Add files using upload-large-folder tool
Browse filesThis view is limited to 50 files because it contains too many changes. See raw diff
- .gitattributes +1 -0
- config.json +574 -0
- generation_config.json +8 -0
- model-00002-of-00071.safetensors +3 -0
- model-00005-of-00071.safetensors +3 -0
- model-00006-of-00071.safetensors +3 -0
- model-00007-of-00071.safetensors +3 -0
- model-00008-of-00071.safetensors +3 -0
- model-00009-of-00071.safetensors +3 -0
- model-00010-of-00071.safetensors +3 -0
- model-00011-of-00071.safetensors +3 -0
- model-00012-of-00071.safetensors +3 -0
- model-00013-of-00071.safetensors +3 -0
- model-00015-of-00071.safetensors +3 -0
- model-00017-of-00071.safetensors +3 -0
- model-00019-of-00071.safetensors +3 -0
- model-00021-of-00071.safetensors +3 -0
- model-00022-of-00071.safetensors +3 -0
- model-00023-of-00071.safetensors +3 -0
- model-00024-of-00071.safetensors +3 -0
- model-00029-of-00071.safetensors +3 -0
- model-00030-of-00071.safetensors +3 -0
- model-00032-of-00071.safetensors +3 -0
- model-00033-of-00071.safetensors +3 -0
- model-00034-of-00071.safetensors +3 -0
- model-00035-of-00071.safetensors +3 -0
- model-00036-of-00071.safetensors +3 -0
- model-00037-of-00071.safetensors +3 -0
- model-00039-of-00071.safetensors +3 -0
- model-00040-of-00071.safetensors +3 -0
- model-00041-of-00071.safetensors +3 -0
- model-00042-of-00071.safetensors +3 -0
- model-00044-of-00071.safetensors +3 -0
- model-00047-of-00071.safetensors +3 -0
- model-00052-of-00071.safetensors +3 -0
- model-00054-of-00071.safetensors +3 -0
- model-00056-of-00071.safetensors +3 -0
- model-00057-of-00071.safetensors +3 -0
- model-00058-of-00071.safetensors +3 -0
- model-00062-of-00071.safetensors +3 -0
- model-00064-of-00071.safetensors +3 -0
- model-00065-of-00071.safetensors +3 -0
- model-00066-of-00071.safetensors +3 -0
- model-00067-of-00071.safetensors +3 -0
- model-00068-of-00071.safetensors +3 -0
- model-00071-of-00071.safetensors +3 -0
- model.safetensors.index.json +3 -0
- quantization_config.json +501 -0
- special_tokens_map.json +23 -0
- tokenizer.json +0 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
model.safetensors.index.json filter=lfs diff=lfs merge=lfs -text
|
config.json
ADDED
|
@@ -0,0 +1,574 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"DeepseekV32ForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"aux_loss_alpha": 0.001,
|
| 8 |
+
"beta_fast": 32,
|
| 9 |
+
"beta_slow": 1,
|
| 10 |
+
"bos_token_id": 0,
|
| 11 |
+
"dim": 7168,
|
| 12 |
+
"dtype": "bfloat16",
|
| 13 |
+
"eos_token_id": 1,
|
| 14 |
+
"ep_size": 1,
|
| 15 |
+
"first_k_dense_replace": 3,
|
| 16 |
+
"head_dim": 64,
|
| 17 |
+
"hidden_act": "silu",
|
| 18 |
+
"hidden_size": 7168,
|
| 19 |
+
"index_head_dim": 128,
|
| 20 |
+
"index_n_heads": 64,
|
| 21 |
+
"index_top_k": 2048,
|
| 22 |
+
"index_topk": 2048,
|
| 23 |
+
"initializer_range": 0.02,
|
| 24 |
+
"intermediate_size": 18432,
|
| 25 |
+
"kv_lora_rank": 512,
|
| 26 |
+
"max_batch_size": 8,
|
| 27 |
+
"max_position_embeddings": 163840,
|
| 28 |
+
"max_seq_len": 16384,
|
| 29 |
+
"mlp_bias": false,
|
| 30 |
+
"model_type": "deepseek_v32",
|
| 31 |
+
"moe_intermediate_size": 2048,
|
| 32 |
+
"moe_layer_freq": 1,
|
| 33 |
+
"mscale": 1.0,
|
| 34 |
+
"n_group": 8,
|
| 35 |
+
"n_routed_experts": 256,
|
| 36 |
+
"n_shared_experts": 1,
|
| 37 |
+
"norm_topk_prob": true,
|
| 38 |
+
"num_attention_heads": 128,
|
| 39 |
+
"num_experts_per_tok": 8,
|
| 40 |
+
"num_hidden_layers": 61,
|
| 41 |
+
"num_key_value_heads": 128,
|
| 42 |
+
"num_nextn_predict_layers": 1,
|
| 43 |
+
"original_seq_len": 4096,
|
| 44 |
+
"q_lora_rank": 1536,
|
| 45 |
+
"qk_head_dim": 192,
|
| 46 |
+
"qk_nope_head_dim": 128,
|
| 47 |
+
"qk_rope_head_dim": 64,
|
| 48 |
+
"quantization_config": {
|
| 49 |
+
"autoround_version": "0.9.5",
|
| 50 |
+
"bits": 4,
|
| 51 |
+
"data_type": "int",
|
| 52 |
+
"extra_config": {
|
| 53 |
+
"model.layers.0.self_attn.indexer.wk": {
|
| 54 |
+
"bits": 16,
|
| 55 |
+
"data_type": "float"
|
| 56 |
+
},
|
| 57 |
+
"model.layers.0.self_attn.indexer.wq_b": {
|
| 58 |
+
"bits": 16,
|
| 59 |
+
"data_type": "float"
|
| 60 |
+
},
|
| 61 |
+
"model.layers.1.self_attn.indexer.wk": {
|
| 62 |
+
"bits": 16,
|
| 63 |
+
"data_type": "float"
|
| 64 |
+
},
|
| 65 |
+
"model.layers.1.self_attn.indexer.wq_b": {
|
| 66 |
+
"bits": 16,
|
| 67 |
+
"data_type": "float"
|
| 68 |
+
},
|
| 69 |
+
"model.layers.10.self_attn.indexer.wk": {
|
| 70 |
+
"bits": 16,
|
| 71 |
+
"data_type": "float"
|
| 72 |
+
},
|
| 73 |
+
"model.layers.10.self_attn.indexer.wq_b": {
|
| 74 |
+
"bits": 16,
|
| 75 |
+
"data_type": "float"
|
| 76 |
+
},
|
| 77 |
+
"model.layers.11.self_attn.indexer.wk": {
|
| 78 |
+
"bits": 16,
|
| 79 |
+
"data_type": "float"
|
| 80 |
+
},
|
| 81 |
+
"model.layers.11.self_attn.indexer.wq_b": {
|
| 82 |
+
"bits": 16,
|
| 83 |
+
"data_type": "float"
|
| 84 |
+
},
|
| 85 |
+
"model.layers.12.self_attn.indexer.wk": {
|
| 86 |
+
"bits": 16,
|
| 87 |
+
"data_type": "float"
|
| 88 |
+
},
|
| 89 |
+
"model.layers.12.self_attn.indexer.wq_b": {
|
| 90 |
+
"bits": 16,
|
| 91 |
+
"data_type": "float"
|
| 92 |
+
},
|
| 93 |
+
"model.layers.13.self_attn.indexer.wk": {
|
| 94 |
+
"bits": 16,
|
| 95 |
+
"data_type": "float"
|
| 96 |
+
},
|
| 97 |
+
"model.layers.13.self_attn.indexer.wq_b": {
|
| 98 |
+
"bits": 16,
|
| 99 |
+
"data_type": "float"
|
| 100 |
+
},
|
| 101 |
+
"model.layers.14.self_attn.indexer.wk": {
|
| 102 |
+
"bits": 16,
|
| 103 |
+
"data_type": "float"
|
| 104 |
+
},
|
| 105 |
+
