "model.layers.23.ln2.weight",
|
| 242 |
+
"decoderLayer.23.feedForward.intermediateDense2.weight": "model.layers.23.mlp.up_proj.weight",
|
| 243 |
+
"decoderLayer.24.multiHeadAttention.q.weight": "model.layers.24.self_attn.q_proj.weight",
|
| 244 |
+
"decoderLayer.24.multiHeadAttention.k.weight": "model.layers.24.self_attn.k_proj.weight",
|
| 245 |
+
"decoderLayer.24.multiHeadAttention.v.weight": "model.layers.24.self_attn.v_proj.weight",
|
| 246 |
+
"decoderLayer.24.multiHeadAttention.o.weight": "model.layers.24.self_attn.o_proj.weight",
|
| 247 |
+
"decoderLayer.24.attnLayerNorm.weight": "model.layers.24.ln1.weight",
|
| 248 |
+
"decoderLayer.24.feedForward.intermediateDense.weight": "model.layers.24.mlp.gate_proj.weight",
|
| 249 |
+
"decoderLayer.24.feedForward.outputDense.weight": "model.layers.24.mlp.down_proj.weight",
|
| 250 |
+
"decoderLayer.24.ffnLayerNorm.weight": "model.layers.24.ln2.weight",
|
| 251 |
+
"decoderLayer.24.feedForward.intermediateDense2.weight": "model.layers.24.mlp.up_proj.weight",
|
| 252 |
+
"decoderLayer.25.multiHeadAttention.q.weight": "model.layers.25.self_attn.q_proj.weight",
|
| 253 |
+
"decoderLayer.25.multiHeadAttention.k.weight": "model.layers.25.self_attn.k_proj.weight",
|
| 254 |
+
"decoderLayer.25.multiHeadAttention.v.weight": "model.layers.25.self_attn.v_proj.weight",
|
| 255 |
+
"decoderLayer.25.multiHeadAttention.o.weight": "model.layers.25.self_attn.o_proj.weight",
|
| 256 |
+
"decoderLayer.25.attnLayerNorm.weight": "model.layers.25.ln1.weight",
|
| 257 |
+
"decoderLayer.25.feedForward.intermediateDense.weight": "model.layers.25.mlp.gate_proj.weight",
|
| 258 |
+
"decoderLayer.25.feedForward.outputDense.weight": "model.layers.25.mlp.down_proj.weight",
|
| 259 |
+
"decoderLayer.25.ffnLayerNorm.weight": "model.layers.25.ln2.weight",
|
| 260 |
+
"decoderLayer.25.feedForward.intermediateDense2.weight": "model.layers.25.mlp.up_proj.weight",
|
| 261 |
+
"decoderLayer.26.multiHeadAttention.q.weight": "model.layers.26.self_attn.q_proj.weight",
|
| 262 |
+
"decoderLayer.26.multiHeadAttention.k.weight": "model.layers.26.self_attn.k_proj.weight",
|
| 263 |
+
"decoderLayer.26.multiHeadAttention.v.weight": "model.layers.26.self_attn.v_proj.weight",
|
| 264 |
+
"decoderLayer.26.multiHeadAttention.o.weight": "model.layers.26.self_attn.o_proj.weight",
|
| 265 |
+
"decoderLayer.26.attnLayerNorm.weight": "model.layers.26.ln1.weight",
|
| 266 |
+
"decoderLayer.26.feedForward.intermediateDense.weight": "model.layers.26.mlp.gate_proj.weight",
|
| 267 |
+
"decoderLayer.26.feedForward.outputDense.weight": "model.layers.26.mlp.down_proj.weight",
|
| 268 |
+
"decoderLayer.26.ffnLayerNorm.weight": "model.layers.26.ln2.weight",
|
| 269 |
+
"decoderLayer.26.feedForward.intermediateDense2.weight": "model.layers.26.mlp.up_proj.weight",
|
| 270 |
+
"decoderLayer.27.multiHeadAttention.q.weight": "model.layers.27.self_attn.q_proj.weight",
|
| 271 |
+
"decoderLayer.27.multiHeadAttention.k.weight": "model.layers.27.self_attn.k_proj.weight",
|
| 272 |
+
"decoderLayer.27.multiHeadAttention.v.weight": "model.layers.27.self_attn.v_proj.weight",
|
| 273 |
+
"decoderLayer.27.multiHeadAttention.o.weight": "model.layers.27.self_attn.o_proj.weight",
|
| 274 |
+
"decoderLayer.27.attnLayerNorm.weight": "model.layers.27.ln1.weight",
|
| 275 |
+
"decoderLayer.27.feedForward.intermediateDense.weight": "model.layers.27.mlp.gate_proj.weight",
|
| 276 |
+
"decoderLayer.27.feedForward.outputDense.weight": "model.layers.27.mlp.down_proj.weight",
|
| 277 |
+
"decoderLayer.27.ffnLayerNorm.weight": "model.layers.27.ln2.weight",
|
| 278 |
+
"decoderLayer.27.feedForward.intermediateDense2.weight": "model.layers.27.mlp.up_proj.weight",
|
| 279 |
+
"decoderLayer.28.multiHeadAttention.q.weight": "model.layers.28.self_attn.q_proj.weight",
|
| 280 |
+
"decoderLayer.28.multiHeadAttention.k.weight": "model.layers.28.self_attn.k_proj.weight",
|
| 281 |
+
"decoderLayer.28.multiHeadAttention.v.weight": "model.layers.28.self_attn.v_proj.weight",
|
| 282 |
+
"decoderLayer.28.multiHeadAttention.o.weight": "model.layers.28.self_attn.o_proj.weight",
|
| 283 |
+
"decoderLayer.28.attnLayerNorm.weight": "model.layers.28.ln1.weight",
|
| 284 |
+
"decoderLayer.28.feedForward.intermediateDense.weight": "model.layers.28.mlp.gate_proj.weight",
|
| 285 |
+
"decoderLayer.28.feedForward.outputDense.weight": "model.layers.28.mlp.down_proj.weight",
|
| 286 |
+
"decoderLayer.28.ffnLayerNorm.weight": "model.layers.28.ln2.weight",
|
| 287 |
+
"decoderLayer.28.feedForward.intermediateDense2.weight": "model.layers.28.mlp.up_proj.weight",
|
| 288 |
+
"decoderLayer.29.multiHeadAttention.q.weight": "model.layers.29.self_attn.q_proj.weight",
|
| 289 |
+
"decoderLayer.29.multiHeadAttention.k.weight": "model.layers.29.self_attn.k_proj.weight",
|
| 290 |
+
"decoderLayer.29.multiHeadAttention.v.weight": "model.layers.29.self_attn.v_proj.weight",
|
| 291 |
+
"decoderLayer.29.multiHeadAttention.o.weight": "model.layers.29.self_attn.o_proj.weight",
|
| 292 |
+
"decoderLayer.29.attnLayerNorm.weight": "model.layers.29.ln1.weight",
|
| 293 |
+
"decoderLayer.29.feedForward.intermediateDense.weight": "model.layers.29.mlp.gate_proj.weight",
|
| 294 |
+
"decoderLayer.29.feedForward.outputDense.weight": "model.layers.29.mlp.down_proj.weight",
|
| 295 |
+
"decoderLayer.29.ffnLayerNorm.weight": "model.layers.29.ln2.weight",
|
| 296 |
+
"decoderLayer.29.feedForward.intermediateDense2.weight": "model.layers.29.mlp.up_proj.weight",
|
| 297 |
+
"decoderLayer.30.multiHeadAttention.q.weight": "model.layers.30.self_attn.q_proj.weight",
|
| 298 |
+
"decoderLayer.30.multiHeadAttention.k.weight": "model.layers.30.self_attn.k_proj.weight",
|
| 299 |
+
"decoderLayer.30.multiHeadAttention.v.weight": "model.layers.30.self_attn.v_proj.weight",
|
| 300 |
+
"decoderLayer.30.multiHeadAttention.o.weight": "model.layers.30.self_attn.o_proj.weight",
|
| 301 |
+
"decoderLayer.30.attnLayerNorm.weight": "model.layers.30.ln1.weight",
|
| 302 |
+
"decoderLayer.30.feedForward.intermediateDense.weight": "model.layers.30.mlp.gate_proj.weight",
|
| 303 |
+
"decoderLayer.30.feedForward.outputDense.weight": "model.layers.30.mlp.down_proj.weight",
|
| 304 |
+
"decoderLayer.30.ffnLayerNorm.weight": "model.layers.30.ln2.weight",
|
| 305 |
+
"decoderLayer.30.feedForward.intermediateDense2.weight": "model.layers.30.mlp.up_proj.weight",
|
| 306 |
+
"decoderLayer.31.multiHeadAttention.q.weight": "model.layers.31.self_attn.q_proj.weight",
|
| 307 |
+
"decoderLayer.31.multiHeadAttention.k.weight": "model.layers.31.self_attn.k_proj.weight",
|
| 308 |
+
"decoderLayer.31.multiHeadAttention.v.weight": "model.layers.31.self_attn.v_proj.weight",
|
| 309 |
+
"decoderLayer.31.multiHeadAttention.o.weight": "model.layers.31.self_attn.o_proj.weight",
|
| 310 |
+
"decoderLayer.31.attnLayerNorm.weight": "model.layers.31.ln1.weight",
|
| 311 |
+
"decoderLayer.31.feedForward.intermediateDense.weight": "model.layers.31.mlp.gate_proj.weight",
|
| 312 |
+
"decoderLayer.31.feedForward.outputDense.weight": "model.layers.31.mlp.down_proj.weight",
|
| 313 |
+
"decoderLayer.31.ffnLayerNorm.weight": "model.layers.31.ln2.weight",
|
| 314 |
+
"decoderLayer.31.feedForward.intermediateDense2.weight": "model.layers.31.mlp.up_proj.weight",
|
| 315 |
+
"decoderLayer.32.multiHeadAttention.q.weight": "model.layers.32.self_attn.q_proj.weight",
|
| 316 |
+
"decoderLayer.32.multiHeadAttention.k.weight": "model.layers.32.self_attn.k_proj.weight",
|
| 317 |
+
"decoderLayer.32.multiHeadAttention.v.weight": "model.layers.32.self_attn.v_proj.weight",
|
| 318 |
+
"decoderLayer.32.multiHeadAttention.o.weight": "model.layers.32.self_attn.o_proj.weight",
|
| 319 |
+
"decoderLayer.32.attnLayerNorm.weight": "model.layers.32.ln1.weight",
|
| 320 |
+
"decoderLayer.32.feedForward.intermediateDense.weight": "model.layers.32.mlp.gate_proj.weight",
|
| 321 |
+
"decoderLayer.32.feedForward.outputDense.weight": "model.layers.32.mlp.down_proj.weight",
|
| 322 |
+
"decoderLayer.32.ffnLayerNorm.weight": "model.layers.32.ln2.weight",
|
| 323 |
+
"decoderLayer.32.feedForward.intermediateDense2.weight": "model.layers.32.mlp.up_proj.weight",
