Add files using upload-large-folder tool
Browse files- config.json +122 -0
- generation_config.json +9 -0
- model-00001-of-000163.safetensors +3 -0
- model-00002-of-000163.safetensors +3 -0
- model-00016-of-000163.safetensors +3 -0
- model-00017-of-000163.safetensors +3 -0
- model-00020-of-000163.safetensors +3 -0
- model-00021-of-000163.safetensors +3 -0
- model-00023-of-000163.safetensors +3 -0
- model-00024-of-000163.safetensors +3 -0
- model-00026-of-000163.safetensors +3 -0
- model-00027-of-000163.safetensors +3 -0
- model-00030-of-000163.safetensors +3 -0
- model-00033-of-000163.safetensors +3 -0
- model-00034-of-000163.safetensors +3 -0
- model-00035-of-000163.safetensors +3 -0
- model-00037-of-000163.safetensors +3 -0
- model-00040-of-000163.safetensors +3 -0
- model-00045-of-000163.safetensors +3 -0
- model-00046-of-000163.safetensors +3 -0
- model-00047-of-000163.safetensors +3 -0
- model-00048-of-000163.safetensors +3 -0
- model-00050-of-000163.safetensors +3 -0
- model-00057-of-000163.safetensors +3 -0
- model-00058-of-000163.safetensors +3 -0
- model-00059-of-000163.safetensors +3 -0
- model-00065-of-000163.safetensors +3 -0
- model-00067-of-000163.safetensors +3 -0
- model-00070-of-000163.safetensors +3 -0
- model-00073-of-000163.safetensors +3 -0
- model-00075-of-000163.safetensors +3 -0
- model-00094-of-000163.safetensors +3 -0
- model-00107-of-000163.safetensors +3 -0
- model-00111-of-000163.safetensors +3 -0
- model-00112-of-000163.safetensors +3 -0
- model-00118-of-000163.safetensors +3 -0
- model-00124-of-000163.safetensors +3 -0
- model-00127-of-000163.safetensors +3 -0
- model-00129-of-000163.safetensors +3 -0
- model-00135-of-000163.safetensors +3 -0
- model-00136-of-000163.safetensors +3 -0
- model-00137-of-000163.safetensors +3 -0
- model-00138-of-000163.safetensors +3 -0
- model-00152-of-000163.safetensors_.gstmp +0 -0
- model-00153-of-000163.safetensors_.gstmp +0 -0
- model-00154-of-000163.safetensors_.gstmp +0 -0
- model-00161-of-000163.safetensors +3 -0
- model-00162-of-000163.safetensors +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +35 -0
config.json
ADDED
|
@@ -0,0 +1,122 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"vocab_size": 129280,
|
| 3 |
+
"max_position_embeddings": 163840,
|
| 4 |
+
"hidden_size": 7168,
|
| 5 |
+
"intermediate_size": 18432,
|
| 6 |
+
"moe_intermediate_size": 2048,
|
| 7 |
+
"num_hidden_layers": 61,
|
| 8 |
+
"num_nextn_predict_layers": 1,
|
| 9 |
+
"num_attention_heads": 128,
|
| 10 |
+
"n_shared_experts": 1,
|
| 11 |
+
"n_routed_experts": 256,
|
| 12 |
+
"ep_size": 1,
|
| 13 |
+
"routed_scaling_factor": 2.5,
|
| 14 |
+
"kv_lora_rank": 512,
|
| 15 |
+
"q_lora_rank": 1536,
|
| 16 |
+
"qk_rope_head_dim": 64,
|
| 17 |
+
"v_head_dim": 128,
|
| 18 |
+
"qk_nope_head_dim": 128,
|
| 19 |
+
"topk_method": "noaux_tc",
|
| 20 |
+
"n_group": 8,
|
| 21 |
+
"topk_group": 4,
|
| 22 |
+
"num_experts_per_tok": 8,
|
| 23 |
+
"moe_layer_freq": 1,
|
| 24 |
+
"first_k_dense_replace": 3,
|
| 25 |
+
"norm_topk_prob": true,
|
| 26 |
+
"scoring_func": "sigmoid",
|
| 27 |
+
"num_key_value_heads": 128,
|
| 28 |
+
"hidden_act": "silu",
|
| 29 |
+
"initializer_range": 0.02,
|
| 30 |
+
"rms_norm_eps": 1e-06,
|
| 31 |
+
"use_cache": true,
|
| 32 |
+
"rope_theta": 10000,
|
| 33 |
+
"rope_scaling": {
|
| 34 |
+
"beta_fast": 32,
|
| 35 |
+
"beta_slow": 1,
|
| 36 |
+
"factor": 40,
|
| 37 |
+
"mscale": 1.0,
|
| 38 |
+
"mscale_all_dim": 1.0,
|
| 39 |
+
"original_max_position_embeddings": 4096,
|
| 40 |
+
"type": "yarn"
|
| 41 |
+
},
|
| 42 |
+
"attention_bias": false,
|
| 43 |
+
"attention_dropout": 0.0,
|
| 44 |
+
"return_dict": true,
|
| 45 |
+
"output_hidden_states": false,
|
| 46 |
+
"torchscript": false,
|
| 47 |
+
"dtype": "bfloat16",
|
| 48 |
+
"pruned_heads": {},
|
| 49 |
+
"tie_word_embeddings": false,
