Upload model

config.json

@@ -1,21 +1,21 @@
 {
-  "_name_or_path": "yujiepan/llama-2-tiny-3layers-random",
+  "_name_or_path": "michaelbenayoun/llama-2-tiny-16layers-random",
   "architectures": [
-    "LlamaForCausalLM"
+    "LlamaModel"
   ],
   "attention_bias": false,
   "bos_token_id": 1,
   "eos_token_id": 2,
   "hidden_act": "silu",
-  "hidden_size": 8,
+  "hidden_size": 32,
   "initializer_range": 0.02,
   "intermediate_size": 32,
   "is_decoder": true,
   "max_position_embeddings": 4096,
   "model_type": "llama",
-  "num_attention_heads": 2,
+  "num_attention_heads": 32,
   "num_hidden_layers": 16,
-  "num_key_value_heads": 2,
+  "num_key_value_heads": 32,
   "pad_token_id": 0,
   "pretraining_tp": 1,
   "rms_norm_eps": 1e-06,
@@ -23,7 +23,7 @@
   "rope_theta": 10000.0,
   "tie_word_embeddings": false,
   "torch_dtype": "float32",
-  "transformers_version": "4.35.0.dev0",
+  "transformers_version": "4.35.0",
   "use_cache": true,
   "vocab_size": 32000
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:73ac0d273620206476297d8052d4adcb5796d1cd6571052a4b8cceb9306e59eb
-size 2129840
+oid sha256:a69884da893fe5f8c6dd79a0854c4916dfd322a04e6a363a44e11754b370e7da
+size 4573472