Upload 13 files

.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
+aurora_one_mini_deterministic_v2_f16.gguf filter=lfs diff=lfs merge=lfs -text
+aurora_one_mini_deterministic_v2_q4_k_m.gguf filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,111 @@
+---
+language:
+- en
+tags:
+- causal-lm
+- text-generation
+- gpt2
+- small-language-model
+pipeline_tag: text-generation
+library_name: transformers
+---
+
+# Aurora One Mini — 124M
+
+Aurora One Mini is a compact, community-built language model designed for fast local chat, experiments, and lightweight AI applications.
+
+At only **124 million parameters**, it is small enough to run comfortably on ordinary laptops and edge devices while remaining useful for short-form generation and experimentation.
+
+## What makes it interesting
+
+- **Tiny and fast:** practical for local inference and rapid prototyping
+- **Native ChatML format:** structured user/assistant conversations
+- **Hugging Face + GGUF exports:** works with Transformers and llama.cpp-compatible tools
+- **Open experiment:** trained and evaluated on a single consumer GPU
+
+## Model details
+
+- Architecture: GPT-style causal language model
+- Parameters: approximately 124M
+- Layers: 12
+- Hidden size: 768
+- Attention heads: 12
+- Context length: 1,024 tokens
+- Vocabulary: GPT-2 BPE plus ChatML control tokens
+- Final pretraining: 45,000 steps, approximately 15 tokens per parameter
+- Released checkpoint: deterministic v2, step 2,000 of targeted post-training
+
+## Quick start
+
+```python
+from transformers import AutoTokenizer, AutoModelForCausalLM
+import torch
+
+model_id = "YOUR_USERNAME/aurora-one-mini-124m"
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForCausalLM.from_pretrained(model_id)
+
+prompt = "What is the capital of France?"
+messages = [{"role": "user", "content": prompt}]
+text = tokenizer.apply_chat_template(
+    messages, tokenize=False, add_generation_prompt=True
+)
+inputs = tokenizer(text, return_tensors="pt")
+
+with torch.no_grad():
+    output = model.generate(
+        **inputs,
+        max_new_tokens=80,
+        temperature=0.7,
+        top_p=0.9,
+        do_sample=True,
+    )
+
+print(tokenizer.decode(output[0], skip_special_tokens=True))
+```
+
+## GGUF files
+
+The companion GGUF files are provided for local runtimes:
+
+- `aurora_one_mini_deterministic_v2_f16.gguf` — highest fidelity
+- `aurora_one_mini_deterministic_v2_q4_k_m.gguf` — compact CPU-friendly quantization
+
+Use the Q4_K_M file for a fast, low-memory demo. Use the F16 file when preserving maximum quality is more important.
+
+## Honest limitations
+
+This is an experimental 124M model, not a frontier assistant. It can produce fluent short responses, but it may hallucinate, repeat itself, or answer arithmetic and factual questions incorrectly. For dependable applications, pair it with a calculator, retrieval system, memory layer, and explicit output validation.
+
+The native-ChatML factual smoke test scored **3/20** on a small internal suite. This score is reported to set realistic expectations and should not be interpreted as a general benchmark.
+
+## Intended use
+
+Good fits include:
+
+- local chat experiments
+- educational model training projects
+- embedded or low-resource inference
+- prompt-format and agent-runtime experiments
+- fast prototyping with Transformers or llama.cpp
+
+Avoid using it as the sole source of truth for medical, legal, financial, safety-critical, or factual decision-making.
+
+## Prompt format
+
+The model was post-trained using ChatML-style turns:
+
+```text
+<|im_start|><|user|>Your question<|im_end|>
+<|im_start|><|assistant|>
+```
+
+The included tokenizer metadata contains the required special tokens.
+
+## Acknowledgements
+
+Aurora One Mini was trained as a small-scale independent experiment using PyTorch and a consumer NVIDIA GPU. Contributions, evaluations, and improvements are welcome.
+
+## License
+
+Released for research and experimentation. Add the project’s final license here before redistributing commercially.

added_tokens.json

@@ -0,0 +1,6 @@
+{
+  "<|assistant|>": 50260,
+  "<|im_end|>": 50258,
+  "<|im_start|>": 50257,
+  "<|user|>": 50259
+}

aurora_metadata.json

@@ -0,0 +1,10 @@
+{
+  "source_checkpoint": "checkpoints/aurora_one_mini_deterministic_v2.pt",
+  "step": 2000,
+  "special_tokens": {
+    "im_start": 50257,
+    "im_end": 50258,
+    "user": 50259,
+    "assistant": 50260
+  }
+}

aurora_one_mini_deterministic_v2_f16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49c305ea83996f3b7520474c96915d9b7a39ceff3f3b9b09a569c87ea74a9ee9
+size 252476576

aurora_one_mini_deterministic_v2_q4_k_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff55f1c99d57b3f864522f85c6e78fef637f291cd7c54e4d786bc98754550363
+size 91233248

config.json

@@ -0,0 +1,32 @@
+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.0,
+  "bos_token_id": 50256,
+  "dtype": "float32",
+  "embd_pdrop": 0.0,
+  "eos_token_id": 50256,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.0,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "transformers_version": "4.57.6",
+  "use_cache": true,
+  "vocab_size": 50261
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.57.6"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:822ecd302aafc6b487bbe03c9411f8ec736aa698fe3a53a6b8d917e3b49d954d
+size 497786496

special_tokens_map.json

@@ -0,0 +1,35 @@
+{
+  "additional_special_tokens": [
+    {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|user|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|assistant|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50257": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50258": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50259": {
+      "content": "<|user|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50260": {
+      "content": "<|assistant|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|user|>",
+    "<|assistant|>"
+  ],
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1024,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}