Upload MobileLLMForCausalLM

config.json

@@ -1,33 +1,35 @@
 {
-  "_name_or_path": "MobiLlama",
   "architectures": [
-    "MobiLlamaForCausalLM"
+    "MobileLLMForCausalLM"
   ],
-  "auto_map": {
-    "AutoModelForCausalLM": "modeling_mobillama.MobiLlamaForCausalLM"
-  },
   "attention_bias": false,
   "attention_dropout": 0.0,
+  "auto_map": {
+    "AutoConfig": "facebook/MobileLLM-1B--configuration_mobilellm.MobileLLMConfig",
+    "AutoModelForCausalLM": "facebook/MobileLLM-1B--modeling_mobilellm.MobileLLMForCausalLM"
+  },
   "bos_token_id": 1,
   "eos_token_id": 2,
   "head_dim": 64,
   "hidden_act": "silu",
-  "hidden_size": 2048,
+  "hidden_size": 1280,
   "initializer_range": 0.02,
-  "intermediate_size": 5632,
+  "intermediate_size": 3584,
+  "layer_sharing": false,
   "max_position_embeddings": 2048,
   "mlp_bias": false,
-  "model_type": "llama",
-  "num_attention_heads": 32,
-  "num_hidden_layers": 22,
-  "num_key_value_heads": 4,
+  "model_type": "mobilellm",
+  "num_attention_heads": 20,
+  "num_hidden_layers": 54,
+  "num_key_value_heads": 5,
   "pretraining_tp": 1,
   "rms_norm_eps": 1e-05,
   "rope_scaling": null,
   "rope_theta": 10000.0,
+  "share_embedding": true,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.50.0",
   "use_cache": true,
-  "vocab_size": 32000
+  "vocab_size": 32064
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a2b6f2b860b119c1d6f7b3225d79742047a9f58e0cfdb50c2895794e6f9f0dc2
-size 2523085296
+oid sha256:11d164a8250297a034a4c95a4d526a0fb6f20cd6cca56f75e33bc7424f482de7
+size 2011143520