初始化项目，由ModelHub XC社区提供模型

Model: mlx-community/sarashina2.2-3b-instruct-v0.1 Source: Original Platform
2026-04-29 02:16:59 +08:00
commit f5faf9157d
13 changed files with 729 additions and 0 deletions
--- a/config.json
+++ b/config.json
@@ -0,0 +1,29 @@
+{
+    "architectures": [
+        "LlamaForCausalLM"
+    ],
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "bos_token_id": 1,
+    "eos_token_id": 2,
+    "head_dim": 160,
+    "hidden_act": "silu",
+    "hidden_size": 2560,
+    "initializer_range": 0.02,
+    "intermediate_size": 8960,
+    "max_position_embeddings": 8192,
+    "mlp_bias": false,
+    "model_type": "llama",
+    "num_attention_heads": 16,
+    "num_hidden_layers": 32,
+    "num_key_value_heads": 8,
+    "pretraining_tp": 1,
+    "rms_norm_eps": 1e-05,
+    "rope_scaling": null,
+    "rope_theta": 500000,
+    "tie_word_embeddings": false,
+    "torch_dtype": "bfloat16",
+    "transformers_version": "4.46.3",
+    "use_cache": false,
+    "vocab_size": 102400
+}