|
| 50 |
+
"chunk_size_feed_forward": 0,
|
| 51 |
+
"is_encoder_decoder": false,
|
| 52 |
+
"is_decoder": false,
|
| 53 |
+
"cross_attention_hidden_size": null,
|
| 54 |
+
"add_cross_attention": false,
|
| 55 |
+
"tie_encoder_decoder": false,
|
| 56 |
+
"architectures": [
|
| 57 |
+
"DeepseekV3ForCausalLM"
|
| 58 |
+
],
|
| 59 |
+
"finetuning_task": null,
|
| 60 |
+
"id2label": {
|
| 61 |
+
"0": "LABEL_0",
|
| 62 |
+
"1": "LABEL_1"
|
| 63 |
+
},
|
| 64 |
+
"label2id": {
|
| 65 |
+
"LABEL_0": 0,
|
| 66 |
+
"LABEL_1": 1
|
| 67 |
+
},
|
| 68 |
+
"task_specific_params": null,
|
| 69 |
+
"problem_type": null,
|
| 70 |
+
"tokenizer_class": null,
|
| 71 |
+
"prefix": null,
|
| 72 |
+
"bos_token_id": 0,
|
| 73 |
+
"pad_token_id": null,
|
| 74 |
+
"eos_token_id": 1,
|
| 75 |
+
"sep_token_id": null,
|
| 76 |
+
"decoder_start_token_id": null,
|
| 77 |
+
"max_length": 20,
|
| 78 |
+
"min_length": 0,
|
| 79 |
+
"do_sample": false,
|
| 80 |
+
"early_stopping": false,
|
| 81 |
+
"num_beams": 1,
|
| 82 |
+
"temperature": 1.0,
|
| 83 |
+
"top_k": 50,
|
| 84 |
+
"top_p": 1.0,
|
| 85 |
+
"typical_p": 1.0,
|
| 86 |
+
"repetition_penalty": 1.0,
|
| 87 |
+
"length_penalty": 1.0,
|
| 88 |
+
"no_repeat_ngram_size": 0,
|
| 89 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 90 |
+
"bad_words_ids": null,
|
| 91 |
+
"num_return_sequences": 1,
|
| 92 |
+
"output_scores": false,
|
| 93 |
+
"return_dict_in_generate": false,
|
| 94 |
+
"forced_bos_token_id": null,
|
| 95 |
+
"forced_eos_token_id": null,
|
| 96 |
+
"remove_invalid_values": false,
|
| 97 |
+
"exponential_decay_length_penalty": null,
|
| 98 |
+
"suppress_tokens": null,
|
| 99 |
+
"begin_suppress_tokens": null,
|
| 100 |
+
"num_beam_groups": 1,
|
| 101 |
+
"diversity_penalty": 0.0,
|
| 102 |
+
"_name_or_path": "deepseek-ai/DeepSeek-R1",
|
| 103 |
+
"transformers_version": "4.57.3",
|
| 104 |
+
"auto_map": {
|
| 105 |
+
"AutoConfig": "configuration_deepseek.DeepseekV3Config",
|
| 106 |
+
"AutoModel": "modeling_deepseek.DeepseekV3Model",
|
| 107 |
+
"AutoModelForCausalLM": "modeling_deepseek.DeepseekV3ForCausalLM"
|
| 108 |
+
},
|
| 109 |
+
"model_type": "deepseek_v3",
|
| 110 |
+
"quantization_config": {
|
| 111 |
+
"activation_scheme": "dynamic",
|
| 112 |
+
"fmt": "e4m3",
|
| 113 |
+
"quant_method": "fp8",
|
| 114 |
+
"weight_block_size": [
|
| 115 |
+
1,
|
| 116 |
+
512
|
| 117 |
+
]
|
| 118 |
+
},
|
| 119 |
+
"tf_legacy_loss": false,
|
| 120 |
+
"use_bfloat16": false,
|
| 121 |
+
"output_attentions": false
|
| 122 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 0,
|
| 4 |
+
"eos_token_id": 1,
|
| 5 |
+
"do_sample": true,
|
| 6 |
+
"temperature": 0.6,
|
| 7 |
+
"top_p": 0.95,
|
| 8 |
+
"transformers_version": "4.39.3"
|
| 9 |
+
}
|
model-00001-of-000163.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aaf3fc8db67e25fe6974bc59e5bfaa17b21b64ccc1a94a7a2a3d41e16e9c88ce
|
| 3 |
+
size 5259579368
|
model-00002-of-000163.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:36dd90955de00163817d733feaaf8ef338443bc60afd9cb68b8c2c9d3a1a5a7e
|
| 3 |
+
size 4334936704
|
model-00016-of-000163.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:07f8c2f51a0cf0f814855e292a1335135aae0a4271bf707648d0e1d15b40e82d
|
| 3 |
+
size 4334936672
|
model-00017-of-000163.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:359120c7bab2311d96139569bd36e79c3cb7ed7643d022f2822518e7ce9e8858
|
| 3 |
+
size 4334937120
|
model-00020-of-000163.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0f59bfe5d477e3dcac819fcd2a8f6beca9fef3125ed06a549e15324ffffcbff8
|
| 3 |
+
size 4334937120
|
model-00021-of-000163.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d8338fe616531ad9f7a5f12c2656b4300a0d68ac7a2a5a513133ae5de2b32c20
|
| 3 |
+
size 4334874744
|
model-00023-of-000163.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3b58e5f12679cc74fc066e5723350ecdf0903936057f2203db6cd2acea5ff1e7