|
| 324 |
+
"decoderLayer.33.multiHeadAttention.q.weight": "model.layers.33.self_attn.q_proj.weight",
|
| 325 |
+
"decoderLayer.33.multiHeadAttention.k.weight": "model.layers.33.self_attn.k_proj.weight",
|
| 326 |
+
"decoderLayer.33.multiHeadAttention.v.weight": "model.layers.33.self_attn.v_proj.weight",
|
| 327 |
+
"decoderLayer.33.multiHeadAttention.o.weight": "model.layers.33.self_attn.o_proj.weight",
|
| 328 |
+
"decoderLayer.33.attnLayerNorm.weight": "model.layers.33.ln1.weight",
|
| 329 |
+
"decoderLayer.33.feedForward.intermediateDense.weight": "model.layers.33.mlp.gate_proj.weight",
|
| 330 |
+
"decoderLayer.33.feedForward.outputDense.weight": "model.layers.33.mlp.down_proj.weight",
|
| 331 |
+
"decoderLayer.33.ffnLayerNorm.weight": "model.layers.33.ln2.weight",
|
| 332 |
+
"decoderLayer.33.feedForward.intermediateDense2.weight": "model.layers.33.mlp.up_proj.weight",
|
| 333 |
+
"decoderLayer.34.multiHeadAttention.q.weight": "model.layers.34.self_attn.q_proj.weight",
|
| 334 |
+
"decoderLayer.34.multiHeadAttention.k.weight": "model.layers.34.self_attn.k_proj.weight",
|
| 335 |
+
"decoderLayer.34.multiHeadAttention.v.weight": "model.layers.34.self_attn.v_proj.weight",
|
| 336 |
+
"decoderLayer.34.multiHeadAttention.o.weight": "model.layers.34.self_attn.o_proj.weight",
|
| 337 |
+
"decoderLayer.34.attnLayerNorm.weight": "model.layers.34.ln1.weight",
|
| 338 |
+
"decoderLayer.34.feedForward.intermediateDense.weight": "model.layers.34.mlp.gate_proj.weight",
|
| 339 |
+
"decoderLayer.34.feedForward.outputDense.weight": "model.layers.34.mlp.down_proj.weight",
|
| 340 |
+
"decoderLayer.34.ffnLayerNorm.weight": "model.layers.34.ln2.weight",
|
| 341 |
+
"decoderLayer.34.feedForward.intermediateDense2.weight": "model.layers.34.mlp.up_proj.weight",
|
| 342 |
+
"decoderLayer.35.multiHeadAttention.q.weight": "model.layers.35.self_attn.q_proj.weight",
|
| 343 |
+
"decoderLayer.35.multiHeadAttention.k.weight": "model.layers.35.self_attn.k_proj.weight",
|
| 344 |
+
"decoderLayer.35.multiHeadAttention.v.weight": "model.layers.35.self_attn.v_proj.weight",
|
| 345 |
+
"decoderLayer.35.multiHeadAttention.o.weight": "model.layers.35.self_attn.o_proj.weight",
|
| 346 |
+
"decoderLayer.35.attnLayerNorm.weight": "model.layers.35.ln1.weight",
|
| 347 |
+
"decoderLayer.35.feedForward.intermediateDense.weight": "model.layers.35.mlp.gate_proj.weight",
|
| 348 |
+
"decoderLayer.35.feedForward.outputDense.weight": "model.layers.35.mlp.down_proj.weight",
|
| 349 |
+
"decoderLayer.35.ffnLayerNorm.weight": "model.layers.35.ln2.weight",
|
| 350 |
+
"decoderLayer.35.feedForward.intermediateDense2.weight": "model.layers.35.mlp.up_proj.weight",
|
| 351 |
+
"decoderLayer.36.multiHeadAttention.q.weight": "model.layers.36.self_attn.q_proj.weight",
|
| 352 |
+
"decoderLayer.36.multiHeadAttention.k.weight": "model.layers.36.self_attn.k_proj.weight",
|
| 353 |
+
"decoderLayer.36.multiHeadAttention.v.weight": "model.layers.36.self_attn.v_proj.weight",
|
| 354 |
+
"decoderLayer.36.multiHeadAttention.o.weight": "model.layers.36.self_attn.o_proj.weight",
|
| 355 |
+
"decoderLayer.36.attnLayerNorm.weight": "model.layers.36.ln1.weight",
|
| 356 |
+
"decoderLayer.36.feedForward.intermediateDense.weight": "model.layers.36.mlp.gate_proj.weight",
|
| 357 |
+
"decoderLayer.36.feedForward.outputDense.weight": "model.layers.36.mlp.down_proj.weight",
|
| 358 |
+
"decoderLayer.36.ffnLayerNorm.weight": "model.layers.36.ln2.weight",
|
| 359 |
+
"decoderLayer.36.feedForward.intermediateDense2.weight": "model.layers.36.mlp.up_proj.weight",
|
| 360 |
+
"decoderLayer.37.multiHeadAttention.q.weight": "model.layers.37.self_attn.q_proj.weight",
|
| 361 |
+
"decoderLayer.37.multiHeadAttention.k.weight": "model.layers.37.self_attn.k_proj.weight",
|
| 362 |
+
"decoderLayer.37.multiHeadAttention.v.weight": "model.layers.37.self_attn.v_proj.weight",
|
| 363 |
+
"decoderLayer.37.multiHeadAttention.o.weight": "model.layers.37.self_attn.o_proj.weight",
|
| 364 |
+
"decoderLayer.37.attnLayerNorm.weight": "model.layers.37.ln1.weight",
|
| 365 |
+
"decoderLayer.37.feedForward.intermediateDense.weight": "model.layers.37.mlp.gate_proj.weight",
|
| 366 |
+
"decoderLayer.37.feedForward.outputDense.weight": "model.layers.37.mlp.down_proj.weight",
|
| 367 |
+
"decoderLayer.37.ffnLayerNorm.weight": "model.layers.37.ln2.weight",
|
| 368 |
+
"decoderLayer.37.feedForward.intermediateDense2.weight": "model.layers.37.mlp.up_proj.weight",
|
| 369 |
+
"decoderLayer.38.multiHeadAttention.q.weight": "model.layers.38.self_attn.q_proj.weight",
|
| 370 |
+
"decoderLayer.38.multiHeadAttention.k.weight": "model.layers.38.self_attn.k_proj.weight",
|
| 371 |
+
"decoderLayer.38.multiHeadAttention.v.weight": "model.layers.38.self_attn.v_proj.weight",
|
| 372 |
+
"decoderLayer.38.multiHeadAttention.o.weight": "model.layers.38.self_attn.o_proj.weight",
|
| 373 |
+
"decoderLayer.38.attnLayerNorm.weight": "model.layers.38.ln1.weight",
|
| 374 |
+
"decoderLayer.38.feedForward.intermediateDense.weight": "model.layers.38.mlp.gate_proj.weight",
|
| 375 |
+
"decoderLayer.38.feedForward.outputDense.weight": "model.layers.38.mlp.down_proj.weight",
|
| 376 |
+
"decoderLayer.38.ffnLayerNorm.weight": "model.layers.38.ln2.weight",
|
| 377 |
+
"decoderLayer.38.feedForward.intermediateDense2.weight": "model.layers.38.mlp.up_proj.weight",
|
| 378 |
+
"decoderLayer.39.multiHeadAttention.q.weight": "model.layers.39.self_attn.q_proj.weight",
|
| 379 |
+
"decoderLayer.39.multiHeadAttention.k.weight": "model.layers.39.self_attn.k_proj.weight",
|
| 380 |
+
"decoderLayer.39.multiHeadAttention.v.weight": "model.layers.39.self_attn.v_proj.weight",
|
| 381 |
+
"decoderLayer.39.multiHeadAttention.o.weight": "model.layers.39.self_attn.o_proj.weight",
|
| 382 |
+
"decoderLayer.39.attnLayerNorm.weight": "model.layers.39.ln1.weight",
|
| 383 |
+
"decoderLayer.39.feedForward.intermediateDense.weight": "model.layers.39.mlp.gate_proj.weight",
|
| 384 |
+
"decoderLayer.39.feedForward.outputDense.weight": "model.layers.39.mlp.down_proj.weight",
|
| 385 |
+
"decoderLayer.39.ffnLayerNorm.weight": "model.layers.39.ln2.weight",
|
| 386 |
+
"decoderLayer.39.feedForward.intermediateDense2.weight": "model.layers.39.mlp.up_proj.weight",
|
| 387 |
+
"decoderLayer.40.multiHeadAttention.q.weight": "model.layers.40.self_attn.q_proj.weight",
|
| 388 |
+
"decoderLayer.40.multiHeadAttention.k.weight": "model.layers.40.self_attn.k_proj.weight",
|
| 389 |
+
"decoderLayer.40.multiHeadAttention.v.weight": "model.layers.40.self_attn.v_proj.weight",
|
| 390 |
+
"decoderLayer.40.multiHeadAttention.o.weight": "model.layers.40.self_attn.o_proj.weight",
|
| 391 |
+
"decoderLayer.40.attnLayerNorm.weight": "model.layers.40.ln1.weight",
|
| 392 |
+
"decoderLayer.40.feedForward.intermediateDense.weight": "model.layers.40.mlp.gate_proj.weight",
|
| 393 |
+
"decoderLayer.40.feedForward.outputDense.weight": "model.layers.40.mlp.down_proj.weight",
|
| 394 |
+
"decoderLayer.40.ffnLayerNorm.weight": "model.layers.40.ln2.weight",
|
| 395 |
+
"decoderLayer.40.feedForward.intermediateDense2.weight": "model.layers.40.mlp.up_proj.weight",
|
| 396 |
+
"decoderLayer.41.multiHeadAttention.q.weight": "model.layers.41.self_attn.q_proj.weight",
|
| 397 |
+
"decoderLayer.41.multiHeadAttention.k.weight": "model.layers.41.self_attn.k_proj.weight",
|
| 398 |
+
"decoderLayer.41.multiHeadAttention.v.weight": "model.layers.41.self_attn.v_proj.weight",
|
| 399 |
+
"decoderLayer.41.multiHeadAttention.o.weight": "model.layers.41.self_attn.o_proj.weight",
|
| 400 |
+
"decoderLayer.41.attnLayerNorm.weight": "model.layers.41.ln1.weight",
|
| 401 |
+
"decoderLayer.41.feedForward.intermediateDense.weight": "model.layers.41.mlp.gate_proj.weight",
|
| 402 |
+
"decoderLayer.41.feedForward.outputDense.weight": "model.layers.41.mlp.down_proj.weight",
|
| 403 |
+
"decoderLayer.41.ffnLayerNorm.weight": "model.layers.41.ln2.weight",
|
| 404 |
+
"decoderLayer.41.feedForward.intermediateDense2.weight": "model.layers.41.mlp.up_proj.weight",
|
| 405 |
+
"decoderLayer.42.multiHeadAttention.q.weight": "model.layers.42.self_attn.q_proj.weight",
|
| 406 |
+
