Create README.md

README.md

@@ -0,0 +1,268 @@
+---
+---
+
+# Model Card for Mimir-1.6B-Instruct
+
+## How to Get Started with the Model
+
+Below you can find an example of model usage. To facilitate its usage, we recommend to follow these steps:
+
+```
+huggingface-cli download mimir-lcm/Mimir-1.6B-Instruct --local-dir mimir-lcm/Mimir-1.6B-Instruct 
+git clone https://github.com/facebookresearch/large_concept_model.git
+mv large_concept_model/lcm .
+pip install torch==2.5.1 --extra-index-url https://download.pytorch.org/whl/cu121 --upgrade
+pip install fairseq2==v0.3.0rc1 --pre --extra-index-url  https://fair.pkg.atmeta.com/fairseq2/whl/rc/pt2.5.1/cu121 --upgrade
+pip install omegaconf==2.3.0
+pip install sonar-space==0.3.2
+pip install wtpsplit==2.1.2
+```
+
+Now you should be able to run the following:
+
+```python
+import lcm
+import torch
+from pathlib import Path
+
+from lcm.models.two_tower_diffusion_lcm.builder import (
+    create_two_tower_diffusion_lcm_model,
+)
+from lcm.models.two_tower_diffusion_lcm.archs import two_tower_diffusion_lcm_1_6B
+from lcm.inference.two_tower_diffusion_lcm.generator import (
+    TwoTowerDiffusionLCMGenerator,
+    DiffusionLCMGeneratorOptions,
+)
+from lcm.datasets.batch import EmbeddingsBatch
+from sonar.inference_pipelines.text import TextToEmbeddingModelPipeline, EmbeddingToTextModelPipeline
+
+from wtpsplit import SaT
+
+lcm.setup_fairseq2()
+
+DEVICE = "cuda" if torch.cuda.is_available() else "cpu"
+
+from lcm.models.two_tower_diffusion_lcm.builder import TwoTowerDiffusionLCModel
+
+_original_sample_fn = TwoTowerDiffusionLCModel.sample_initial_noise_vectors
+
+def _patched_sample_fn(self, batch_size: int):
+    latents = _original_sample_fn(self, batch_size)
+    return latents.to(dtype=self.dtype)
+
+TwoTowerDiffusionLCModel.sample_initial_noise_vectors = _patched_sample_fn
+
+CHECKPOINT_PATH = "mimir-lcm/Mimir-1.6B-Instruct/model.pt"
+INFERENCE_DTYPE = torch.float16
+
+TEXT_DECODER = EmbeddingToTextModelPipeline(decoder="text_sonar_basic_decoder", tokenizer="text_sonar_basic_decoder", device=torch.device(DEVICE))
+TEXT_EMBEDDER = TextToEmbeddingModelPipeline(encoder="text_sonar_basic_encoder", tokenizer="text_sonar_basic_encoder", device=torch.device(DEVICE))
+
+def decode_embeddings(embeddings):
+    
+    embeddings = embeddings.to(device=DEVICE, dtype=torch.float32)
+    
+    print("Decoding...")
+    results = TEXT_DECODER.predict(
+        embeddings, 
+        target_lang="eng_Latn"
+    )
+    
+    return results
+
+def get_eos_vector():
+    return TEXT_EMBEDDER.predict(["End of text."], source_lang="eng_Latn").squeeze().to(device=DEVICE, dtype=INFERENCE_DTYPE)
+
+def load_two_tower_model(checkpoint_path, device="cuda"):
+    
+    config = two_tower_diffusion_lcm_1_6B()
+
+    print("Building model structure...")
+    model = create_two_tower_diffusion_lcm_model(
+        config, 
+        device=torch.device(device),
+        dtype=INFERENCE_DTYPE
+    )
+
+    print(f"Loading weights from {checkpoint_path}...")
+    state_dict = torch.load(checkpoint_path, map_location=device)
+    
+    if "model" in state_dict:
+        state_dict = state_dict["model"]
+        
+    model.load_state_dict(state_dict, strict=True)
+    
+    model.eval()
+    model.to(device=DEVICE, dtype=INFERENCE_DTYPE)
+    print("Model loaded successfully.")