|
| 3 |
+
size 4334875160
|
model-00024-of-000163.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6880adc4625cad56bedaeacf2aad2c9f1e30aec5896377c47841e8cd64082ef5
|
| 3 |
+
size 4334937248
|
model-00026-of-000163.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fa4d28bf92fdd2ffd92a71d97673e1e958eb0a521880563442d220197e8a0ff7
|
| 3 |
+
size 4334874968
|
model-00027-of-000163.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bd156c3652208967dd700a00f0229a7515dd546b54dbe2f90f47347c0863330f
|
| 3 |
+
size 4334937432
|
model-00030-of-000163.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:00044d25e80d9da84a24aeff86748cfdeff659df0468f7260c0c0fdff7e803e0
|
| 3 |
+
size 4334937624
|
model-00033-of-000163.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fb812b106c02fa69c8ccd323de02fa72af2792aa2ac7a55d193553db7d7a05d2
|
| 3 |
+
size 4334937704
|
model-00034-of-000163.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:699fb2b0588fd5a7ffad1a211a343f499a3606f1ee7deee087f9ccbc00ee91f4
|
| 3 |
+
size 1760749616
|
model-00035-of-000163.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:205f3dda2bb070109df87cce8063dc8cac56979f3836866a6117fa34dbf3af29
|
| 3 |
+
size 4334731032
|
model-00037-of-000163.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d4398f68fa0934a9b449cb36a02547d31e5095fd122e30b31d60952b45415425
|
| 3 |
+
size 4334875144
|
model-00040-of-000163.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2f5e49214eb6a4a1a7cf35347d70d42c1c6c79c0bb3b8138941aeccd1b2ee0cd
|
| 3 |
+
size 4334874952
|
model-00045-of-000163.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:58a40641fb4acb76f157e87c636f8f5bb559cd00447a84b6d89017376ebe3d66
|
| 3 |
+
size 4334875160
|
model-00046-of-000163.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d78b5b17bfd98f3c9551b943d5b169e541d25ed8bb4ec2cd4fdeca5da01b9088
|
| 3 |
+
size 4334937248
|
model-00047-of-000163.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:48b5232527d813c7c3bdacb9ad894c75155e374722379b277fb3fa8b3c0a1169
|
| 3 |
+
size 4334937704
|
model-00048-of-000163.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:618c19828eda825ca95e0e190b10a1716cc6f3bb8646b06b6a7076d56b03c978
|
| 3 |
+
size 4334874968
|
model-00050-of-000163.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f55c575bd07cbf18d4e85123d77aaf1e3ce0e7f5293bb97e324a94aba296cf53
|
| 3 |
+
size 4334937704
|
model-00057-of-000163.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fadb2388bd8b5322661a144c79f019a1f2271e9b0bb0c6cf9d2830ca39317b04
|
| 3 |
+
size 4334731032
|
model-00058-of-000163.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e831f8ce3b0b37b9e5642622d4c6c0c9d0d149d0b8d4c7b9ef5bf23a0d972eb8
|
| 3 |
+
size 4334937656
|
model-00059-of-000163.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:26e7b27f0fdac43ba0aafffec892d698f77aee58554c1282522dcf2aa68c4272
|
| 3 |
+
size 4334875144
|
model-00065-of-000163.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:94c12c8bb2c58d32bfa87e0416525572e71486622a62aa65ce90c7702d8b35e6
|
| 3 |
+
size 4334874760
|
model-00067-of-000163.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5f1549e01e967010e7e32256e60fb32e8a795c40650845568d82bc0d26bec362
|
| 3 |
+
size 4334875160
|
model-00070-of-000163.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cab912e5ba782a95878277fd750c25af48dee643ed613fea750cea636cd450b0
|
| 3 |
+
size 4334874968
|
model-00073-of-000163.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0b146ecfd3387b4e68814ef2959b16da3b8a97623d5cb63bfcc45fbd99e4875b
|
| 3 |
+
size 4334874776
|
model-00075-of-000163.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:13599a08078fc083e64624a44fd3caab07df26d6bdb115f6d50c17999cf2d6e2
|
| 3 |
+
size 4334875176
|
