Add files using upload-large-folder tool
Browse files- config.json +116 -0
- model-00001-of-00527.safetensors +3 -0
- model-00026-of-00527.safetensors +3 -0
- model-00039-of-00527.safetensors +3 -0
- model-00044-of-00527.safetensors +3 -0
- model-00045-of-00527.safetensors +3 -0
- model-00049-of-00527.safetensors +3 -0
- model-00056-of-00527.safetensors +3 -0
- model-00069-of-00527.safetensors +3 -0
- model-00076-of-00527.safetensors +3 -0
- model-00083-of-00527.safetensors +3 -0
- model-00085-of-00527.safetensors +3 -0
- model-00088-of-00527.safetensors +3 -0
- model-00098-of-00527.safetensors +3 -0
- model-00100-of-00527.safetensors +3 -0
- model-00106-of-00527.safetensors +3 -0
- model-00111-of-00527.safetensors +3 -0
- model-00127-of-00527.safetensors +3 -0
- model-00137-of-00527.safetensors +3 -0
- model-00139-of-00527.safetensors +3 -0
- model-00158-of-00527.safetensors +3 -0
- model-00194-of-00527.safetensors +3 -0
- model-00202-of-00527.safetensors +3 -0
- model-00258-of-00527.safetensors +3 -0
- model-00259-of-00527.safetensors +3 -0
- model-00262-of-00527.safetensors +3 -0
- model-00276-of-00527.safetensors +3 -0
- model-00287-of-00527.safetensors +3 -0
- model-00307-of-00527.safetensors +3 -0
- model-00326-of-00527.safetensors +3 -0
- model-00327-of-00527.safetensors +3 -0
- model-00341-of-00527.safetensors +3 -0
- model-00353-of-00527.safetensors +3 -0
- model-00356-of-00527.safetensors +3 -0
- model-00365-of-00527.safetensors +3 -0
- model-00367-of-00527.safetensors +3 -0
- model-00369-of-00527.safetensors +3 -0
- model-00386-of-00527.safetensors +3 -0
- model-00387-of-00527.safetensors +3 -0
- model-00391-of-00527.safetensors +3 -0
- model-00397-of-00527.safetensors +3 -0
- model-00412-of-00527.safetensors +3 -0
- model-00428-of-00527.safetensors +3 -0
- model-00449-of-00527.safetensors +3 -0
- model-00470-of-00527.safetensors +3 -0
- model-00507-of-00527.safetensors +3 -0
- model-00516-of-00527.safetensors +3 -0
- model-00519-of-00527.safetensors +3 -0
- special_tokens_map.json +40 -0
- tokenizer_config.json +180 -0
config.json
ADDED
|
@@ -0,0 +1,116 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_attn_implementation_autoset": false,
|
| 3 |
+
"architectures": [
|
| 4 |
+
"DeepseekV3ForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_bias": false,
|
| 7 |
+
"attention_dropout": 0.0,
|
| 8 |
+
"auto_map": {
|
| 9 |
+
"AutoConfig": "configuration_deepseek.DeepseekV3Config",
|
| 10 |
+
"AutoModel": "modeling_deepseek.DeepseekV3Model",
|
| 11 |
+
"AutoModelForCausalLM": "modeling_deepseek.DeepseekV3ForCausalLM"
|
| 12 |
+
},
|
| 13 |
+
"aux_loss_alpha": 0.001,
|
| 14 |
+
"bos_token_id": 163584,
|
| 15 |
+
"dtype": "bfloat16",
|
| 16 |
+
"eos_token_id": 163586,
|
| 17 |
+
"ep_size": 1,
|
| 18 |
+
"first_k_dense_replace": 1,
|
| 19 |
+
"hidden_act": "silu",
|
| 20 |
+
"hidden_size": 7168,
|
| 21 |
+
"initializer_range": 0.02,
|
| 22 |
+
"intermediate_size": 18432,
|
| 23 |
+
"kv_lora_rank": 512,
|
| 24 |
+
"max_position_embeddings": 262144,
|
| 25 |
+
"model_type": "deepseek_v3",
|
| 26 |
+
"moe_intermediate_size": 2048,
|
| 27 |
+
"moe_layer_freq": 1,
|
| 28 |
+
"n_group": 1,
|
| 29 |
+
"n_routed_experts": 384,
|
| 30 |
+
"n_shared_experts": 1,
|