"model.layers.14.self_attn.indexer.wq_b": {
|
| 106 |
+
"bits": 16,
|
| 107 |
+
"data_type": "float"
|
| 108 |
+
},
|
| 109 |
+
"model.layers.15.self_attn.indexer.wk": {
|
| 110 |
+
"bits": 16,
|
| 111 |
+
"data_type": "float"
|
| 112 |
+
},
|
| 113 |
+
"model.layers.15.self_attn.indexer.wq_b": {
|
| 114 |
+
"bits": 16,
|
| 115 |
+
"data_type": "float"
|
| 116 |
+
},
|
| 117 |
+
"model.layers.16.self_attn.indexer.wk": {
|
| 118 |
+
"bits": 16,
|
| 119 |
+
"data_type": "float"
|
| 120 |
+
},
|
| 121 |
+
"model.layers.16.self_attn.indexer.wq_b": {
|
| 122 |
+
"bits": 16,
|
| 123 |
+
"data_type": "float"
|
| 124 |
+
},
|
| 125 |
+
"model.layers.17.self_attn.indexer.wk": {
|
| 126 |
+
"bits": 16,
|
| 127 |
+
"data_type": "float"
|
| 128 |
+
},
|
| 129 |
+
"model.layers.17.self_attn.indexer.wq_b": {
|
| 130 |
+
"bits": 16,
|
| 131 |
+
"data_type": "float"
|
| 132 |
+
},
|
| 133 |
+
"model.layers.18.self_attn.indexer.wk": {
|
| 134 |
+
"bits": 16,
|
| 135 |
+
"data_type": "float"
|
| 136 |
+
},
|
| 137 |
+
"model.layers.18.self_attn.indexer.wq_b": {
|
| 138 |
+
"bits": 16,
|
| 139 |
+
"data_type": "float"
|
| 140 |
+
},
|
| 141 |
+
"model.layers.19.self_attn.indexer.wk": {
|
| 142 |
+
"bits": 16,
|
| 143 |
+
"data_type": "float"
|
| 144 |
+
},
|
| 145 |
+
"model.layers.19.self_attn.indexer.wq_b": {
|
| 146 |
+
"bits": 16,
|
| 147 |
+
"data_type": "float"
|
| 148 |
+
},
|
| 149 |
+
"model.layers.2.self_attn.indexer.wk": {
|
| 150 |
+
"bits": 16,
|
| 151 |
+
"data_type": "float"
|
| 152 |
+
},
|
| 153 |
+
"model.layers.2.self_attn.indexer.wq_b": {
|
| 154 |
+
"bits": 16,
|
| 155 |
+
"data_type": "float"
|
| 156 |
+
},
|
| 157 |
+
"model.layers.20.self_attn.indexer.wk": {
|
| 158 |
+
"bits": 16,
|
| 159 |
+
"data_type": "float"
|
| 160 |
+
},
|
| 161 |
+
"model.layers.20.self_attn.indexer.wq_b": {
|
| 162 |
+
"bits": 16,
|
| 163 |
+
"data_type": "float"
|
| 164 |
+
},
|
| 165 |
+
"model.layers.21.self_attn.indexer.wk": {
|
| 166 |
+
"bits": 16,
|
| 167 |
+
"data_type": "float"
|
| 168 |
+
},
|
| 169 |
+
"model.layers.21.self_attn.indexer.wq_b": {
|
| 170 |
+
"bits": 16,
|
| 171 |
+
"data_type": "float"
|
| 172 |
+
},
|
| 173 |
+
"model.layers.22.self_attn.indexer.wk": {
|
| 174 |
+
"bits": 16,
|
| 175 |
+
"data_type": "float"
|
| 176 |
+
},
|
| 177 |
+
"model.layers.22.self_attn.indexer.wq_b": {
|
| 178 |
+
"bits": 16,
|
| 179 |
+
"data_type": "float"
|
| 180 |
+
},
|
| 181 |
+
"model.layers.23.self_attn.indexer.wk": {
|
| 182 |
+
"bits": 16,
|
| 183 |
+
"data_type": "float"
|
| 184 |
+
},
|
| 185 |
+
"model.layers.23.self_attn.indexer.wq_b": {
|
| 186 |
+
"bits": 16,
|
| 187 |
+
"data_type": "float"
|
| 188 |
+
},
|
| 189 |
+
"model.layers.24.self_attn.indexer.wk": {
|
| 190 |
+
"bits": 16,
|
| 191 |
+
"data_type": "float"
|
| 192 |
+
},
|
| 193 |
+
"model.layers.24.self_attn.indexer.wq_b": {
|
| 194 |
+
"bits": 16,
|
| 195 |
+
"data_type": "float"
|
| 196 |
+
},
|
| 197 |
+
"model.layers.25.self_attn.indexer.wk": {
|
| 198 |
+
"bits": 16,
|
| 199 |
+
"data_type": "float"
|
| 200 |
+
},
|
| 201 |
+
"model.layers.25.self_attn.indexer.wq_b": {
|
| 202 |
+
"bits": 16,
|
| 203 |
+
"data_type": "float"
|
| 204 |
+
},
|
| 205 |
+
"model.layers.26.self_attn.indexer.wk": {
|
| 206 |
+
"bits": 16,
|
| 207 |
+
"data_type": "float"
|
| 208 |
+
},
|
| 209 |
+
"model.layers.26.self_attn.indexer.wq_b": {
|
| 210 |
+
"bits": 16,
|
| 211 |
+
"data_type": "float"
|
| 212 |
+
},
|
| 213 |
+
"model.layers.27.self_attn.indexer.wk": {
|
| 214 |
+
"bits": 16,
|
| 215 |
+
"data_type": "float"
|
| 216 |
+
},
|
| 217 |
+
"model.layers.27.self_attn.indexer.wq_b": {
|
| 218 |
+
"bits": 16,
|
| 219 |
+
"data_type": "float"
|
| 220 |
+
},
|
| 221 |
+
"model.layers.28.self_attn.indexer.wk": {
|
| 222 |
+
"bits": 16,
|
| 223 |
+
"data_type": "float"
|
| 224 |
+
},
|
| 225 |
+
"model.layers.28.self_attn.indexer.wq_b": {
|
| 226 |
+
"bits": 16,
|
| 227 |
+
"data_type": "float"
|
| 228 |
+
},
|
| 229 |
+
"model.layers.29.self_attn.indexer.wk": {
|
| 230 |
+
"bits": 16,
|
| 231 |
+
"data_type": "float"
|
| 232 |
+
},
|
| 233 |
+
"model.layers.29.self_attn.indexer.wq_b": {
|
| 234 |
+
"bits": 16,
|
| 235 |
+
"data_type": "float"
|
| 236 |
+
},
|
| 237 |
+
"model.layers.3.self_attn.indexer.wk": {
|
| 238 |
+
"bits": 16,
|
| 239 |
+
"data_type": "float"
|
| 240 |
+
},
|
| 241 |
+
"model.layers.3.self_attn.indexer.wq_b": {
|
| 242 |
+
"bits": 16,
|
| 243 |
+
"data_type": "float"
|
| 244 |
+
},
|
| 245 |
+
"model.layers.30.self_attn.indexer.wk": {
|
| 246 |
+
"bits": 16,
|
| 247 |
+
"data_type": "float"
|
| 248 |
+
},
|
| 249 |
+
"model.layers.30.self_attn.indexer.wq_b": {
|
| 250 |
+
"bits": 16,
|
| 251 |
+
"data_type": "float"
|
| 252 |
+
},
|
| 253 |
+
"model.layers.31.self_attn.indexer.wk": {
|
| 254 |
+
"bits": 16,
|
| 255 |
+
"data_type": "float"
|
| 256 |
+
},
|
| 257 |
+
"model.layers.31.self_attn.indexer.wq_b": {
|
| 258 |
+
"bits": 16,
|
| 259 |
+
"data_type": "float"
|
| 260 |
+
},
|
| 261 |
+
"model.layers.32.self_attn.indexer.wk": {
|
| 262 |
+
"bits": 16,
|
| 263 |
+
"data_type": "float"
|
| 264 |
+
},
|
| 265 |
+
"model.layers.32.self_attn.indexer.wq_b": {
|
| 266 |
+
"bits": 16,
|
| 267 |
+
"data_type": "float"
|
| 268 |
+
},
|
| 269 |
+
"model.layers.33.self_attn.indexer.wk": {
|
| 270 |
+
"bits": 16,
|
| 271 |
+
"data_type": "float"
|
| 272 |
+
},
|
| 273 |
+
"model.layers.33.self_attn.indexer.wq_b": {
|
| 274 |
+
"bits": 16,
|
| 275 |
+
"data_type": "float"
|
| 276 |
+
},
|
| 277 |
+
"model.layers.34.self_attn.indexer.wk": {
|
| 278 |
+
"bits": 16,
