safetensors

.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
+.safetensors filter=lfs diff=lfs merge=lfs -text

config.json

@@ -1,49 +1,51 @@
 {
-    "architectures": ["DeepseekV3ForCausalLM"],
-    "attention_bias": false,
-    "attention_dropout": 0.0,
-    "aux_loss_alpha": 0.001,
-    "bos_token_id": 0,
-    "eos_token_id": 1,
-    "ep_size": 1,
-    "first_k_dense_replace": 6,
-    "head_dim": 64,
-    "hidden_act": "silu",
-    "hidden_size": 2560,
-    "initializer_range": 0.02,
-    "intermediate_size": 9216,
-    "kv_lora_rank": 256,
-    "max_position_embeddings": 2048,
-    "model_type": "deepseek_v3",
-    "moe_intermediate_size": 1024,
-    "moe_layer_freq": 2,
-    "n_group": 8,
-    "n_routed_experts": 1,
-    "n_shared_experts": 1,
-    "norm_topk_prob": true,
-    "num_attention_heads": 40,
-    "num_experts_per_tok": 4,
-    "num_hidden_layers": 28,
-    "num_key_value_heads": 8,
-    "num_nextn_predict_layers": 1,
-    "pretraining_tp": 1,
-    "q_lora_rank": 512,
-    "qk_head_dim": 128,
-    "qk_nope_head_dim": 64,
-    "qk_rope_head_dim": 64,
-    "rms_norm_eps": 1e-6,
-    "rope_interleave": true,
-    "rope_scaling": null,
-    "rope_theta": 10000,
-    "routed_scaling_factor": 2.5,
-    "scoring_func": "sigmoid",
-    "seq_aux": true,
-    "tie_word_embeddings": false,
-    "topk_group": 4,
-    "topk_method": "noaux_tc",
-    "torch_dtype": "bfloat16",
-    "transformers_version": "4.51.3",
-    "use_cache": true,
-    "v_head_dim": 128,
-    "vocab_size": 129280
+  "architectures": [
+    "DeepseekV3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "aux_loss_alpha": 0.001,
+  "bos_token_id": 0,
+  "eos_token_id": 1,
+  "ep_size": 1,
+  "first_k_dense_replace": 6,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 2560,
+  "initializer_range": 0.02,
+  "intermediate_size": 9216,
+  "kv_lora_rank": 256,
+  "max_position_embeddings": 2048,
+  "model_type": "deepseek_v3",
+  "moe_intermediate_size": 1024,
+  "moe_layer_freq": 2,
+  "n_group": 8,
+  "n_routed_experts": 1,
+  "n_shared_experts": 1,
+  "norm_topk_prob": true,
+  "num_attention_heads": 40,
+  "num_experts_per_tok": 4,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 8,
+  "num_nextn_predict_layers": 1,
+  "pretraining_tp": 1,
+  "q_lora_rank": 512,
+  "qk_head_dim": 128,
+  "qk_nope_head_dim": 64,
+  "qk_rope_head_dim": 64,
+  "rms_norm_eps": 1e-06,
+  "rope_interleave": true,
+  "rope_scaling": null,
+  "rope_theta": 10000,
+  "routed_scaling_factor": 2.5,
+  "scoring_func": "sigmoid",
+  "seq_aux": true,
+  "tie_word_embeddings": false,
+  "topk_group": 4,
+  "topk_method": "noaux_tc",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.54.0.dev0",
+  "use_cache": true,
+  "v_head_dim": 128,
+  "vocab_size": 129280
 }

generation_config.json

@@ -2,5 +2,5 @@
   "_from_model_config": true,
   "bos_token_id": 0,
   "eos_token_id": 1,
-  "transformers_version": "4.51.3"
+  "transformers_version": "4.54.0.dev0"
 }

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1dcc2b9a970d1d13ca9c46b2280f5bdc0f3bfe9b440536d70cc784ee9cac7bc
+size 3975915404

tokenizer_config.json

@@ -6549,7 +6549,6 @@
     }
   },
   "bos_token": "<｜begin▁of▁sentence｜>",
-  "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 %}",
   "clean_up_tokenization_spaces": false,
   "eos_token": "<｜end▁of▁sentence｜>",
   "extra_special_tokens": {},