| 31 |
+
"norm_topk_prob": true,
|
| 32 |
+
"num_attention_heads": 64,
|
| 33 |
+
"num_experts_per_tok": 8,
|
| 34 |
+
"num_hidden_layers": 61,
|
| 35 |
+
"num_key_value_heads": 64,
|
| 36 |
+
"num_nextn_predict_layers": 0,
|
| 37 |
+
"pad_token_id": 163839,
|
| 38 |
+
"pretraining_tp": 1,
|
| 39 |
+
"q_lora_rank": 1536,
|
| 40 |
+
"qk_nope_head_dim": 128,
|
| 41 |
+
"qk_rope_head_dim": 64,
|
| 42 |
+
"quantization_config": {
|
| 43 |
+
"config_groups": {
|
| 44 |
+
"FP8_BLOCK": {
|
| 45 |
+
"format": "float-quantized",
|
| 46 |
+
"input_activations": {
|
| 47 |
+
"actorder": null,
|
| 48 |
+
"block_structure": null,
|
| 49 |
+
"dynamic": true,
|
| 50 |
+
"group_size": 128,
|
| 51 |
+
"num_bits": 8,
|
| 52 |
+
"observer": null,
|
| 53 |
+
"observer_kwargs": {},
|
| 54 |
+
"strategy": "group",
|
| 55 |
+
"symmetric": true,
|
| 56 |
+
"type": "float"
|
| 57 |
+
},
|
| 58 |
+
"output_activations": null,
|
| 59 |
+
"targets": [
|
| 60 |
+
"Linear"
|
| 61 |
+
],
|
| 62 |
+
"weights": {
|
| 63 |
+
"actorder": null,
|
| 64 |
+
"block_structure": [
|
| 65 |
+
128,
|
| 66 |
+
128
|
| 67 |
+
],
|
| 68 |
+
"dynamic": false,
|
| 69 |
+
"group_size": null,
|
| 70 |
+
"num_bits": 8,
|
| 71 |
+
"observer": "static_minmax",
|
| 72 |
+
"observer_kwargs": {},
|
| 73 |
+
"strategy": "block",
|
| 74 |
+
"symmetric": true,
|
| 75 |
+
"type": "float"
|
| 76 |
+
}
|
| 77 |
+
}
|
| 78 |
+
},
|
| 79 |
+
"format": "float-quantized",
|
| 80 |
+
"global_compression_ratio": null,
|
| 81 |
+
"ignore": [
|
| 82 |
+
"re:.*gate$",
|
| 83 |
+
"lm_head",
|
| 84 |
+
"re:.*kv_a_proj_with_mqa$",
|
| 85 |
+
"re:.*q_a_proj$",
|
| 86 |
+
"model.embed_tokens"
|
| 87 |
+
],
|
| 88 |
+
"kv_cache_scheme": null,
|
| 89 |
+
"quant_method": "compressed-tensors",
|
| 90 |
+
"quantization_status": "compressed",
|
| 91 |
+
"sparsity_config": {},
|
| 92 |
+
"transform_config": {},
|
| 93 |
+
"version": "0.12.3.a20251030"
|
| 94 |
+
},
|
| 95 |
+
"rms_norm_eps": 1e-05,
|
| 96 |
+
"rope_scaling": {
|
| 97 |
+
"beta_fast": 1.0,
|
| 98 |
+
"beta_slow": 1.0,
|
| 99 |
+
"factor": 64.0,
|
| 100 |
+
"mscale": 1.0,
|
| 101 |
+
"mscale_all_dim": 1.0,
|
| 102 |
+
"original_max_position_embeddings": 4096,
|
| 103 |
+
"type": "yarn"
|
| 104 |
+
},
|
| 105 |
+
"rope_theta": 50000.0,
|
| 106 |
+
"routed_scaling_factor": 2.827,
|
| 107 |
+
"scoring_func": "sigmoid",
|
| 108 |
+
"seq_aux": true,
|
| 109 |
+
"tie_word_embeddings": false,
|
| 110 |
+
"topk_group": 1,
|
| 111 |
+
"topk_method": "noaux_tc",
|
| 112 |
+
"transformers_version": "4.57.1",
|
| 113 |
+
"use_cache": true,
|
| 114 |
+
"v_head_dim": 128,
|
| 115 |
+
"vocab_size": 163840
|
| 116 |
+
}
|
model-00001-of-00527.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:19efd1edde96997487ee906ea5080020288522b2de315a9baf4bb60e52c6c1b7
|
| 3 |
+
size 3535723512
|
model-00026-of-00527.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d14a74cc175f94aec0a865274afbe735df73ea0a436b214c0f812448e1523772
|
| 3 |
+
size 1952719528
|
model-00039-of-00527.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c534e19901d865f2648c25567319a299ed73815267ad0dbc697e2f5018047ec5
|
| 3 |
+
size 1938037416
|
model-00044-of-00527.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:07935137ca1bdbb5e1c162206689b9e97ba8cf8856441c07bb058a0e565d9c5b
