Upload folder using huggingface_hub

README.md

@@ -1,3 +1,32 @@
----
-license: apache-2.0
----
+# TinyStories-150M-Starter
+
+This is a small decoder-only language model exported from the Kitsune Fine-Tuning Suite `Create` pipeline.
+
+## What This Export Is
+
+- Architecture family for tooling compatibility: `LlamaForCausalLM`
+- Original project type: manual-first small transformer scaffold
+- Export source checkpoint: `final.pt`
+
+## Notes
+
+This export is meant to behave like a normal Hugging Face causal LM checkpoint so it can be loaded by standard tooling.
+It was not originally trained as an off-the-shelf Llama release; it was mapped into a Llama-compatible layout for portability.
+
+## Training Context
+
+- Dataset ID: `roneneldan/TinyStories`
+- Dataset Path: `None`
+- Train Split: `train`
+- Max Steps: `20000`
+- Learning Rate: `0.0003`
+
+## Example
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model_id = "hf_llama"
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForCausalLM.from_pretrained(model_id)
+```

config.json

@@ -0,0 +1,31 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 2048,
+  "max_position_embeddings": 1024,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "num_key_value_heads": 12,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.55.4",
+  "unk_token_id": 3,
+  "use_cache": true,
+  "vocab_size": 32000
+}

export_meta.json

@@ -0,0 +1,8 @@
+{
+  "status": "completed",
+  "export_type": "hf_llama_compatible",
+  "project_name": "TinyStories-150M-Starter",
+  "checkpoint": "D:\\Ollama\\ollama_ui\\kitsune_training_suite\\training\\projects\\tinystories-150m-starter\\artifacts\\checkpoints\\final.pt",
+  "out_dir": "D:\\Ollama\\ollama_ui\\kitsune_training_suite\\training\\projects\\tinystories-150m-starter\\artifacts\\exports\\hf_llama",
+  "missing_keys": []
+}

generation_config.json

@@ -0,0 +1,10 @@
+{
+  "bos_token_id": 1,
+  "do_sample": true,
+  "eos_token_id": 2,
+  "max_new_tokens": 120,
+  "pad_token_id": 0,
+  "temperature": 0.7,
+  "top_p": 0.95,
+  "transformers_version": "4.55.4"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80825893f6d59c89b472d7ca169c1f562c8349a011a6f1a39ff7547ffc63d755
+size 536435744

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e34325d9faf80e8ef7a7807ebb6d3f47ef98b7f56e0dc561740946ff692a6578
+size 779422

tokenizer_config.json

@@ -0,0 +1,51 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "legacy": true,
+  "model_max_length": 1024,
+  "pad_token": "<pad>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}