Upload folder using huggingface_hub

chat_template.jinja

@@ -0,0 +1 @@
+{% 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 %}

config.json

@@ -0,0 +1,479 @@
+{
+  "architectures": [
+    "DeepseekV3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "auto_map": {
+    "AutoConfig": "configuration_deepseek.DeepseekV3Config",
+    "AutoModel": "modeling_deepseek.DeepseekV3Model",
+    "AutoModelForCausalLM": "modeling_deepseek.DeepseekV3ForCausalLM"
+  },
+  "aux_loss_alpha": 0.001,
+  "bos_token_id": 0,
+  "dtype": "bfloat16",
+  "eos_token_id": 1,
+  "ep_size": 1,
+  "first_k_dense_replace": 3,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 7168,
+  "initializer_range": 0.02,
+  "intermediate_size": 18432,
+  "kv_lora_rank": 512,
+  "max_position_embeddings": 163840,
+  "model_type": "deepseek_v3",
+  "moe_intermediate_size": 2048,
+  "moe_layer_freq": 1,
+  "n_group": 8,
+  "n_routed_experts": 256,
+  "n_shared_experts": 1,
+  "norm_topk_prob": true,
+  "num_attention_heads": 128,
+  "num_experts_per_tok": 8,
+  "num_hidden_layers": 61,
+  "num_key_value_heads": 128,
+  "num_nextn_predict_layers": 1,
+  "pad_token_id": 128815,
+  "pretraining_tp": 1,
+  "q_lora_rank": 1536,
+  "qk_head_dim": 192,
+  "qk_nope_head_dim": 128,
+  "qk_rope_head_dim": 64,
+  "quantization_config": {
+    "config_groups": {
+      "group_0": {
+        "format": null,
+        "input_activations": {
+          "actorder": null,
+          "block_structure": null,
+          "dynamic": true,
+          "group_size": 32,
+          "num_bits": 4,
+          "observer": null,
+          "observer_kwargs": {},
+          "scale_dtype": "torch.uint8",
+          "strategy": "group",
+          "symmetric": true,
+          "type": "float",
+          "zp_dtype": null
+        },
+        "output_activations": null,
+        "targets": [
+          "Linear"
+        ],
+        "weights": {
+          "actorder": null,
+          "block_structure": null,
+          "dynamic": false,
+          "group_size": 32,
+          "num_bits": 4,
+          "observer": "memoryless_minmax",
+          "observer_kwargs": {},
+          "scale_dtype": "torch.uint8",
+          "strategy": "group",
+          "symmetric": true,
+          "type": "float",
+          "zp_dtype": null
+        }
+      }
+    },
+    "format": "mxfp4-pack-quantized",
+    "global_compression_ratio": null,
+    "ignore": [
+      "re:.*self_attn.*",
+      "re:.*model\\.layers\\.3\\.mlp\\.gate.*",
+      "re:.*model\\.layers\\.4\\.mlp\\.gate.*",
+      "re:.*model\\.layers\\.5\\.mlp\\.gate.*",
+      "re:.*model\\.layers\\.6\\.mlp\\.gate.*",
+      "re:.*model\\.layers\\.7\\.mlp\\.gate.*",
+      "re:.*model\\.layers\\.8\\.mlp\\.gate.*",
+      "re:.*model\\.layers\\.9\\.mlp\\.gate.*",
+      "re:.*model\\.layers\\.10\\.mlp\\.gate.*",
+      "re:.*model\\.layers\\.11\\.mlp\\.gate.*",
+      "re:.*model\\.layers\\.12\\.mlp\\.gate.*",
+      "re:.*model\\.layers\\.13\\.mlp\\.gate.*",
+      "re:.*model\\.layers\\.14\\.mlp\\.gate.*",
+      "re:.*model\\.layers\\.15\\.mlp\\.gate.*",
+      "re:.*model\\.layers\\.16\\.mlp\\.gate.*",
+      "re:.*model\\.layers\\.17\\.mlp\\.gate.*",
+      "re:.*model\\.layers\\.18\\.mlp\\.gate.*",
+      "re:.*model\\.layers\\.19\\.mlp\\.gate.*",
+      "re:.*model\\.layers\\.20\\.mlp\\.gate.*",
+      "re:.*model\\.layers\\.21\\.mlp\\.gate.*",
+      "re:.*model\\.layers\\.22\\.mlp\\.gate.*",
+      "re:.*model\\.layers\\.23\\.mlp\\.gate.*",
+      "re:.*model\\.layers\\.24\\.mlp\\.gate.*",
+      "re:.*model\\.layers\\.25\\.mlp\\.gate.*",
+      "re:.*model\\.layers\\.26\\.mlp\\.gate.*",
+      "re:.*model\\.layers\\.27\\.mlp\\.gate.*",
+      "re:.*model\\.layers\\.28\\.mlp\\.gate.*",
+      "re:.*model\\.layers\\.29\\.mlp\\.gate.*",
+      "re:.*model\\.layers\\.30\\.mlp\\.gate.*",
+      "re:.*model\\.layers\\.31\\.mlp\\.gate.*",
+      "re:.*model\\.layers\\.32\\.mlp\\.gate.*",
+      "re:.*model\\.layers\\.33\\.mlp\\.gate.*",
+      "re:.*model\\.layers\\.34\\.mlp\\.gate.*",
+      "re:.*model\\.layers\\.35\\.mlp\\.gate.*",
+      "re:.*model\\.layers\\.36\\.mlp\\.gate.*",
+      "re:.*model\\.layers\\.37\\.mlp\\.gate.*",
+      "re:.*model\\.layers\\.38\\.mlp\\.gate.*",
+      "re:.*model\\.layers\\.39\\.mlp\\.gate.*",
+      "re:.*model\\.layers\\.40\\.mlp\\.gate.*",
+      "re:.*model\\.layers\\.41\\.mlp\\.gate.*",
+      "re:.*model\\.layers\\.42\\.mlp\\.gate.*",
+      "re:.*model\\.layers\\.43\\.mlp\\.gate.*",
+      "re:.*model\\.layers\\.44\\.mlp\\.gate.*",
+      "re:.*model\\.layers\\.45\\.mlp\\.gate.*",
+      "re:.*model\\.layers\\.46\\.mlp\\.gate.*",
+      "re:.*model\\.layers\\.47\\.mlp\\.gate.*",
+      "re:.*model\\.layers\\.48\\.mlp\\.gate.*",
+      "re:.*model\\.layers\\.49\\.mlp\\.gate.*",
+      "re:.*model\\.layers\\.50\\.mlp\\.gate.*",
+      "re:.*model\\.layers\\.51\\.mlp\\.gate.*",
+      "re:.*model\\.layers\\.52\\.mlp\\.gate.*",
+      "re:.*model\\.layers\\.53\\.mlp\\.gate.*",
+      "re:.*model\\.layers\\.54\\.mlp\\.gate.*",