|
| 3 |
+
size 1952719528
|
model-00045-of-00527.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f3840d976cc43816b5b052b3a13f55ff84ab754deff8dae28d7929b7a170104b
|
| 3 |
+
size 2001120536
|
model-00049-of-00527.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c563949ddd5b01264c1826cff061bc09c0c1c5024cbd41eaa666cb3c9288ce32
|
| 3 |
+
size 1952719528
|
model-00056-of-00527.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bd9e5ca19606d9f616080cdf930fc43318dd9483d0bde8c038089195bd4148ac
|
| 3 |
+
size 1952719400
|
model-00069-of-00527.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bc642ab5205b96503dfd7a5d5d7953f03d59579bec528559b96796eeb5980716
|
| 3 |
+
size 1952719520
|
model-00076-of-00527.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6aa9cdd603f21f571673036f02e68a1acf535956b707328252a992fe98dbaef1
|
| 3 |
+
size 1952719528
|
model-00083-of-00527.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ed83779b90a0636dadc936ea59c3658de49520a73492bca53012760faea1583a
|
| 3 |
+
size 1952719792
|
model-00085-of-00527.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:183e6d875d54d7b68c8da28f30b7e4c9072697539c71ad3556e910778790cbd8
|
| 3 |
+
size 1952719792
|
model-00088-of-00527.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:21d7fcc1ba596270e3f20a239ad0acda7f7f37bfbcc5bc478aecb6e191f7707b
|
| 3 |
+
size 1938037680
|
model-00098-of-00527.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5418f3fd6e589a2a6bc97f86c591b1ceed6bc95f2a075d904e61ecd44d148aa0
|
| 3 |
+
size 1938037368
|
model-00100-of-00527.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b2e0a99f98157f6ac4676a7741036ccf27be5b87f772f0021dd1a07b1eb41b90
|
| 3 |
+
size 1938037624
|
model-00106-of-00527.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c8d945df87546b5cf9bd02acad9f21e4ea1b1578d0a059966ff4b99d48584cfc
|
| 3 |
+
size 2001120808
|
model-00111-of-00527.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1c6c8fc1fc247b7610fd9f737a7279b4ebfe20cfe8ab6fc7f4cf0c4754c1dd98
|
| 3 |
+
size 1938037680
|
model-00127-of-00527.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:eabdc7725922e642ff439e6242fd3cbdc2a2a9f151dbc27301b43eb6773d7678
|
| 3 |
+
size 1938037680
|
model-00137-of-00527.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aa3f275a2fd969d77d0e3b09d79857c33f5b4e0e29926afca87609cc1da44d86
|
| 3 |
+
size 1952719792
|
model-00139-of-00527.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6f1c130509b75352b102b1d9cfcad7d8cff4dc94810242ecd19ca2444eca9181
|
| 3 |
+
size 1952719792
|
model-00158-of-00527.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f371443aadc07007bf000510778f4b22ff0b092bd847b4e85a4ee548edf14372
|
| 3 |
+
size 1938037680
|
model-00194-of-00527.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d50fe61061027a148f5cb5f544ab92c2b507d63e26f3a53a40a5540a40c02849
|
| 3 |
+
size 2001120848
|
model-00202-of-00527.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:66cb85cba5c0eae713413ad91076e016304ce28d22851af44f52b853dda3b217
|
| 3 |
+
size 2001120864
|
model-00258-of-00527.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3568d742bceffa05ee785178a0453df96ced117b5c70baebeeda1aabe083dd0d
