Upload ExtendedLlamaForCausalLM

config.json

@@ -3,10 +3,6 @@
   "architectures": [
     "ExtendedLlamaForCausalLM"
   ],
-  "auto_map": {
-    "AutoConfig": "configuration_llama.ExtendedLlamaConfig",
-    "AutoModelForCausalLM": "modeling_llama.ExtendedLlamaForCausalLM"
-  },
   "attention_bias": false,
   "attention_dropout": 0.0,
   "bos_token_id": 1,
@@ -16,15 +12,16 @@
   "initializer_range": 0.02,
   "intermediate_size": 11008,
   "mask_by_sim": true,
-  "max_position_embeddings": 2048,
+  "max_position_embeddings": 4096,
   "memory_device": "cpu",
   "memory_type": "manual",
   "model_type": "extended-llama",
   "num_attention_heads": 32,
   "num_hidden_layers": 32,
   "num_key_value_heads": 32,
+  "pad_token_id": 0,
   "pretraining_tp": 1,
-  "rms_norm_eps": 1e-06,
+  "rms_norm_eps": 1e-05,
   "rope_scaling": null,
   "rope_theta": 10000.0,
   "sim_threshold": 0.25,

generation_config.json

@@ -0,0 +1,10 @@
+{
+  "bos_token_id": 1,
+  "do_sample": true,
+  "eos_token_id": 2,
+  "max_length": 4096,
+  "pad_token_id": 0,
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.32.0"
+}

pytorch_model-00001-of-00003.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ddeadea41be4444c64dec83e3401d7cb98463af0a49e3689e7c06442059e7f6
-size 9877991673
+oid sha256:539bf751b68061957c4dab561a1e9a1f7da2549bb2aaeb390f0f9cb0c0e85166
+size 9877990073

pytorch_model-00002-of-00003.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6dfcc690e9ce1555d682a3ae396ffabbb90dd54d5817b2c66a81e8526685e001
-size 9894803229
+oid sha256:72a9aba67ed4a7aa2e103ac7faec800dc8dffa230f09c139c185e2dd0afe50bf
+size 9894801501

pytorch_model-00003-of-00003.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0de6cf55d0c498b3f6a5463ac215e43ff1bcde723af45eadc24b10ac840922bc
-size 7180992352
+oid sha256:bc105461dbecf5eb4f905c3aaf253be05dcc94051dd4b268f38f926044e4c569
+size 7180991136