|
| 279 |
+
"data_type": "float"
|
| 280 |
+
},
|
| 281 |
+
"model.layers.34.self_attn.indexer.wq_b": {
|
| 282 |
+
"bits": 16,
|
| 283 |
+
"data_type": "float"
|
| 284 |
+
},
|
| 285 |
+
"model.layers.35.self_attn.indexer.wk": {
|
| 286 |
+
"bits": 16,
|
| 287 |
+
"data_type": "float"
|
| 288 |
+
},
|
| 289 |
+
"model.layers.35.self_attn.indexer.wq_b": {
|
| 290 |
+
"bits": 16,
|
| 291 |
+
"data_type": "float"
|
| 292 |
+
},
|
| 293 |
+
"model.layers.36.self_attn.indexer.wk": {
|
| 294 |
+
"bits": 16,
|
| 295 |
+
"data_type": "float"
|
| 296 |
+
},
|
| 297 |
+
"model.layers.36.self_attn.indexer.wq_b": {
|
| 298 |
+
"bits": 16,
|
| 299 |
+
"data_type": "float"
|
| 300 |
+
},
|
| 301 |
+
"model.layers.37.self_attn.indexer.wk": {
|
| 302 |
+
"bits": 16,
|
| 303 |
+
"data_type": "float"
|
| 304 |
+
},
|
| 305 |
+
"model.layers.37.self_attn.indexer.wq_b": {
|
| 306 |
+
"bits": 16,
|
| 307 |
+
"data_type": "float"
|
| 308 |
+
},
|
| 309 |
+
"model.layers.38.self_attn.indexer.wk": {
|
| 310 |
+
"bits": 16,
|
| 311 |
+
"data_type": "float"
|
| 312 |
+
},
|
| 313 |
+
"model.layers.38.self_attn.indexer.wq_b": {
|
| 314 |
+
"bits": 16,
|
| 315 |
+
"data_type": "float"
|
| 316 |
+
},
|
| 317 |
+
"model.layers.39.self_attn.indexer.wk": {
|
| 318 |
+
"bits": 16,
|
| 319 |
+
"data_type": "float"
|
| 320 |
+
},
|
| 321 |
+
"model.layers.39.self_attn.indexer.wq_b": {
|
| 322 |
+
"bits": 16,
|
| 323 |
+
"data_type": "float"
|
| 324 |
+
},
|
| 325 |
+
"model.layers.4.self_attn.indexer.wk": {
|
| 326 |
+
"bits": 16,
|
| 327 |
+
"data_type": "float"
|
| 328 |
+
},
|
| 329 |
+
"model.layers.4.self_attn.indexer.wq_b": {
|
| 330 |
+
"bits": 16,
|
| 331 |
+
"data_type": "float"
|
| 332 |
+
},
|
| 333 |
+
"model.layers.40.self_attn.indexer.wk": {
|
| 334 |
+
"bits": 16,
|
| 335 |
+
"data_type": "float"
|
| 336 |
+
},
|
| 337 |
+
"model.layers.40.self_attn.indexer.wq_b": {
|
| 338 |
+
"bits": 16,
|
| 339 |
+
"data_type": "float"
|
| 340 |
+
},
|
| 341 |
+
"model.layers.41.self_attn.indexer.wk": {
|
| 342 |
+
"bits": 16,
|
| 343 |
+
"data_type": "float"
|
| 344 |
+
},
|
| 345 |
+
"model.layers.41.self_attn.indexer.wq_b": {
|
| 346 |
+
"bits": 16,
|
| 347 |
+
"data_type": "float"
|
| 348 |
+
},
|
| 349 |
+
"model.layers.42.self_attn.indexer.wk": {
|
| 350 |
+
"bits": 16,
|
| 351 |
+
"data_type": "float"
|
| 352 |
+
},
|
| 353 |
+
"model.layers.42.self_attn.indexer.wq_b": {
|
| 354 |
+
"bits": 16,
|
| 355 |
+
"data_type": "float"
|
| 356 |
+
},
|
| 357 |
+
"model.layers.43.self_attn.indexer.wk": {
|
| 358 |
+
"bits": 16,
|
| 359 |
+
"data_type": "float"
|
| 360 |
+
},
|
| 361 |
+
"model.layers.43.self_attn.indexer.wq_b": {
|
| 362 |
+
"bits": 16,
|
| 363 |
+
"data_type": "float"
|
| 364 |
+
},
|
| 365 |
+
"model.layers.44.self_attn.indexer.wk": {
|
| 366 |
+
"bits": 16,
|
| 367 |
+
"data_type": "float"
|
| 368 |
+
},
|
| 369 |
+
"model.layers.44.self_attn.indexer.wq_b": {
|
| 370 |
+
"bits": 16,
|
| 371 |
+
"data_type": "float"
|
| 372 |
+
},
|
| 373 |
+
"model.layers.45.self_attn.indexer.wk": {
|
| 374 |
+
"bits": 16,
|
| 375 |
+
"data_type": "float"
|
| 376 |
+
},
|
| 377 |
+
"model.layers.45.self_attn.indexer.wq_b": {
|
| 378 |
+
"bits": 16,
|
| 379 |
+
"data_type": "float"
|
| 380 |
+
},
|
| 381 |
+
"model.layers.46.self_attn.indexer.wk": {
|
| 382 |
+
"bits": 16,
|
| 383 |
+
"data_type": "float"
|
| 384 |
+
},
|
| 385 |
+
"model.layers.46.self_attn.indexer.wq_b": {
|
| 386 |
+
"bits": 16,
|
| 387 |
+
"data_type": "float"
|
| 388 |
+
},
|
| 389 |
+
"model.layers.47.self_attn.indexer.wk": {
|
| 390 |
+
"bits": 16,
|
| 391 |
+
"data_type": "float"
|
| 392 |
+
},
|
| 393 |
+
"model.layers.47.self_attn.indexer.wq_b": {
|
| 394 |
+
"bits": 16,
|
| 395 |
+
"data_type": "float"
|
| 396 |
+
},
|
| 397 |
+
"model.layers.48.self_attn.indexer.wk": {
|
| 398 |
+
"bits": 16,
|
| 399 |
+
"data_type": "float"
|
| 400 |
+
},
|
| 401 |
+
"model.layers.48.self_attn.indexer.wq_b": {
|
| 402 |
+
"bits": 16,
|
| 403 |
+
"data_type": "float"
|
| 404 |
+
},
|
| 405 |
+
"model.layers.49.self_attn.indexer.wk": {
|
| 406 |
+
"bits": 16,
|
| 407 |
+
"data_type": "float"
|
| 408 |
+
},
|
| 409 |
+
"model.layers.49.self_attn.indexer.wq_b": {
|
| 410 |
+
"bits": 16,
|
| 411 |
+
"data_type": "float"
|
| 412 |
+
},
|
| 413 |
+
"model.layers.5.self_attn.indexer.wk": {
|
| 414 |
+
"bits": 16,
|
| 415 |
+
"data_type": "float"
|
| 416 |
+
},
|
| 417 |
+
"model.layers.5.self_attn.indexer.wq_b": {
|
| 418 |
+
"bits": 16,
|
| 419 |
+
"data_type": "float"
|
| 420 |
+
},
|
| 421 |
+
"model.layers.50.self_attn.indexer.wk": {
|
| 422 |
+
"bits": 16,
|
| 423 |
+
"data_type": "float"
|
| 424 |
+
},
|
| 425 |
+
"model.layers.50.self_attn.indexer.wq_b": {
|
| 426 |
+
"bits": 16,
|
| 427 |
+
"data_type": "float"
|
| 428 |
+
},
|
| 429 |
+
"model.layers.51.self_attn.indexer.wk": {
|
| 430 |
+
"bits": 16,
|
| 431 |
+
"data_type": "float"
|
| 432 |
+
},
|
| 433 |
+
"model.layers.51.self_attn.indexer.wq_b": {
|
| 434 |
+
"bits": 16,
|
| 435 |
+
"data_type": "float"
|
| 436 |
+
},
|
| 437 |
+
"model.layers.52.self_attn.indexer.wk": {
|
| 438 |
+
"bits": 16,
|
| 439 |
+
"data_type": "float"
|
| 440 |
+
},
|
| 441 |
+
"model.layers.52.self_attn.indexer.wq_b": {
|
| 442 |
+
"bits": 16,
|
| 443 |
+
"data_type": "float"
|
| 444 |
+
},
|
| 445 |
+
"model.layers.53.self_attn.indexer.wk": {
|
| 446 |
+
"bits": 16,
|
| 447 |
+
"data_type": "float"
|
| 448 |
+
},
|
| 449 |
+
"model.layers.53.self_attn.indexer.wq_b": {
|
| 450 |
+
"bits": 16,
|
| 451 |
+
"data_type": "float"
|
| 452 |
+
},
|
| 453 |
