initial model release

.gitattributes

@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+lora.safetensors filter=lfs diff=lfs merge=lfs -text
+tekken.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,9 @@
+# Overview
+
+This model was trained via [mistral-finetune](https://github.com/mistralai/mistral-finetune/) on top
+of the [orkl.eu](https://orkl.eu) dataset.
+For details on the model, the data and training, please read [https://github.com/ctitools/neurocti/](https://github.com/ctitools/neurocti/).
+
+For understanding how to run this model, please read: [https://github.com/ctitools/neurocti/blob/main/inference.md](https://github.com/ctitools/neurocti/blob/main/inference.md) 
+
+

lora.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8be7f9c38b9eea74d0257878ff62264f886493d64d4f85235ae893d907c1abfb
+size 912324400

params.json

@@ -0,0 +1,18 @@
+{
+    "dim": 5120,
+    "n_layers": 40,
+    "head_dim": 128,
+    "hidden_dim": 14336,
+    "n_heads": 32,
+    "n_kv_heads": 8,
+    "norm_eps": 1e-05,
+    "vocab_size": 131072,
+    "rope_theta": 1000000.0,
+    "lora": {
+        "enable": true,
+        "rank": 128,
+        "dropout": 0.0,
+        "scaling": 2.0
+    },
+    "moe": null
+}

tekken.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eccd1665d2e477697c33cb7f0daa6f6dfefc57a0a6bceb66d4be52952f827516
+size 14801223