Add files using upload-large-folder tool
Browse files- config.json +67 -0
- model-00001-of-00135.safetensors +3 -0
- model-00002-of-00135.safetensors +3 -0
- model-00003-of-00135.safetensors +3 -0
- model-00004-of-00135.safetensors +3 -0
- model-00005-of-00135.safetensors +3 -0
- model-00006-of-00135.safetensors +3 -0
- model-00007-of-00135.safetensors +3 -0
- model-00008-of-00135.safetensors +3 -0
- model-00009-of-00135.safetensors +3 -0
- model-00010-of-00135.safetensors +3 -0
- model-00011-of-00135.safetensors +3 -0
- model-00012-of-00135.safetensors +3 -0
- model-00013-of-00135.safetensors +3 -0
- model-00014-of-00135.safetensors +3 -0
- model-00015-of-00135.safetensors +3 -0
- model-00016-of-00135.safetensors +3 -0
- model-00017-of-00135.safetensors +3 -0
- model-00018-of-00135.safetensors +3 -0
- model-00019-of-00135.safetensors +3 -0
- model-00020-of-00135.safetensors +3 -0
- model-00021-of-00135.safetensors +3 -0
- model-00022-of-00135.safetensors +3 -0
- model-00023-of-00135.safetensors +3 -0
- model-00024-of-00135.safetensors +3 -0
- model-00025-of-00135.safetensors +3 -0
- model-00026-of-00135.safetensors +3 -0
- model-00027-of-00135.safetensors +3 -0
- model-00028-of-00135.safetensors +3 -0
- model-00029-of-00135.safetensors +3 -0
- model-00030-of-00135.safetensors +3 -0
- model-00031-of-00135.safetensors +3 -0
- model-00032-of-00135.safetensors +3 -0
- model-00033-of-00135.safetensors +3 -0
- model-00034-of-00135.safetensors +3 -0
- model-00035-of-00135.safetensors +3 -0
- model-00036-of-00135.safetensors +3 -0
- model-00037-of-00135.safetensors +3 -0
- model-00038-of-00135.safetensors +3 -0
- model-00039-of-00135.safetensors +3 -0
- model-00040-of-00135.safetensors +3 -0
- model-00041-of-00135.safetensors +3 -0
- model-00042-of-00135.safetensors +3 -0
- model-00043-of-00135.safetensors +3 -0
- model-00044-of-00135.safetensors +3 -0
- model-00045-of-00135.safetensors +3 -0
- model-00046-of-00135.safetensors +3 -0
- model.safetensors.index.json +0 -0
- tokenizer.json +0 -0
- tokenizer_config.json +35 -0
config.json
ADDED
|
@@ -0,0 +1,67 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"DeepseekV3ForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"auto_map": {
|
| 8 |
+
"AutoConfig": "configuration_deepseek.DeepseekV3Config",
|
| 9 |
+
"AutoModel": "modeling_deepseek.DeepseekV3Model",
|
| 10 |
+
"AutoModelForCausalLM": "modeling_deepseek.DeepseekV3ForCausalLM"
|
| 11 |
+
},
|
| 12 |
+
"bos_token_id": 0,
|
| 13 |
+
"eos_token_id": 1,
|
| 14 |
+
"ep_size": 1,
|
| 15 |
+
"first_k_dense_replace": 3,
|
| 16 |
+
"hidden_act": "silu",
|
| 17 |
+
"hidden_size": 7168,
|
| 18 |
+
"initializer_range": 0.02,
|
| 19 |
+
"intermediate_size": 18432,
|
| 20 |
+
"kv_lora_rank": 512,
|
| 21 |
+
"max_position_embeddings": 163840,
|
| 22 |
+
"model_type": "deepseek_v3",
|
| 23 |
+
"moe_intermediate_size": 2048,
|
| 24 |
+
"moe_layer_freq": 1,
|
| 25 |
+
"n_group": 8,
|
| 26 |
+
"n_routed_experts": 256,
|
| 27 |
+
"n_shared_experts": 1,
|
| 28 |
+
"norm_topk_prob": true,
|
| 29 |
+
"num_attention_heads": 128,
|
| 30 |
+
"num_experts_per_tok": 8,
|
| 31 |
+
"num_hidden_layers": 61,
|
| 32 |
+
"num_key_value_heads": 128,
|
| 33 |
+
"num_nextn_predict_layers": 1,
|
| 34 |
+
"q_lora_rank": 1536,
|
| 35 |
+
"qk_nope_head_dim": 128,
|
| 36 |
+
"qk_rope_head_dim": 64,
|
| 37 |
+
"quantization_config": {
|
| 38 |
+
"activation_scheme": "dynamic",
|
| 39 |
+
"fmt": "e4m3",
|
| 40 |
+
"quant_method": "fp8",
|
| 41 |
+
"weight_block_size": [
|
| 42 |
+
128,
|
| 43 |
+
128
|
| 44 |
+
]
|
| 45 |
+
},
|
| 46 |
+
"rms_norm_eps": 1e-06,
|
| 47 |
+
"rope_scaling": {
|
| 48 |
+
"beta_fast": 32,
|
