初始化项目，由ModelHub XC社区提供模型

Model: mehmetkeremturkcan/SmollerLM2-10M-sftb Source: Original Platform
2026-04-11 12:37:01 +08:00
commit bb2e296c5a
15 changed files with 338637 additions and 0 deletions
--- a/config.json
+++ b/config.json
@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "mehmetkeremturkcan/SmollerLM2-10M",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 60,
+  "initializer_range": 0.041666666666666664,
+  "intermediate_size": 168,
+  "is_llama_config": true,
+  "max_position_embeddings": 8192,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 9,
+  "num_hidden_layers": 30,
+  "num_key_value_heads": 3,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_interleaved": false,
+  "rope_scaling": null,
+  "rope_theta": 100000,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.48.1",
+  "use_cache": false,
+  "vocab_size": 49152
+}