Upload LlamaForCausalLM

config.json

@@ -4,34 +4,24 @@
   ],
   "attention_bias": false,
   "attention_dropout": 0.0,
-  "bos_token_id": 128000,
-  "dtype": "bfloat16",
-  "eos_token_id": [
-    128001,
-    128008,
-    128009
-  ],
-  "head_dim": 128,
+  "bos_token_id": 1,
+  "dtype": "float32",
+  "eos_token_id": 2,
+  "head_dim": 2,
   "hidden_act": "silu",
   "hidden_size": 8,
   "initializer_range": 0.02,
   "intermediate_size": 32,
-  "max_position_embeddings": 131072,
+  "max_position_embeddings": 2048,
   "mlp_bias": false,
   "model_type": "llama",
   "num_attention_heads": 4,
   "num_hidden_layers": 2,
   "num_key_value_heads": 2,
   "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,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
   "tie_word_embeddings": false,
   "transformers_version": "4.57.0.dev0",
   "use_cache": true,

generation_config.json

@@ -1,10 +1,6 @@
 {
   "_from_model_config": true,
-  "bos_token_id": 128000,
-  "eos_token_id": [
-    128001,
-    128008,
-    128009
-  ],
+  "bos_token_id": 1,
+  "eos_token_id": 2,
   "transformers_version": "4.57.0.dev0"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c1afb326c8e2d0b95b3f50073235a0230debacae62b35828c349fa7cedd17a75
-size 4158696
+oid sha256:0f7494b6afe60a6022798573d2492b1783ee19da35207e5aa63b0ad6b6524111
+size 8218384