trained with long-pajama v1.0.0

neurocache_adapter/adapter_config.json

@@ -0,0 +1,38 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-1.5B",
+  "bias": "none",
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": false,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": [
+    21,
+    23,
+    25,
+    27
+  ],
+  "loftq_config": {},
+  "lora_alpha": 128,
+  "lora_bias": false,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj",
+    "k_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

neurocache_config.json

@@ -0,0 +1,27 @@
+{
+  "attention_layers": [
+    21,
+    23,
+    25,
+    27
+  ],
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-1.5B",
+  "cache_dtype": "float16",
+  "cache_size": 32768,
+  "cache_type": "FIFO",
+  "compression_factor": 3,
+  "context_size": 2,
+  "global_cache": true,
+  "inference_mode": true,
+  "neighborhood_size": 2,
+  "neurocache_type": "ONDEVICE",
+  "pooling_window": 16,
+  "retrieval_map": {
+    "16": 16
+  },
+  "retrieval_stride": 4,
+  "similarity_fn": "l2",
+  "task_type": "CAUSAL_LM",
+  "topk": 8
+}

neurocache_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29316c6e2639e64c3701ec419d9ce433f024b284183d26841053794ff9f1b986
+size 66928206