+      "re:.*model\\.layers\\.55\\.mlp\\.gate.*",
+      "re:.*model\\.layers\\.56\\.mlp\\.gate.*",
+      "re:.*model\\.layers\\.57\\.mlp\\.gate.*",
+      "re:.*model\\.layers\\.58\\.mlp\\.gate.*",
+      "re:.*model\\.layers\\.59\\.mlp\\.gate.*",
+      "re:.*model\\.layers\\.60\\.mlp\\.gate.*",
+      "lm_head",
+      "model.layers.0.self_attn.q_a_proj",
+      "model.layers.0.self_attn.q_b_proj",
+      "model.layers.0.self_attn.kv_a_proj_with_mqa",
+      "model.layers.0.self_attn.kv_b_proj",
+      "model.layers.0.self_attn.o_proj",
+      "model.layers.1.self_attn.q_a_proj",
+      "model.layers.1.self_attn.q_b_proj",
+      "model.layers.1.self_attn.kv_a_proj_with_mqa",
+      "model.layers.1.self_attn.kv_b_proj",
+      "model.layers.1.self_attn.o_proj",
+      "model.layers.2.self_attn.q_a_proj",
+      "model.layers.2.self_attn.q_b_proj",
+      "model.layers.2.self_attn.kv_a_proj_with_mqa",
+      "model.layers.2.self_attn.kv_b_proj",
+      "model.layers.2.self_attn.o_proj",
+      "model.layers.3.self_attn.q_a_proj",
+      "model.layers.3.self_attn.q_b_proj",
+      "model.layers.3.self_attn.kv_a_proj_with_mqa",
+      "model.layers.3.self_attn.kv_b_proj",
+      "model.layers.3.self_attn.o_proj",
+      "model.layers.4.self_attn.q_a_proj",
+      "model.layers.4.self_attn.q_b_proj",
+      "model.layers.4.self_attn.kv_a_proj_with_mqa",
+      "model.layers.4.self_attn.kv_b_proj",
+      "model.layers.4.self_attn.o_proj",
+      "model.layers.5.self_attn.q_a_proj",
+      "model.layers.5.self_attn.q_b_proj",
+      "model.layers.5.self_attn.kv_a_proj_with_mqa",
+      "model.layers.5.self_attn.kv_b_proj",
+      "model.layers.5.self_attn.o_proj",
+      "model.layers.6.self_attn.q_a_proj",
+      "model.layers.6.self_attn.q_b_proj",
+      "model.layers.6.self_attn.kv_a_proj_with_mqa",
+      "model.layers.6.self_attn.kv_b_proj",
+      "model.layers.6.self_attn.o_proj",
+      "model.layers.7.self_attn.q_a_proj",
+      "model.layers.7.self_attn.q_b_proj",
+      "model.layers.7.self_attn.kv_a_proj_with_mqa",
+      "model.layers.7.self_attn.kv_b_proj",
+      "model.layers.7.self_attn.o_proj",
+      "model.layers.8.self_attn.q_a_proj",
+      "model.layers.8.self_attn.q_b_proj",
+      "model.layers.8.self_attn.kv_a_proj_with_mqa",
+      "model.layers.8.self_attn.kv_b_proj",
+      "model.layers.8.self_attn.o_proj",
+      "model.layers.9.self_attn.q_a_proj",
+      "model.layers.9.self_attn.q_b_proj",
+      "model.layers.9.self_attn.kv_a_proj_with_mqa",
+      "model.layers.9.self_attn.kv_b_proj",
+      "model.layers.9.self_attn.o_proj",
+      "model.layers.10.self_attn.q_a_proj",
+      "model.layers.10.self_attn.q_b_proj",
+      "model.layers.10.self_attn.kv_a_proj_with_mqa",
+      "model.layers.10.self_attn.kv_b_proj",
+      "model.layers.10.self_attn.o_proj",
+      "model.layers.11.self_attn.q_a_proj",
+      "model.layers.11.self_attn.q_b_proj",
+      "model.layers.11.self_attn.kv_a_proj_with_mqa",
+      "model.layers.11.self_attn.kv_b_proj",
+      "model.layers.11.self_attn.o_proj",
+      "model.layers.12.self_attn.q_a_proj",
+      "model.layers.12.self_attn.q_b_proj",
+      "model.layers.12.self_attn.kv_a_proj_with_mqa",
+      "model.layers.12.self_attn.kv_b_proj",
+      "model.layers.12.self_attn.o_proj",
+      "model.layers.13.self_attn.q_a_proj",
+      "model.layers.13.self_attn.q_b_proj",
+      "model.layers.13.self_attn.kv_a_proj_with_mqa",
+      "model.layers.13.self_attn.kv_b_proj",
+      "model.layers.13.self_attn.o_proj",
+      "model.layers.14.self_attn.q_a_proj",
+      "model.layers.14.self_attn.q_b_proj",
+      "model.layers.14.self_attn.kv_a_proj_with_mqa",
+      "model.layers.14.self_attn.kv_b_proj",
+      "model.layers.14.self_attn.o_proj",
+      "model.layers.15.self_attn.q_a_proj",
+      "model.layers.15.self_attn.q_b_proj",
+      "model.layers.15.self_attn.kv_a_proj_with_mqa",
+      "model.layers.15.self_attn.kv_b_proj",
+      "model.layers.15.self_attn.o_proj",
+      "model.layers.16.self_attn.q_a_proj",
+      "model.layers.16.self_attn.q_b_proj",
+      "model.layers.16.self_attn.kv_a_proj_with_mqa",
+      "model.layers.16.self_attn.kv_b_proj",
+      "model.layers.16.self_attn.o_proj",
+      "model.layers.17.self_attn.q_a_proj",
+      "model.layers.17.self_attn.q_b_proj",
+      "model.layers.17.self_attn.kv_a_proj_with_mqa",
+      "model.layers.17.self_attn.kv_b_proj",
+      "model.layers.17.self_attn.o_proj",
+      "model.layers.18.self_attn.q_a_proj",
+      "model.layers.18.self_attn.q_b_proj",
+      "model.layers.18.self_attn.kv_a_proj_with_mqa",
+      "model.layers.18.self_attn.kv_b_proj",
+      "model.layers.18.self_attn.o_proj",
+      "model.layers.19.self_attn.q_a_proj",
+      "model.layers.19.self_attn.q_b_proj",
+      "model.layers.19.self_attn.kv_a_proj_with_mqa",
+      "model.layers.19.self_attn.kv_b_proj",
+      "model.layers.19.self_attn.o_proj",
+      "model.layers.20.self_attn.q_a_proj",
+      "model.layers.20.self_attn.q_b_proj",
+      "model.layers.20.self_attn.kv_a_proj_with_mqa",