"decoderLayer.42.multiHeadAttention.k.weight": "model.layers.42.self_attn.k_proj.weight",
|
| 407 |
+
"decoderLayer.42.multiHeadAttention.v.weight": "model.layers.42.self_attn.v_proj.weight",
|
| 408 |
+
"decoderLayer.42.multiHeadAttention.o.weight": "model.layers.42.self_attn.o_proj.weight",
|
| 409 |
+
"decoderLayer.42.attnLayerNorm.weight": "model.layers.42.ln1.weight",
|
| 410 |
+
"decoderLayer.42.feedForward.intermediateDense.weight": "model.layers.42.mlp.gate_proj.weight",
|
| 411 |
+
"decoderLayer.42.feedForward.outputDense.weight": "model.layers.42.mlp.down_proj.weight",
|
| 412 |
+
"decoderLayer.42.ffnLayerNorm.weight": "model.layers.42.ln2.weight",
|
| 413 |
+
"decoderLayer.42.feedForward.intermediateDense2.weight": "model.layers.42.mlp.up_proj.weight",
|
| 414 |
+
"decoderLayer.43.multiHeadAttention.q.weight": "model.layers.43.self_attn.q_proj.weight",
|
| 415 |
+
"decoderLayer.43.multiHeadAttention.k.weight": "model.layers.43.self_attn.k_proj.weight",
|
| 416 |
+
"decoderLayer.43.multiHeadAttention.v.weight": "model.layers.43.self_attn.v_proj.weight",
|
| 417 |
+
"decoderLayer.43.multiHeadAttention.o.weight": "model.layers.43.self_attn.o_proj.weight",
|
| 418 |
+
"decoderLayer.43.attnLayerNorm.weight": "model.layers.43.ln1.weight",
|
| 419 |
+
"decoderLayer.43.feedForward.intermediateDense.weight": "model.layers.43.mlp.gate_proj.weight",
|
| 420 |
+
"decoderLayer.43.feedForward.outputDense.weight": "model.layers.43.mlp.down_proj.weight",
|
| 421 |
+
"decoderLayer.43.ffnLayerNorm.weight": "model.layers.43.ln2.weight",
|
| 422 |
+
"decoderLayer.43.feedForward.intermediateDense2.weight": "model.layers.43.mlp.up_proj.weight",
|
| 423 |
+
"decoderLayer.44.multiHeadAttention.q.weight": "model.layers.44.self_attn.q_proj.weight",
|
| 424 |
+
"decoderLayer.44.multiHeadAttention.k.weight": "model.layers.44.self_attn.k_proj.weight",
|
| 425 |
+
"decoderLayer.44.multiHeadAttention.v.weight": "model.layers.44.self_attn.v_proj.weight",
|
| 426 |
+
"decoderLayer.44.multiHeadAttention.o.weight": "model.layers.44.self_attn.o_proj.weight",
|
| 427 |
+
"decoderLayer.44.attnLayerNorm.weight": "model.layers.44.ln1.weight",
|
| 428 |
+
"decoderLayer.44.feedForward.intermediateDense.weight": "model.layers.44.mlp.gate_proj.weight",
|
| 429 |
+
"decoderLayer.44.feedForward.outputDense.weight": "model.layers.44.mlp.down_proj.weight",
|
| 430 |
+
"decoderLayer.44.ffnLayerNorm.weight": "model.layers.44.ln2.weight",
|
| 431 |
+
"decoderLayer.44.feedForward.intermediateDense2.weight": "model.layers.44.mlp.up_proj.weight",
|
| 432 |
+
"decoderLayer.45.multiHeadAttention.q.weight": "model.layers.45.self_attn.q_proj.weight",
|
| 433 |
+
"decoderLayer.45.multiHeadAttention.k.weight": "model.layers.45.self_attn.k_proj.weight",
|
| 434 |
+
"decoderLayer.45.multiHeadAttention.v.weight": "model.layers.45.self_attn.v_proj.weight",
|
| 435 |
+
"decoderLayer.45.multiHeadAttention.o.weight": "model.layers.45.self_attn.o_proj.weight",
|
| 436 |
+
"decoderLayer.45.attnLayerNorm.weight": "model.layers.45.ln1.weight",
|
| 437 |
+
"decoderLayer.45.feedForward.intermediateDense.weight": "model.layers.45.mlp.gate_proj.weight",
|
| 438 |
+
"decoderLayer.45.feedForward.outputDense.weight": "model.layers.45.mlp.down_proj.weight",
|
| 439 |
+
"decoderLayer.45.ffnLayerNorm.weight": "model.layers.45.ln2.weight",
|
| 440 |
+
"decoderLayer.45.feedForward.intermediateDense2.weight": "model.layers.45.mlp.up_proj.weight",
|
| 441 |
+
"decoderLayer.46.multiHeadAttention.q.weight": "model.layers.46.self_attn.q_proj.weight",
|
| 442 |
+
"decoderLayer.46.multiHeadAttention.k.weight": "model.layers.46.self_attn.k_proj.weight",
|
| 443 |
+
"decoderLayer.46.multiHeadAttention.v.weight": "model.layers.46.self_attn.v_proj.weight",
|
| 444 |
+
"decoderLayer.46.multiHeadAttention.o.weight": "model.layers.46.self_attn.o_proj.weight",
|
| 445 |
+
"decoderLayer.46.attnLayerNorm.weight": "model.layers.46.ln1.weight",
|
| 446 |
+
"decoderLayer.46.feedForward.intermediateDense.weight": "model.layers.46.mlp.gate_proj.weight",
|
| 447 |
+
"decoderLayer.46.feedForward.outputDense.weight": "model.layers.46.mlp.down_proj.weight",
|
| 448 |
+
"decoderLayer.46.ffnLayerNorm.weight": "model.layers.46.ln2.weight",
|
| 449 |
+
"decoderLayer.46.feedForward.intermediateDense2.weight": "model.layers.46.mlp.up_proj.weight",
|
| 450 |
+
"decoderLayer.47.multiHeadAttention.q.weight": "model.layers.47.self_attn.q_proj.weight",
|
| 451 |
+
"decoderLayer.47.multiHeadAttention.k.weight": "model.layers.47.self_attn.k_proj.weight",
|
| 452 |
+
"decoderLayer.47.multiHeadAttention.v.weight": "model.layers.47.self_attn.v_proj.weight",
|
| 453 |
+
"decoderLayer.47.multiHeadAttention.o.weight": "model.layers.47.self_attn.o_proj.weight",
|
| 454 |
+
"decoderLayer.47.attnLayerNorm.weight": "model.layers.47.ln1.weight",
|
| 455 |
+
"decoderLayer.47.feedForward.intermediateDense.weight": "model.layers.47.mlp.gate_proj.weight",
|
| 456 |
+
"decoderLayer.47.feedForward.outputDense.weight": "model.layers.47.mlp.down_proj.weight",
|
| 457 |
+
"decoderLayer.47.ffnLayerNorm.weight": "model.layers.47.ln2.weight",
|
| 458 |
+
"decoderLayer.47.feedForward.intermediateDense2.weight": "model.layers.47.mlp.up_proj.weight"
|
| 459 |
+
}
|
| 460 |
+
}
|
Yi-1.5-9B/bert4torch_config.json
ADDED
|
@@ -0,0 +1,460 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 1,
|
| 3 |
+
"eos_token_id": 2,
|
| 4 |
+
"hidden_act": "silu",
|
| 5 |
+
"hidden_size": 4096,
|
| 6 |
+
"initializer_range": 0.02,
|
| 7 |
+
"intermediate_size": 11008,
|
| 8 |
+
"max_position_embeddings": 4096,
|
| 9 |
+
"model": "llama",
|
| 10 |
+
"num_attention_heads": 32,
|
| 11 |
+
"num_hidden_layers": 48,
|
| 12 |
+
"num_key_value_heads": 4,
|
| 13 |
+
"pad_token_id": 0,
|
| 14 |
+
"layer_norm_eps": 1e-06,
|
| 15 |
+
"rope_theta": 5000000.0,
|
| 16 |
+
"tie_word_embeddings": false,
|
| 17 |
+
"torch_dtype": "bfloat16",
|
| 18 |
+
"vocab_size": 64000,
|
| 19 |
+
"skip_init": true,
|
| 20 |
+
"rope_rank": "updown",
|
| 21 |
+
"segment_vocab_size": 0,
|
| 22 |
+
"generation_config": {"tokenizer_decode_config": {"skip_special_tokens": true}, "max_length": 4096, "eos_token_id": 2},
|
| 23 |
+
"mapping": {
|
| 24 |
+
"embeddings.word_embeddings.weight": "model.embed_tokens.weight",
|
| 25 |
+
"LayerNormFinal.weight": "model.norm.weight",
|
| 26 |
+
"lm_head.weight": "lm_head.weight",
|
| 27 |
+
"decoderLayer.0.multiHeadAttention.q.weight": "model.layers.0.self_attn.q_proj.weight",
|
| 28 |
+
"decoderLayer.0.multiHeadAttention.k.weight": "model.layers.0.self_attn.k_proj.weight",
|
| 29 |
+
"decoderLayer.0.multiHeadAttention.v.weight": "model.layers.0.self_attn.v_proj.weight",
|
| 30 |
+
"decoderLayer.0.multiHeadAttention.o.weight": "model.layers.0.self_attn.o_proj.weight",
|
| 31 |
+
"decoderLayer.0.attnLayerNorm.weight": "model.layers.0.ln1.weight",
|
| 32 |
+
"decoderLayer.0.feedForward.intermediateDense.weight": "model.layers.0.mlp.gate_proj.weight",
|
| 33 |
+
"decoderLayer.0.feedForward.outputDense.weight": "model.layers.0.mlp.down_proj.weight",
|
| 34 |
+
"decoderLayer.0.ffnLayerNorm.weight": "model.layers.0.ln2.weight",
|
| 35 |
+
"decoderLayer.0.feedForward.intermediateDense2.weight": "model.layers.0.mlp.up_proj.weight",
|
| 36 |
+
"decoderLayer.1.multiHeadAttention.q.weight": "model.layers.1.self_attn.q_proj.weight",
|
| 37 |
+
"decoderLayer.1.multiHeadAttention.k.weight": "model.layers.1.self_attn.k_proj.weight",
|
| 38 |
+
"decoderLayer.1.multiHeadAttention.v.weight": "model.layers.1.self_attn.v_proj.weight",
|
| 39 |
+
"decoderLayer.1.multiHeadAttention.o.weight": "model.layers.1.self_attn.o_proj.weight",
|
| 40 |
+
"decoderLayer.1.attnLayerNorm.weight": "model.layers.1.ln1.weight",
|
| 41 |
+
"decoderLayer.1.feedForward.intermediateDense.weight": "model.layers.1.mlp.gate_proj.weight",
|
| 42 |
+
"decoderLayer.1.feedForward.outputDense.weight": "model.layers.1.mlp.down_proj.weight",
|
| 43 |
+
"decoderLayer.1.ffnLayerNorm.weight": "model.layers.1.ln2.weight",
|
| 44 |
+
"decoderLayer.1.feedForward.intermediateDense2.weight": "model.layers.1.mlp.up_proj.weight",
|
| 45 |
+
"decoderLayer.2.multiHeadAttention.q.weight": "model.layers.2.self_attn.q_proj.weight",