|
| 3 |
+
size 1938037680
|
model-00259-of-00527.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6d96e69dce2fcdaaed6e4d1c0436e153b0ad30ebee156ab3a02eb17030511d77
|
| 3 |
+
size 1952719792
|
model-00262-of-00527.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6c17b919033729b2b57eae26e5b16285d7a3bcbb313d726105055c87d70e8476
|
| 3 |
+
size 1938037680
|
model-00276-of-00527.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:87e048bc803061f5860efafdff6308e9b539fe958b5cd9dd2d40e99aebafcd53
|
| 3 |
+
size 1938037680
|
model-00287-of-00527.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:67a7d866b1978187bb89407bb7d0279600c7a8155487e255ae74a25302a1abdb
|
| 3 |
+
size 1938037680
|
model-00307-of-00527.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0d8975afa0d9357d1ce1c3306d016089b9813ddd075b3d261f8967bfe04df741
|
| 3 |
+
size 2001120864
|
model-00326-of-00527.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d5428addcb509651f6c405e0bfb530f610a61128a8b03bdc3557e90543397090
|
| 3 |
+
size 1938037416
|
model-00327-of-00527.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7cb8850bd096aac93f2af8ccba05bab60542c308e2d1995940bcc76b39fe781e
|
| 3 |
+
size 1952719584
|
model-00341-of-00527.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:085a4f316ba4619575bebe42aa3394175a6cedb51705ca32d5cce3b7dee19778
|
| 3 |
+
size 1938037680
|
model-00353-of-00527.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:73215bcf70f13f127b727f3f027cb804491999d6d9dff87d0f7402b65168f240
|
| 3 |
+
size 1938037416
|
model-00356-of-00527.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b29be3342c84de046f407c45bdb342d21cb534c10210138e5c0e81990cd1b606
|
| 3 |
+
size 1952719792
|
model-00365-of-00527.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d0802bbdb2f50cd03cdb902d69c2489f746d11d7a67607863db8f1d424d9b6d8
|
| 3 |
+
size 1952719792
|
model-00367-of-00527.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:39704a18d1fbd04467d0812435b3afe31361274ea9a5be35e4732b7ca15fe5da
|
| 3 |
+
size 1952719792
|
model-00369-of-00527.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:34b5f2ef3627e4847df5cadda271d83ec05482fc9dce84b22435305a85881b31
|
| 3 |
+
size 2001120848
|
model-00386-of-00527.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:83a4f3f804f1531afc106a16920f3414ae482bdd803214051adbef04648500b6
|
| 3 |
+
size 2001120808
|
model-00387-of-00527.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7f4834b66223b2c5f4caf5a49950599f41e4c244aed6b7edccb0d2136a2b3f6a
|
| 3 |
+
size 1938037416
|
model-00391-of-00527.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8ef61f58ffb1f2b040a808345c97eb66968e2055a77814fdfa0988409f8f9e65
|
| 3 |
+
size 1938037680
|
model-00397-of-00527.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1ea6c01dfbd2e92913313190110435ae125b764f87a4ffea9c70d16303edd330
|
| 3 |
+
size 1952719584
|
model-00412-of-00527.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e6703649c368eb952f5e54e13a4c958b4858f28eaeb5d29943bde90c726ed5bd
|
| 3 |
+
size 1957075312
|
model-00428-of-00527.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c5137e30d4722a92b84bd6770444139ef09e813aa62e1030926dded5fcb422f4
|
| 3 |
+
size 1938037680
|