| 49 |
+
"beta_slow": 1,
|
| 50 |
+
"factor": 40,
|
| 51 |
+
"mscale": 1.0,
|
| 52 |
+
"mscale_all_dim": 1.0,
|
| 53 |
+
"original_max_position_embeddings": 4096,
|
| 54 |
+
"type": "yarn"
|
| 55 |
+
},
|
| 56 |
+
"rope_theta": 10000,
|
| 57 |
+
"routed_scaling_factor": 2.5,
|
| 58 |
+
"scoring_func": "sigmoid",
|
| 59 |
+
"tie_word_embeddings": false,
|
| 60 |
+
"topk_group": 4,
|
| 61 |
+
"topk_method": "noaux_tc",
|
| 62 |
+
"torch_dtype": "bfloat16",
|
| 63 |
+
"transformers_version": "4.33.1",
|
| 64 |
+
"use_cache": true,
|
| 65 |
+
"v_head_dim": 128,
|
| 66 |
+
"vocab_size": 129280
|
| 67 |
+
}
|
model-00001-of-00135.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c30ecdf1881201f9311342dcd515ac7e8678be8d48aabf6ad34f8c45f02123d8
|
| 3 |
+
size 4894921824
|
model-00002-of-00135.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8bad6cb7b9acdeb0d806ca68f0f9046d02141fab8aceb3afe24df15d715e25e0
|
| 3 |
+
size 4933686504
|
model-00003-of-00135.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6d184534e5a5b0d0401f0a7f65edf3f5a072d6b03bccec00ac0e82ad28a97f72
|
| 3 |
+
size 4933686504
|
model-00004-of-00135.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1e29231fdcf5e395eac897d18731639e2191a1c871ab388af5b39a83019c57ab
|
| 3 |
+
size 4933686504
|
model-00005-of-00135.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c098e3e115320b21a31e0d79be43d9e4779952e33f4b296864ebaf25deea11a5
|
| 3 |
+
size 4993477416
|
model-00006-of-00135.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a9eb6c464bcab1b47fb0d6aa332e3bed7de9e99c4e020af16193289fa0206003
|
| 3 |
+
size 4992422104
|
model-00007-of-00135.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0ae2be20d73175651112e934286daea170799a0ebaf736625e7dbe38f07b9a2c
|
| 3 |
+
size 4992422104
|
model-00008-of-00135.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4b6974cbdc6b0e115fe376e8e7c625fc195c6f0659be65e4eeca87ef37b46dc8
|
| 3 |
+
size 4992421944
|
model-00009-of-00135.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2d787467c9d8f896abaf471e6e80af2d3af3252a0d3319deba6e04fcc5a6efd8
|
| 3 |
+
size 4992422056
|
model-00010-of-00135.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:72771c348818762ff4386f9869094bc1284b934a920e5bc111f65276ced88902
|
| 3 |
+
size 4992422104
|
model-00011-of-00135.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c68d1eb2ceed52d76fdee185a71001c0ec50b003f6bce3e467706ba3526ae0de
|
| 3 |
+
size 4992422104
|
model-00012-of-00135.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3b4b37f4a52b69bed85694fb94dcf67ea5d9fc4841df43ed434a95709a58177e
|
| 3 |
+
size 4992421880
|
model-00013-of-00135.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:28c4e0d67b2de032b89c4f2d6939ccd31cbcc67d341fbcccc11d53e20696bb42
|
| 3 |
+
size 4996092864
|
model-00014-of-00135.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a8abdfcf8e83e8c2c3acd3685eac2ebbf553aed1acb9afe6228e43302e99c184
|
| 3 |
+
size 4983984800
|
model-00015-of-00135.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e696d0d7538106bed327ad3475f5bc3f997f5db1733c10e42425969382960753
|
| 3 |
+
size 4933686496
|
model-00016-of-00135.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:228e6c244e9e74824d471c11b3700caec43f848ed0b710934bcbf28f35f4e515
|
| 3 |
+
size 4933686296
|
model-00017-of-00135.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:baeaff312a1a1397417ffe1a95a6f7346af370224b32e27c66f55b6acd70d4a4
|
| 3 |
+
size 4933686504
|
model-00018-of-00135.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:517c2442abf7a945005e79497b7da9bf6326a36a8a503f8a068eff8896143c61
|
| 3 |
+
size 4933686504
|