|
| 46 |
+
"decoderLayer.2.multiHeadAttention.k.weight": "model.layers.2.self_attn.k_proj.weight",
|
| 47 |
+
"decoderLayer.2.multiHeadAttention.v.weight": "model.layers.2.self_attn.v_proj.weight",
|
| 48 |
+
"decoderLayer.2.multiHeadAttention.o.weight": "model.layers.2.self_attn.o_proj.weight",
|
| 49 |
+
"decoderLayer.2.attnLayerNorm.weight": "model.layers.2.ln1.weight",
|
| 50 |
+
"decoderLayer.2.feedForward.intermediateDense.weight": "model.layers.2.mlp.gate_proj.weight",
|
| 51 |
+
"decoderLayer.2.feedForward.outputDense.weight": "model.layers.2.mlp.down_proj.weight",
|
| 52 |
+
"decoderLayer.2.ffnLayerNorm.weight": "model.layers.2.ln2.weight",
|
| 53 |
+
"decoderLayer.2.feedForward.intermediateDense2.weight": "model.layers.2.mlp.up_proj.weight",
|
| 54 |
+
"decoderLayer.3.multiHeadAttention.q.weight": "model.layers.3.self_attn.q_proj.weight",
|
| 55 |
+
"decoderLayer.3.multiHeadAttention.k.weight": "model.layers.3.self_attn.k_proj.weight",
|
| 56 |
+
"decoderLayer.3.multiHeadAttention.v.weight": "model.layers.3.self_attn.v_proj.weight",
|
| 57 |
+
"decoderLayer.3.multiHeadAttention.o.weight": "model.layers.3.self_attn.o_proj.weight",
|
| 58 |
+
"decoderLayer.3.attnLayerNorm.weight": "model.layers.3.ln1.weight",
|
| 59 |
+
"decoderLayer.3.feedForward.intermediateDense.weight": "model.layers.3.mlp.gate_proj.weight",
|
| 60 |
+
"decoderLayer.3.feedForward.outputDense.weight": "model.layers.3.mlp.down_proj.weight",
|
| 61 |
+
"decoderLayer.3.ffnLayerNorm.weight": "model.layers.3.ln2.weight",
|
| 62 |
+
"decoderLayer.3.feedForward.intermediateDense2.weight": "model.layers.3.mlp.up_proj.weight",
|
| 63 |
+
"decoderLayer.4.multiHeadAttention.q.weight": "model.layers.4.self_attn.q_proj.weight",
|
| 64 |
+
"decoderLayer.4.multiHeadAttention.k.weight": "model.layers.4.self_attn.k_proj.weight",
|
| 65 |
+
"decoderLayer.4.multiHeadAttention.v.weight": "model.layers.4.self_attn.v_proj.weight",
|
| 66 |
+
"decoderLayer.4.multiHeadAttention.o.weight": "model.layers.4.self_attn.o_proj.weight",
|
| 67 |
+
"decoderLayer.4.attnLayerNorm.weight": "model.layers.4.ln1.weight",
|
| 68 |
+
"decoderLayer.4.feedForward.intermediateDense.weight": "model.layers.4.mlp.gate_proj.weight",
|
| 69 |
+
"decoderLayer.4.feedForward.outputDense.weight": "model.layers.4.mlp.down_proj.weight",
|
| 70 |
+
"decoderLayer.4.ffnLayerNorm.weight": "model.layers.4.ln2.weight",
|
| 71 |
+
"decoderLayer.4.feedForward.intermediateDense2.weight": "model.layers.4.mlp.up_proj.weight",
|
| 72 |
+
"decoderLayer.5.multiHeadAttention.q.weight": "model.layers.5.self_attn.q_proj.weight",
|
| 73 |
+
"decoderLayer.5.multiHeadAttention.k.weight": "model.layers.5.self_attn.k_proj.weight",
|
| 74 |
+
"decoderLayer.5.multiHeadAttention.v.weight": "model.layers.5.self_attn.v_proj.weight",
|
| 75 |
+
"decoderLayer.5.multiHeadAttention.o.weight": "model.layers.5.self_attn.o_proj.weight",
|
| 76 |
+
"decoderLayer.5.attnLayerNorm.weight": "model.layers.5.ln1.weight",
|
| 77 |
+
"decoderLayer.5.feedForward.intermediateDense.weight": "model.layers.5.mlp.gate_proj.weight",
|
| 78 |
+
"decoderLayer.5.feedForward.outputDense.weight": "model.layers.5.mlp.down_proj.weight",
|
| 79 |
+
"decoderLayer.5.ffnLayerNorm.weight": "model.layers.5.ln2.weight",
|
| 80 |
+
"decoderLayer.5.feedForward.intermediateDense2.weight": "model.layers.5.mlp.up_proj.weight",
|
| 81 |
+
"decoderLayer.6.multiHeadAttention.q.weight": "model.layers.6.self_attn.q_proj.weight",
|
| 82 |
+
"decoderLayer.6.multiHeadAttention.k.weight": "model.layers.6.self_attn.k_proj.weight",
|
| 83 |
+
"decoderLayer.6.multiHeadAttention.v.weight": "model.layers.6.self_attn.v_proj.weight",
|
| 84 |
+
"decoderLayer.6.multiHeadAttention.o.weight": "model.layers.6.self_attn.o_proj.weight",
|
| 85 |
+
"decoderLayer.6.attnLayerNorm.weight": "model.layers.6.ln1.weight",
|
| 86 |
+
"decoderLayer.6.feedForward.intermediateDense.weight": "model.layers.6.mlp.gate_proj.weight",
|
| 87 |
+
"decoderLayer.6.feedForward.outputDense.weight": "model.layers.6.mlp.down_proj.weight",
|
| 88 |
+
"decoderLayer.6.ffnLayerNorm.weight": "model.layers.6.ln2.weight",
|
| 89 |
+
"decoderLayer.6.feedForward.intermediateDense2.weight": "model.layers.6.mlp.up_proj.weight",
|
| 90 |
+
"decoderLayer.7.multiHeadAttention.q.weight": "model.layers.7.self_attn.q_proj.weight",
|
| 91 |
+
"decoderLayer.7.multiHeadAttention.k.weight": "model.layers.7.self_attn.k_proj.weight",
|
| 92 |
+
"decoderLayer.7.multiHeadAttention.v.weight": "model.layers.7.self_attn.v_proj.weight",
|
| 93 |
+
"decoderLayer.7.multiHeadAttention.o.weight": "model.layers.7.self_attn.o_proj.weight",
|
| 94 |
+
"decoderLayer.7.attnLayerNorm.weight": "model.layers.7.ln1.weight",
|
| 95 |
+
"decoderLayer.7.feedForward.intermediateDense.weight": "model.layers.7.mlp.gate_proj.weight",
|
| 96 |
+
"decoderLayer.7.feedForward.outputDense.weight": "model.layers.7.mlp.down_proj.weight",
|
| 97 |
+
"decoderLayer.7.ffnLayerNorm.weight": "model.layers.7.ln2.weight",
|
| 98 |
+
"decoderLayer.7.feedForward.intermediateDense2.weight": "model.layers.7.mlp.up_proj.weight",
|
| 99 |
+
"decoderLayer.8.multiHeadAttention.q.weight": "model.layers.8.self_attn.q_proj.weight",
|
| 100 |
+
"decoderLayer.8.multiHeadAttention.k.weight": "model.layers.8.self_attn.k_proj.weight",
|
| 101 |
+
"decoderLayer.8.multiHeadAttention.v.weight": "model.layers.8.self_attn.v_proj.weight",
|
| 102 |
+
"decoderLayer.8.multiHeadAttention.o.weight": "model.layers.8.self_attn.o_proj.weight",
|
| 103 |
+
"decoderLayer.8.attnLayerNorm.weight": "model.layers.8.ln1.weight",
|
| 104 |
+
"decoderLayer.8.feedForward.intermediateDense.weight": "model.layers.8.mlp.gate_proj.weight",
|
| 105 |
+
"decoderLayer.8.feedForward.outputDense.weight": "model.layers.8.mlp.down_proj.weight",
|
| 106 |
+
"decoderLayer.8.ffnLayerNorm.weight": "model.layers.8.ln2.weight",
|
| 107 |
+
"decoderLayer.8.feedForward.intermediateDense2.weight": "model.layers.8.mlp.up_proj.weight",
|
| 108 |
+
"decoderLayer.9.multiHeadAttention.q.weight": "model.layers.9.self_attn.q_proj.weight",
|
| 109 |
+
"decoderLayer.9.multiHeadAttention.k.weight": "model.layers.9.self_attn.k_proj.weight",
|
| 110 |
+
"decoderLayer.9.multiHeadAttention.v.weight": "model.layers.9.self_attn.v_proj.weight",
|
| 111 |
+
"decoderLayer.9.multiHeadAttention.o.weight": "model.layers.9.self_attn.o_proj.weight",
|
| 112 |
+
"decoderLayer.9.attnLayerNorm.weight": "model.layers.9.ln1.weight",
|
| 113 |
+
"decoderLayer.9.feedForward.intermediateDense.weight": "model.layers.9.mlp.gate_proj.weight",
|
| 114 |
+
"decoderLayer.9.feedForward.outputDense.weight": "model.layers.9.mlp.down_proj.weight",
|
| 115 |
+
"decoderLayer.9.ffnLayerNorm.weight": "model.layers.9.ln2.weight",
|
| 116 |
+
"decoderLayer.9.feedForward.intermediateDense2.weight": "model.layers.9.mlp.up_proj.weight",
|
| 117 |
+
"decoderLayer.10.multiHeadAttention.q.weight": "model.layers.10.self_attn.q_proj.weight",
|
| 118 |
+
"decoderLayer.10.multiHeadAttention.k.weight": "model.layers.10.self_attn.k_proj.weight",
|
| 119 |
+
"decoderLayer.10.multiHeadAttention.v.weight": "model.layers.10.self_attn.v_proj.weight",
|
| 120 |
+
"decoderLayer.10.multiHeadAttention.o.weight": "model.layers.10.self_attn.o_proj.weight",
|
| 121 |
+
"decoderLayer.10.attnLayerNorm.weight": "model.layers.10.ln1.weight",
|
| 122 |
+
"decoderLayer.10.feedForward.intermediateDense.weight": "model.layers.10.mlp.gate_proj.weight",
|
| 123 |
+
"decoderLayer.10.feedForward.outputDense.weight": "model.layers.10.mlp.down_proj.weight",
|
| 124 |
+
"decoderLayer.10.ffnLayerNorm.weight": "model.layers.10.ln2.weight",
|
| 125 |
+
"decoderLayer.10.feedForward.intermediateDense2.weight": "model.layers.10.mlp.up_proj.weight",
|
| 126 |
+
"decoderLayer.11.multiHeadAttention.q.weight": "model.layers.11.self_attn.q_proj.weight",
|
| 127 |
+
"decoderLayer.11.multiHeadAttention.k.weight": "model.layers.11.self_attn.k_proj.weight",
|
| 128 |
+
"decoderLayer.11.multiHeadAttention.v.weight": "model.layers.11.self_attn.v_proj.weight",
|
| 129 |
+
"decoderLayer.11.multiHeadAttention.o.weight": "model.layers.11.self_attn.o_proj.weight",
