Upload LlamaForCausalLM

config.json

@@ -4,34 +4,26 @@
   ],
   "attention_bias": false,
   "attention_dropout": 0.0,
-  "bos_token_id": 128000,
+  "bos_token_id": 1,
   "dtype": "float32",
-  "eos_token_id": 128009,
+  "eos_token_id": 2,
   "head_dim": 32,
   "hidden_act": "silu",
   "hidden_size": 4096,
   "initializer_range": 0.02,
   "intermediate_size": 512,
-  "max_position_embeddings": 131072,
+  "max_position_embeddings": 4096,
   "mlp_bias": false,
   "model_type": "llama",
   "num_attention_heads": 4,
   "num_hidden_layers": 4,
   "num_key_value_heads": 2,
-  "pad_token_id": 1,
   "pretraining_tp": 1,
   "rms_norm_eps": 1e-05,
-  "rope_scaling": {
-    "factor": 8.0,
-    "high_freq_factor": 4.0,
-    "low_freq_factor": 1.0,
-    "original_max_position_embeddings": 8192,
-    "rope_type": "llama3"
-  },
-  "rope_theta": 500000.0,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
   "tie_word_embeddings": false,
   "transformers_version": "4.56.2",
-  "unsloth_fixed": true,
   "use_cache": true,
-  "vocab_size": 16384
+  "vocab_size": 32000
 }

generation_config.json

@@ -1,7 +1,6 @@
 {
   "_from_model_config": true,
-  "bos_token_id": 128000,
-  "eos_token_id": 128009,
-  "pad_token_id": 1,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
   "transformers_version": "4.56.2"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb64dade7389ae684347ef8a69c7faa532b47dd9399ab4450f8ed9918500c2ba
-size 662851816
+oid sha256:c9d5026d9952394f3b93230977e09f63674787ee603f29f8d51d97c50a34bd16
+size 1174556976