SykoLLM V5.6 - Initial upload

README.md

@@ -0,0 +1,29 @@
+---
+language:
+  - tr
+  - en
+license: apache-2.0
+library_name: transformers
+tags:
+  - causal-lm
+  - turkish
+  - phi3
+  - llm
+  - text-generation
+pipeline_tag: text-generation
+datasets:
+  - uonlp/CulturaX
+  - HuggingFaceTB/cosmopedia
+  - roneneldan/TinyStories
+  - nampdn-ai/tiny-textbooks
+  - nampdn-ai/tiny-codes
+  - ise-uiuc/Magicoder-Evol-Instruct-110K
+  - theblackcat102/evol-codealpaca-v1
+  - turkish-nlp-suite/InstrucTurca
+---
+
+# SykoLLM V5.6
+
+SykoLLM ailesinin en büyük ve en gelişmiş modeli. ~1.7M örnek ile A100 GPU üzerinde eğitilmiştir.
+
+Detaylı model kartı yakında güncellenecektir.

config.json

@@ -0,0 +1,35 @@
+{
+  "architectures": [
+    "Phi3ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "dtype": "bfloat16",
+  "embd_pdrop": 0.0,
+  "eos_token_id": 0,
+  "hidden_act": "silu",
+  "hidden_size": 1024,
+  "ignore_keys_at_rope_validation": null,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "max_position_embeddings": 1024,
+  "model_type": "phi3",
+  "num_attention_heads": 8,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 8,
+  "original_max_position_embeddings": 4096,
+  "pad_token_id": 4,
+  "partial_rotary_factor": 1.0,
+  "resid_pdrop": 0.0,
+  "rms_norm_eps": 1e-05,
+  "rope_parameters": {
+    "partial_rotary_factor": 1.0,
+    "rope_theta": 10000.0,
+    "rope_type": "default"
+  },
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "transformers_version": "5.0.0",
+  "use_cache": false,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,10 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "output_attentions": false,
+  "output_hidden_states": false,
+  "pad_token_id": 4,
+  "transformers_version": "5.0.0",
+  "use_cache": true
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf65f8f1fa61ed49565b81d93cfc53e540d426ab691f104bc275bd7f681dc892
+size 894571696

tokenizer_config.json

@@ -0,0 +1,10 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "is_local": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|pad|>",
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": "<|endoftext|>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79a8ea9d2cbf18079f605474c0346332cac183bd72d1b461a0044eab074ddece
+size 5201