|
| 130 |
+
"decoderLayer.11.attnLayerNorm.weight": "model.layers.11.ln1.weight",
|
| 131 |
+
"decoderLayer.11.feedForward.intermediateDense.weight": "model.layers.11.mlp.gate_proj.weight",
|
| 132 |
+
"decoderLayer.11.feedForward.outputDense.weight": "model.layers.11.mlp.down_proj.weight",
|
| 133 |
+
"decoderLayer.11.ffnLayerNorm.weight": "model.layers.11.ln2.weight",
|
| 134 |
+
"decoderLayer.11.feedForward.intermediateDense2.weight": "model.layers.11.mlp.up_proj.weight",
|
| 135 |
+
"decoderLayer.12.multiHeadAttention.q.weight": "model.layers.12.self_attn.q_proj.weight",
|
| 136 |
+
"decoderLayer.12.multiHeadAttention.k.weight": "model.layers.12.self_attn.k_proj.weight",
|
| 137 |
+
"decoderLayer.12.multiHeadAttention.v.weight": "model.layers.12.self_attn.v_proj.weight",
|
| 138 |
+
"decoderLayer.12.multiHeadAttention.o.weight": "model.layers.12.self_attn.o_proj.weight",
|
| 139 |
+
"decoderLayer.12.attnLayerNorm.weight": "model.layers.12.ln1.weight",
|
| 140 |
+
"decoderLayer.12.feedForward.intermediateDense.weight": "model.layers.12.mlp.gate_proj.weight",
|
| 141 |
+
"decoderLayer.12.feedForward.outputDense.weight": "model.layers.12.mlp.down_proj.weight",
|
| 142 |
+
"decoderLayer.12.ffnLayerNorm.weight": "model.layers.12.ln2.weight",
|
| 143 |
+
"decoderLayer.12.feedForward.intermediateDense2.weight": "model.layers.12.mlp.up_proj.weight",
|
| 144 |
+
"decoderLayer.13.multiHeadAttention.q.weight": "model.layers.13.self_attn.q_proj.weight",
|
| 145 |
+
"decoderLayer.13.multiHeadAttention.k.weight": "model.layers.13.self_attn.k_proj.weight",
|
| 146 |
+
"decoderLayer.13.multiHeadAttention.v.weight": "model.layers.13.self_attn.v_proj.weight",
|
| 147 |
+
"decoderLayer.13.multiHeadAttention.o.weight": "model.layers.13.self_attn.o_proj.weight",
|
| 148 |
+
"decoderLayer.13.attnLayerNorm.weight": "model.layers.13.ln1.weight",
|
| 149 |
+
"decoderLayer.13.feedForward.intermediateDense.weight": "model.layers.13.mlp.gate_proj.weight",
|
| 150 |
+
"decoderLayer.13.feedForward.outputDense.weight": "model.layers.13.mlp.down_proj.weight",
|
| 151 |
+
"decoderLayer.13.ffnLayerNorm.weight": "model.layers.13.ln2.weight",
|
| 152 |
+
"decoderLayer.13.feedForward.intermediateDense2.weight": "model.layers.13.mlp.up_proj.weight",
|
| 153 |
+
"decoderLayer.14.multiHeadAttention.q.weight": "model.layers.14.self_attn.q_proj.weight",
|
| 154 |
+
"decoderLayer.14.multiHeadAttention.k.weight": "model.layers.14.self_attn.k_proj.weight",
|
| 155 |
+
"decoderLayer.14.multiHeadAttention.v.weight": "model.layers.14.self_attn.v_proj.weight",
|
| 156 |
+
"decoderLayer.14.multiHeadAttention.o.weight": "model.layers.14.self_attn.o_proj.weight",
|
| 157 |
+
"decoderLayer.14.attnLayerNorm.weight": "model.layers.14.ln1.weight",
|
| 158 |
+
"decoderLayer.14.feedForward.intermediateDense.weight": "model.layers.14.mlp.gate_proj.weight",
|
| 159 |
+
"decoderLayer.14.feedForward.outputDense.weight": "model.layers.14.mlp.down_proj.weight",
|
| 160 |
+
"decoderLayer.14.ffnLayerNorm.weight": "model.layers.14.ln2.weight",
|
| 161 |
+
"decoderLayer.14.feedForward.intermediateDense2.weight": "model.layers.14.mlp.up_proj.weight",
|
| 162 |
+
"decoderLayer.15.multiHeadAttention.q.weight": "model.layers.15.self_attn.q_proj.weight",
|
| 163 |
+
"decoderLayer.15.multiHeadAttention.k.weight": "model.layers.15.self_attn.k_proj.weight",
|
| 164 |
+
"decoderLayer.15.multiHeadAttention.v.weight": "model.layers.15.self_attn.v_proj.weight",
|
| 165 |
+
"decoderLayer.15.multiHeadAttention.o.weight": "model.layers.15.self_attn.o_proj.weight",
|
| 166 |
+
"decoderLayer.15.attnLayerNorm.weight": "model.layers.15.ln1.weight",
|
| 167 |
+
"decoderLayer.15.feedForward.intermediateDense.weight": "model.layers.15.mlp.gate_proj.weight",
|
| 168 |
+
"decoderLayer.15.feedForward.outputDense.weight": "model.layers.15.mlp.down_proj.weight",
|
| 169 |
+
"decoderLayer.15.ffnLayerNorm.weight": "model.layers.15.ln2.weight",
|
| 170 |
+
"decoderLayer.15.feedForward.intermediateDense2.weight": "model.layers.15.mlp.up_proj.weight",
|
| 171 |
+
"decoderLayer.16.multiHeadAttention.q.weight": "model.layers.16.self_attn.q_proj.weight",
|
| 172 |
+
"decoderLayer.16.multiHeadAttention.k.weight": "model.layers.16.self_attn.k_proj.weight",
|
| 173 |
+
"decoderLayer.16.multiHeadAttention.v.weight": "model.layers.16.self_attn.v_proj.weight",
|
| 174 |
+
"decoderLayer.16.multiHeadAttention.o.weight": "model.layers.16.self_attn.o_proj.weight",
|
| 175 |
+
"decoderLayer.16.attnLayerNorm.weight": "model.layers.16.ln1.weight",
|
| 176 |
+
"decoderLayer.16.feedForward.intermediateDense.weight": "model.layers.16.mlp.gate_proj.weight",
|
| 177 |
+
"decoderLayer.16.feedForward.outputDense.weight": "model.layers.16.mlp.down_proj.weight",
|
| 178 |
+
"decoderLayer.16.ffnLayerNorm.weight": "model.layers.16.ln2.weight",
|
| 179 |
+
"decoderLayer.16.feedForward.intermediateDense2.weight": "model.layers.16.mlp.up_proj.weight",
|
| 180 |
+
"decoderLayer.17.multiHeadAttention.q.weight": "model.layers.17.self_attn.q_proj.weight",
|
| 181 |
+
"decoderLayer.17.multiHeadAttention.k.weight": "model.layers.17.self_attn.k_proj.weight",
|
| 182 |
+
"decoderLayer.17.multiHeadAttention.v.weight": "model.layers.17.self_attn.v_proj.weight",
|
| 183 |
+
"decoderLayer.17.multiHeadAttention.o.weight": "model.layers.17.self_attn.o_proj.weight",
|
| 184 |
+
"decoderLayer.17.attnLayerNorm.weight": "model.layers.17.ln1.weight",
|
| 185 |
+
"decoderLayer.17.feedForward.intermediateDense.weight": "model.layers.17.mlp.gate_proj.weight",
|
| 186 |
+
"decoderLayer.17.feedForward.outputDense.weight": "model.layers.17.mlp.down_proj.weight",
|
| 187 |
+
"decoderLayer.17.ffnLayerNorm.weight": "model.layers.17.ln2.weight",
|
| 188 |
+
"decoderLayer.17.feedForward.intermediateDense2.weight": "model.layers.17.mlp.up_proj.weight",
|
| 189 |
+
"decoderLayer.18.multiHeadAttention.q.weight": "model.layers.18.self_attn.q_proj.weight",
|
| 190 |
+
"decoderLayer.18.multiHeadAttention.k.weight": "model.layers.18.self_attn.k_proj.weight",
|
| 191 |
+
"decoderLayer.18.multiHeadAttention.v.weight": "model.layers.18.self_attn.v_proj.weight",
|
| 192 |
+
"decoderLayer.18.multiHeadAttention.o.weight": "model.layers.18.self_attn.o_proj.weight",
|
| 193 |
+
"decoderLayer.18.attnLayerNorm.weight": "model.layers.18.ln1.weight",
|
| 194 |
+
"decoderLayer.18.feedForward.intermediateDense.weight": "model.layers.18.mlp.gate_proj.weight",
|
| 195 |
+
"decoderLayer.18.feedForward.outputDense.weight": "model.layers.18.mlp.down_proj.weight",
|
| 196 |
+
"decoderLayer.18.ffnLayerNorm.weight": "model.layers.18.ln2.weight",
|
| 197 |
+
"decoderLayer.18.feedForward.intermediateDense2.weight": "model.layers.18.mlp.up_proj.weight",
|
| 198 |
+
"decoderLayer.19.multiHeadAttention.q.weight": "model.layers.19.self_attn.q_proj.weight",
|
| 199 |
+
"decoderLayer.19.multiHeadAttention.k.weight": "model.layers.19.self_attn.k_proj.weight",
|
| 200 |
+
"decoderLayer.19.multiHeadAttention.v.weight": "model.layers.19.self_attn.v_proj.weight",
|
| 201 |
+
"decoderLayer.19.multiHeadAttention.o.weight": "model.layers.19.self_attn.o_proj.weight",
|
| 202 |
+
"decoderLayer.19.attnLayerNorm.weight": "model.layers.19.ln1.weight",
|
| 203 |
+
"decoderLayer.19.feedForward.intermediateDense.weight": "model.layers.19.mlp.gate_proj.weight",
|
| 204 |
+
"decoderLayer.19.feedForward.outputDense.weight": "model.layers.19.mlp.down_proj.weight",
|
| 205 |
+
"decoderLayer.19.ffnLayerNorm.weight": "model.layers.19.ln2.weight",
|
| 206 |
+
"decoderLayer.19.feedForward.intermediateDense2.weight": "model.layers.19.mlp.up_proj.weight",
|
| 207 |
+
"decoderLayer.20.multiHeadAttention.q.weight": "model.layers.20.self_attn.q_proj.weight",
|
| 208 |
+
"decoderLayer.20.multiHeadAttention.k.weight": "model.layers.20.self_attn.k_proj.weight",
|
| 209 |
+
"decoderLayer.20.multiHeadAttention.v.weight": "model.layers.20.self_attn.v_proj.weight",
|
| 210 |
+
"decoderLayer.20.multiHeadAttention.o.weight": "model.layers.20.self_attn.o_proj.weight",
|
| 211 |
+
"decoderLayer.20.attnLayerNorm.weight": "model.layers.20.ln1.weight",
|
| 212 |
+