+
"model.layers.54.self_attn.indexer.wk": {
|
| 454 |
+
"bits": 16,
|
| 455 |
+
"data_type": "float"
|
| 456 |
+
},
|
| 457 |
+
"model.layers.54.self_attn.indexer.wq_b": {
|
| 458 |
+
"bits": 16,
|
| 459 |
+
"data_type": "float"
|
| 460 |
+
},
|
| 461 |
+
"model.layers.55.self_attn.indexer.wk": {
|
| 462 |
+
"bits": 16,
|
| 463 |
+
"data_type": "float"
|
| 464 |
+
},
|
| 465 |
+
"model.layers.55.self_attn.indexer.wq_b": {
|
| 466 |
+
"bits": 16,
|
| 467 |
+
"data_type": "float"
|
| 468 |
+
},
|
| 469 |
+
"model.layers.56.self_attn.indexer.wk": {
|
| 470 |
+
"bits": 16,
|
| 471 |
+
"data_type": "float"
|
| 472 |
+
},
|
| 473 |
+
"model.layers.56.self_attn.indexer.wq_b": {
|
| 474 |
+
"bits": 16,
|
| 475 |
+
"data_type": "float"
|
| 476 |
+
},
|
| 477 |
+
"model.layers.57.self_attn.indexer.wk": {
|
| 478 |
+
"bits": 16,
|
| 479 |
+
"data_type": "float"
|
| 480 |
+
},
|
| 481 |
+
"model.layers.57.self_attn.indexer.wq_b": {
|
| 482 |
+
"bits": 16,
|
| 483 |
+
"data_type": "float"
|
| 484 |
+
},
|
| 485 |
+
"model.layers.58.self_attn.indexer.wk": {
|
| 486 |
+
"bits": 16,
|
| 487 |
+
"data_type": "float"
|
| 488 |
+
},
|
| 489 |
+
"model.layers.58.self_attn.indexer.wq_b": {
|
| 490 |
+
"bits": 16,
|
| 491 |
+
"data_type": "float"
|
| 492 |
+
},
|
| 493 |
+
"model.layers.59.self_attn.indexer.wk": {
|
| 494 |
+
"bits": 16,
|
| 495 |
+
"data_type": "float"
|
| 496 |
+
},
|
| 497 |
+
"model.layers.59.self_attn.indexer.wq_b": {
|
| 498 |
+
"bits": 16,
|
| 499 |
+
"data_type": "float"
|
| 500 |
+
},
|
| 501 |
+
"model.layers.6.self_attn.indexer.wk": {
|
| 502 |
+
"bits": 16,
|
| 503 |
+
"data_type": "float"
|
| 504 |
+
},
|
| 505 |
+
"model.layers.6.self_attn.indexer.wq_b": {
|
| 506 |
+
"bits": 16,
|
| 507 |
+
"data_type": "float"
|
| 508 |
+
},
|
| 509 |
+
"model.layers.60.self_attn.indexer.wk": {
|
| 510 |
+
"bits": 16,
|
| 511 |
+
"data_type": "float"
|
| 512 |
+
},
|
| 513 |
+
"model.layers.60.self_attn.indexer.wq_b": {
|
| 514 |
+
"bits": 16,
|
| 515 |
+
"data_type": "float"
|
| 516 |
+
},
|
| 517 |
+
"model.layers.7.self_attn.indexer.wk": {
|
| 518 |
+
"bits": 16,
|
| 519 |
+
"data_type": "float"
|
| 520 |
+
},
|
| 521 |
+
"model.layers.7.self_attn.indexer.wq_b": {
|
| 522 |
+
"bits": 16,
|
| 523 |
+
"data_type": "float"
|
| 524 |
+
},
|
| 525 |
+
"model.layers.8.self_attn.indexer.wk": {
|
| 526 |
+
"bits": 16,
|
| 527 |
+
"data_type": "float"
|
| 528 |
+
},
|
| 529 |
+
"model.layers.8.self_attn.indexer.wq_b": {
|
| 530 |
+
"bits": 16,
|
| 531 |
+
"data_type": "float"
|
| 532 |
+
},
|
| 533 |
+
"model.layers.9.self_attn.indexer.wk": {
|
| 534 |
+
"bits": 16,
|
| 535 |
+
"data_type": "float"
|
| 536 |
+
},
|
| 537 |
+
"model.layers.9.self_attn.indexer.wq_b": {
|
| 538 |
+
"bits": 16,
|
| 539 |
+
"data_type": "float"
|
| 540 |
+
}
|
| 541 |
+
},
|
| 542 |
+
"group_size": 128,
|
| 543 |
+
"iters": 0,
|
| 544 |
+
"low_gpu_mem_usage": true,
|
| 545 |
+
"packing_format": "auto_round:auto_gptq",
|
| 546 |
+
"quant_method": "auto-round",
|
| 547 |
+
"sym": true
|
| 548 |
+
},
|
| 549 |
+
"rms_norm_eps": 1e-06,
|
| 550 |
+
"rope_factor": 40,
|
| 551 |
+
"rope_interleave": true,
|
| 552 |
+
"rope_scaling": {
|
| 553 |
+
"beta_fast": 32,
|
| 554 |
+
"beta_slow": 1,
|
| 555 |
+
"factor": 40,
|
| 556 |
+
"mscale": 1.0,
|
| 557 |
+
"mscale_all_dim": 1.0,
|
| 558 |
+
"original_max_position_embeddings": 4096,
|
| 559 |
+
"rope_type": "yarn",
|
| 560 |
+
"type": "yarn"
|
| 561 |
+
},
|
| 562 |
+
"rope_theta": 10000.0,
|
| 563 |
+
"routed_scaling_factor": 2.5,
|
| 564 |
+
"scale_fmt": null,
|
| 565 |
+
"scoring_func": "sigmoid",
|
| 566 |
+
"seq_aux": true,
|
| 567 |
+
"tie_word_embeddings": false,
|
| 568 |
+
"topk_group": 4,
|
| 569 |
+
"topk_method": "noaux_tc",
|
| 570 |
+
"transformers_version": "4.57.3",
|
| 571 |
+
"use_cache": true,
|
| 572 |
+
"v_head_dim": 128,
|
| 573 |
+
"vocab_size": 129280
|
| 574 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 0,
|
| 4 |
+
"do_sample": true,
|
| 5 |
+
"eos_token_id": 1,
|
| 6 |
+
"top_p": 0.95,
|
| 7 |
+
"transformers_version": "4.57.3"
|
| 8 |
+
}
|
model-00002-of-00071.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8f77b0eb41a40451bb66f9da97eb8997afcc3eabd0786e12cff8e6dc1ec3514b
|
| 3 |
+
size 4996689424
|
model-00005-of-00071.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ec8fc493bb1dffac8d221ea3070ba98d5ed8e4ae72af83d52100748bcd1cc0ae
|
| 3 |
+
size 4996689032
|
model-00006-of-00071.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:14f5225acfc3e20d27e71a3ede2a3d645448f9338e15fc50afdeaec14c37dc62
|
| 3 |
+
size 4996689032
|
model-00007-of-00071.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d8654cc755b9a2e38c5ad1344b2a1e05f33f02a28aafd03097f8352c782ede0b
|
| 3 |
+
size 4996689112
|
model-00008-of-00071.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a4962b362e9cfee05c3939baf459892ab4533c3357ba5936d91e98ce7a11a131
|
| 3 |
+
size 4996689424
|
model-00009-of-00071.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f186b539c9333a62468f337eb37fbbde0f51a2571a02dd5e6ea2f5f9295f1ed1
|
| 3 |
+
size 4996689568
|
model-00010-of-00071.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6c5921d77373ea164f9e98fa729b84c23150859f5a6e1fe76f895ad77268d42b
|
| 3 |
+
size 4995764080
|
model-00011-of-00071.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:81c1824b69bfcb20ba521c382ebc54190b26685cdb5f19a1f52107d054205dcc
|
| 3 |
+
size 4996690984
|
model-00012-of-00071.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ddb1202a9a839f4c0469205f5fab085193a4259219c97ccb81b85359e76ff6e7
