Duplicate from PleIAs/Monad

Co-authored-by: Pierre-Carl Langlais <Pclanglais@users.noreply.huggingface.co>

.gitattributes

@@ -0,0 +1,36 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz 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
+figures/monad_structure.png filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,69 @@
+---
+language:
+- en
+license: apache-2.0
+pipeline_tag: text-generation
+tags:
+- transformers
+library_name: transformers
+datasets:
+- PleIAs/SYNTH
+---
+
+# ⚛️ Monad
+
+<div align="center">
+  <img src="figures/pleias.jpg" width="60%" alt="Pleias" />
+</div>
+
+<p align="center">
+  <a href="https://pleias.fr/blog/blogsynth-the-new-data-frontier"><b>Blog announcement</b></a>
+</p>
+
+**Monad** is a 56 million parameters generalist Small Reasoning Model, trained on 200 billions tokens from <a href="https://huggingface.co/PleIAs/Baguettotron">SYNTH</a>, a fully open generalist dataset.
+
+As of 2025, Monad is the best contender for the smallest viable language models. Despite being less than half of gpt-2, Monad not only answers in consistent English but performs significanly beyond chance on MMLU and other major industry benchmarks.
+
+<p align="center">
+  <img width="80%" src="figures/training_efficiency.jpeg">
+</p>
+
+Monad's name is a reference to Leibniz concept and general idea of the smallest possible unit of intelligence.
+
+## Features
+Monad has been natively trained for instructions with thinking traces. We implemented a series of dedicated pipelines for:
+* Memorization of encyclopedic knowledge (50,000 vital articles from Wikipedia), though in this size range hallucinations have to be expected.
+* Retrieval-Augmented Generation with grounding (following on our initial experiments with Pleias-RAG series)
+* Arithmetic and simple math resolution problem
+* Editing tasks
+* Information extraction
+* Creative writing, including unusual synthetic exercises like lipograms or layout poems.
+
+Monad is strictly monolingual in English. We trained a new custom tokenizer (likely one of the smallest tokenizer to date, less than 8,000 individual tokens), exclusively trained on SYNTH so that we maintain a relatively good compression ratio. 
+
+## Model design and training
+Monad is a 56M parameters decoders with a standard Qwen/Llama-like design, except for its extremely compact size and overall opiniated architecture for depth (with 64 layers)
+<p align="center">
+  <img width="80%" src="figures/monad_structure.png">
+</p>
+
+Monad was trained on 16 h100 from Jean Zay (compute plan n°A0191016886). Full pre-training took a bit less than 6 hours.
+
+## Evaluation
+Monad attains performance on MMLU significantly beyond chance with close to 30% of positive rate. We also find non-random results on gsm8k (8%) and HotPotQA (8%)
+
+To our knowledge, there is no model remotely close in this size range for evaluation comparison. Spiritually and practically, Monad remains unique.
+
+## Use and deployment
+Monad has been trained on the standard instruction style from Qwen.
+
+```xml
+<|im_start|>user
+Who are you?<|im_end|>
+<|im_start|>assistant
+<think>
+```
+
+Monad has no support yet for multi-turn.
+
+A major envisioned use case for Monad is explainability, as the model does provide a unique trade-off between observability and actual reasoning performance.

chat_template.json

@@ -0,0 +1,7 @@
+{
+  "chat_template": "{% for m in messages %}<|im_start|>{{ m['role'] }}\n{{ m['content'] }}<|im_end|>\n{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n<think>\n{% endif %}",
+  "eos_token": "<|im_end|>",
+  "bos_token": "<|im_start|>",
+  "stop": ["<|im_end|>"],
+  "roles": { "user": "user", "assistant": "assistant", "system": "system" }
+}

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": 768,
+  "max_position_embeddings": 2048,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 4,
+  "num_hidden_layers": 64,
+  "num_key_value_heads": 4,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.51.3",
+  "use_cache": true,
+  "vocab_size": 8192
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.51.3"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d99bffef2d388cfbd0b39b8a0e1665e64afd7e0f7b055f7abebadc756a7227bf
+size 113376216

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<|begin_of_text|>",
+  "eos_token": "<|end_of_text|>",
+  "pad_token": "[PAD]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,44 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<|begin_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<|end_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|begin_of_text|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|end_of_text|>",
+  "extra_special_tokens": {},
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "tokenizer_class": "PreTrainedTokenizer",
+  "unk_token": "[UNK]"
+}