+      "model.layers.20.self_attn.kv_b_proj",
+      "model.layers.20.self_attn.o_proj",
+      "model.layers.21.self_attn.q_a_proj",
+      "model.layers.21.self_attn.q_b_proj",
+      "model.layers.21.self_attn.kv_a_proj_with_mqa",
+      "model.layers.21.self_attn.kv_b_proj",
+      "model.layers.21.self_attn.o_proj",
+      "model.layers.22.self_attn.q_a_proj",
+      "model.layers.22.self_attn.q_b_proj",
+      "model.layers.22.self_attn.kv_a_proj_with_mqa",
+      "model.layers.22.self_attn.kv_b_proj",
+      "model.layers.22.self_attn.o_proj",
+      "model.layers.23.self_attn.q_a_proj",
+      "model.layers.23.self_attn.q_b_proj",
+      "model.layers.23.self_attn.kv_a_proj_with_mqa",
+      "model.layers.23.self_attn.kv_b_proj",
+      "model.layers.23.self_attn.o_proj",
+      "model.layers.24.self_attn.q_a_proj",
+      "model.layers.24.self_attn.q_b_proj",
+      "model.layers.24.self_attn.kv_a_proj_with_mqa",
+      "model.layers.24.self_attn.kv_b_proj",
+      "model.layers.24.self_attn.o_proj",
+      "model.layers.25.self_attn.q_a_proj",
+      "model.layers.25.self_attn.q_b_proj",
+      "model.layers.25.self_attn.kv_a_proj_with_mqa",
+      "model.layers.25.self_attn.kv_b_proj",
+      "model.layers.25.self_attn.o_proj",
+      "model.layers.26.self_attn.q_a_proj",
+      "model.layers.26.self_attn.q_b_proj",
+      "model.layers.26.self_attn.kv_a_proj_with_mqa",
+      "model.layers.26.self_attn.kv_b_proj",
+      "model.layers.26.self_attn.o_proj",
+      "model.layers.27.self_attn.q_a_proj",
+      "model.layers.27.self_attn.q_b_proj",
+      "model.layers.27.self_attn.kv_a_proj_with_mqa",
+      "model.layers.27.self_attn.kv_b_proj",
+      "model.layers.27.self_attn.o_proj",
+      "model.layers.28.self_attn.q_a_proj",
+      "model.layers.28.self_attn.q_b_proj",
+      "model.layers.28.self_attn.kv_a_proj_with_mqa",
+      "model.layers.28.self_attn.kv_b_proj",
+      "model.layers.28.self_attn.o_proj",
+      "model.layers.29.self_attn.q_a_proj",
+      "model.layers.29.self_attn.q_b_proj",
+      "model.layers.29.self_attn.kv_a_proj_with_mqa",
+      "model.layers.29.self_attn.kv_b_proj",
+      "model.layers.29.self_attn.o_proj",
+      "model.layers.30.self_attn.q_a_proj",
+      "model.layers.30.self_attn.q_b_proj",
+      "model.layers.30.self_attn.kv_a_proj_with_mqa",
+      "model.layers.30.self_attn.kv_b_proj",
+      "model.layers.30.self_attn.o_proj",
+      "model.layers.31.self_attn.q_a_proj",
+      "model.layers.31.self_attn.q_b_proj",
+      "model.layers.31.self_attn.kv_a_proj_with_mqa",
+      "model.layers.31.self_attn.kv_b_proj",
+      "model.layers.31.self_attn.o_proj",
+      "model.layers.32.self_attn.q_a_proj",
+      "model.layers.32.self_attn.q_b_proj",
+      "model.layers.32.self_attn.kv_a_proj_with_mqa",
+      "model.layers.32.self_attn.kv_b_proj",
+      "model.layers.32.self_attn.o_proj",
+      "model.layers.33.self_attn.q_a_proj",
+      "model.layers.33.self_attn.q_b_proj",
+      "model.layers.33.self_attn.kv_a_proj_with_mqa",
+      "model.layers.33.self_attn.kv_b_proj",
+      "model.layers.33.self_attn.o_proj",
+      "model.layers.34.self_attn.q_a_proj",
+      "model.layers.34.self_attn.q_b_proj",
+      "model.layers.34.self_attn.kv_a_proj_with_mqa",
+      "model.layers.34.self_attn.kv_b_proj",
+      "model.layers.34.self_attn.o_proj",
+      "model.layers.35.self_attn.q_a_proj",
+      "model.layers.35.self_attn.q_b_proj",
+      "model.layers.35.self_attn.kv_a_proj_with_mqa",
+      "model.layers.35.self_attn.kv_b_proj",
+      "model.layers.35.self_attn.o_proj",
+      "model.layers.36.self_attn.q_a_proj",
+      "model.layers.36.self_attn.q_b_proj",
+      "model.layers.36.self_attn.kv_a_proj_with_mqa",
+      "model.layers.36.self_attn.kv_b_proj",
+      "model.layers.36.self_attn.o_proj",
+      "model.layers.37.self_attn.q_a_proj",
+      "model.layers.37.self_attn.q_b_proj",
+      "model.layers.37.self_attn.kv_a_proj_with_mqa",
+      "model.layers.37.self_attn.kv_b_proj",
+      "model.layers.37.self_attn.o_proj",
+      "model.layers.38.self_attn.q_a_proj",
+      "model.layers.38.self_attn.q_b_proj",
+      "model.layers.38.self_attn.kv_a_proj_with_mqa",
+      "model.layers.38.self_attn.kv_b_proj",
+      "model.layers.38.self_attn.o_proj",
+      "model.layers.39.self_attn.q_a_proj",
+      "model.layers.39.self_attn.q_b_proj",
+      "model.layers.39.self_attn.kv_a_proj_with_mqa",
+      "model.layers.39.self_attn.kv_b_proj",
+      "model.layers.39.self_attn.o_proj",
+      "model.layers.40.self_attn.q_a_proj",
+      "model.layers.40.self_attn.q_b_proj",
+      "model.layers.40.self_attn.kv_a_proj_with_mqa",
+      "model.layers.40.self_attn.kv_b_proj",
+      "model.layers.40.self_attn.o_proj",
+      "model.layers.41.self_attn.q_a_proj",
+      "model.layers.41.self_attn.q_b_proj",
+      "model.layers.41.self_attn.kv_a_proj_with_mqa",
+      "model.layers.41.self_attn.kv_b_proj",
+      "model.layers.41.self_attn.o_proj",
+      "model.layers.42.self_attn.q_a_proj",