model-00019-of-00135.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d7f89f865500aad7969f1a3dd95aa889f0352d4d0fdf9c62e6a05561eca62ae6
|
| 3 |
+
size 4933686288
|
model-00020-of-00135.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5303e4afed8d5bc1e654368dcabbcb5aa4a154916b60231127bed478b07d00c3
|
| 3 |
+
size 4933686072
|
model-00021-of-00135.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:518481a0d4740360d721d189f8e6ae0e96d85cdfaa7282d1efce0acc25fd7236
|
| 3 |
+
size 4986273104
|
model-00022-of-00135.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:04de265cc3ae6f76da9211197f6deedbf1fd9ecd18331e633a5c74fadffa5e40
|
| 3 |
+
size 4992525496
|
model-00023-of-00135.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f59f64c158b70f540fd312f723a2478a98e422d0a2fa6bf8f4fcc161ca6f088b
|
| 3 |
+
size 4992525496
|
model-00024-of-00135.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fa530afaa8565d4e62292fc946e6f94545e20471b9d7bc8639dc7639ee6f5462
|
| 3 |
+
size 4992525496
|
model-00025-of-00135.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e4187241ee99e3c444d75b28ec973cc3aa08c386c3a3364d5a3733bf36eb20e4
|
| 3 |
+
size 4992525496
|
model-00026-of-00135.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0ab2f5aab5bb97c0426a70d25d3c90200412ff3053a7286005b8b67b3660de5e
|
| 3 |
+
size 4992525480
|
model-00027-of-00135.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:93d8ce7043e77f4d37f1668082825acddc6c0f0f072cc319a8e09797c2377607
|
| 3 |
+
size 4992525328
|
model-00028-of-00135.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9644d4e8a5796b25be9a4d40bacbd355cec0f357d63dca7165321b0a0903ef04
|
| 3 |
+
size 4992525496
|
model-00029-of-00135.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f9f203756a6c983f1c4664bdc07b00fd31c489627b9e636bef9fe88a9f105f7b
|
| 3 |
+
size 4992525496
|
model-00030-of-00135.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:db1c9cdf9e585be7a38e86aeaae038a8c400e8a410b063c921d5bf8ae9d08286
|
| 3 |
+
size 4992525304
|
model-00031-of-00135.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b8f53f7d04a7a3c475d1b0e60ac53c72df7eaec584fc0172d34238a29e91ffaa
|
| 3 |
+
size 4992525496
|
model-00032-of-00135.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b83ab02e071804bc38e2d39bf1a750f7be4b9f46e94f2c8c73338f20c91ec895
|
| 3 |
+
size 4992525496
|
model-00033-of-00135.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:62daa64b2b6e17890a2febad2367e99104d1ae93abc79c1e34ae98b3483fa0dc
|
| 3 |
+
size 4992525304
|
model-00034-of-00135.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ecac06d70678d1272c1813f813745cb37e9817d0ddf4c7b13fd1154f5d36f3bd
|
| 3 |
+
size 4992525496
|
model-00035-of-00135.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7baa6956d1513a3c72da102912bc785be67a611e105029f361bb8b337cff8725
|
| 3 |
+
size 4992525496
|
model-00036-of-00135.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:48ebf0d363d1a3b3984e02dc682977beeb866e60f14ae78c316430821542e459
|
| 3 |
+
size 4992525208
|
model-00037-of-00135.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6b1899809272b57c2ca4521f8aeca014299e570200ea68daf530f61a9c6b840b
|
| 3 |
+
size 4992525024
|
model-00038-of-00135.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:405372e270652b7b7f6a7d36dbf8afbaebeef5a6fad1da83885e65d3433087d5
|
| 3 |
+
size 4992525496
|
model-00039-of-00135.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3656e7b56e94efbc76e82e6a09c78df5f82cc070013158e48b78ce6057254963
|
| 3 |
+
size 4992525496
|
model-00040-of-00135.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:afa075001a27e1387f1325510c9422a6e02a13838fed61840d58a6b32d6c3f0b
|
| 3 |
+
size 4992525496
