Upload folder using huggingface_hub

README.md

@@ -1,5 +1,42 @@
+
 ---
-license: other
-license_name: pth-licence.md
-license_link: LICENSE
+license: mit
+tags:
+- llama
+- behavioral-consciousness-engine
+- synthetic-data
+- text-generation
 ---
+
+# BCE Core 6M (Fine-Tuned)
+
+## Model Description
+This is a custom 6M parameter Llama-based model, fine-tuned as part of the Behavioral Consciousness Engine (BCE) project. It is designed to act as a lightweight policy guard and control layer ('small_guard_model').
+
+## Architecture
+- **Type**: LlamaForCausalLM
+- **Parameters**: ~12M (Trainable)
+- **Hidden Size**: 256
+- **Intermediate Size**: 1024
+- **Layers**: 8
+- **Heads**: 8
+- **Context Window**: 2048 tokens
+- **Tokenizer**: Custom ByteLevelBPE
+
+## Training Data
+The model was initially trained on a streaming mixture of:
+1. **Technical Data**: CodeParrot (Clean)
+2. **Humanities**: Wikitext-103
+3. **Base Schema**: BCE Simple Firewall Dataset
+
+It was then fine-tuned on **1,000 synthetic records** generated from the `BCE-Controlled-LLM` schema (`type.json`), which enforces policy checking and risk assessment logic.
+
+## Usage
+This model expects input in a specific JSON structure representing a request and outputs the corresponding policy decision and response JSON.
+
+```json
+{"request": {"input": {"text": "your prompt here"}}}
+```
+
+## License
+MIT License

config.json

@@ -0,0 +1,30 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "dtype": "float32",
+  "eos_token_id": 2,
+  "head_dim": 32,
+  "hidden_act": "silu",
+  "hidden_size": 256,
+  "initializer_range": 0.02,
+  "intermediate_size": 1024,
+  "max_position_embeddings": 2048,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 8,
+  "num_hidden_layers": 8,
+  "num_key_value_heads": 8,
+  "pad_token_id": 1,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": true,
+  "transformers_version": "4.57.3",
+  "use_cache": true,
+  "vocab_size": 16384
+}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": [
+    2
+  ],
+  "pad_token_id": 1,
+  "transformers_version": "4.57.3"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8c4726895b70f0b9bc61f057720a9d3b3fce0f41f3a509d75b0a2271a975547
+size 50357128

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_config.json

@@ -0,0 +1,56 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "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
+    },
+    "4": {
+      "content": "<mask>",
+      "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": {},
+  "max_length": 512,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "stride": 0,
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1f8efb62e412839c7a9485278bf1ba937ad28fda76ba94226930bc7257a5ae4
+size 5777