+      "model.layers.42.self_attn.q_b_proj",
+      "model.layers.42.self_attn.kv_a_proj_with_mqa",
+      "model.layers.42.self_attn.kv_b_proj",
+      "model.layers.42.self_attn.o_proj",
+      "model.layers.43.self_attn.q_a_proj",
+      "model.layers.43.self_attn.q_b_proj",
+      "model.layers.43.self_attn.kv_a_proj_with_mqa",
+      "model.layers.43.self_attn.kv_b_proj",
+      "model.layers.43.self_attn.o_proj",
+      "model.layers.44.self_attn.q_a_proj",
+      "model.layers.44.self_attn.q_b_proj",
+      "model.layers.44.self_attn.kv_a_proj_with_mqa",
+      "model.layers.44.self_attn.kv_b_proj",
+      "model.layers.44.self_attn.o_proj",
+      "model.layers.45.self_attn.q_a_proj",
+      "model.layers.45.self_attn.q_b_proj",
+      "model.layers.45.self_attn.kv_a_proj_with_mqa",
+      "model.layers.45.self_attn.kv_b_proj",
+      "model.layers.45.self_attn.o_proj",
+      "model.layers.46.self_attn.q_a_proj",
+      "model.layers.46.self_attn.q_b_proj",
+      "model.layers.46.self_attn.kv_a_proj_with_mqa",
+      "model.layers.46.self_attn.kv_b_proj",
+      "model.layers.46.self_attn.o_proj",
+      "model.layers.47.self_attn.q_a_proj",
+      "model.layers.47.self_attn.q_b_proj",
+      "model.layers.47.self_attn.kv_a_proj_with_mqa",
+      "model.layers.47.self_attn.kv_b_proj",
+      "model.layers.47.self_attn.o_proj",
+      "model.layers.48.self_attn.q_a_proj",
+      "model.layers.48.self_attn.q_b_proj",
+      "model.layers.48.self_attn.kv_a_proj_with_mqa",
+      "model.layers.48.self_attn.kv_b_proj",
+      "model.layers.48.self_attn.o_proj",
+      "model.layers.49.self_attn.q_a_proj",
+      "model.layers.49.self_attn.q_b_proj",
+      "model.layers.49.self_attn.kv_a_proj_with_mqa",
+      "model.layers.49.self_attn.kv_b_proj",
+      "model.layers.49.self_attn.o_proj",
+      "model.layers.50.self_attn.q_a_proj",
+      "model.layers.50.self_attn.q_b_proj",
+      "model.layers.50.self_attn.kv_a_proj_with_mqa",
+      "model.layers.50.self_attn.kv_b_proj",
+      "model.layers.50.self_attn.o_proj",
+      "model.layers.51.self_attn.q_a_proj",
+      "model.layers.51.self_attn.q_b_proj",
+      "model.layers.51.self_attn.kv_a_proj_with_mqa",
+      "model.layers.51.self_attn.kv_b_proj",
+      "model.layers.51.self_attn.o_proj",
+      "model.layers.52.self_attn.q_a_proj",
+      "model.layers.52.self_attn.q_b_proj",
+      "model.layers.52.self_attn.kv_a_proj_with_mqa",
+      "model.layers.52.self_attn.kv_b_proj",
+      "model.layers.52.self_attn.o_proj",
+      "model.layers.53.self_attn.q_a_proj",
+      "model.layers.53.self_attn.q_b_proj",
+      "model.layers.53.self_attn.kv_a_proj_with_mqa",
+      "model.layers.53.self_attn.kv_b_proj",
+      "model.layers.53.self_attn.o_proj",
+      "model.layers.54.self_attn.q_a_proj",
+      "model.layers.54.self_attn.q_b_proj",
+      "model.layers.54.self_attn.kv_a_proj_with_mqa",
+      "model.layers.54.self_attn.kv_b_proj",
+      "model.layers.54.self_attn.o_proj",
+      "model.layers.55.self_attn.q_a_proj",
+      "model.layers.55.self_attn.q_b_proj",
+      "model.layers.55.self_attn.kv_a_proj_with_mqa",
+      "model.layers.55.self_attn.kv_b_proj",
+      "model.layers.55.self_attn.o_proj",
+      "model.layers.56.self_attn.q_a_proj",
+      "model.layers.56.self_attn.q_b_proj",
+      "model.layers.56.self_attn.kv_a_proj_with_mqa",
+      "model.layers.56.self_attn.kv_b_proj",
+      "model.layers.56.self_attn.o_proj",
+      "model.layers.57.self_attn.q_a_proj",
+      "model.layers.57.self_attn.q_b_proj",
+      "model.layers.57.self_attn.kv_a_proj_with_mqa",
+      "model.layers.57.self_attn.kv_b_proj",
+      "model.layers.57.self_attn.o_proj",
+      "model.layers.58.self_attn.q_a_proj",
+      "model.layers.58.self_attn.q_b_proj",
+      "model.layers.58.self_attn.kv_a_proj_with_mqa",
+      "model.layers.58.self_attn.kv_b_proj",
+      "model.layers.58.self_attn.o_proj",
+      "model.layers.59.self_attn.q_a_proj",
+      "model.layers.59.self_attn.q_b_proj",
+      "model.layers.59.self_attn.kv_a_proj_with_mqa",
+      "model.layers.59.self_attn.kv_b_proj",
+      "model.layers.59.self_attn.o_proj",
+      "model.layers.60.self_attn.q_a_proj",
+      "model.layers.60.self_attn.q_b_proj",
+      "model.layers.60.self_attn.kv_a_proj_with_mqa",
+      "model.layers.60.self_attn.kv_b_proj",
+      "model.layers.60.self_attn.o_proj"
+    ],
+    "kv_cache_scheme": null,
+    "provider": "auto-round",
+    "quant_method": "compressed-tensors",
+    "quantization_status": "compressed"
+  },
+  "rms_norm_eps": 1e-06,
+  "rope_interleave": true,
+  "rope_scaling": {
+    "beta_fast": 32.0,
+    "beta_slow": 1.0,
+    "factor": 40.0,
+    "mscale": 1.0,
+    "mscale_all_dim": 1.0,
+    "original_max_position_embeddings": 4096,
+    "rope_type": "yarn",
+    "type": "yarn"
+  },
+  "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",
+  "transformers_version": "4.57.6",
+  "unsloth_fixed": true,
+  "use_cache": true,
+  "v_head_dim": 128,
+  "vocab_size": 129280
+}

