Upload MemoryLLM

config.json

@@ -0,0 +1,57 @@
+{
+  "_name_or_path": "memoryllm-8b",
+  "add_bos_embedding": true,
+  "add_decoder_lora": true,
+  "architectures": [
+    "MemoryLLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "drop_memory_per_layer": true,
+  "eos_token_id": 128001,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "lora_config": {
+    "inference_mode": false,
+    "lora_alpha": 32,
+    "lora_dropout": 0.1,
+    "r": 16,
+    "target_modules": [
+      "q_proj",
+      "v_proj",
+      "k_proj",
+      "up_proj",
+      "down_proj",
+      "gate_proj"
+    ]
+  },
+  "max_length": 512,
+  "max_position_embeddings": 8192,
+  "max_seq_length": 2048,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "new_memory_embedding_fullset": true,
+  "num_attention_heads": 32,
+  "num_blocks": 50,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "num_memory_tokens": 12800,
+  "num_tokens": 256,
+  "pad_token_id": 128001,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 1.8125,
+    "type": "linear"
+  },
+  "rope_theta": 500000.0,
+  "shrink_to_one_embedding": true,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.43.0.dev0",
+  "use_cache": true,
+  "vocab_size": 128256
+}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": 128001,
+  "max_length": 4096,
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.43.0.dev0"
+}

model-00001-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8e08962581754c00a1629d551316f96657cadd2e74347f145c733a48f8c7772
+size 6710886520

model-00002-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6106190f4ebbcd495a788dbac3a905ccfbfc4e88497393facb2c018bc82f6331
+size 4917689241

model-00003-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f295de529ad2fcf6e82c0c70f289d6fc609fc2e9e054b887ff430233502bd2f
+size 4883929088

model-00004-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd32f16d2abdf2cc5f11cc7ac48d8e98b3c45cbb4e30f7c5b89474d2d01e1084
+size 4816854808

model-00005-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:377706345fd2e811011b2fc316a9cdc185660d7657b9ba7721e2d964f7cb29fd
+size 4883929264

model-00006-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1618014f1e97e50f3feb2451ebac0a7081251529c9afbd9b09dae7d9533e373c
+size 4816854856

model-00007-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d210c8100af2339cedf5f45a2018dc8b490a59b0b9d8e8c89150d22e3a29ca4f
+size 4883929264

model-00008-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a491996b7f24ef0153397115891857332dc82cb4767a75f881eb59ff99b4805
+size 3220526344