|
| 3 |
+
size 4996690976
|
model-00013-of-00071.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2041ecaf3cec1c379eef01b3e1c112d28fa866f566df03510037ccd792cefc0d
|
| 3 |
+
size 4996691064
|
model-00015-of-00071.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ade1354cd7e3dcbbf2867d5b7d3e06450da285345b1b2bccf60a0eb51333aa2c
|
| 3 |
+
size 4996691424
|
model-00017-of-00071.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5c9d63922a1154235c25e58d269546d8fb8fdad19d3223d41cefc300b93e36fb
|
| 3 |
+
size 4996690984
|
model-00019-of-00071.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:232b2038f3f8edc053d7656b6bbf6e1e3def48ebf04034f5b76fbc5cf86cddcc
|
| 3 |
+
size 4996691064
|
model-00021-of-00071.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:23c19e37019189695cd76b2d72633f5c20553063404f3611200304119d90f7f4
|
| 3 |
+
size 4996691424
|
model-00022-of-00071.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:924461202adf582815ecd8b9dc9699326ad05732f9f8b39cb3bd340e83816f32
|
| 3 |
+
size 4995764080
|
model-00023-of-00071.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:90b48161875f7551d71fc30887849ebede9d894a8dd0eb53ddf20a6b6c15469b
|
| 3 |
+
size 4996690984
|
model-00024-of-00071.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a63ea521b382c56e965938a4e0769b5953bd1e2bcc153c493dda364211c73f32
|
| 3 |
+
size 4996690976
|
model-00029-of-00071.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0215ee380ab2834da4937b8e18d9103ee116d053970d5d2af2fe81bdaa30b161
|
| 3 |
+
size 4996690984
|
model-00030-of-00071.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:38317dd6f3ed6e5215e65c714b199151276c15b1550f1e7c4f8769d62440b0f9
|
| 3 |
+
size 4996690976
|
model-00032-of-00071.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:35ab1e00425851b1bfd46471b664d500551c61f460e86ceb5668dc902cd1578a
|
| 3 |
+
size 4996691376
|
model-00033-of-00071.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c7634539ecb51b445ae423a85e2585b2c63578dab7c29d5d9c96018b5a0a6452
|
| 3 |
+
size 4996691424
|
model-00034-of-00071.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:20bd4841aa66d6be369cdfeb7afccfccec5a23f900f1a00fbafadcd153311be5
|
| 3 |
+
size 4995764080
|
model-00035-of-00071.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:be8ab5407294fae448580015b3e75064eb337f9756664db3a7c59b254cb89af2
|
| 3 |
+
size 4996690984
|
model-00036-of-00071.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:81d8a7ec9a2748734b190c7bdb04c0b5d6a763e5136503a951fdae809687887e
|
| 3 |
+
size 4996690976
|
model-00037-of-00071.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ed751b36e3a25de954d05dedbc31f2b4e125f611e034ae7097d793b5fd563968
|
| 3 |
+
size 4996691064
|
model-00039-of-00071.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:431a950d1b3a77abe9388f9609f6a847f8c0ea3fd044dc54b0a5fd331f6c3daa
|
| 3 |
+
size 4996691424
|
model-00040-of-00071.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d742595c36a53413cf661adb6bff0a4aa9cc1b11ffadfd97cc1de0e4dfb625e8
|
| 3 |
+
size 4995764080
|
model-00041-of-00071.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ce5b407adc9f20c6aeacb18f40a2f5d54a43071b085c5b92361daf69616719ca
|
| 3 |
+
size 4996690984
|
model-00042-of-00071.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:095565971af5591c8e4a3b62f970513b4a74a29b7e87a1891bd4509198ec6daf
|
| 3 |
+
size 4996690976
|
model-00044-of-00071.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e48500758bd6ed0a981926a573dfe7f82a6ff89555a0413f354a77f979308f1c
|
| 3 |
+
size 4996691376
|
model-00047-of-00071.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:42eb0150a1c67b3dbcc66f869f70e2dc3dd671691a0698be4a27f1f58f8813de
|
| 3 |
+
size 4996690984
|
model-00052-of-00071.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:18d4434f61dae24f5e9a9011fb6e37fc55162bdbfced73c81f6f3139631cb3fc
|
| 3 |
+
size 4995764080
|
model-00054-of-00071.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c6dcbb6a5ad6094b27c23305190ce724bd6ea15ffc59cef68bbe202e54e48ab8
|
| 3 |
+
size 4996690976
|
model-00056-of-00071.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:59dda62463be07888ea34580754bf157c70362768d6c4c11b31cce94160089d0
|
| 3 |
+
size 4996691376
|
model-00057-of-00071.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4e9e9e06e8fe5186bd82ea6a5c34332e3fa021fba6c05a33a3a6c9d783b98935
|
| 3 |
+
size 4996691424
|
model-00058-of-00071.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2394a6118387b59a2cc516f3968ded82822362a01647e16440fe357dcb53237e
|
| 3 |
+
size 4995764080
|
model-00062-of-00071.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ea7d721acf13c725c175d71f135700e0a128ad6a5637adfd6456c6140b15e44e
|
| 3 |
+
size 4996691376
|
model-00064-of-00071.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:817fa61298ffaa46867c636680389f0d19e379eef78cecd7ccede4f5a7173a17
|
| 3 |
+
size 4995764080
|
model-00065-of-00071.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8633be35b6863d0a9f81d68acc1a3b0965cd662a79f554cbea06a84d36992eb4
|
| 3 |
+
size 4996690984
|
model-00066-of-00071.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:780416a51b9a5b87fa11075926173d2096343ec2dc3b5d7de51af5d5b8c981ba
|
| 3 |
+
size 4996690976
|
model-00067-of-00071.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:64eb8c28cd2ae87f149a42ac397533fdd0a90fe5298653f80e07169fa03efeb3
|
| 3 |
+
size 4996691064
|
model-00068-of-00071.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5bddeab0cdc33dc1fa520872d1f621ada8cc956b30e3bbea08592c70d5d5ee5d