configuration_deepseek.py

@@ -0,0 +1,210 @@
+from transformers.configuration_utils import PretrainedConfig
+from transformers.utils import logging
+
+logger = logging.get_logger(__name__)
+
+DEEPSEEK_PRETRAINED_CONFIG_ARCHIVE_MAP = {}
+class DeepseekV3Config(PretrainedConfig):
+    r"""
+    This is the configuration class to store the configuration of a [`DeepseekV3Model`]. It is used to instantiate an DeepSeek
+    model according to the specified arguments, defining the model architecture. Instantiating a configuration with the
+    defaults will yield a similar configuration to that of the DeepSeek-V3.
+
+    Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the
+    documentation from [`PretrainedConfig`] for more information.
+
+
+    Args:
+        vocab_size (`int`, *optional*, defaults to 129280):
+            Vocabulary size of the Deep model. Defines the number of different tokens that can be represented by the
+            `inputs_ids` passed when calling [`DeepseekV3Model`]
+        hidden_size (`int`, *optional*, defaults to 4096):
+            Dimension of the hidden representations.
+        intermediate_size (`int`, *optional*, defaults to 11008):
+            Dimension of the MLP representations.
+        moe_intermediate_size (`int`, *optional*, defaults to 1407):
+            Dimension of the MoE representations.
+        num_hidden_layers (`int`, *optional*, defaults to 32):
+            Number of hidden layers in the Transformer decoder.
+        num_nextn_predict_layers (`int`, *optional*, defaults to 1):
+            Number of nextn predict layers in the DeepSeekV3 Model.
+        num_attention_heads (`int`, *optional*, defaults to 32):
+            Number of attention heads for each attention layer in the Transformer decoder.
+        n_shared_experts (`int`, *optional*, defaults to None):
+            Number of shared experts, None means dense model.
+        n_routed_experts (`int`, *optional*, defaults to None):
+            Number of routed experts, None means dense model.
+        routed_scaling_factor (`float`, *optional*, defaults to 1.0):
+            Scaling factor or routed experts.
+        topk_method (`str`, *optional*, defaults to `gready`):
+            Topk method used in routed gate.
+        n_group (`int`, *optional*, defaults to None):
+            Number of groups for routed experts.
+        topk_group (`int`, *optional*, defaults to None):
+            Number of selected groups for each token(for each token, ensuring the selected experts is only within `topk_group` groups).
+        num_experts_per_tok (`int`, *optional*, defaults to None):
+            Number of selected experts, None means dense model.
+        moe_layer_freq (`int`, *optional*, defaults to 1):
+            The frequency of the MoE layer: one expert layer for every `moe_layer_freq - 1` dense layers.
+        first_k_dense_replace (`int`, *optional*, defaults to 0):
+            Number of dense layers in shallow layers(embed->dense->dense->...->dense->moe->moe...->lm_head).
+                                                            \--k dense layers--/
+        norm_topk_prob (`bool`, *optional*, defaults to False):
+            Whether to normalize the weights of the routed experts.
+        scoring_func (`str`, *optional*, defaults to 'softmax'):
+            Method of computing expert weights.
+        aux_loss_alpha (`float`, *optional*, defaults to 0.001):
+            Auxiliary loss weight coefficient.
+        seq_aux = (`bool`, *optional*, defaults to True):
+            Whether to compute the auxiliary loss for each individual sample.
+        num_key_value_heads (`int`, *optional*):
+            This is the number of key_value heads that should be used to implement Grouped Query Attention. If
+            `num_key_value_heads=num_attention_heads`, the model will use Multi Head Attention (MHA), if
+            `num_key_value_heads=1 the model will use Multi Query Attention (MQA) otherwise GQA is used. When
+            converting a multi-head checkpoint to a GQA checkpoint, each group key and value head should be constructed
+            by meanpooling all the original heads within that group. For more details checkout [this
+            paper](https://arxiv.org/pdf/2305.13245.pdf). If it is not specified, will default to
+            `num_attention_heads`.
+        hidden_act (`str` or `function`, *optional*, defaults to `"silu"`):
+            The non-linear activation function (function or string) in the decoder.
+        max_position_embeddings (`int`, *optional*, defaults to 2048):
+            The maximum sequence length that this model might ever be used with.
+        initializer_range (`float`, *optional*, defaults to 0.02):
+            The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
+        rms_norm_eps (`float`, *optional*, defaults to 1e-06):
+            The epsilon used by the rms normalization layers.
+        use_cache (`bool`, *optional*, defaults to `True`):
+            Whether or not the model should return the last key/values attentions (not used by all models). Only
+            relevant if `config.is_decoder=True`.
+        pad_token_id (`int`, *optional*):
+            Padding token id.
+        bos_token_id (`int`, *optional*, defaults to 1):
+            Beginning of stream token id.
