Upload folder using huggingface_hub

README.md

@@ -0,0 +1,61 @@
+---
+license: apache-2.0
+base_model: llama
+library_name: transformers
+pipeline_tag: text-generation
+tags:
+- one-way-polyglot
+- japanese
+- english
+- bilingual
+- small-model
+---
+
+# one-way-polyglot-8m-tied
+
+A one-way polyglot language model trained to understand Japanese but generate only English.
+
+## Model Details
+
+- **Architecture**: LLaMA-based transformer
+- **Parameters**: 8,519,936 (8.5M)
+- **Vocabulary**: 16,384 tokens (bilingual SentencePiece)
+- **Context Length**: 512 tokens
+- **Embedding Strategy**: Tied
+
+## Capabilities
+
+- **Semantic Transfer**: Understands Japanese input and generates contextually appropriate English
+- **One-Way Constraint**: Strong bias toward English-only generation
+- **Name Transliteration**: Can transliterate Japanese names to English (context-dependent)
+
+## Training Data
+
+Trained on bilingual Japanese-English story data with masked loss on Japanese prefixes to enforce one-way generation.
+
+## Usage
+
+```python
+from transformers import LlamaForCausalLM, LlamaTokenizer
+
+model = LlamaForCausalLM.from_pretrained("one-way-polyglot-8m-tied")
+tokenizer = LlamaTokenizer.from_pretrained("one-way-polyglot-8m-tied")
+
+# Japanese input, English output
+prompt = "昔々、赤い傘を持った少女がいました。"
+inputs = tokenizer(prompt, return_tensors="pt")
+outputs = model.generate(**inputs, max_new_tokens=50, temperature=0.7)
+print(tokenizer.decode(outputs[0], skip_special_tokens=True))
+```
+
+## Model Variants
+
+This is part of a series exploring one-way polyglot capabilities:
+- 1.25M parameters (tied embeddings)
+- 8.5M parameters (tied embeddings) 
+- 12.7M parameters (untied embeddings)
+- 15.7M parameters (tied embeddings)
+
+## License
+
+Apache 2.0

config.json

@@ -0,0 +1,29 @@
+{
+  "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": 256,
+  "initializer_range": 0.02,
+  "intermediate_size": 682,
+  "max_position_embeddings": 512,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 4,
+  "num_hidden_layers": 6,
+  "num_key_value_heads": 2,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.54.1",
+  "use_cache": true,
+  "vocab_size": 16384
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.54.1"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1804e76de82b0380509a595273b62af4117bf200d42183ba15d433243bfbac91
+size 34085832

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4359c7d373bfaa6bc9ec396e10c9cde2d0e7604a0821075d8529b3561b7c2778
+size 34102703

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18fd3bcd564240df1343dda502457ea5db419f4061ca442a9b204796d3d79301
+size 581374

tokenizer_config.json

@@ -0,0 +1,12 @@
+{
+  "tokenizer_class": "LlamaTokenizer",
+  "vocab_size": 16384,
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "bos_token": "[BOS]",
+  "eos_token": "[EOS]",
+  "unk_token": "[UNK]",
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "clean_up_tokenization_spaces": false
+}