Upload LlamaForCausalLM

config.json

@@ -1,30 +1,40 @@
 {
-  "_name_or_path": "open-unlearning/tofu_Llama-2-7b-chat-hf_full",
+  "_name_or_path": "open-unlearning/tofu_Llama-3.2-1B-Instruct_full",
   "architectures": [
     "LlamaForCausalLM"
   ],
   "attention_bias": false,
   "attention_dropout": 0.0,
-  "bos_token_id": 1,
-  "eos_token_id": 2,
-  "head_dim": 128,
+  "bos_token_id": 128000,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "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": 8192,
+  "max_position_embeddings": 131072,
   "mlp_bias": false,
   "model_type": "llama",
   "num_attention_heads": 32,
-  "num_hidden_layers": 32,
-  "num_key_value_heads": 32,
+  "num_hidden_layers": 16,
+  "num_key_value_heads": 8,
   "pretraining_tp": 1,
   "rms_norm_eps": 1e-05,
-  "rope_scaling": null,
-  "rope_theta": 10000.0,
-  "tie_word_embeddings": false,
+  "rope_scaling": {
+    "factor": 32.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": true,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.45.1",
   "use_cache": true,
-  "vocab_size": 32000
+  "vocab_size": 128256
 }

generation_config.json

@@ -1,9 +1,11 @@
 {
-  "bos_token_id": 1,
+  "bos_token_id": 128000,
   "do_sample": true,
-  "eos_token_id": 2,
-  "max_length": 4096,
-  "pad_token_id": 0,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
   "temperature": 0.6,
   "top_p": 0.9,
   "transformers_version": "4.45.1"

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9304f9dbe048b33de28e13bc79b659b9d62ccc66f5f0348d173ec4bf88ea888
+size 2471645608