+        eos_token_id (`int`, *optional*, defaults to 2):
+            End of stream token id.
+        pretraining_tp (`int`, *optional*, defaults to 1):
+            Experimental feature. Tensor parallelism rank used during pretraining. Please refer to [this
+            document](https://huggingface.co/docs/transformers/parallelism) to understand more about it. This value is
+            necessary to ensure exact reproducibility of the pretraining results. Please refer to [this
+            issue](https://github.com/pytorch/pytorch/issues/76232).
+        tie_word_embeddings (`bool`, *optional*, defaults to `False`):
+            Whether to tie weight embeddings
+        rope_theta (`float`, *optional*, defaults to 10000.0):
+            The base period of the RoPE embeddings.
+        rope_scaling (`Dict`, *optional*):
+            Dictionary containing the scaling configuration for the RoPE embeddings. Currently supports two scaling
+            strategies: linear and dynamic. Their scaling factor must be a float greater than 1. The expected format is
+            `{"type": strategy name, "factor": scaling factor}`. When using this flag, don't update
+            `max_position_embeddings` to the expected new maximum.
+        attention_bias (`bool`, defaults to `False`, *optional*, defaults to `False`):
+            Whether to use a bias in the query, key, value and output projection layers during self-attention.
+        attention_dropout (`float`, *optional*, defaults to 0.0):
+            The dropout ratio for the attention probabilities.
+
+    ```python
+    >>> from transformers import DeepseekV3Model, DeepseekV3Config
+
+    >>> # Initializing a Deepseek-V3 style configuration
+    >>> configuration = DeepseekV3Config()
+
+    >>> # Accessing the model configuration
+    >>> configuration = model.config
+    ```"""
+
+    model_type = "deepseek_v3"
+    keys_to_ignore_at_inference = ["past_key_values"]
+
+    def __init__(
+        self,
+        vocab_size=129280,
+        hidden_size=7168,
+        intermediate_size=18432,
+        moe_intermediate_size = 2048,
+        num_hidden_layers=61,
+        num_nextn_predict_layers=1,
+        num_attention_heads=128,
+        num_key_value_heads=128,
+        n_shared_experts = 1,
+        n_routed_experts = 256,
+        ep_size = 1,
+        routed_scaling_factor = 2.5,
+        kv_lora_rank = 512,
+        q_lora_rank = 1536,
+        qk_rope_head_dim = 64,
+        v_head_dim = 128,
+        qk_nope_head_dim = 128,
+        topk_method = 'noaux_tc',
+        n_group = 8,
+        topk_group = 4,
+        num_experts_per_tok = 8,
+        moe_layer_freq = 1,
+        first_k_dense_replace = 3,
+        norm_topk_prob = True,
+        scoring_func = 'sigmoid',
+        aux_loss_alpha = 0.001,
+        seq_aux = True,
+        hidden_act="silu",
+        max_position_embeddings=4096,
+        initializer_range=0.02,
+        rms_norm_eps=1e-6,
+        use_cache=True,
+        pad_token_id=None,
+        bos_token_id=0,
+        eos_token_id=1,
+        pretraining_tp=1,
+        tie_word_embeddings=False,
+        rope_theta=10000.0,
+        rope_scaling=None,
+        attention_bias=False,
+        attention_dropout=0.0,
+        **kwargs,
+    ):
+        self.vocab_size = vocab_size
+        self.max_position_embeddings = max_position_embeddings
+        self.hidden_size = hidden_size
+        self.intermediate_size = intermediate_size
+        self.moe_intermediate_size = moe_intermediate_size
+        self.num_hidden_layers = num_hidden_layers
+        self.num_nextn_predict_layers = num_nextn_predict_layers
+        self.num_attention_heads = num_attention_heads
+        self.n_shared_experts = n_shared_experts
+        self.n_routed_experts = n_routed_experts
+        self.ep_size = ep_size
+        self.routed_scaling_factor = routed_scaling_factor
+        self.kv_lora_rank = kv_lora_rank
+        self.q_lora_rank = q_lora_rank
+        self.qk_rope_head_dim = qk_rope_head_dim
+        self.v_head_dim = v_head_dim
+        self.qk_nope_head_dim = qk_nope_head_dim
+        self.topk_method = topk_method
+        self.n_group = n_group
+        self.topk_group = topk_group
+        self.num_experts_per_tok = num_experts_per_tok
+        self.moe_layer_freq = moe_layer_freq
+        self.first_k_dense_replace = first_k_dense_replace
+        self.norm_topk_prob = norm_topk_prob
+        self.scoring_func = scoring_func
+        self.aux_loss_alpha = aux_loss_alpha
+        self.seq_aux = seq_aux
+        # for backward compatibility
+        if num_key_value_heads is None:
+            num_key_value_heads = num_attention_heads
+
+        self.num_key_value_heads = num_key_value_heads
+        self.hidden_act = hidden_act
+        self.initializer_range = initializer_range
+        self.rms_norm_eps = rms_norm_eps
+        self.pretraining_tp = pretraining_tp
+        self.use_cache = use_cache
+        self.rope_theta = rope_theta
+        self.rope_scaling = rope_scaling
+        self.attention_bias = attention_bias
+        self.attention_dropout = attention_dropout
+
+        super().__init__(
+            pad_token_id=pad_token_id,
+            bos_token_id=bos_token_id,
+            eos_token_id=eos_token_id,
+            tie_word_embeddings=tie_word_embeddings,
+            **kwargs,
+        )

