Upload Kayra-Stable with SafeTensors format - 85M params, fine-tuned on 21K Turkish QA

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5fbfb41d9496a98b485cd2d67e20531e23603c17f8913d59c6f9af77f9ced7
+size 429978064

model.safetensors.index.json

@@ -0,0 +1,91 @@
+{
+  "metadata": {
+    "total_size": 429978064
+  },
+  "weight_map": {
+    "tok_emb.weight": "model.safetensors",
+    "pos_emb.weight": "model.safetensors",
+    "blocks.0.norm1.weight": "model.safetensors",
+    "blocks.0.attn.mask": "model.safetensors",
+    "blocks.0.attn.qkv.weight": "model.safetensors",
+    "blocks.0.attn.proj.weight": "model.safetensors",
+    "blocks.0.norm2.weight": "model.safetensors",
+    "blocks.0.ff.w1.weight": "model.safetensors",
+    "blocks.0.ff.w2.weight": "model.safetensors",
+    "blocks.0.ff.w3.weight": "model.safetensors",
+    "blocks.1.norm1.weight": "model.safetensors",
+    "blocks.1.attn.mask": "model.safetensors",
+    "blocks.1.attn.qkv.weight": "model.safetensors",
+    "blocks.1.attn.proj.weight": "model.safetensors",
+    "blocks.1.norm2.weight": "model.safetensors",
+    "blocks.1.ff.w1.weight": "model.safetensors",
+    "blocks.1.ff.w2.weight": "model.safetensors",
+    "blocks.1.ff.w3.weight": "model.safetensors",
+    "blocks.2.norm1.weight": "model.safetensors",
+    "blocks.2.attn.mask": "model.safetensors",
+    "blocks.2.attn.qkv.weight": "model.safetensors",
+    "blocks.2.attn.proj.weight": "model.safetensors",
+    "blocks.2.norm2.weight": "model.safetensors",
+    "blocks.2.ff.w1.weight": "model.safetensors",
+    "blocks.2.ff.w2.weight": "model.safetensors",
+    "blocks.2.ff.w3.weight": "model.safetensors",
+    "blocks.3.norm1.weight": "model.safetensors",
+    "blocks.3.attn.mask": "model.safetensors",
+    "blocks.3.attn.qkv.weight": "model.safetensors",
+    "blocks.3.attn.proj.weight": "model.safetensors",
+    "blocks.3.norm2.weight": "model.safetensors",
+    "blocks.3.ff.w1.weight": "model.safetensors",
+    "blocks.3.ff.w2.weight": "model.safetensors",
+    "blocks.3.ff.w3.weight": "model.safetensors",
+    "blocks.4.norm1.weight": "model.safetensors",
+    "blocks.4.attn.mask": "model.safetensors",
+    "blocks.4.attn.qkv.weight": "model.safetensors",
+    "blocks.4.attn.proj.weight": "model.safetensors",
+    "blocks.4.norm2.weight": "model.safetensors",
+    "blocks.4.ff.w1.weight": "model.safetensors",
+    "blocks.4.ff.w2.weight": "model.safetensors",
+    "blocks.4.ff.w3.weight": "model.safetensors",
+    "blocks.5.norm1.weight": "model.safetensors",
+    "blocks.5.attn.mask": "model.safetensors",
+    "blocks.5.attn.qkv.weight": "model.safetensors",
+    "blocks.5.attn.proj.weight": "model.safetensors",
+    "blocks.5.norm2.weight": "model.safetensors",
+    "blocks.5.ff.w1.weight": "model.safetensors",
+    "blocks.5.ff.w2.weight": "model.safetensors",
+    "blocks.5.ff.w3.weight": "model.safetensors",
+    "blocks.6.norm1.weight": "model.safetensors",
+    "blocks.6.attn.mask": "model.safetensors",
+    "blocks.6.attn.qkv.weight": "model.safetensors",
+    "blocks.6.attn.proj.weight": "model.safetensors",
+    "blocks.6.norm2.weight": "model.safetensors",
+    "blocks.6.ff.w1.weight": "model.safetensors",
+    "blocks.6.ff.w2.weight": "model.safetensors",
+    "blocks.6.ff.w3.weight": "model.safetensors",
+    "blocks.7.norm1.weight": "model.safetensors",
+    "blocks.7.attn.mask": "model.safetensors",
+    "blocks.7.attn.qkv.weight": "model.safetensors",
+    "blocks.7.attn.proj.weight": "model.safetensors",
+    "blocks.7.norm2.weight": "model.safetensors",
+    "blocks.7.ff.w1.weight": "model.safetensors",
+    "blocks.7.ff.w2.weight": "model.safetensors",
+    "blocks.7.ff.w3.weight": "model.safetensors",
+    "blocks.8.norm1.weight": "model.safetensors",
+    "blocks.8.attn.mask": "model.safetensors",
+    "blocks.8.attn.qkv.weight": "model.safetensors",
+    "blocks.8.attn.proj.weight": "model.safetensors",
+    "blocks.8.norm2.weight": "model.safetensors",
+    "blocks.8.ff.w1.weight": "model.safetensors",
+    "blocks.8.ff.w2.weight": "model.safetensors",
+    "blocks.8.ff.w3.weight": "model.safetensors",
+    "blocks.9.norm1.weight": "model.safetensors",
+    "blocks.9.attn.mask": "model.safetensors",
+    "blocks.9.attn.qkv.weight": "model.safetensors",
+    "blocks.9.attn.proj.weight": "model.safetensors",
+    "blocks.9.norm2.weight": "model.safetensors",
+    "blocks.9.ff.w1.weight": "model.safetensors",
+    "blocks.9.ff.w2.weight": "model.safetensors",
+    "blocks.9.ff.w3.weight": "model.safetensors",
+    "norm.weight": "model.safetensors",
+    "lm_head.weight": "model.safetensors"
+  }
+}

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c16a92b3b5f4483bf009f380f64d102490fb370ee19193f77bdfe1672de471c6
-size 348075968
+oid sha256:2fcc6374e94e8a9f680e93c64b7d54171647b14e1461ba396ca2d80e4727c1b7
+size 348077120

special_tokens_map.json

@@ -13,13 +13,7 @@
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": {
-    "content": "<|endoftext|>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
+  "pad_token": "<|endoftext|>",
   "unk_token": {
     "content": "<|unk|>",
     "lstrip": false,

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a577fe9fae96c98cb3d9643b3219a7549baa1ab6006e4b6882fe05eb3f32156c
+size 5841