16-bit merge with Unsloth

README.md

@@ -8,6 +8,7 @@ tags:
 - unsloth
 - mistral
 - trl
+- sft
 base_model: Trendyol/Trendyol-LLM-7b-base-v1.0
 ---
 

config.json

@@ -1,3 +1,28 @@
 {
-    "model_type": "mistral"
-}
+  "_name_or_path": "Trendyol/Trendyol-LLM-7b-base-v1.0",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pad_token_id": 0,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.41.2",
+  "unsloth_version": "2024.6",
+  "use_cache": true,
+  "vocab_size": 44312
+}

pytorch_model-00001-of-00003.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cfac0a2933cb4b69f2a12cfc97f9380bc953c55fcf53595b0c67a717c07d7f56
+oid sha256:b39acbcbfbae285c29fb0251e200dee63fc7e2b12c45fce490dec2e3eb9adc0a
 size 4926604722

pytorch_model-00002-of-00003.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1dee117b6380c277bf621f4d2d77d868079a27f816822e00286af17ff77e474f
+oid sha256:956f079ac3fcdf0cd3c489fe1a5821177c146ed69ddc5d2f894f602212e71c47
 size 4915939786

pytorch_model-00003-of-00003.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f8b897acf6c7c4cc311fb5323bfa9066ee6e4107cef31ca87e95742ed9ab433f
+oid sha256:d1ea76561242c77d418778e5c9df76075026fb1593a1656710e938a93683b1c1
 size 4842741812