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "do_sample": true,
+  "eos_token_id": 1,
+  "temperature": 0.6,
+  "top_p": 0.95,
+  "transformers_version": "4.57.6"
+}

model-00001-of-00076.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6759bb71a85f7cd30169344af0939f9529dfd5fca22ae6eed284227b193e5afa
+size 4995885736

model-00002-of-00076.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:adc76e4eae04bb73c56e2c38afaa2608bc8bfa3d119bad71236d27b0e9a6ecef
+size 4995056976

model-00003-of-00076.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4355d57b137b34b67c2b4336a5446b88a62794218afacb13035b9c76e10c0f43
+size 4999075520

model-00004-of-00076.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d92e23e7324b0a30c4e34b947e3e001dda836ee91cdafe5532ec1c2ee0ffe4f
+size 4994947240

model-00005-of-00076.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37b2660c03ef47f51ecc25f99dcc52446c52ef4619d80448259f9bafcaee858c
+size 4994947376

model-00006-of-00076.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3211c405272ebff7120cb2890e2129177a9a880d3a7f1d129394b7a46f6ce56
+size 4994947600

model-00007-of-00076.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ff5f294a1c39d74776b0b699c4e5a4609ce058f238c36d5ea6ae7caa7cafc7a
+size 4999185112

model-00008-of-00076.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fea1a392978fa75e2ea4d20be502bd375cd1af0c7a33b21d2fe5e27fc5baa3f6
+size 4994947240

model-00009-of-00076.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed3751349d2119fe99b96420aedae79ff14411e44c80980c544933cc634ee4b2
+size 4994947240

model-00010-of-00076.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cff1d49c8886b70757f064e14d0c58a5c9f3dd521b3ac2d810151b710c2dff37
+size 4994947864

