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": "bfloat16",
+  "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": 128001,
+  "pad_token_id": 1,
+  "transformers_version": "4.48.0"
+}

pytorch_model-00001-of-00009.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13237deed6b3c535de870ce19964cef33d0a1e657947dfc1a86231f9b070de05
+size 4994075149

pytorch_model-00002-of-00009.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81fb556c13dccdab2bba39c012277036a2a465b953cb1081ea3eb2361c6dd883
+size 4997784867

pytorch_model-00003-of-00009.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ad41c0c164e444b8f212a881cffa5442679524755eee2f08aca796ba085471c
+size 4994368696

pytorch_model-00004-of-00009.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e34a0e502ec7c464e2b8d479c4ea06addf5e17ab779e162d75d4e6522a50052
+size 4997785559

pytorch_model-00005-of-00009.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50c0351b77611930818427f2277a436e26d8b9afd7545a1347d3352ecd7e16e1
+size 4994369208

pytorch_model-00006-of-00009.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b74f2a769bd05d6c1f5cf4e72da71c47114053c8fef84b812959a0265a9d8e16
+size 4994369208

pytorch_model-00007-of-00009.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25c0858727455a375318a872cda7955ca6dbf0fc5883c1d3b220e8b1163f2eb8
+size 4997785559

pytorch_model-00008-of-00009.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a39357ac4bcc5a11550639df14a5370cc2df5728d1843f00a94ee029ca39b16e
+size 4994369208

pytorch_model-00009-of-00009.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f4ae5cc3c061a102c82465b3a42d04f7cba524692c52b22162328a180d0cbed
+size 1215607594

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
+}