model-00094-of-000163.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3aefc80450157ff296bec7c68d45362f1da3fd4a757623ee6600b6f15a9bb13d
|
| 3 |
+
size 4334937704
|
model-00107-of-000163.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:79a2f790b0ffc70fa6b7628cc100d3f20f4bc4d584c8a8daf61e63385ad93a56
|
| 3 |
+
size 4334937448
|
model-00111-of-000163.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ac2c2961093ab47e634dee5fdafc14493c2626ed641285a3c9eb9f1f03f5af82
|
| 3 |
+
size 4334875160
|
model-00112-of-000163.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d6036732966394328c268fe2b065ee8daf5089df3fd2b4293fa11098d8e8700c
|
| 3 |
+
size 4334937248
|
model-00118-of-000163.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:00e22c1c4b2025c4475a3de41f60cd0ef582e4afe4079a9b53cdb2df5427c81c
|
| 3 |
+
size 4334937624
|
model-00124-of-000163.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:047b40174508636c9e806ae20dde8706ca61fe7a2ea43a26aa43724a76a0c052
|
| 3 |
+
size 4334937656
|
model-00127-of-000163.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2b0d12d218f46be7821a5a81c9ee0b3072afdaf03a06bbf81788c2f431009bda
|
| 3 |
+
size 4334937704
|
model-00129-of-000163.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1a7c2bd73dcf1ab72d069244d98a11a5c7ac23a93fc6042f0386f1987c70f582
|
| 3 |
+
size 4334937448
|
model-00135-of-000163.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a7a07659d4ad0cab6e79166af5e77ec046c048f7f9069fd1531da0d131b581ee
|
| 3 |
+
size 4334937704
|
model-00136-of-000163.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0789aa50dc052cab7f95e048d7a1ef56677386c2ce47bd031174230e7e999933
|
| 3 |
+
size 4334874968
|
model-00137-of-000163.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2c84f904433d5d96ab3857558ef3e3d8fdc1a5a29d4919b6de0f89724ca25979
|
| 3 |
+
size 4334937432
|
model-00138-of-000163.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:71dcf440b6372ca8787e15cce256a179bb52799cfc411caee9308639a443f7a3
|
| 3 |
+
size 4334937704
|
model-00152-of-000163.safetensors_.gstmp
ADDED
|
File without changes
|
model-00153-of-000163.safetensors_.gstmp
ADDED
|
File without changes
|
model-00154-of-000163.safetensors_.gstmp
ADDED
|
File without changes
|
model-00161-of-000163.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a959559376d639498e8af6e718212c71916c5cc3033ed5ee8b561ba5712c0f93
|
| 3 |
+
size 4334937064
|
model-00162-of-000163.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1b03868001ebb300c4810bb0e8521bb4b59581ba819f2293a6586dc3673f2c60
|
| 3 |
+
size 4334937688
|
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": 16384,
|
| 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 'tool_calls' in message %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls'] %}{%- if not ns.is_first %}{%- if message['content'] is none %}{{'<|Assistant|><|tool▁calls▁begin|><|tool▁call▁begin|>' + tool['type'] + '<|tool▁sep|>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<|tool▁call▁end|>'}}{%- else %}{{'<|Assistant|>' + message['content'] + '<|tool▁calls▁begin|><|tool▁call▁begin|>' + tool['type'] + '<|tool▁sep|>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<|tool▁call▁end|>'}}{%- endif %}{%- 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|>'}}{%- endif %}{%- endfor %}{{'<|tool▁calls▁end|><|end▁of▁sentence|>'}}{%- endif %}{%- if message['role'] == 'assistant' and 'tool_calls' not in message %}{%- if ns.is_tool %}{{'<|tool▁outputs▁end|>' + message['content'] + '<|end▁of▁sentence|>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '</think>' in content %}{% set content = content.split('</think>')[-1] %}{% endif %}{{'<|Assistant|>' + 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 %}{{'<|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|><think>\\n'}}{% endif %}"
|
| 35 |
+
}
|