|
| 3 |
+
size 4996691376
|
model-00071-of-00071.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7e82109f73ac0de759e8d0a759ac4c8db0ae010d9772c5c3d84190df0a63f0fd
|
| 3 |
+
size 2657919768
|
model.safetensors.index.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:17ed9448ed90312160d9b38acf4324a6610c4d021dfd34c8495070b0c4215eb3
|
| 3 |
+
size 12378152
|
quantization_config.json
ADDED
|
@@ -0,0 +1,501 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bits": 4,
|
| 3 |
+
"data_type": "int",
|
| 4 |
+
"group_size": 128,
|
| 5 |
+
"sym": true,
|
| 6 |
+
"iters": 0,
|
| 7 |
+
"low_gpu_mem_usage": true,
|
| 8 |
+
"autoround_version": "0.9.5",
|
| 9 |
+
"quant_method": "auto-round",
|
| 10 |
+
"packing_format": "auto_round:auto_gptq",
|
| 11 |
+
"extra_config": {
|
| 12 |
+
"model.layers.0.self_attn.indexer.wq_b": {
|
| 13 |
+
"bits": 16,
|
| 14 |
+
"data_type": "float"
|
| 15 |
+
},
|
| 16 |
+
"model.layers.0.self_attn.indexer.wk": {
|
| 17 |
+
"bits": 16,
|
| 18 |
+
"data_type": "float"
|
| 19 |
+
},
|
| 20 |
+
"model.layers.1.self_attn.indexer.wq_b": {
|
| 21 |
+
"bits": 16,
|
| 22 |
+
"data_type": "float"
|
| 23 |
+
},
|
| 24 |
+
"model.layers.1.self_attn.indexer.wk": {
|
| 25 |
+
"bits": 16,
|
| 26 |
+
"data_type": "float"
|
| 27 |
+
},
|
| 28 |
+
"model.layers.2.self_attn.indexer.wq_b": {
|
| 29 |
+
"bits": 16,
|
| 30 |
+
"data_type": "float"
|
| 31 |
+
},
|
| 32 |
+
"model.layers.2.self_attn.indexer.wk": {
|
| 33 |
+
"bits": 16,
|
| 34 |
+
"data_type": "float"
|
| 35 |
+
},
|
| 36 |
+
"model.layers.3.self_attn.indexer.wq_b": {
|
| 37 |
+
"bits": 16,
|
| 38 |
+
"data_type": "float"
|
| 39 |
+
},
|
| 40 |
+
"model.layers.3.self_attn.indexer.wk": {
|
| 41 |
+
"bits": 16,
|
| 42 |
+
"data_type": "float"
|
| 43 |
+
},
|
| 44 |
+
"model.layers.4.self_attn.indexer.wq_b": {
|
| 45 |
+
"bits": 16,
|
| 46 |
+
"data_type": "float"
|
| 47 |
+
},
|
| 48 |
+
"model.layers.4.self_attn.indexer.wk": {
|
| 49 |
+
"bits": 16,
|
| 50 |
+
"data_type": "float"
|
| 51 |
+
},
|
| 52 |
+
"model.layers.5.self_attn.indexer.wq_b": {
|
| 53 |
+
"bits": 16,
|
| 54 |
+
"data_type": "float"
|
| 55 |
+
},
|
| 56 |
+
"model.layers.5.self_attn.indexer.wk": {
|
| 57 |
+
"bits": 16,
|
| 58 |
+
"data_type": "float"
|
| 59 |
+
},
|
| 60 |
+
"model.layers.6.self_attn.indexer.wq_b": {
|
| 61 |
+
"bits": 16,
|
| 62 |
+
"data_type": "float"
|
| 63 |
+
},
|
| 64 |
+
"model.layers.6.self_attn.indexer.wk": {
|
| 65 |
+
"bits": 16,
|
| 66 |
+
"data_type": "float"
|
| 67 |
+
},
|
| 68 |
+
"model.layers.7.self_attn.indexer.wq_b": {
|
| 69 |
+
"bits": 16,
|
| 70 |
+
"data_type": "float"
|
| 71 |
+
},
|
| 72 |
+
"model.layers.7.self_attn.indexer.wk": {
|
| 73 |
+
"bits": 16,
|
| 74 |
+
"data_type": "float"
|
| 75 |
+
},
|
| 76 |
+
"model.layers.8.self_attn.indexer.wq_b": {
|
| 77 |
+
"bits": 16,
|
| 78 |
+
"data_type": "float"
|
| 79 |
+
},
|
| 80 |
+
"model.layers.8.self_attn.indexer.wk": {
|
| 81 |
+
"bits": 16,
|
| 82 |
+
"data_type": "float"
|
| 83 |
+
},
|
| 84 |
+
"model.layers.9.self_attn.indexer.wq_b": {
|
| 85 |
+
"bits": 16,
|
| 86 |
+
"data_type": "float"
|
| 87 |
+
},
|
| 88 |
+
"model.layers.9.self_attn.indexer.wk": {
|
| 89 |
+
"bits": 16,
|
| 90 |
+
"data_type": "float"
|
| 91 |
+
},
|
| 92 |
+
"model.layers.10.self_attn.indexer.wq_b": {
|
| 93 |
+
"bits": 16,
|
| 94 |
+
"data_type": "float"
|
| 95 |
+
},
|
| 96 |
+
"model.layers.10.self_attn.indexer.wk": {
|
| 97 |
+
"bits": 16,
|
| 98 |
+
"data_type": "float"
|
| 99 |
+
},
|
| 100 |
+
"model.layers.11.self_attn.indexer.wq_b": {
|
| 101 |
+
"bits": 16,
|
| 102 |
+
"data_type": "float"
|
| 103 |
+
},
|
| 104 |
+
"model.layers.11.self_attn.indexer.wk": {
|
| 105 |
+
"bits": 16,
|
| 106 |
+
"data_type": "float"
|
| 107 |
+
},
|
| 108 |
+
"model.layers.12.self_attn.indexer.wq_b": {
|
| 109 |
+
"bits": 16,
|
| 110 |
+
"data_type": "float"
|
| 111 |
+
},
|
| 112 |
+
"model.layers.12.self_attn.indexer.wk": {
|
| 113 |
+
"bits": 16,
|
| 114 |
+
"data_type": "float"
|
| 115 |
+
},
|
| 116 |
+
"model.layers.13.self_attn.indexer.wq_b": {
|
| 117 |
+
"bits": 16,
|
| 118 |
+
"data_type": "float"
|
| 119 |
+
},
|
| 120 |
+
"model.layers.13.self_attn.indexer.wk": {
|
| 121 |
+
"bits": 16,
|
| 122 |
+
"data_type": "float"
|
| 123 |
+
},
|
| 124 |
+
"model.layers.14.self_attn.indexer.wq_b": {
|
| 125 |
+
"bits": 16,
|
| 126 |
+
"data_type": "float"
|
| 127 |
+
},
|
| 128 |
+
"model.layers.14.self_attn.indexer.wk": {
|
| 129 |
+
"bits": 16,
|
| 130 |
+
"data_type": "float"
|
| 131 |
+
},
|
| 132 |
+
"model.layers.15.self_attn.indexer.wq_b": {
|
| 133 |
+
"bits": 16,
|
| 134 |
+
"data_type": "float"
|
| 135 |
+
},
|
| 136 |
+
"model.layers.15.self_attn.indexer.wk": {
|
| 137 |
+
"bits": 16,
|
| 138 |
+
"data_type": "float"
|
| 139 |
+
},
|
| 140 |
+
"model.layers.16.self_attn.indexer.wq_b": {
|
| 141 |
+
"bits": 16,
|
| 142 |
+
"data_type": "float"
|
| 143 |
+
},
|
| 144 |
+
"model.layers.16.self_attn.indexer.wk": {
|
| 145 |
+
"bits": 16,
|
| 146 |
+
"data_type": "float"
|
| 147 |
+
},
|
| 148 |
+
"model.layers.17.self_attn.indexer.wq_b": {
|
| 149 |
+
"bits": 16,
|
| 150 |
+
"data_type": "float"
|
| 151 |
+
},
|
| 152 |
+
"model.layers.17.self_attn.indexer.wk": {
|
| 153 |
+
"bits": 16,
|
| 154 |
+
"data_type": "float"
|
| 155 |
+
},
|
| 156 |
+
"model.layers.18.self_attn.indexer.wq_b": {
|
| 157 |
+
"bits": 16,
|
| 158 |
+
"data_type": "float"
|
| 159 |
+
},
|
| 160 |
+
"model.layers.18.self_attn.indexer.wk": {
|
| 161 |
+
"bits": 16,
|
| 162 |
+
"data_type": "float"
|
| 163 |