"decoderLayer.20.feedForward.intermediateDense.weight": "model.layers.20.mlp.gate_proj.weight",
|
| 213 |
+
"decoderLayer.20.feedForward.outputDense.weight": "model.layers.20.mlp.down_proj.weight",
|
| 214 |
+
"decoderLayer.20.ffnLayerNorm.weight": "model.layers.20.ln2.weight",
|
| 215 |
+
"decoderLayer.20.feedForward.intermediateDense2.weight": "model.layers.20.mlp.up_proj.weight",
|
| 216 |
+
"decoderLayer.21.multiHeadAttention.q.weight": "model.layers.21.self_attn.q_proj.weight",
|
| 217 |
+
"decoderLayer.21.multiHeadAttention.k.weight": "model.layers.21.self_attn.k_proj.weight",
|
| 218 |
+
"decoderLayer.21.multiHeadAttention.v.weight": "model.layers.21.self_attn.v_proj.weight",
|
| 219 |
+
"decoderLayer.21.multiHeadAttention.o.weight": "model.layers.21.self_attn.o_proj.weight",
|
| 220 |
+
"decoderLayer.21.attnLayerNorm.weight": "model.layers.21.ln1.weight",
|
| 221 |
+
"decoderLayer.21.feedForward.intermediateDense.weight": "model.layers.21.mlp.gate_proj.weight",
|
| 222 |
+
"decoderLayer.21.feedForward.outputDense.weight": "model.layers.21.mlp.down_proj.weight",
|
| 223 |
+
"decoderLayer.21.ffnLayerNorm.weight": "model.layers.21.ln2.weight",
|
| 224 |
+
"decoderLayer.21.feedForward.intermediateDense2.weight": "model.layers.21.mlp.up_proj.weight",
|
| 225 |
+
"decoderLayer.22.multiHeadAttention.q.weight": "model.layers.22.self_attn.q_proj.weight",
|
| 226 |
+
"decoderLayer.22.multiHeadAttention.k.weight": "model.layers.22.self_attn.k_proj.weight",
|
| 227 |
+
"decoderLayer.22.multiHeadAttention.v.weight": "model.layers.22.self_attn.v_proj.weight",
|
| 228 |
+
"decoderLayer.22.multiHeadAttention.o.weight": "model.layers.22.self_attn.o_proj.weight",
|
| 229 |
+
"decoderLayer.22.attnLayerNorm.weight": "model.layers.22.ln1.weight",
|
| 230 |
+
"decoderLayer.22.feedForward.intermediateDense.weight": "model.layers.22.mlp.gate_proj.weight",
|
| 231 |
+
"decoderLayer.22.feedForward.outputDense.weight": "model.layers.22.mlp.down_proj.weight",
|
| 232 |
+
"decoderLayer.22.ffnLayerNorm.weight": "model.layers.22.ln2.weight",
|
| 233 |
+
"decoderLayer.22.feedForward.intermediateDense2.weight": "model.layers.22.mlp.up_proj.weight",
|
| 234 |
+
"decoderLayer.23.multiHeadAttention.q.weight": "model.layers.23.self_attn.q_proj.weight",
|
| 235 |
+
"decoderLayer.23.multiHeadAttention.k.weight": "model.layers.23.self_attn.k_proj.weight",
|
| 236 |
+
"decoderLayer.23.multiHeadAttention.v.weight": "model.layers.23.self_attn.v_proj.weight",
|
| 237 |
+
"decoderLayer.23.multiHeadAttention.o.weight": "model.layers.23.self_attn.o_proj.weight",
|
| 238 |
+
"decoderLayer.23.attnLayerNorm.weight": "model.layers.23.ln1.weight",
|
| 239 |
+
"decoderLayer.23.feedForward.intermediateDense.weight": "model.layers.23.mlp.gate_proj.weight",
|
| 240 |
+
"decoderLayer.23.feedForward.outputDense.weight": "model.layers.23.mlp.down_proj.weight",
|
| 241 |
+
"decoderLayer.23.ffnLayerNorm.weight": "model.layers.23.ln2.weight",
|
| 242 |
+
"decoderLayer.23.feedForward.intermediateDense2.weight": "model.layers.23.mlp.up_proj.weight",
|
| 243 |
+
"decoderLayer.24.multiHeadAttention.q.weight": "model.layers.24.self_attn.q_proj.weight",
|
| 244 |
+
"decoderLayer.24.multiHeadAttention.k.weight": "model.layers.24.self_attn.k_proj.weight",
|
| 245 |
+
"decoderLayer.24.multiHeadAttention.v.weight": "model.layers.24.self_attn.v_proj.weight",
|
| 246 |
+
"decoderLayer.24.multiHeadAttention.o.weight": "model.layers.24.self_attn.o_proj.weight",
|
| 247 |
+
"decoderLayer.24.attnLayerNorm.weight": "model.layers.24.ln1.weight",
|
| 248 |
+
"decoderLayer.24.feedForward.intermediateDense.weight": "model.layers.24.mlp.gate_proj.weight",
|
| 249 |
+
"decoderLayer.24.feedForward.outputDense.weight": "model.layers.24.mlp.down_proj.weight",
|
| 250 |
+
"decoderLayer.24.ffnLayerNorm.weight": "model.layers.24.ln2.weight",
|
| 251 |
+
"decoderLayer.24.feedForward.intermediateDense2.weight": "model.layers.24.mlp.up_proj.weight",
|
| 252 |
+
"decoderLayer.25.multiHeadAttention.q.weight": "model.layers.25.self_attn.q_proj.weight",
|
| 253 |
+
"decoderLayer.25.multiHeadAttention.k.weight": "model.layers.25.self_attn.k_proj.weight",
|
| 254 |
+
"decoderLayer.25.multiHeadAttention.v.weight": "model.layers.25.self_attn.v_proj.weight",
|
| 255 |
+
"decoderLayer.25.multiHeadAttention.o.weight": "model.layers.25.self_attn.o_proj.weight",
|
| 256 |
+
"decoderLayer.25.attnLayerNorm.weight": "model.layers.25.ln1.weight",
|
| 257 |
+
"decoderLayer.25.feedForward.intermediateDense.weight": "model.layers.25.mlp.gate_proj.weight",
|
| 258 |
+
"decoderLayer.25.feedForward.outputDense.weight": "model.layers.25.mlp.down_proj.weight",
|
| 259 |
+
"decoderLayer.25.ffnLayerNorm.weight": "model.layers.25.ln2.weight",
|
| 260 |
+
"decoderLayer.25.feedForward.intermediateDense2.weight": "model.layers.25.mlp.up_proj.weight",
|
| 261 |
+
"decoderLayer.26.multiHeadAttention.q.weight": "model.layers.26.self_attn.q_proj.weight",
|
| 262 |
+
"decoderLayer.26.multiHeadAttention.k.weight": "model.layers.26.self_attn.k_proj.weight",
|
| 263 |
+
"decoderLayer.26.multiHeadAttention.v.weight": "model.layers.26.self_attn.v_proj.weight",
|
| 264 |
+
"decoderLayer.26.multiHeadAttention.o.weight": "model.layers.26.self_attn.o_proj.weight",
|
| 265 |
+
"decoderLayer.26.attnLayerNorm.weight": "model.layers.26.ln1.weight",
|
| 266 |
+
"decoderLayer.26.feedForward.intermediateDense.weight": "model.layers.26.mlp.gate_proj.weight",
|
| 267 |
+
"decoderLayer.26.feedForward.outputDense.weight": "model.layers.26.mlp.down_proj.weight",
|
| 268 |
+
"decoderLayer.26.ffnLayerNorm.weight": "model.layers.26.ln2.weight",
|
| 269 |
+
"decoderLayer.26.feedForward.intermediateDense2.weight": "model.layers.26.mlp.up_proj.weight",
|
| 270 |
+
"decoderLayer.27.multiHeadAttention.q.weight": "model.layers.27.self_attn.q_proj.weight",
|
| 271 |
+
"decoderLayer.27.multiHeadAttention.k.weight": "model.layers.27.self_attn.k_proj.weight",
|
| 272 |
+
"decoderLayer.27.multiHeadAttention.v.weight": "model.layers.27.self_attn.v_proj.weight",
|
| 273 |
+
"decoderLayer.27.multiHeadAttention.o.weight": "model.layers.27.self_attn.o_proj.weight",
|
| 274 |
+
"decoderLayer.27.attnLayerNorm.weight": "model.layers.27.ln1.weight",
|
| 275 |
+
"decoderLayer.27.feedForward.intermediateDense.weight": "model.layers.27.mlp.gate_proj.weight",
|
| 276 |
+
"decoderLayer.27.feedForward.outputDense.weight": "model.layers.27.mlp.down_proj.weight",
|
| 277 |
+
"decoderLayer.27.ffnLayerNorm.weight": "model.layers.27.ln2.weight",
|
| 278 |
+
"decoderLayer.27.feedForward.intermediateDense2.weight": "model.layers.27.mlp.up_proj.weight",
|
| 279 |
+
"decoderLayer.28.multiHeadAttention.q.weight": "model.layers.28.self_attn.q_proj.weight",
|
| 280 |
+
"decoderLayer.28.multiHeadAttention.k.weight": "model.layers.28.self_attn.k_proj.weight",
|
| 281 |
+
"decoderLayer.28.multiHeadAttention.v.weight": "model.layers.28.self_attn.v_proj.weight",
|
| 282 |
+
"decoderLayer.28.multiHeadAttention.o.weight": "model.layers.28.self_attn.o_proj.weight",
|
| 283 |
+
"decoderLayer.28.attnLayerNorm.weight": "model.layers.28.ln1.weight",
|
| 284 |
+
"decoderLayer.28.feedForward.intermediateDense.weight": "model.layers.28.mlp.gate_proj.weight",
|
| 285 |
+
"decoderLayer.28.feedForward.outputDense.weight": "model.layers.28.mlp.down_proj.weight",
|
| 286 |
+
"decoderLayer.28.ffnLayerNorm.weight": "model.layers.28.ln2.weight",
|
| 287 |
+
"decoderLayer.28.feedForward.intermediateDense2.weight": "model.layers.28.mlp.up_proj.weight",
|
| 288 |
+
"decoderLayer.29.multiHeadAttention.q.weight": "model.layers.29.self_attn.q_proj.weight",
|
| 289 |
+
"decoderLayer.29.multiHeadAttention.k.weight": "model.layers.29.self_attn.k_proj.weight",
|
| 290 |
+
"decoderLayer.29.multiHeadAttention.v.weight": "model.layers.29.self_attn.v_proj.weight",
|
| 291 |
+
"decoderLayer.29.multiHeadAttention.o.weight": "model.layers.29.self_attn.o_proj.weight",
|
| 292 |
+
"decoderLayer.29.attnLayerNorm.weight": "model.layers.29.ln1.weight",
|
| 293 |
+
"decoderLayer.29.feedForward.intermediateDense.weight": "model.layers.29.mlp.gate_proj.weight",
|
| 294 |
+
