Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* 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
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,208 @@
+---
+base_model: google/translategemma-12b-it
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- axolotl
+- base_model:adapter:google/translategemma-12b-it
+- lora
+- transformers
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.18.1

adapter_config.json

@@ -0,0 +1,46 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "google/translategemma-12b-it",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": null,
+  "inference_mode": false,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 128,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "q_proj",
+    "gate_proj",
+    "v_proj",
+    "down_proj",
+    "o_proj",
+    "up_proj"
+  ],
+  "target_parameters": [],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8dda38546ad7ea97bc5b467e16f787dc3f5d640e5e5c25714430d715fe3a85a
+size 1047618408

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<image_soft_token>": 262144
+}

chat_template.jinja

@@ -0,0 +1,641 @@
+{%- set languages = {
+    "aa": "Afar",
+    "aa-DJ": "Afar",
+    "aa-ER": "Afar",
+    "ab": "Abkhazian",
+    "af": "Afrikaans",
+    "af-NA": "Afrikaans",
+    "ak": "Akan",
+    "am": "Amharic",
+    "an": "Aragonese",
+    "ar": "Arabic",
+    "ar-AE": "Arabic",
+    "ar-BH": "Arabic",
+    "ar-DJ": "Arabic",
+    "ar-DZ": "Arabic",
+    "ar-EG": "Arabic",
+    "ar-EH": "Arabic",
+    "ar-ER": "Arabic",
+    "ar-IL": "Arabic",
+    "ar-IQ": "Arabic",
+    "ar-JO": "Arabic",
+    "ar-KM": "Arabic",
+    "ar-KW": "Arabic",
+    "ar-LB": "Arabic",
+    "ar-LY": "Arabic",
+    "ar-MA": "Arabic",
+    "ar-MR": "Arabic",
+    "ar-OM": "Arabic",
+    "ar-PS": "Arabic",
+    "ar-QA": "Arabic",
+    "ar-SA": "Arabic",
+    "ar-SD": "Arabic",
+    "ar-SO": "Arabic",
+    "ar-SS": "Arabic",
+    "ar-SY": "Arabic",
+    "ar-TD": "Arabic",
+    "ar-TN": "Arabic",
+    "ar-YE": "Arabic",
+    "as": "Assamese",
+    "az": "Azerbaijani",
+    "az-Arab": "Azerbaijani",
+    "az-Arab-IQ": "Azerbaijani",
+    "az-Arab-TR": "Azerbaijani",
+    "az-Cyrl": "Azerbaijani",
+    "az-Latn": "Azerbaijani",
+    "ba": "Bashkir",
+    "be": "Belarusian",
+    "be-tarask": "Belarusian",
+    "bg": "Bulgarian",
+    "bg-BG": "Bulgarian",
+    "bm": "Bambara",
+    "bm-Nkoo": "Bambara",
+    "bn": "Bengali",
+    "bn-IN": "Bengali",
+    "bo": "Tibetan",
+    "bo-IN": "Tibetan",
+    "br": "Breton",
+    "bs": "Bosnian",
+    "bs-Cyrl": "Bosnian",
+    "bs-Latn": "Bosnian",
+    "ca": "Catalan",
+    "ca-AD": "Catalan",
+    "ca-ES": "Catalan",
+    "ca-FR": "Catalan",
+    "ca-IT": "Catalan",
+    "ce": "Chechen",
+    "co": "Corsican",
+    "cs": "Czech",
+    "cs-CZ": "Czech",
+    "cv": "Chuvash",
+    "cy": "Welsh",
+    "da": "Danish",
+    "da-DK": "Danish",
+    "da-GL": "Danish",
+    "de": "German",
+    "de-AT": "German",
+    "de-BE": "German",
+    "de-CH": "German",
+    "de-DE": "German",
+    "de-IT": "German",
+    "de-LI": "German",
+    "de-LU": "German",
+    "dv": "Divehi",
+    "dz": "Dzongkha",