+
},
|
| 164 |
+
"model.layers.19.self_attn.indexer.wq_b": {
|
| 165 |
+
"bits": 16,
|
| 166 |
+
"data_type": "float"
|
| 167 |
+
},
|
| 168 |
+
"model.layers.19.self_attn.indexer.wk": {
|
| 169 |
+
"bits": 16,
|
| 170 |
+
"data_type": "float"
|
| 171 |
+
},
|
| 172 |
+
"model.layers.20.self_attn.indexer.wq_b": {
|
| 173 |
+
"bits": 16,
|
| 174 |
+
"data_type": "float"
|
| 175 |
+
},
|
| 176 |
+
"model.layers.20.self_attn.indexer.wk": {
|
| 177 |
+
"bits": 16,
|
| 178 |
+
"data_type": "float"
|
| 179 |
+
},
|
| 180 |
+
"model.layers.21.self_attn.indexer.wq_b": {
|
| 181 |
+
"bits": 16,
|
| 182 |
+
"data_type": "float"
|
| 183 |
+
},
|
| 184 |
+
"model.layers.21.self_attn.indexer.wk": {
|
| 185 |
+
"bits": 16,
|
| 186 |
+
"data_type": "float"
|
| 187 |
+
},
|
| 188 |
+
"model.layers.22.self_attn.indexer.wq_b": {
|
| 189 |
+
"bits": 16,
|
| 190 |
+
"data_type": "float"
|
| 191 |
+
},
|
| 192 |
+
"model.layers.22.self_attn.indexer.wk": {
|
| 193 |
+
"bits": 16,
|
| 194 |
+
"data_type": "float"
|
| 195 |
+
},
|
| 196 |
+
"model.layers.23.self_attn.indexer.wq_b": {
|
| 197 |
+
"bits": 16,
|
| 198 |
+
"data_type": "float"
|
| 199 |
+
},
|
| 200 |
+
"model.layers.23.self_attn.indexer.wk": {
|
| 201 |
+
"bits": 16,
|
| 202 |
+
"data_type": "float"
|
| 203 |
+
},
|
| 204 |
+
"model.layers.24.self_attn.indexer.wq_b": {
|
| 205 |
+
"bits": 16,
|
| 206 |
+
"data_type": "float"
|
| 207 |
+
},
|
| 208 |
+
"model.layers.24.self_attn.indexer.wk": {
|
| 209 |
+
"bits": 16,
|
| 210 |
+
"data_type": "float"
|
| 211 |
+
},
|
| 212 |
+
"model.layers.25.self_attn.indexer.wq_b": {
|
| 213 |
+
"bits": 16,
|
| 214 |
+
"data_type": "float"
|
| 215 |
+
},
|
| 216 |
+
"model.layers.25.self_attn.indexer.wk": {
|
| 217 |
+
"bits": 16,
|
| 218 |
+
"data_type": "float"
|
| 219 |
+
},
|
| 220 |
+
"model.layers.26.self_attn.indexer.wq_b": {
|
| 221 |
+
"bits": 16,
|
| 222 |
+
"data_type": "float"
|
| 223 |
+
},
|
| 224 |
+
"model.layers.26.self_attn.indexer.wk": {
|
| 225 |
+
"bits": 16,
|
| 226 |
+
"data_type": "float"
|
| 227 |
+
},
|
| 228 |
+
"model.layers.27.self_attn.indexer.wq_b": {
|
| 229 |
+
"bits": 16,
|
| 230 |
+
"data_type": "float"
|
| 231 |
+
},
|
| 232 |
+
"model.layers.27.self_attn.indexer.wk": {
|
| 233 |
+
"bits": 16,
|
| 234 |
+
"data_type": "float"
|
| 235 |
+
},
|
| 236 |
+
"model.layers.28.self_attn.indexer.wq_b": {
|
| 237 |
+
"bits": 16,
|
| 238 |
+
"data_type": "float"
|
| 239 |
+
},
|
| 240 |
+
"model.layers.28.self_attn.indexer.wk": {
|
| 241 |
+
"bits": 16,
|
| 242 |
+
"data_type": "float"
|
| 243 |
+
},
|
| 244 |
+
"model.layers.29.self_attn.indexer.wq_b": {
|
| 245 |
+
"bits": 16,
|
| 246 |
+
"data_type": "float"
|
| 247 |
+
},
|
| 248 |
+
"model.layers.29.self_attn.indexer.wk": {
|
| 249 |
+
"bits": 16,
|
| 250 |
+
"data_type": "float"
|
| 251 |
+
},
|
| 252 |
+
"model.layers.30.self_attn.indexer.wq_b": {
|
| 253 |
+
"bits": 16,
|
| 254 |
+
"data_type": "float"
|
| 255 |
+
},
|
| 256 |
+
"model.layers.30.self_attn.indexer.wk": {
|
| 257 |
+
"bits": 16,
|
| 258 |
+
"data_type": "float"
|
| 259 |
+
},
|
| 260 |
+
"model.layers.31.self_attn.indexer.wq_b": {
|
| 261 |
+
"bits": 16,
|
| 262 |
+
"data_type": "float"
|
| 263 |
+
},
|
| 264 |
+
"model.layers.31.self_attn.indexer.wk": {
|
| 265 |
+
"bits": 16,
|
| 266 |
+
"data_type": "float"
|
| 267 |
+
},
|
| 268 |
+
"model.layers.32.self_attn.indexer.wq_b": {
|
| 269 |
+
"bits": 16,
|
| 270 |
+
"data_type": "float"
|
| 271 |
+
},
|
| 272 |
+
"model.layers.32.self_attn.indexer.wk": {
|
| 273 |
+
"bits": 16,
|
| 274 |
+
"data_type": "float"
|
| 275 |
+
},
|
| 276 |
+
"model.layers.33.self_attn.indexer.wq_b": {
|
| 277 |
+
"bits": 16,
|
| 278 |
+
"data_type": "float"
|
| 279 |
+
},
|
| 280 |
+
"model.layers.33.self_attn.indexer.wk": {
|
| 281 |
+
"bits": 16,
|
| 282 |
+
"data_type": "float"
|
| 283 |
+
},
|
| 284 |
+
"model.layers.34.self_attn.indexer.wq_b": {
|
| 285 |
+
"bits": 16,
|
| 286 |
+
"data_type": "float"
|
| 287 |
+
},
|
| 288 |
+
"model.layers.34.self_attn.indexer.wk": {
|
| 289 |
+
"bits": 16,
|
| 290 |
+
"data_type": "float"
|
| 291 |
+
},
|
| 292 |
+
"model.layers.35.self_attn.indexer.wq_b": {
|
| 293 |
+
"bits": 16,
|
| 294 |
+
"data_type": "float"
|
| 295 |
+
},
|
| 296 |
+
"model.layers.35.self_attn.indexer.wk": {
|
| 297 |
+
"bits": 16,
|
| 298 |
+
"data_type": "float"
|
| 299 |
+
},
|
| 300 |
+
"model.layers.36.self_attn.indexer.wq_b": {
|
| 301 |
+
"bits": 16,
|
| 302 |
+
"data_type": "float"
|
| 303 |
+
},
|
| 304 |
+
"model.layers.36.self_attn.indexer.wk": {
|
| 305 |
+
"bits": 16,
|
| 306 |
+
"data_type": "float"
|
| 307 |
+
},
|
| 308 |
+
"model.layers.37.self_attn.indexer.wq_b": {
|
| 309 |
+
"bits": 16,
|
| 310 |
+
"data_type": "float"
|
| 311 |
+
},
|
| 312 |
+
"model.layers.37.self_attn.indexer.wk": {
|
| 313 |
+
"bits": 16,
|
| 314 |
+
"data_type": "float"
|
| 315 |
+
},
|
| 316 |
+
"model.layers.38.self_attn.indexer.wq_b": {
|
| 317 |
+
"bits": 16,
|
| 318 |
+
"data_type": "float"
|
| 319 |
+
},
|
| 320 |
+
"model.layers.38.self_attn.indexer.wk": {
|
| 321 |
+
"bits": 16,
|
| 322 |
+
"data_type": "float"
|
| 323 |
+
},
|
| 324 |
+
"model.layers.39.self_attn.indexer.wq_b": {
|
| 325 |
+
"bits": 16,
|
| 326 |
+
"data_type": "float"
|
| 327 |
+
},
|
| 328 |
+
"model.layers.39.self_attn.indexer.wk": {
|
| 329 |
+
"bits": 16,
|
| 330 |
+
"data_type": "float"
|
| 331 |
+
},
|
| 332 |
+
"model.layers.40.self_attn.indexer.wq_b": {
|
| 333 |
+
"bits": 16,
|
| 334 |
+
"data_type": "float"
|
| 335 |
+
},
|
| 336 |
+
"model.layers.40.self_attn.indexer.wk": {