|
model-00041-of-00135.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1074c6a4431d9b4de4a84559eaae14b4b1de2ebc79d6fcc1a2676817ad1dd2d0
|
| 3 |
+
size 4992525496
|
model-00042-of-00135.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d0ddfe8f740c293e6036d3e7a27cd81176ee64db71d8309393badee3e42da3a4
|
| 3 |
+
size 4992525496
|
model-00043-of-00135.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e6427ed3a9efe86df41eba06f50dcf598c19b0839dca85183ea4c520962407de
|
| 3 |
+
size 4992525304
|
model-00044-of-00135.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e6de1783d2e52738e2806c96995592ca02ce0f0d6bfcb87ab5098d3fe56925cc
|
| 3 |
+
size 4992525496
|
model-00045-of-00135.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b22b0a353386294b439406c44c424687dc08dfec75d26d0c2e1d7f6369c67978
|
| 3 |
+
size 4992525496
|
model-00046-of-00135.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:723533f61605f7b8028c57ab5016b18649a29fd2381b91a5e4d5285f58efbf1d
|
| 3 |
+
size 4992525304
|
model.safetensors.index.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"bos_token": {
|
| 5 |
+
"__type": "AddedToken",
|
| 6 |
+
"content": "<|begin▁of▁sentence|>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": true,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false
|
| 11 |
+
},
|
| 12 |
+
"clean_up_tokenization_spaces": false,
|
| 13 |
+
"eos_token": {
|
| 14 |
+
"__type": "AddedToken",
|
| 15 |
+
"content": "<|end▁of▁sentence|>",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": true,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false
|
| 20 |
+
},
|
| 21 |
+
"legacy": true,
|
| 22 |
+
"model_max_length": 131072,
|
| 23 |
+
"pad_token": {
|
| 24 |
+
"__type": "AddedToken",
|
| 25 |
+
"content": "<|end▁of▁sentence|>",
|
| 26 |
+
"lstrip": false,
|
| 27 |
+
"normalized": true,
|
| 28 |
+
"rstrip": false,
|
| 29 |
+
"single_word": false
|
| 30 |
+
},
|
| 31 |
+
"sp_model_kwargs": {},
|
| 32 |
+
"unk_token": null,
|
| 33 |
+
"tokenizer_class": "LlamaTokenizerFast",
|
| 34 |
+
"chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='', is_first_sp=true) %}{%- for message in messages %}{%- if message['role'] == 'system' %}{%- if ns.is_first_sp %}{% set ns.system_prompt = ns.system_prompt + message['content'] %}{% set ns.is_first_sp = false %}{%- else %}{% set ns.system_prompt = ns.system_prompt + '\n\n' + message['content'] %}{%- endif %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<|User|>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<|Assistant|><|tool▁calls▁begin|><|tool▁call▁begin|>' + tool['type'] + '<|tool▁sep|>' + tool['function']['name'] + '\n' + '```json' + '\n' + tool['function']['arguments'] + '\n' + '```' + '<|tool▁call▁end|>'}}{%- set ns.is_first = true -%}{%- else %}{{'\n' + '<|tool▁call▁begin|>' + tool['type'] + '<|tool▁sep|>' + tool['function']['name'] + '\n' + '```json' + '\n' + tool['function']['arguments'] + '\n' + '```' + '<|tool▁call▁end|>'}}{{'<|tool▁calls▁end|><|end▁of▁sentence|>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<|tool▁outputs▁end|>' + message['content'] + '<|end▁of▁sentence|>'}}{%- set ns.is_tool = false -%}{%- else %}{{'<|Assistant|>' + message['content'] + '<|end▁of▁sentence|>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<|tool▁outputs▁begin|><|tool▁output▁begin|>' + message['content'] + '<|tool▁output▁end|>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\n<|tool▁output▁begin|>' + message['content'] + '<|tool▁output▁end|>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<|tool▁outputs▁end|>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<|Assistant|>'}}{% endif %}"
|
| 35 |
+
}
|