"decoderLayer.29.feedForward.outputDense.weight": "model.layers.29.mlp.down_proj.weight",
|
| 295 |
+
"decoderLayer.29.ffnLayerNorm.weight": "model.layers.29.ln2.weight",
|
| 296 |
+
"decoderLayer.29.feedForward.intermediateDense2.weight": "model.layers.29.mlp.up_proj.weight",
|
| 297 |
+
"decoderLayer.30.multiHeadAttention.q.weight": "model.layers.30.self_attn.q_proj.weight",
|
| 298 |
+
"decoderLayer.30.multiHeadAttention.k.weight": "model.layers.30.self_attn.k_proj.weight",
|
| 299 |
+
"decoderLayer.30.multiHeadAttention.v.weight": "model.layers.30.self_attn.v_proj.weight",
|
| 300 |
+
"decoderLayer.30.multiHeadAttention.o.weight": "model.layers.30.self_attn.o_proj.weight",
|
| 301 |
+
"decoderLayer.30.attnLayerNorm.weight": "model.layers.30.ln1.weight",
|
| 302 |
+
"decoderLayer.30.feedForward.intermediateDense.weight": "model.layers.30.mlp.gate_proj.weight",
|
| 303 |
+
"decoderLayer.30.feedForward.outputDense.weight": "model.layers.30.mlp.down_proj.weight",
|
| 304 |
+
"decoderLayer.30.ffnLayerNorm.weight": "model.layers.30.ln2.weight",
|
| 305 |
+
"decoderLayer.30.feedForward.intermediateDense2.weight": "model.layers.30.mlp.up_proj.weight",
|
| 306 |
+
"decoderLayer.31.multiHeadAttention.q.weight": "model.layers.31.self_attn.q_proj.weight",
|
| 307 |
+
"decoderLayer.31.multiHeadAttention.k.weight": "model.layers.31.self_attn.k_proj.weight",
|
| 308 |
+
"decoderLayer.31.multiHeadAttention.v.weight": "model.layers.31.self_attn.v_proj.weight",
|
| 309 |
+
"decoderLayer.31.multiHeadAttention.o.weight": "model.layers.31.self_attn.o_proj.weight",
|
| 310 |
+
"decoderLayer.31.attnLayerNorm.weight": "model.layers.31.ln1.weight",
|
| 311 |
+
"decoderLayer.31.feedForward.intermediateDense.weight": "model.layers.31.mlp.gate_proj.weight",
|
| 312 |
+
"decoderLayer.31.feedForward.outputDense.weight": "model.layers.31.mlp.down_proj.weight",
|
| 313 |
+
"decoderLayer.31.ffnLayerNorm.weight": "model.layers.31.ln2.weight",
|
| 314 |
+
"decoderLayer.31.feedForward.intermediateDense2.weight": "model.layers.31.mlp.up_proj.weight",
|
| 315 |
+
"decoderLayer.32.multiHeadAttention.q.weight": "model.layers.32.self_attn.q_proj.weight",
|
| 316 |
+
"decoderLayer.32.multiHeadAttention.k.weight": "model.layers.32.self_attn.k_proj.weight",
|
| 317 |
+
"decoderLayer.32.multiHeadAttention.v.weight": "model.layers.32.self_attn.v_proj.weight",
|
| 318 |
+
"decoderLayer.32.multiHeadAttention.o.weight": "model.layers.32.self_attn.o_proj.weight",
|
| 319 |
+
"decoderLayer.32.attnLayerNorm.weight": "model.layers.32.ln1.weight",
|
| 320 |
+
"decoderLayer.32.feedForward.intermediateDense.weight": "model.layers.32.mlp.gate_proj.weight",
|
| 321 |
+
"decoderLayer.32.feedForward.outputDense.weight": "model.layers.32.mlp.down_proj.weight",
|
| 322 |
+
"decoderLayer.32.ffnLayerNorm.weight": "model.layers.32.ln2.weight",
|
| 323 |
+
"decoderLayer.32.feedForward.intermediateDense2.weight": "model.layers.32.mlp.up_proj.weight",
|
| 324 |
+
"decoderLayer.33.multiHeadAttention.q.weight": "model.layers.33.self_attn.q_proj.weight",
|
| 325 |
+
"decoderLayer.33.multiHeadAttention.k.weight": "model.layers.33.self_attn.k_proj.weight",
|
| 326 |
+
"decoderLayer.33.multiHeadAttention.v.weight": "model.layers.33.self_attn.v_proj.weight",
|
| 327 |
+
"decoderLayer.33.multiHeadAttention.o.weight": "model.layers.33.self_attn.o_proj.weight",
|
| 328 |
+
"decoderLayer.33.attnLayerNorm.weight": "model.layers.33.ln1.weight",
|
| 329 |
+
"decoderLayer.33.feedForward.intermediateDense.weight": "model.layers.33.mlp.gate_proj.weight",
|
| 330 |
+
"decoderLayer.33.feedForward.outputDense.weight": "model.layers.33.mlp.down_proj.weight",
|
| 331 |
+
"decoderLayer.33.ffnLayerNorm.weight": "model.layers.33.ln2.weight",
|
| 332 |
+
"decoderLayer.33.feedForward.intermediateDense2.weight": "model.layers.33.mlp.up_proj.weight",
|
| 333 |
+
"decoderLayer.34.multiHeadAttention.q.weight": "model.layers.34.self_attn.q_proj.weight",
|
| 334 |
+
"decoderLayer.34.multiHeadAttention.k.weight": "model.layers.34.self_attn.k_proj.weight",
|
| 335 |
+
"decoderLayer.34.multiHeadAttention.v.weight": "model.layers.34.self_attn.v_proj.weight",
|
| 336 |
+
"decoderLayer.34.multiHeadAttention.o.weight": "model.layers.34.self_attn.o_proj.weight",
|
| 337 |
+
"decoderLayer.34.attnLayerNorm.weight": "model.layers.34.ln1.weight",
|
| 338 |
+
"decoderLayer.34.feedForward.intermediateDense.weight": "model.layers.34.mlp.gate_proj.weight",
|
| 339 |
+
"decoderLayer.34.feedForward.outputDense.weight": "model.layers.34.mlp.down_proj.weight",
|
| 340 |
+
"decoderLayer.34.ffnLayerNorm.weight": "model.layers.34.ln2.weight",
|
| 341 |
+
"decoderLayer.34.feedForward.intermediateDense2.weight": "model.layers.34.mlp.up_proj.weight",
|
| 342 |
+
"decoderLayer.35.multiHeadAttention.q.weight": "model.layers.35.self_attn.q_proj.weight",
|
| 343 |
+
"decoderLayer.35.multiHeadAttention.k.weight": "model.layers.35.self_attn.k_proj.weight",
|
| 344 |
+
"decoderLayer.35.multiHeadAttention.v.weight": "model.layers.35.self_attn.v_proj.weight",
|
| 345 |
+
"decoderLayer.35.multiHeadAttention.o.weight": "model.layers.35.self_attn.o_proj.weight",
|
| 346 |
+
"decoderLayer.35.attnLayerNorm.weight": "model.layers.35.ln1.weight",
|
| 347 |
+
"decoderLayer.35.feedForward.intermediateDense.weight": "model.layers.35.mlp.gate_proj.weight",
|
| 348 |
+
"decoderLayer.35.feedForward.outputDense.weight": "model.layers.35.mlp.down_proj.weight",
|
| 349 |
+
"decoderLayer.35.ffnLayerNorm.weight": "model.layers.35.ln2.weight",
|
| 350 |
+
"decoderLayer.35.feedForward.intermediateDense2.weight": "model.layers.35.mlp.up_proj.weight",
|
| 351 |
+
"decoderLayer.36.multiHeadAttention.q.weight": "model.layers.36.self_attn.q_proj.weight",
|
| 352 |
+
"decoderLayer.36.multiHeadAttention.k.weight": "model.layers.36.self_attn.k_proj.weight",
|
| 353 |
+
"decoderLayer.36.multiHeadAttention.v.weight": "model.layers.36.self_attn.v_proj.weight",
|
| 354 |
+
"decoderLayer.36.multiHeadAttention.o.weight": "model.layers.36.self_attn.o_proj.weight",
|
| 355 |
+
"decoderLayer.36.attnLayerNorm.weight": "model.layers.36.ln1.weight",
|
| 356 |
+
"decoderLayer.36.feedForward.intermediateDense.weight": "model.layers.36.mlp.gate_proj.weight",
|
| 357 |
+
"decoderLayer.36.feedForward.outputDense.weight": "model.layers.36.mlp.down_proj.weight",
|
| 358 |
+
"decoderLayer.36.ffnLayerNorm.weight": "model.layers.36.ln2.weight",
|
| 359 |
+
"decoderLayer.36.feedForward.intermediateDense2.weight": "model.layers.36.mlp.up_proj.weight",
|
| 360 |
+
"decoderLayer.37.multiHeadAttention.q.weight": "model.layers.37.self_attn.q_proj.weight",
|
| 361 |
+
"decoderLayer.37.multiHeadAttention.k.weight": "model.layers.37.self_attn.k_proj.weight",
|
| 362 |
+
"decoderLayer.37.multiHeadAttention.v.weight": "model.layers.37.self_attn.v_proj.weight",
|
| 363 |
+
"decoderLayer.37.multiHeadAttention.o.weight": "model.layers.37.self_attn.o_proj.weight",
|
| 364 |
+
"decoderLayer.37.attnLayerNorm.weight": "model.layers.37.ln1.weight",
|
| 365 |
+
"decoderLayer.37.feedForward.intermediateDense.weight": "model.layers.37.mlp.gate_proj.weight",
|
| 366 |
+
"decoderLayer.37.feedForward.outputDense.weight": "model.layers.37.mlp.down_proj.weight",
|
| 367 |
+
"decoderLayer.37.ffnLayerNorm.weight": "model.layers.37.ln2.weight",
|
| 368 |
+
"decoderLayer.37.feedForward.intermediateDense2.weight": "model.layers.37.mlp.up_proj.weight",
|
| 369 |
+
"decoderLayer.38.multiHeadAttention.q.weight": "model.layers.38.self_attn.q_proj.weight",
|
| 370 |
+
"decoderLayer.38.multiHeadAttention.k.weight": "model.layers.38.self_attn.k_proj.weight",
|
| 371 |
+
"decoderLayer.38.multiHeadAttention.v.weight": "model.layers.38.self_attn.v_proj.weight",
|
| 372 |
+
"decoderLayer.38.multiHeadAttention.o.weight": "model.layers.38.self_attn.o_proj.weight",
|
| 373 |
+
"decoderLayer.38.attnLayerNorm.weight": "model.layers.38.ln1.weight",
|
| 374 |
+
"decoderLayer.38.feedForward.intermediateDense.weight": "model.layers.38.mlp.gate_proj.weight",
|
| 375 |
+
"decoderLayer.38.feedForward.outputDense.weight": "model.layers.38.mlp.down_proj.weight",
|
| 376 |
+
"decoderLayer.38.ffnLayerNorm.weight": "model.layers.38.ln2.weight",
|
