Upload folder using huggingface_hub

config.json

@@ -1,10 +1,25 @@
 {
-  "model_type": "test_tiny_model",
-  "vocab_size": 1000,
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
   "hidden_size": 128,
+  "initializer_range": 0.02,
   "intermediate_size": 256,
-  "num_hidden_layers": 1,
-  "architectures": [
-    "TinyTestModel"
-  ]
+  "max_position_embeddings": 512,
+  "model_type": "llama",
+  "num_attention_heads": 4,
+  "num_hidden_layers": 2,
+  "num_key_value_heads": 4,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.36.0",
+  "use_cache": true,
+  "vocab_size": 1000
 }

generation_config.json

@@ -0,0 +1,5 @@
+{
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "max_length": 512
+}

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8523a121065d512d58f624e0f366e4bf88e1fa0655a34a4562bd8b32c518c32
-size 775064
+oid sha256:a3f6296e3d9c8e0b2cb50461d2701147946359d09f476f873a4209192931f641
+size 1169432

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b6da2e1a2a6ef5ec681f1a75263ca86f2c0d4fe8ebc42a52d2ffe7f17e84136
-size 643856
+oid sha256:5487fb43332d62b17d6389ed65ce9eca9ffe1def0135a9fdb1a5c025d6ddb8ac
+size 1170016

model.safetensors.index.json

@@ -1,14 +1,28 @@
 {
   "metadata": {
-    "total_size": 1000000
+    "total_size": 2337280
   },
   "weight_map": {
     "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
     "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.0.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
-    "lm_head.weight": "model-00002-of-00002.safetensors",
-    "model.norm.weight": "model-00002-of-00002.safetensors"
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.norm.weight": "model-00002-of-00002.safetensors",
+    "lm_head.weight": "model-00002-of-00002.safetensors"
   }
 }