model-00011-of-00076.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4106f960319855cd13d2a7235ecdaaaadfb106b4d5c2d5dbf6c9fcf5bf201252
+size 4916048440

model-00012-of-00076.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83431f80971dc4b46a34fbdd74f89137acb27f39f909df9b7ebb8024206a990f
+size 5000096208

model-00013-of-00076.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e86cdeb3aff490a991bcd535bd00b2d09d93bbd7b7ec61251a22533c59dbeeb3
+size 4994948440

model-00014-of-00076.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:252a5e924f2a3b0b5ae65f425888d4cfd3003d1857012a8b3b921651ab0447a4
+size 4994948536

model-00015-of-00076.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db2f03e02b49553e48373d7c5e4fc2b2c292ae7d7082d0324a7af571904df4be
+size 4994948792

model-00016-of-00076.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c89cde61b00b86ff8426a6bc04ee5043a53d8faae9553be9aaa3f075a4c3d496
+size 4999186440

model-00017-of-00076.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:018ea2d645b71476853833a8d1b6d2589ca7003e3320b852ef96657016151663
+size 4994948432

model-00018-of-00076.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:416e8b56db8f06ec4483ff34320624570e94fa60635310e4886609fc84242c26
+size 4994948440

model-00019-of-00076.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2347062fb9d94570b9c38b0e96bd13b0e18c6e981bb9ad5d0013e780a33b765
+size 4994948680

model-00020-of-00076.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e74a9f69aa604aaa0f0dfbe74eeb371faf0959db93b9c927f46c640bab77a9f
+size 4767866632

model-00021-of-00076.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b68dc983941fbd856e95a21ab6dab7fd2cec00cf70dae5678852fc698d827c75
+size 5000096208

model-00022-of-00076.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46fd8f0734b8c332a17640ab3ca92dba66ea64c10ad9583bc9f0a4716a9adacc
+size 4994948440

model-00023-of-00076.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0be82bf4252cd427b5f38c9dedf79cb80eff6bcffec039cbc2574c5a312f756d
+size 4994948536

model-00024-of-00076.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10d56e72dd7fdf54ddef3b4800182fd54e0525a9bc2355035d7091c780d544c9
+size 4994948792

model-00025-of-00076.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4d1b1a64141e55c9a7666d5c6ef8944a81ebb8e3c94554f3604301381a29e4c
+size 4999186440

model-00026-of-00076.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7336e173e3a2d947e6e1150afda5d1e465d53f992e93bfc3114587048a45dc4
+size 4994948432

model-00027-of-00076.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d555207b5fa75ee79e8ab6138b43f2b5062acc2bdb8c385e07ea478519094d57
+size 4994948440

model-00028-of-00076.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0dbe895e7d30bf2f84f463023a844dfcb07da32ba2425a86f5911e302149ebe6
+size 4994948680

model-00029-of-00076.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fcef0a7c4cfc13b2327b1e9c48f53f3973d04c8a0ff9ede061aa718a40b36cf0
+size 4767866632

model-00030-of-00076.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3fedc9cd5e258af53c2723c761b69b4178d8dd2cdb8ec3b2b3540091e8230e8
+size 5000096208

model-00031-of-00076.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2865ba423039f7ed8d1d78ea7565d9616df833ce8cfec53194bfe4b1639825e7
+size 4994948440

model-00032-of-00076.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7d1264b48a563ca998961ddd1c17de6bbaa962673db9ab26f511cc6cf06e103
+size 4994948536

model-00033-of-00076.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:384076b04fa378c492c259906711e3d2d9e23748e244d223b5c7f61f65c3b2cf
+size 4994948792

model-00034-of-00076.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:388168d4031b159e191ce671f8169a01557f868144d100c2e2b2a7a73af2d7b5
+size 4999186440

model-00035-of-00076.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aac8369cc02716f812eb0f89607d6f5c42cb5e56d3ed20031260b3f850752ded
+size 4994948432

model-00036-of-00076.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3bccd18590c02f509b9a4b5e503d3f41d658eede4902c6073542d85c4ab119c8
+size 4994948440

model-00037-of-00076.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf997c179127a4c56bce49ff7922c001c96c0d1abfd7970ef675cf8c64b01aa9
+size 4994948680

model-00038-of-00076.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a77f2ae97905a2616f6a1129b4d27697e1e73f6d8edbf27f9c75f91be25a5fe3
+size 4767866632

model-00039-of-00076.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f257ad80411006f3356005c4eee47bec74e3970b1ff4803e31a5b17fb06c634
+size 5000096208

model-00040-of-00076.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97237e87a51f1a66048ced46a61504585d8c3e25a38d92381c5c120c07dc1145
+size 4994948440

model-00041-of-00076.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e166db426c5986878b52130d0b0171f812901711893d28cecf4e0abd7f9a285b
+size 4994948536

model-00042-of-00076.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f90bd22d9dfe84eee496a1eb4ba21f457dbaed399c0383df6d8dba16676b274
+size 4994948792

model-00043-of-00076.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0edc68a1b0177319632f4ecc595fd24184652dcf4c234cf66c0fd32195b7283e
+size 4999186440

model-00044-of-00076.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:816fc641f71f09c3b32b7345b34f9b0cbfc0a22181f83b80f148d775d14a2347
+size 4994948432

model-00045-of-00076.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea1745877489e4e2cd1980b83e2120e99f93e119d3ba24f873fc445a6cfb5c10
+size 4994948440

model-00046-of-00076.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00b02ea0527176c39e34f12cf79cc0f5f816d7d623d703f1c8d3094fc69bc7d3
+size 4994948680