初始化项目，由ModelHub XC社区提供模型

Model: mlx-community/Nemotron-Mini-4B-Instruct-bf16-mlx Source: Original Platform
2026-09-01 06:31:13 +08:00
commit 272b0415c7
9 changed files with 485 additions and 0 deletions
--- a/config.json
+++ b/config.json
@@ -0,0 +1,25 @@
+{
+    "architectures": [
+        "NemotronForCausalLM"
+    ],
+    "bos_token_id": 2,
+    "eos_token_id": 3,
+    "hidden_act": "relu2",
+    "hidden_size": 3072,
+    "initializer_range": 0.0134,
+    "intermediate_size": 9216,
+    "kv_channels": 128,
+    "max_position_embeddings": 4096,
+    "model_type": "nemotron",
+    "norm_eps": 1e-05,
+    "num_attention_heads": 24,
+    "num_hidden_layers": 32,
+    "num_key_value_heads": 8,
+    "partial_rotary_factor": 0.5,
+    "rope_theta": 10000,
+    "tie_word_embeddings": false,
+    "torch_dtype": "bfloat16",
+    "transformers_version": "4.32.0.dev0",
+    "use_cache": true,
+    "vocab_size": 256000
+}