Upload 3 files

config.json

@@ -1,13 +1,29 @@
 {
-    "model_type": "llama",
-    "block_size": 512,
-    "vocab_size": 4096,
-    "n_layer": 6,
-    "n_head": 4,
-    "n_embd": 256,
-    "n_intermediate": 683,
-    "rotary_dim": 42,
-    "n_ctx": 512,
-    "n_key_value_heads": 2,
-    "flash_attention": true
-  }
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 256,
+  "initializer_range": 0.02,
+  "intermediate_size": 682,
+  "max_position_embeddings": 512,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 4,
+  "num_hidden_layers": 6,
+  "num_key_value_heads": 2,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.48.3",
+  "use_cache": true,
+  "vocab_size": 4096
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.48.3"
+}

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f791f1d93dcabff74b1bbe0e4821eaa4944ed8d52bccde42df8aac6af9b9a358
-size 33022552
+oid sha256:2ec9cd42254ad279e097c6213b4691be6822d9fe644edf0cc255554d1afb8d6d
+size 21502880