+    return model
+
+def run_inference(model, prompt_embeddings, device="cuda"):
+
+    options = DiffusionLCMGeneratorOptions(
+        eos_threshold=0.9,
+        inference_timesteps=40,
+        initial_noise_scale=0.6,
+        guidance_scale=1.5,
+        guidance_rescale=0.7,
+        epsilon_scaling=1.00045,
+        stop_on_repetition_cosine_threshold=0.9,
+        seed=42,
+    )
+    
+    generator = TwoTowerDiffusionLCMGenerator(model, options, eos_vec=get_eos_vector())
+
+    seqs = prompt_embeddings.to(device)
+    batch_input = EmbeddingsBatch(seqs=seqs, padding_mask=None)
+
+    print("Running generation...")
+    output = generator(batch_input)
+    
+    return output
+
+if __name__ == "__main__":
+
+    raw_prompt_text = "User turn.\n\nJohn lives in his house and loves to play soccer.\n\nGive a brief definition of the word \"house\" in the sentence given as input. Generate only the definition.\n\nAssistant turn."
+
+    model = load_two_tower_model(CHECKPOINT_PATH, DEVICE)
+    
+    with torch.no_grad():
+
+        sat_model = SaT("segment-any-text/sat-3l")
+        if torch.cuda.is_available():
+            sat_model.half().to(DEVICE)
+            
+        split_outputs = list(sat_model.split([raw_prompt_text], threshold=0.02))
+        sentences = [s.strip() for s in split_outputs[0] if s.strip()]
+
+        print(sentences)
+
+        prompt = TEXT_EMBEDDER.predict(sentences, source_lang="eng_Latn", batch_size=1024)
+        prompt = prompt.to(device=DEVICE, dtype=INFERENCE_DTYPE)
+        prompt = prompt.unsqueeze(0)
+    
+    results = run_inference(model, prompt, DEVICE)
+    
+    for j, hyp in enumerate(results.hypotheses[0]):
+        print(decode_embeddings(hyp.seq)[prompt.shape[1]:])
+```
+
+Make sure to change the source language from "eng_Latn" to the one you want to perform inference with.
+
+Furthermore, for the instruct model, we used the following mappings for the "User turn." and "Assistant turn." strings.
+
+```python
+USER_TRANSLATION = {
+    "arb_Arab": "دور المستخدم.", 
+    "bel_Cyrl": "Ход карыстальніка.", 
+    "ben_Beng": "ব্যবহারকারীর পালা।",
+    "bos_Latn": "Red korisnika.", 
+    "bul_Cyrl": "Ред е на потребителя.", 
+    "cat_Latn": "Torn de l'usuari.",
+    "ces_Latn": "Je řada na uživateli.", 
+    "cym_Latn": "Tro'r defnyddiwr.", 
+    "dan_Latn": "Brugerens tur.",
+    "deu_Latn": "Der Benutzer ist am Zug.", 
+    "eng_Latn": "User turn.", 
+    "fra_Latn": "C'est au tour de l'utilisateur.",
+    "heb_Hebr": "תור המשתמש.", 
+    "hin_Deva": "उपयोगकर्ता की बारी।", 
+    "hrv_Latn": "Poteg korisnika.",
+    "ind_Latn": "Giliran pengguna.", 
+    "jpn_Jpan": "ユーザーの番です。", 
+    "ita_Latn": "È il turno dell'utente.",
+    "kan_Knda": "ಬಳಕೆದಾರರ ತಿರುವು.", 
+    "kor_Hang": "사용자 차례입니다.", 
+    "lvs_Latn": "Lietotāja kārta.",
+    "mal_Mlym": "ഉപയോക്താവിന്റെ ഊഴം",
+    "mar_Deva": "वापरकर्त्याची पाळी.",
+    "mkd_Cyrl": "Потребен е корисник.",
+    "npi_Deva": "प्रयोगकर्ताको पालो।",
