Add files using upload-large-folder tool

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1,44 @@
+{
+  "architectures": [
+    "DeepseekForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "auto_map": {
+    "AutoConfig": "ai-sage/GigaChat-20B-A3B-base--configuration_deepseek.DeepseekConfig",
+    "AutoModel": "ai-sage/GigaChat-20B-A3B-base--modelling_deepseek.DeepseekModel",
+    "AutoModelForCausalLM": "ai-sage/GigaChat-20B-A3B-base--modelling_deepseek.DeepseekForCausalLM"
+  },
+  "aux_loss_alpha": 0.001,
+  "bos_token_id": 1,
+  "eos_token_id": 128001,
+  "first_k_dense_replace": 1,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.006,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 131072,
+  "moe_implementation": "eager",
+  "moe_intermediate_size": 1792,
+  "moe_layer_freq": 1,
+  "n_routed_experts": 64,
+  "n_shared_experts": 2,
+  "norm_topk_prob": false,
+  "num_attention_heads": 16,
+  "num_experts_per_tok": 6,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 8,
+  "pad_token_id": 1,
+  "pretraining_tp": 1,
+  "return_dict": false,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 1400000,
+  "scoring_func": "softmax",
+  "seq_aux": true,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.48.0",
+  "use_cache": true,
+  "vocab_size": 128256
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 2,
+  "transformers_version": "4.48.0"
+}

pytorch_model-00001-of-00017.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6881be84de3f9cd9d6fa6b224c06ef72d605d40bfb8b799a9bd7be03bb045e89
+size 4990209805

pytorch_model-00002-of-00017.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d22acb31b9d05968618f417e3643f68c6065d70fa7f92b06574ecf1bfa64bdd8
+size 4998156291

pytorch_model-00003-of-00017.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0159a7278b387aad6eb9c8cbb3b4661031ed98dd76d0358c5735c772bffcc566
+size 4990291165

pytorch_model-00004-of-00017.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ed25e86b388338197de8f5388edb1aac55121f3f5fa3b84adda3c8ddfdb4d35
+size 4990291141

pytorch_model-00005-of-00017.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f2444656b6ca44d53552d5f5e5fd0e516a08a5cc1a6de8b22bb5cb0b95bb843
+size 4998156291

pytorch_model-00006-of-00017.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc9cb99812ff088b24e9a92f400f4f3acf143ed421e337f5f4ab5191c0584274
+size 4990291269

pytorch_model-00007-of-00017.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7eee709da015cd42e6edbe7a4d808bb2174381294decd94e71517cbd05319b11
+size 4990291525

pytorch_model-00008-of-00017.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7aed5540694a67d0e135fdada93caf456bce6e3e5088a5735bc63b32892f655
+size 4988194397

pytorch_model-00009-of-00017.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56fd8ccdb745f341d5d1b8a1aca7662dcefa1321e91c14715461133d9ec346dc
+size 4985573296

pytorch_model-00010-of-00017.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c4859fd1d33529e67ecd2f79753bd83b33b3320a13d91d203b01151de365ee8
+size 4990291537

pytorch_model-00011-of-00017.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8cd8c0db6a167cb3cfc46aa1745fd87d08d5fc1dc9561be51e9c4426b71b9a8b
+size 4990291549

pytorch_model-00012-of-00017.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da4dab92becf5f54e355053035c639ff9df6b55e67a89126fb2a8d474d5b29b2
+size 4998156611

pytorch_model-00013-of-00017.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a913eadd76fabde6c9e538e1a10918c7bbb441b24554a6981c796c12529fea3a
+size 4990291549

pytorch_model-00014-of-00017.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12bb48d3c989e2790dfb25e45ada69d297beddb5967fe103f84ee3097b9e0538
+size 4990291549

pytorch_model-00015-of-00017.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:453611aa27e699c490e0597aa955fd344d2bc716daba126dc5a8d51063f4aca3
+size 4998156611

pytorch_model-00016-of-00017.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a56a0a81774371fb7322a88593d1a499758bac8146e700fa04823db7f1abbc18
+size 4990291549

pytorch_model-00017-of-00017.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:698eff1c4741c7b4007e8d55bbce3560f8a2c6abaa744160130fa85319ef9814
+size 2489877692

special_tokens_map.json

@@ -0,0 +1,26 @@
+{
+  "additional_special_tokens": [
+    "<|role_sep|>",
+    "<|message_sep|>",
+    "[",
+    "]",
+    "<|role_sep|>",
+    "<|message_sep|>",
+    "[",
+    "]"
+  ],
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|message_sep|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6fc8146adda45ec7f4876d832f80b55e8dd3e1fa648fbd54d059a601ee73cea3
+size 10678892

tokenizer_config.json

@@ -0,0 +1,106 @@
+{
+  "add_eos_token": false,
+  "added_tokens": {
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128000": {
+      "content": "<|role_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128001": {
+      "content": "<|message_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "61": {
+      "content": "[",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "63": {
+      "content": "]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "added_tokens_decoder": {
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "61": {
+      "content": "[",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "63": {
+      "content": "]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128000": {
+      "content": "<|role_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128001": {
+      "content": "<|message_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|role_sep|>",
+    "<|message_sep|>",
+    "[",
+    "]",
+    "<|role_sep|>",
+    "<|message_sep|>",
+    "[",
+    "]"
+  ],
+  "bos_token": "<s>",
+  "chat_template": "{% if messages[0]['role'] == 'system' -%}\n    {%- set loop_messages = messages[1:] -%}\n    {%- set system_message = bos_token + messages[0]['content'] + additional_special_tokens[1] -%}\n{%- else -%}\n    {%- set loop_messages = messages -%}\n    {%- set system_message = bos_token + '' -%}\n{%- endif -%}\n{%- for message in loop_messages %}\n    {% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}\n        {{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}\n    {% endif %}\n    \n    {%- if loop.index0 == 0 -%}\n        {{ system_message -}}\n    {%- endif -%}\n    {%- if message['role'] == 'user' -%}\n        {{ message['role'] + additional_special_tokens[0] + message['content'] + additional_special_tokens[1] -}}\n        {{ 'available functions' + additional_special_tokens[0] + additional_special_tokens[2] + additional_special_tokens[3]  + additional_special_tokens[1] -}}\n    {%- endif -%}\n    {%- if message['role'] == 'assistant' -%}\n        {{ message['role'] + additional_special_tokens[0] + message['content'] + additional_special_tokens[1] -}}\n    {%- endif -%}\n    {%- if loop.last and add_generation_prompt -%}\n        {{ 'assistant' + additional_special_tokens[0] -}}\n    {%- endif -%}\n{%- endfor %}",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|message_sep|>",
+  "extra_special_tokens": {},
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "unk_token": null
+}