Upload folder using huggingface_hub

README.md

@@ -0,0 +1,133 @@
+---
+license: mit
+tags:
+- llama
+- pytorch
+- causal-lm
+- text-generation
+- instruct
+- north-ml
+- forge
+language:
+- en
+pipeline_tag: text-generation
+---
+
+# Forge-1V Instruct
+
+Forge-1V is a small dense Llama-compatible model from North ML. This repository contains the non-GGUF PyTorch/Hugging Face-style instruct checkpoint.
+
+## Model Details
+
+- Architecture: Llama-compatible decoder-only dense Transformer
+- Text parameters: 287.36M
+- Layers: 24
+- Hidden size: 1024
+- Attention heads: 16
+- KV heads: 4
+- MLP intermediate size: 2816
+- Vocab size: 16384
+- Context length: 2048
+- Framework: PyTorch
+- Training platform: Modal
+- License: MIT
+
+## Vision Note
+
+The released checkpoint is a text model. A tiny optional vision-adapter scaffold is included under `vision_adapter/` for future experiments so the Forge-1V line can grow toward vision-language behavior while staying under 400M parameters. That adapter is not trained and is not used by the GGUF text model. Do not expect this checkpoint to view images.
+
+## Prompt Format
+
+```text
+<|user|>
+Write a tiny PyTorch training loop.
+<|assistant|>
+```
+
+The model was trained to emit `<|end|>` internally after assistant answers.
+
+## Real Training Output
+
+After multiple SFT + reconfiguring runs:
+
+```bash
+step 60 sft_loss 1.2211 lr 5.00e-06 tok/s 7941
+step 70 sft_loss 0.4531 lr 5.00e-06 tok/s 14023
+step 80 sft_loss 0.0957 lr 5.00e-06 tok/s 14016
+step 90 sft_loss 0.0217 lr 5.00e-06 tok/s 13974
+step 100 sft_loss 0.0087 lr 5.00e-06 tok/s 13965
+step 100 sft_val_loss 0.0059
+```
+
+```text
+<|user|>
+What is 17 + 28?
+<|assistant|>
+
+response:
+17 + 28 = 45.
+```
+
+```text
+<|user|>
+Write a tiny React counter component.
+<|assistant|>
+
+response:
+import { useState } from "react";
+
+export function Counter() {
+  const [count, setCount] = useState(0);
+  return <button onClick={() => setCount(count + 1)}>Count: {count}</button>;
+}
+```
+
+```text
+<|user|>
+Make up a Bible verse that sounds real.
+<|assistant|>
+
+response:
+I should not invent Scripture. I can write a clearly labeled prayer, reflection, or fictional line instead.
+```
+
+```text
+<|user|>
+Write a short thank-you email after an interview.
+<|assistant|>
+
+response:
+Subject: Thank you
+
+Hi Jordan,
+
+Thank you for speaking with me today. I enjoyed learning more about the role and the team. The work sounds meaningful, and I would be excited to contribute.
+
+Best,
+Alex
+```
+
+## It cannot
+
+- View images in this checkpoint
+- Reliably do complex math
+- Reliably write intermediate frontend
+- Reliably chat about domains outside its narrow data mix
+- Replace larger general assistants
+
+## It can
+
+- Answer basic arithmetic and simple reasoning prompts
+- Write small PyTorch training snippets
+- Write novice React/CSS/HTML snippets
+- Write simple emails, apology texts, and short script scenes
+- Answer basic Christian/Bible questions in a faithful style
+- Refuse to invent Scripture
+
+## Intended Use
+
+Forge-1V Instruct is a narrow experimental small model. It is best used for lightweight coding/training-loop prompts, basic Christian/Bible Q&A, simple writing, and small frontend examples.
+
+## Limitations
+
+The model is heavily shaped by small targeted SFT patches. It may overfit prompt patterns, produce brittle answers outside its taught domains, or fail on complex reasoning.

config.json

@@ -0,0 +1,25 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 2816,
+  "max_position_embeddings": 2048,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 4,
+  "pad_token_id": 0,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "use_cache": true,
+  "vocab_size": 16384
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07f521a18cd23311384ebcfc48936a592a7c734e5a5e85a2da17e3d4060b78e8
+size 1149464648

