Upload LlamaForCausalLM

config.json

@@ -5,26 +5,26 @@
   "attention_bias": false,
   "attention_dropout": 0.0,
   "bos_token_id": 1,
-  "eos_token_id": 32001,
-  "head_dim": 80,
+  "eos_token_id": 0,
+  "head_dim": 64,
   "hidden_act": "silu",
-  "hidden_size": 480,
+  "hidden_size": 512,
   "initializer_range": 0.02,
-  "intermediate_size": 1920,
+  "intermediate_size": 1280,
   "max_position_embeddings": 2048,
   "mlp_bias": false,
   "model_type": "llama",
-  "num_attention_heads": 6,
-  "num_hidden_layers": 32,
-  "num_key_value_heads": 2,
-  "pad_token_id": 32003,
+  "num_attention_heads": 8,
+  "num_hidden_layers": 30,
+  "num_key_value_heads": 4,
+  "pad_token_id": 0,
   "pretraining_tp": 1,
   "rms_norm_eps": 1e-06,
   "rope_scaling": null,
   "rope_theta": 10000.0,
   "tie_word_embeddings": true,
   "torch_dtype": "float32",
-  "transformers_version": "4.51.3",
+  "transformers_version": "4.53.2",
   "use_cache": true,
-  "vocab_size": 32018
+  "vocab_size": 32000
 }

generation_config.json

@@ -1,7 +1,7 @@
 {
   "_from_model_config": true,
   "bos_token_id": 1,
-  "eos_token_id": 32001,
-  "pad_token_id": 32003,
-  "transformers_version": "4.51.3"
+  "eos_token_id": 0,
+  "pad_token_id": 0,
+  "transformers_version": "4.53.2"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d8bc9cee9bf614f544b87dae1f3d4bb6870b721fd62e7283d8b34c20fe79728
-size 494169296
+oid sha256:de1ba36d17d8e71757b8780935ce701c6847bc876f55575a1981e87f1ea1db43
+size 395992680