|
| 337 |
+
"bits": 16,
|
| 338 |
+
"data_type": "float"
|
| 339 |
+
},
|
| 340 |
+
"model.layers.41.self_attn.indexer.wq_b": {
|
| 341 |
+
"bits": 16,
|
| 342 |
+
"data_type": "float"
|
| 343 |
+
},
|
| 344 |
+
"model.layers.41.self_attn.indexer.wk": {
|
| 345 |
+
"bits": 16,
|
| 346 |
+
"data_type": "float"
|
| 347 |
+
},
|
| 348 |
+
"model.layers.42.self_attn.indexer.wq_b": {
|
| 349 |
+
"bits": 16,
|
| 350 |
+
"data_type": "float"
|
| 351 |
+
},
|
| 352 |
+
"model.layers.42.self_attn.indexer.wk": {
|
| 353 |
+
"bits": 16,
|
| 354 |
+
"data_type": "float"
|
| 355 |
+
},
|
| 356 |
+
"model.layers.43.self_attn.indexer.wq_b": {
|
| 357 |
+
"bits": 16,
|
| 358 |
+
"data_type": "float"
|
| 359 |
+
},
|
| 360 |
+
"model.layers.43.self_attn.indexer.wk": {
|
| 361 |
+
"bits": 16,
|
| 362 |
+
"data_type": "float"
|
| 363 |
+
},
|
| 364 |
+
"model.layers.44.self_attn.indexer.wq_b": {
|
| 365 |
+
"bits": 16,
|
| 366 |
+
"data_type": "float"
|
| 367 |
+
},
|
| 368 |
+
"model.layers.44.self_attn.indexer.wk": {
|
| 369 |
+
"bits": 16,
|
| 370 |
+
"data_type": "float"
|
| 371 |
+
},
|
| 372 |
+
"model.layers.45.self_attn.indexer.wq_b": {
|
| 373 |
+
"bits": 16,
|
| 374 |
+
"data_type": "float"
|
| 375 |
+
},
|
| 376 |
+
"model.layers.45.self_attn.indexer.wk": {
|
| 377 |
+
"bits": 16,
|
| 378 |
+
"data_type": "float"
|
| 379 |
+
},
|
| 380 |
+
"model.layers.46.self_attn.indexer.wq_b": {
|
| 381 |
+
"bits": 16,
|
| 382 |
+
"data_type": "float"
|
| 383 |
+
},
|
| 384 |
+
"model.layers.46.self_attn.indexer.wk": {
|
| 385 |
+
"bits": 16,
|
| 386 |
+
"data_type": "float"
|
| 387 |
+
},
|
| 388 |
+
"model.layers.47.self_attn.indexer.wq_b": {
|
| 389 |
+
"bits": 16,
|
| 390 |
+
"data_type": "float"
|
| 391 |
+
},
|
| 392 |
+
"model.layers.47.self_attn.indexer.wk": {
|
| 393 |
+
"bits": 16,
|
| 394 |
+
"data_type": "float"
|
| 395 |
+
},
|
| 396 |
+
"model.layers.48.self_attn.indexer.wq_b": {
|
| 397 |
+
"bits": 16,
|
| 398 |
+
"data_type": "float"
|
| 399 |
+
},
|
| 400 |
+
"model.layers.48.self_attn.indexer.wk": {
|
| 401 |
+
"bits": 16,
|
| 402 |
+
"data_type": "float"
|
| 403 |
+
},
|
| 404 |
+
"model.layers.49.self_attn.indexer.wq_b": {
|
| 405 |
+
"bits": 16,
|
| 406 |
+
"data_type": "float"
|
| 407 |
+
},
|
| 408 |
+
"model.layers.49.self_attn.indexer.wk": {
|
| 409 |
+
"bits": 16,
|
| 410 |
+
"data_type": "float"
|
| 411 |
+
},
|
| 412 |
+
"model.layers.50.self_attn.indexer.wq_b": {
|
| 413 |
+
"bits": 16,
|
| 414 |
+
"data_type": "float"
|
| 415 |
+
},
|
| 416 |
+
"model.layers.50.self_attn.indexer.wk": {
|
| 417 |
+
"bits": 16,
|
| 418 |
+
"data_type": "float"
|
| 419 |
+
},
|
| 420 |
+
"model.layers.51.self_attn.indexer.wq_b": {
|
| 421 |
+
"bits": 16,
|
| 422 |
+
"data_type": "float"
|
| 423 |
+
},
|
| 424 |
+
"model.layers.51.self_attn.indexer.wk": {
|
| 425 |
+
"bits": 16,
|
| 426 |
+
"data_type": "float"
|
| 427 |
+
},
|
| 428 |
+
"model.layers.52.self_attn.indexer.wq_b": {
|
| 429 |
+
"bits": 16,
|
| 430 |
+
"data_type": "float"
|
| 431 |
+
},
|
| 432 |
+
"model.layers.52.self_attn.indexer.wk": {
|
| 433 |
+
"bits": 16,
|
| 434 |
+
"data_type": "float"
|
| 435 |
+
},
|
| 436 |
+
"model.layers.53.self_attn.indexer.wq_b": {
|
| 437 |
+
"bits": 16,
|
| 438 |
+
"data_type": "float"
|
| 439 |
+
},
|
| 440 |
+
"model.layers.53.self_attn.indexer.wk": {
|
| 441 |
+
"bits": 16,
|
| 442 |
+
"data_type": "float"
|
| 443 |
+
},
|
| 444 |
+
"model.layers.54.self_attn.indexer.wq_b": {
|
| 445 |
+
"bits": 16,
|
| 446 |
+
"data_type": "float"
|
| 447 |
+
},
|
| 448 |
+
"model.layers.54.self_attn.indexer.wk": {
|
| 449 |
+
"bits": 16,
|
| 450 |
+
"data_type": "float"
|
| 451 |
+
},
|
| 452 |
+
"model.layers.55.self_attn.indexer.wq_b": {
|
| 453 |
+
"bits": 16,
|
| 454 |
+
"data_type": "float"
|
| 455 |
+
},
|
| 456 |
+
"model.layers.55.self_attn.indexer.wk": {
|
| 457 |
+
"bits": 16,
|
| 458 |
+
"data_type": "float"
|
| 459 |
+
},
|
| 460 |
+
"model.layers.56.self_attn.indexer.wq_b": {
|
| 461 |
+
"bits": 16,
|
| 462 |
+
"data_type": "float"
|
| 463 |
+
},
|
| 464 |
+
"model.layers.56.self_attn.indexer.wk": {
|
| 465 |
+
"bits": 16,
|
| 466 |
+
"data_type": "float"
|
| 467 |
+
},
|
| 468 |
+
"model.layers.57.self_attn.indexer.wq_b": {
|
| 469 |
+
"bits": 16,
|
| 470 |
+
"data_type": "float"
|
| 471 |
+
},
|
| 472 |
+
"model.layers.57.self_attn.indexer.wk": {
|
| 473 |
+
"bits": 16,
|
| 474 |
+
"data_type": "float"
|
| 475 |
+
},
|
| 476 |
+
"model.layers.58.self_attn.indexer.wq_b": {
|
| 477 |
+
"bits": 16,
|
| 478 |
+
"data_type": "float"
|
| 479 |
+
},
|
| 480 |
+
"model.layers.58.self_attn.indexer.wk": {
|
| 481 |
+
"bits": 16,
|
| 482 |
+
"data_type": "float"
|
| 483 |
+
},
|
| 484 |
+
"model.layers.59.self_attn.indexer.wq_b": {
|
| 485 |
+
"bits": 16,
|
| 486 |
+
"data_type": "float"
|
| 487 |
+
},
|
| 488 |
+
"model.layers.59.self_attn.indexer.wk": {
|
| 489 |
+
"bits": 16,
|
| 490 |
+
"data_type": "float"
|
| 491 |
+
},
|
| 492 |
+
"model.layers.60.self_attn.indexer.wq_b": {
|
| 493 |
+
"bits": 16,
|
| 494 |
+
"data_type": "float"
|
| 495 |
+
},
|
| 496 |
+
"model.layers.60.self_attn.indexer.wk": {
|
| 497 |
+
"bits": 16,
|
| 498 |
+
"data_type": "float"
|
| 499 |
+
}
|
| 500 |
+
}
|
| 501 |
+
}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<|begin▁of▁sentence|>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<|end▁of▁sentence|>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "<|end▁of▁sentence|>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
}
|
| 23 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|