Upload LlamaForCausalLM

config.json

@@ -6,17 +6,17 @@
   "attention_dropout": 0.0,
   "bos_token_id": 1,
   "eos_token_id": 2,
-  "head_dim": 128,
+  "head_dim": 64,
   "hidden_act": "silu",
-  "hidden_size": 4096,
+  "hidden_size": 2048,
   "initializer_range": 0.02,
-  "intermediate_size": 11008,
-  "max_position_embeddings": 4096,
+  "intermediate_size": 5632,
+  "max_position_embeddings": 2048,
   "mlp_bias": false,
   "model_type": "llama",
   "num_attention_heads": 32,
-  "num_hidden_layers": 32,
-  "num_key_value_heads": 32,
+  "num_hidden_layers": 22,
+  "num_key_value_heads": 4,
   "pretraining_tp": 1,
   "rms_norm_eps": 1e-05,
   "rope_scaling": null,
@@ -25,5 +25,5 @@
   "torch_dtype": "bfloat16",
   "transformers_version": "4.50.0",
   "use_cache": true,
-  "vocab_size": 32064
+  "vocab_size": 32000
 }

generation_config.json

@@ -1,10 +1,7 @@
 {
   "bos_token_id": 1,
-  "do_sample": true,
   "eos_token_id": 2,
-  "max_length": 4096,
+  "max_length": 2048,
   "pad_token_id": 0,
-  "temperature": 0.6,
-  "top_p": 0.9,
   "transformers_version": "4.50.0"
 }

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fec7585dc085ebdc5c89fcada48c950170213249f22b2f6b4e6ac04bb224027b
+size 2200119864