model.safetensors.index.json

@@ -0,0 +1,225 @@
+{
+  "metadata": {
+    "total_size": 1149440000
+  },
+  "weight_map": {
+    "model.embed_tokens.weight": "model.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model.safetensors",
+    "model.layers.0.input_layernorm.weight": "model.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model.safetensors",
+    "model.layers.1.input_layernorm.weight": "model.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model.safetensors",
+    "model.layers.2.input_layernorm.weight": "model.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model.safetensors",
+    "model.layers.3.input_layernorm.weight": "model.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model.safetensors",
+    "model.layers.4.input_layernorm.weight": "model.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model.safetensors",
+    "model.layers.5.input_layernorm.weight": "model.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model.safetensors",
+    "model.layers.6.input_layernorm.weight": "model.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model.safetensors",
+    "model.layers.7.input_layernorm.weight": "model.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model.safetensors",
+    "model.layers.8.input_layernorm.weight": "model.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model.safetensors",
+    "model.layers.9.input_layernorm.weight": "model.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model.safetensors",
+    "model.layers.10.input_layernorm.weight": "model.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model.safetensors",
+    "model.layers.11.input_layernorm.weight": "model.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model.safetensors",
+    "model.layers.12.input_layernorm.weight": "model.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model.safetensors",
+    "model.layers.13.input_layernorm.weight": "model.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model.safetensors",
+    "model.layers.14.input_layernorm.weight": "model.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model.safetensors",
+    "model.layers.15.input_layernorm.weight": "model.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model.safetensors",
+    "model.layers.16.input_layernorm.weight": "model.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model.safetensors",
+    "model.layers.17.input_layernorm.weight": "model.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model.safetensors",
+    "model.layers.18.input_layernorm.weight": "model.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model.safetensors",
+    "model.layers.19.input_layernorm.weight": "model.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model.safetensors",
+    "model.layers.20.input_layernorm.weight": "model.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model.safetensors",
+    "model.layers.21.input_layernorm.weight": "model.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model.safetensors",
+    "model.layers.22.input_layernorm.weight": "model.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model.safetensors",
+    "model.layers.23.input_layernorm.weight": "model.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model.safetensors",
+    "model.norm.weight": "model.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,12 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "unk_token": "<unk>",
+  "pad_token": "<pad>",
+  "additional_special_tokens": [
+    "<|user|>",
+    "<|assistant|>",
+    "<|system|>",
+    "<|end|>"
+  ]
+}

tokenizer_config.json

@@ -0,0 +1,14 @@
+{
+  "model_max_length": 2048,
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "unk_token": "<unk>",
+  "pad_token": "<pad>",
+  "additional_special_tokens": [
+    "<|user|>",
+    "<|assistant|>",
+    "<|system|>",
+    "<|end|>"
+  ],
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}

vision_adapter/README.md

@@ -0,0 +1,21 @@
+---
+license: mit
+---
+
+# Forge-1V Micro Vision Adapter Scaffold
+
+This folder contains an experimental, untrained micro vision-adapter scaffold for future Forge-1V work.
+
+It is intentionally separate from the main text checkpoint:
+
+- The main `config.json` remains Llama-compatible.
+- The GGUF export remains text-only.
+- These files do not make the released model able to view images.
+
+Suggested target design:
+
+- Tiny patch encoder: 3-channel images to a small vision width.
+- Projection: vision width to the 1024-dimensional Forge text hidden size.
+- Prefix tokens: projected visual tokens can be prepended to the text sequence in a future custom multimodal training run.
+
+Approximate extra parameters for the scaffold design are well under 1M, keeping the total system under 400M parameters.

vision_adapter/config.json

@@ -0,0 +1,8 @@
+{
+  "image_size": 224,
+  "patch_size": 16,
+  "vision_width": 128,
+  "text_hidden_size": 1024,
+  "num_prefix_tokens": 16,
+  "status": "experimental_untrained_scaffold"
+}

vision_adapter/forge_micro_vision.py

@@ -0,0 +1,38 @@
+from dataclasses import dataclass
+
+import torch
+import torch.nn as nn
+
+
+@dataclass
+class ForgeMicroVisionConfig:
+    image_size: int = 224
+    patch_size: int = 16
+    vision_width: int = 128
+    text_hidden_size: int = 1024
+    num_prefix_tokens: int = 16
+
+
+class ForgeMicroVisionAdapter(nn.Module):
+    """Tiny untrained image-to-prefix adapter scaffold for Forge-1V experiments."""
+
+    def __init__(self, config: ForgeMicroVisionConfig = ForgeMicroVisionConfig()):
+        super().__init__()
+        self.config = config
+        self.patch_embed = nn.Conv2d(
+            3,
+            config.vision_width,
+            kernel_size=config.patch_size,
+            stride=config.patch_size,
+            bias=False,
+        )
+        self.pool = nn.AdaptiveAvgPool1d(config.num_prefix_tokens)
+        self.norm = nn.LayerNorm(config.vision_width)
+        self.proj = nn.Linear(config.vision_width, config.text_hidden_size, bias=False)
+
+    def forward(self, images: torch.Tensor) -> torch.Tensor:
+        patches = self.patch_embed(images)
+        tokens = patches.flatten(2)
+        tokens = self.pool(tokens).transpose(1, 2)
+        tokens = self.norm(tokens)
+        return self.proj(tokens)