Upload config.json with huggingface_hub

config.json

@@ -0,0 +1,96 @@
+{
+  "architectures": [
+    "DeepseekV41ForCausalLM"
+  ],
+  "model_type": "deepseek_v41",
+  "dtype": "bfloat16",
+  "transformers_version": "5.6.0",
+  "bos_token_id": 1,
+  "eos_token_id": 1,
+  "pad_token_id": 2,
+  "text_config": {
+    "model_type": "deepseek_v41_text",
+    "vocab_size": 129280,
+    "hidden_size": 128,
+    "moe_intermediate_size": 256,
+    "num_hidden_layers": 6,
+    "num_attention_heads": 4,
+    "num_key_value_heads": 1,
+    "head_dim": 512,
+    "qk_rope_head_dim": 64,
+    "q_lora_rank": 128,
+    "o_lora_rank": 128,
+    "o_groups": 2,
+    "hidden_act": "silu",
+    "swiglu_limit": 10.0,
+    "rms_norm_eps": 1e-20,
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "initializer_range": 0.02,
+    "use_cache": true,
+    "tie_word_embeddings": false,
+    "max_position_embeddings": 1048576,
+    "rope_theta": 10000,
+    "rope_scaling": {
+      "rope_type": "yarn",
+      "factor": 16,
+      "beta_fast": 32,
+      "beta_slow": 1,
+      "original_max_position_embeddings": 65536
+    },
+    "n_routed_experts": 32,
+    "n_shared_experts": 1,
+    "num_experts_per_tok": 6,
+    "scoring_func": "sqrtsoftplus",
+    "topk_method": "noaux_tc",
+    "norm_topk_prob": true,
+    "routed_scaling_factor": 1.5,
+    "sliding_window": 128,
+    "compress_ratios": [
+      0,
+      2,
+      2,
+      1,
+      1,
+      0
+    ],
+    "compress_rope_theta": 160000,
+    "kv_source_layer_ids": [
+      1,
+      3
+    ],
+    "index_source_layer_ids": [
+      1,
+      3
+    ],
+    "index_n_heads": 4,
+    "index_head_dim": 128,
+    "index_topk": 512,
+    "candidate_source_layer_id": 3,
+    "candidate_topk_blocks": 2048,
+    "candidate_block_size": 8,
+    "hc_mult": 4,
+    "hc_sinkhorn_iters": 20,
+    "hc_eps": 1e-06,
+    "engram_layer_ids": [
+      1,
+      2
+    ],
+    "engram_num_embeddings": [
+      6748,
+      7592
+    ],
+    "engram_max_ngram_size": 4,
+    "engram_vocab_size": 512,
+    "engram_n_heads": 4,
+    "engram_head_dim": 64,
+    "engram_pad_token_id": 2,
+    "engram_compressed_vocab_size": 99092,
+    "num_nextn_predict_layers": 0,
+    "bos_token_id": 1
+  },
+  "penny": {
+    "trained_seq_len": 8192,
+    "source_checkpoint": "outputs/model_final.pt"
+  }
+}