+    "nld_Latn": "De gebruiker is aan de beurt.",
+    "ory_Orya": "ୟୁଜର୍ ଟର୍ନ୍ |",
+    "pol_Latn": "Ruch użytkownika.",
+    "por_Latn": "É a vez do utilizador.",
+    "ron_Latn": "E rândul utilizatorului.",
+    "rus_Cyrl": "Ход пользователя.",
+    "slk_Latn": "Je na ťa.",
+    "slv_Latn": "Na vrsti je uporabnik.",
+    "srp_Cyrl": "Кориснички потез.",
+    "spa_Latn": "Turno del usuario.",
+    "swe_Latn": "Användarens tur.",
+    "swh_Latn": "Mzunguko wa mtumiaji.",
+    "tam_Taml": "பயனர் முறை.",
+    "tel_Telu": "వినియోగదారుని వంతు",
+    "tha_Thai": "ผู้ใช้เทิร์น",
+    "tur_Latn": "Kullanıcı sırası.",
+    "ukr_Cyrl": "Хід користувача.",
+    "urd_Arab": "صارف کی باری۔",
+    "vie_Latn": "Đến lượt người dùng.",
+    "zho_Hans": "轮到用户了。"
+}
+```
+
+```python
+ASSISTANT_TRANSLATION = {
+    "arb_Arab": "دور المساعد.", 
+    "bel_Cyrl": "Памочнік, свой ход.", 
+    "ben_Beng": "সহকারী পালা।",
+    "bos_Latn": "Pomoćni potez.", 
+    "bul_Cyrl": "Ред е на помощника.", 
+    "cat_Latn": "Torn de l'ajudant.",
+    "ces_Latn": "Na řadě je asistent.", 
+    "cym_Latn": "Tro'r cynorthwyydd.", 
+    "dan_Latn": "Assistenten er på tur.",
+    "deu_Latn": "Der Assistent ist an der Reihe.", 
+    "eng_Latn": "Assistant turn.", 
+    "fra_Latn": "C'est au tour de l'assistant.",
+    "heb_Hebr": "תורו של העוזר.", 
+    "hin_Deva": "सहायक की बारी।", 
+    "hrv_Latn": "Pomoćni potez.",
+    "ind_Latn": "Giliran asisten.", 
+    "jpn_Jpan": "アシスタントの番。", 
+    "ita_Latn": "È il turno dell'assistente.",
+    "kan_Knda": "ಸಹಾಯಕ ತಿರುವು.", 
+    "kor_Hang": "조수 차례.", 
+    "lvs_Latn": "Palīga kārta.",
+    "mal_Mlym": "സഹായിയുടെ ഊഴം",
+    "mar_Deva": "सहाय्यक पालवी.",
+    "mkd_Cyrl": "Помошник-ред.",
+    "npi_Deva": "सहायक पालो।",
+    "nld_Latn": "De assistent is aan de beurt.",
+    "ory_Orya": "ଆସିଷ୍ଟାଣ୍ଟ ଟର୍ନ୍ |",
+    "pol_Latn": "Rzuty pomocników.",
+    "por_Latn": "É a vez do assistente.",
+    "ron_Latn": "E rândul asistentului.",
+    "rus_Cyrl": "Очередь помощника.",
+    "slk_Latn": "Na rade je asistent.",
+    "slv_Latn": "Na vrsti je pomočnik.",
+    "srp_Cyrl": "Помоћни круг.",
+    "spa_Latn": "Turno del asistente.",
+    "swe_Latn": "Assistenten är på tur.",
+    "swh_Latn": "Mzunguko wa msaidizi.",
+    "tam_Taml": "துணைவரின் முறை.",
+    "tel_Telu": "సహాయకుడి వంతు",
+    "tha_Thai": "ผู้ช่วยเลี้ยว",
+    "tur_Latn": "Sıra asistanında.",
+    "ukr_Cyrl": "Черга помічника.",
+    "urd_Arab": "معاون کی باری۔",
+    "vie_Latn": "Đến lượt trợ lý.",
+    "zho_Hans": "助手的回合。"
+}
+```
+
+## Citation
+
+If you use this model in your research, please cite the following:
+
+```bibtex
+@misc{musacchio2026mimirlargescalemultilingualconcept,
+      title={Mimir: Large-scale Multilingual Concept Modeling}, 
+      author={Elio Musacchio and Lucia Siciliani and Pierpaolo Basile},
+      year={2026},
+      eprint={2605.25263},
+      archivePrefix={arXiv},
+      primaryClass={cs.CL},
+      url={https://arxiv.org/abs/2605.25263}, 
+}
+```