Upload LlamaForCausalLM

config.json

@@ -8,14 +8,15 @@
   "bos_token_id": 1,
   "eos_token_id": 2,
   "hidden_act": "silu",
-  "hidden_size": 4096,
+  "hidden_size": 16,
   "initializer_range": 0.02,
-  "intermediate_size": 11008,
+  "intermediate_size": 43,
   "max_position_embeddings": 4096,
   "model_type": "llama",
-  "num_attention_heads": 32,
-  "num_hidden_layers": 32,
-  "num_key_value_heads": 32,
+  "num_attention_heads": 4,
+  "num_hidden_layers": 4,
+  "num_key_value_heads": 4,
+  "pad_token_id": 0,
   "pretraining_tp": 1,
   "rms_norm_eps": 1e-05,
   "rope_scaling": null,

generation_config.json

@@ -2,5 +2,6 @@
   "_from_model_config": true,
   "bos_token_id": 1,
   "eos_token_id": 2,
+  "pad_token_id": 0,
   "transformers_version": "4.39.0.dev0"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:621ce77eeac2cf4ee003c4283ac8431b6b2639e445cc91cdd931b75fd0c394c8
-size 4150064
+oid sha256:7d2530ad0e41fd373983807e2554e71a9390dce60b7bd6c396ca72eaf2e82e7c
+size 2077072