model-00449-of-00527.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8efb2a5724de5dbbb3aecacfaea5a7b0324ca0869bc4a30c80875db869ed05e0
|
| 3 |
+
size 1938037416
|
model-00470-of-00527.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0ea409aece294262b4534cc866db334f87b7dbf12dbdac58f9029315854f7ac4
|
| 3 |
+
size 1952719784
|
model-00507-of-00527.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:42f402eb343a1515a6c6a0c6daa776e551b3ff5f9767a11568a25f1e441ceba8
|
| 3 |
+
size 1952719784
|
model-00516-of-00527.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d072b3e8a606f7549a992bdc8599ddbbbdc133446dfb9aa6064f2c8e605b35f2
|
| 3 |
+
size 1952719784
|
model-00519-of-00527.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:38222929477b4b1ff24522f05451e61c5dd33505284f31ef6e436713a53241a4
|
| 3 |
+
size 1952719520
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|im_end|>",
|
| 4 |
+
"<|im_user|>",
|
| 5 |
+
"<|im_assistant|>",
|
| 6 |
+
"<|start_header_id|>",
|
| 7 |
+
"<|end_header_id|>",
|
| 8 |
+
"[EOT]",
|
| 9 |
+
"<|im_system|>",
|
| 10 |
+
"<|im_middle|>"
|
| 11 |
+
],
|
| 12 |
+
"bos_token": {
|
| 13 |
+
"content": "[BOS]",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": false,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false
|
| 18 |
+
},
|
| 19 |
+
"eos_token": {
|
| 20 |
+
"content": "[EOS]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false
|
| 25 |
+
},
|
| 26 |
+
"pad_token": {
|
| 27 |
+
"content": "[PAD]",
|
| 28 |
+
"lstrip": false,
|
| 29 |
+
"normalized": false,
|
| 30 |
+
"rstrip": false,
|
| 31 |
+
"single_word": false
|
| 32 |
+
},
|
| 33 |
+
"unk_token": {
|
| 34 |
+
"content": "[UNK]",
|
| 35 |
+
"lstrip": false,
|
| 36 |
+
"normalized": false,
|
| 37 |
+
"rstrip": false,
|
| 38 |
+
"single_word": false
|
| 39 |
+
}
|
| 40 |
+
}
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,180 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"163584": {
|
| 4 |
+
"content": "[BOS]",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"163585": {
|
| 12 |
+
"content": "[EOS]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"163586": {
|
| 20 |
+
"content": "<|im_end|>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"163587": {
|
| 28 |
+
"content": "<|im_user|>",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"163588": {
|
| 36 |
+
"content": "<|im_assistant|>",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
},
|
| 43 |
+
"163590": {
|
| 44 |
+
"content": "<|start_header_id|>",
|
| 45 |
+
"lstrip": false,
|
| 46 |
+
"normalized": false,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"single_word": false,
|
| 49 |
+
"special": true
|
| 50 |
+
},
|
| 51 |
+
"163591": {
|
| 52 |
+
"content": "<|end_header_id|>",
|
| 53 |
+
"lstrip": false,
|
| 54 |
+
"normalized": false,
|
| 55 |
+
"rstrip": false,
|
| 56 |
+
"single_word": false,
|
| 57 |
+
"special": true
|
| 58 |
+
},
|
| 59 |
+
"163593": {
|
| 60 |
+
"content": "[EOT]",
|
| 61 |
+
"lstrip": false,
|
| 62 |
+
"normalized": false,
|
| 63 |
+
"rstrip": false,
|
| 64 |
+
"single_word": false,
|
| 65 |
+
"special": true
|
| 66 |
+
},
|
| 67 |
+
"163594": {
|
| 68 |
+
"content": "<|im_system|>",
|
| 69 |
+
"lstrip": false,
|
| 70 |
+
"normalized": false,
|
| 71 |
+