| 377 |
+
"decoderLayer.38.feedForward.intermediateDense2.weight": "model.layers.38.mlp.up_proj.weight",
|
| 378 |
+
"decoderLayer.39.multiHeadAttention.q.weight": "model.layers.39.self_attn.q_proj.weight",
|
| 379 |
+
"decoderLayer.39.multiHeadAttention.k.weight": "model.layers.39.self_attn.k_proj.weight",
|
| 380 |
+
"decoderLayer.39.multiHeadAttention.v.weight": "model.layers.39.self_attn.v_proj.weight",
|
| 381 |
+
"decoderLayer.39.multiHeadAttention.o.weight": "model.layers.39.self_attn.o_proj.weight",
|
| 382 |
+
"decoderLayer.39.attnLayerNorm.weight": "model.layers.39.ln1.weight",
|
| 383 |
+
"decoderLayer.39.feedForward.intermediateDense.weight": "model.layers.39.mlp.gate_proj.weight",
|
| 384 |
+
"decoderLayer.39.feedForward.outputDense.weight": "model.layers.39.mlp.down_proj.weight",
|
| 385 |
+
"decoderLayer.39.ffnLayerNorm.weight": "model.layers.39.ln2.weight",
|
| 386 |
+
"decoderLayer.39.feedForward.intermediateDense2.weight": "model.layers.39.mlp.up_proj.weight",
|
| 387 |
+
"decoderLayer.40.multiHeadAttention.q.weight": "model.layers.40.self_attn.q_proj.weight",
|
| 388 |
+
"decoderLayer.40.multiHeadAttention.k.weight": "model.layers.40.self_attn.k_proj.weight",
|
| 389 |
+
"decoderLayer.40.multiHeadAttention.v.weight": "model.layers.40.self_attn.v_proj.weight",
|
| 390 |
+
"decoderLayer.40.multiHeadAttention.o.weight": "model.layers.40.self_attn.o_proj.weight",
|
| 391 |
+
"decoderLayer.40.attnLayerNorm.weight": "model.layers.40.ln1.weight",
|
| 392 |
+
"decoderLayer.40.feedForward.intermediateDense.weight": "model.layers.40.mlp.gate_proj.weight",
|
| 393 |
+
"decoderLayer.40.feedForward.outputDense.weight": "model.layers.40.mlp.down_proj.weight",
|
| 394 |
+
"decoderLayer.40.ffnLayerNorm.weight": "model.layers.40.ln2.weight",
|
| 395 |
+
"decoderLayer.40.feedForward.intermediateDense2.weight": "model.layers.40.mlp.up_proj.weight",
|
| 396 |
+
"decoderLayer.41.multiHeadAttention.q.weight": "model.layers.41.self_attn.q_proj.weight",
|
| 397 |
+
"decoderLayer.41.multiHeadAttention.k.weight": "model.layers.41.self_attn.k_proj.weight",
|
| 398 |
+
"decoderLayer.41.multiHeadAttention.v.weight": "model.layers.41.self_attn.v_proj.weight",
|
| 399 |
+
"decoderLayer.41.multiHeadAttention.o.weight": "model.layers.41.self_attn.o_proj.weight",
|
| 400 |
+
"decoderLayer.41.attnLayerNorm.weight": "model.layers.41.ln1.weight",
|
| 401 |
+
"decoderLayer.41.feedForward.intermediateDense.weight": "model.layers.41.mlp.gate_proj.weight",
|
| 402 |
+
"decoderLayer.41.feedForward.outputDense.weight": "model.layers.41.mlp.down_proj.weight",
|
| 403 |
+
"decoderLayer.41.ffnLayerNorm.weight": "model.layers.41.ln2.weight",
|
| 404 |
+
"decoderLayer.41.feedForward.intermediateDense2.weight": "model.layers.41.mlp.up_proj.weight",
|
| 405 |
+
"decoderLayer.42.multiHeadAttention.q.weight": "model.layers.42.self_attn.q_proj.weight",
|
| 406 |
+
"decoderLayer.42.multiHeadAttention.k.weight": "model.layers.42.self_attn.k_proj.weight",
|
| 407 |
+
"decoderLayer.42.multiHeadAttention.v.weight": "model.layers.42.self_attn.v_proj.weight",
|
| 408 |
+
"decoderLayer.42.multiHeadAttention.o.weight": "model.layers.42.self_attn.o_proj.weight",
|
| 409 |
+
"decoderLayer.42.attnLayerNorm.weight": "model.layers.42.ln1.weight",
|
| 410 |
+
"decoderLayer.42.feedForward.intermediateDense.weight": "model.layers.42.mlp.gate_proj.weight",
|
| 411 |
+
"decoderLayer.42.feedForward.outputDense.weight": "model.layers.42.mlp.down_proj.weight",
|
| 412 |
+
"decoderLayer.42.ffnLayerNorm.weight": "model.layers.42.ln2.weight",
|
| 413 |
+
"decoderLayer.42.feedForward.intermediateDense2.weight": "model.layers.42.mlp.up_proj.weight",
|
| 414 |
+
"decoderLayer.43.multiHeadAttention.q.weight": "model.layers.43.self_attn.q_proj.weight",
|
| 415 |
+
"decoderLayer.43.multiHeadAttention.k.weight": "model.layers.43.self_attn.k_proj.weight",
|
| 416 |
+
"decoderLayer.43.multiHeadAttention.v.weight": "model.layers.43.self_attn.v_proj.weight",
|
| 417 |
+
"decoderLayer.43.multiHeadAttention.o.weight": "model.layers.43.self_attn.o_proj.weight",
|
| 418 |
+
"decoderLayer.43.attnLayerNorm.weight": "model.layers.43.ln1.weight",
|
| 419 |
+
"decoderLayer.43.feedForward.intermediateDense.weight": "model.layers.43.mlp.gate_proj.weight",
|
| 420 |
+
"decoderLayer.43.feedForward.outputDense.weight": "model.layers.43.mlp.down_proj.weight",
|
| 421 |
+
"decoderLayer.43.ffnLayerNorm.weight": "model.layers.43.ln2.weight",
|
| 422 |
+
"decoderLayer.43.feedForward.intermediateDense2.weight": "model.layers.43.mlp.up_proj.weight",
|
| 423 |
+
"decoderLayer.44.multiHeadAttention.q.weight": "model.layers.44.self_attn.q_proj.weight",
|
| 424 |
+
"decoderLayer.44.multiHeadAttention.k.weight": "model.layers.44.self_attn.k_proj.weight",
|
| 425 |
+
"decoderLayer.44.multiHeadAttention.v.weight": "model.layers.44.self_attn.v_proj.weight",
|
| 426 |
+
"decoderLayer.44.multiHeadAttention.o.weight": "model.layers.44.self_attn.o_proj.weight",
|
| 427 |
+
"decoderLayer.44.attnLayerNorm.weight": "model.layers.44.ln1.weight",
|
| 428 |
+
"decoderLayer.44.feedForward.intermediateDense.weight": "model.layers.44.mlp.gate_proj.weight",
|
| 429 |
+
"decoderLayer.44.feedForward.outputDense.weight": "model.layers.44.mlp.down_proj.weight",
|
| 430 |
+
"decoderLayer.44.ffnLayerNorm.weight": "model.layers.44.ln2.weight",
|
| 431 |
+
"decoderLayer.44.feedForward.intermediateDense2.weight": "model.layers.44.mlp.up_proj.weight",
|
| 432 |
+
"decoderLayer.45.multiHeadAttention.q.weight": "model.layers.45.self_attn.q_proj.weight",
|
| 433 |
+
"decoderLayer.45.multiHeadAttention.k.weight": "model.layers.45.self_attn.k_proj.weight",
|
| 434 |
+
"decoderLayer.45.multiHeadAttention.v.weight": "model.layers.45.self_attn.v_proj.weight",
|
| 435 |
+
"decoderLayer.45.multiHeadAttention.o.weight": "model.layers.45.self_attn.o_proj.weight",
|
| 436 |
+
"decoderLayer.45.attnLayerNorm.weight": "model.layers.45.ln1.weight",
|
| 437 |
+
"decoderLayer.45.feedForward.intermediateDense.weight": "model.layers.45.mlp.gate_proj.weight",
|
| 438 |
+
"decoderLayer.45.feedForward.outputDense.weight": "model.layers.45.mlp.down_proj.weight",
|
| 439 |
+
"decoderLayer.45.ffnLayerNorm.weight": "model.layers.45.ln2.weight",
|
| 440 |
+
"decoderLayer.45.feedForward.intermediateDense2.weight": "model.layers.45.mlp.up_proj.weight",
|
| 441 |
+
"decoderLayer.46.multiHeadAttention.q.weight": "model.layers.46.self_attn.q_proj.weight",
|
| 442 |
+
"decoderLayer.46.multiHeadAttention.k.weight": "model.layers.46.self_attn.k_proj.weight",
|
| 443 |
+
"decoderLayer.46.multiHeadAttention.v.weight": "model.layers.46.self_attn.v_proj.weight",
|
| 444 |
+
"decoderLayer.46.multiHeadAttention.o.weight": "model.layers.46.self_attn.o_proj.weight",
|
| 445 |
+
"decoderLayer.46.attnLayerNorm.weight": "model.layers.46.ln1.weight",
|
| 446 |
+
"decoderLayer.46.feedForward.intermediateDense.weight": "model.layers.46.mlp.gate_proj.weight",
|
| 447 |
+
"decoderLayer.46.feedForward.outputDense.weight": "model.layers.46.mlp.down_proj.weight",
|
| 448 |
+
"decoderLayer.46.ffnLayerNorm.weight": "model.layers.46.ln2.weight",
|
| 449 |
+
"decoderLayer.46.feedForward.intermediateDense2.weight": "model.layers.46.mlp.up_proj.weight",
|
| 450 |
+
"decoderLayer.47.multiHeadAttention.q.weight": "model.layers.47.self_attn.q_proj.weight",
|
| 451 |
+
"decoderLayer.47.multiHeadAttention.k.weight": "model.layers.47.self_attn.k_proj.weight",
|
| 452 |
+
"decoderLayer.47.multiHeadAttention.v.weight": "model.layers.47.self_attn.v_proj.weight",
|
| 453 |
+
"decoderLayer.47.multiHeadAttention.o.weight": "model.layers.47.self_attn.o_proj.weight",
|
| 454 |
+
"decoderLayer.47.attnLayerNorm.weight": "model.layers.47.ln1.weight",
|
| 455 |
+
"decoderLayer.47.feedForward.intermediateDense.weight": "model.layers.47.mlp.gate_proj.weight",
|
| 456 |
+
"decoderLayer.47.feedForward.outputDense.weight": "model.layers.47.mlp.down_proj.weight",
|
| 457 |
+
"decoderLayer.47.ffnLayerNorm.weight": "model.layers.47.ln2.weight",
|
| 458 |
+
"decoderLayer.47.feedForward.intermediateDense2.weight": "model.layers.47.mlp.up_proj.weight"
|
| 459 |
+
}
|
| 460 |
+
}
|