"rstrip": false,
|
| 72 |
+
"single_word": false,
|
| 73 |
+
"special": true
|
| 74 |
+
},
|
| 75 |
+
"163595": {
|
| 76 |
+
"content": "<|tool_calls_section_begin|>",
|
| 77 |
+
"lstrip": false,
|
| 78 |
+
"normalized": false,
|
| 79 |
+
"rstrip": false,
|
| 80 |
+
"single_word": false,
|
| 81 |
+
"special": false
|
| 82 |
+
},
|
| 83 |
+
"163596": {
|
| 84 |
+
"content": "<|tool_calls_section_end|>",
|
| 85 |
+
"lstrip": false,
|
| 86 |
+
"normalized": false,
|
| 87 |
+
"rstrip": false,
|
| 88 |
+
"single_word": false,
|
| 89 |
+
"special": false
|
| 90 |
+
},
|
| 91 |
+
"163597": {
|
| 92 |
+
"content": "<|tool_call_begin|>",
|
| 93 |
+
"lstrip": false,
|
| 94 |
+
"normalized": false,
|
| 95 |
+
"rstrip": false,
|
| 96 |
+
"single_word": false,
|
| 97 |
+
"special": false
|
| 98 |
+
},
|
| 99 |
+
"163598": {
|
| 100 |
+
"content": "<|tool_call_argument_begin|>",
|
| 101 |
+
"lstrip": false,
|
| 102 |
+
"normalized": false,
|
| 103 |
+
"rstrip": false,
|
| 104 |
+
"single_word": false,
|
| 105 |
+
"special": false
|
| 106 |
+
},
|
| 107 |
+
"163599": {
|
| 108 |
+
"content": "<|tool_call_end|>",
|
| 109 |
+
"lstrip": false,
|
| 110 |
+
"normalized": false,
|
| 111 |
+
"rstrip": false,
|
| 112 |
+
"single_word": false,
|
| 113 |
+
"special": false
|
| 114 |
+
},
|
| 115 |
+
"163601": {
|
| 116 |
+
"content": "<|im_middle|>",
|
| 117 |
+
"lstrip": false,
|
| 118 |
+
"normalized": false,
|
| 119 |
+
"rstrip": false,
|
| 120 |
+
"single_word": false,
|
| 121 |
+
"special": true
|
| 122 |
+
},
|
| 123 |
+
"163606": {
|
| 124 |
+
"content": "<think>",
|
| 125 |
+
"lstrip": false,
|
| 126 |
+
"normalized": false,
|
| 127 |
+
"rstrip": false,
|
| 128 |
+
"single_word": false,
|
| 129 |
+
"special": false
|
| 130 |
+
},
|
| 131 |
+
"163607": {
|
| 132 |
+
"content": "</think>",
|
| 133 |
+
"lstrip": false,
|
| 134 |
+
"normalized": false,
|
| 135 |
+
"rstrip": false,
|
| 136 |
+
"single_word": false,
|
| 137 |
+
"special": false
|
| 138 |
+
},
|
| 139 |
+
"163838": {
|
| 140 |
+
"content": "[UNK]",
|
| 141 |
+
"lstrip": false,
|
| 142 |
+
"normalized": false,
|
| 143 |
+
"rstrip": false,
|
| 144 |
+
"single_word": false,
|
| 145 |
+
"special": true
|
| 146 |
+
},
|
| 147 |
+
"163839": {
|
| 148 |
+
"content": "[PAD]",
|
| 149 |
+
"lstrip": false,
|
| 150 |
+
"normalized": false,
|
| 151 |
+
"rstrip": false,
|
| 152 |
+
"single_word": false,
|
| 153 |
+
"special": true
|
| 154 |
+
}
|
| 155 |
+
},
|
| 156 |
+
"additional_special_tokens": [
|
| 157 |
+
"<|im_end|>",
|
| 158 |
+
"<|im_user|>",
|
| 159 |
+
"<|im_assistant|>",
|
| 160 |
+
"<|start_header_id|>",
|
| 161 |
+
"<|end_header_id|>",
|
| 162 |
+
"[EOT]",
|
| 163 |
+
"<|im_system|>",
|
| 164 |
+
"<|im_middle|>"
|
| 165 |
+
],
|
| 166 |
+
"auto_map": {
|
| 167 |
+
"AutoTokenizer": [
|
| 168 |
+
"tokenization_kimi.TikTokenTokenizer",
|
| 169 |
+
null
|
| 170 |
+
]
|
| 171 |
+
},
|
| 172 |
+
"bos_token": "[BOS]",
|
| 173 |
+
"clean_up_tokenization_spaces": false,
|
| 174 |
+
"eos_token": "[EOS]",
|
| 175 |
+
"extra_special_tokens": {},
|
| 176 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 177 |
+
"pad_token": "[PAD]",
|
| 178 |
+
"tokenizer_class": "TikTokenTokenizer",
|
| 179 |
+
"unk_token": "[UNK]"
|
| 180 |
+
}
|