+    "ee": "Ewe",
+    "ee-TG": "Ewe",
+    "el": "Greek",
+    "el-CY": "Greek",
+    "el-GR": "Greek",
+    "el-polyton": "Greek",
+    "en": "English",
+    "en-AE": "English",
+    "en-AG": "English",
+    "en-AI": "English",
+    "en-AS": "English",
+    "en-AT": "English",
+    "en-AU": "English",
+    "en-BB": "English",
+    "en-BE": "English",
+    "en-BI": "English",
+    "en-BM": "English",
+    "en-BS": "English",
+    "en-BW": "English",
+    "en-BZ": "English",
+    "en-CA": "English",
+    "en-CC": "English",
+    "en-CH": "English",
+    "en-CK": "English",
+    "en-CM": "English",
+    "en-CX": "English",
+    "en-CY": "English",
+    "en-CZ": "English",
+    "en-DE": "English",
+    "en-DG": "English",
+    "en-DK": "English",
+    "en-DM": "English",
+    "en-ER": "English",
+    "en-ES": "English",
+    "en-FI": "English",
+    "en-FJ": "English",
+    "en-FK": "English",
+    "en-FM": "English",
+    "en-FR": "English",
+    "en-GB": "English",
+    "en-GD": "English",
+    "en-GG": "English",
+    "en-GH": "English",
+    "en-GI": "English",
+    "en-GM": "English",
+    "en-GS": "English",
+    "en-GU": "English",
+    "en-GY": "English",
+    "en-HK": "English",
+    "en-HU": "English",
+    "en-ID": "English",
+    "en-IE": "English",
+    "en-IL": "English",
+    "en-IM": "English",
+    "en-IN": "English",
+    "en-IO": "English",
+    "en-IT": "English",
+    "en-JE": "English",
+    "en-JM": "English",
+    "en-KE": "English",
+    "en-KI": "English",
+    "en-KN": "English",
+    "en-KY": "English",
+    "en-LC": "English",
+    "en-LR": "English",
+    "en-LS": "English",
+    "en-MG": "English",
+    "en-MH": "English",
+    "en-MO": "English",
+    "en-MP": "English",
+    "en-MS": "English",
+    "en-MT": "English",
+    "en-MU": "English",
+    "en-MV": "English",
+    "en-MW": "English",
+    "en-MY": "English",
+    "en-NA": "English",
+    "en-NF": "English",
+    "en-NG": "English",
+    "en-NL": "English",
+    "en-NO": "English",
+    "en-NR": "English",
+    "en-NU": "English",
+    "en-NZ": "English",
+    "en-PG": "English",
+    "en-PH": "English",
+    "en-PK": "English",
+    "en-PL": "English",
+    "en-PN": "English",
+    "en-PR": "English",
+    "en-PT": "English",
+    "en-PW": "English",
+    "en-RO": "English",
+    "en-RW": "English",
+    "en-SB": "English",
+    "en-SC": "English",
+    "en-SD": "English",
+    "en-SE": "English",
+    "en-SG": "English",
+    "en-SH": "English",
+    "en-SI": "English",
+    "en-SK": "English",
+    "en-SL": "English",
+    "en-SS": "English",
+    "en-SX": "English",
+    "en-SZ": "English",
+    "en-TC": "English",
+    "en-TK": "English",
+    "en-TO": "English",
+    "en-TT": "English",
+    "en-TV": "English",
+    "en-TZ": "English",
+    "en-UG": "English",
+    "en-UM": "English",
+    "en-VC": "English",
+    "en-VG": "English",
+    "en-VI": "English",
+    "en-VU": "English",
+    "en-WS": "English",
+    "en-ZA": "English",
+    "en-ZM": "English",
+    "en-ZW": "English",
+    "eo": "Esperanto",
+    "es": "Spanish",
+    "es-AR": "Spanish",
+    "es-BO": "Spanish",
+    "es-BR": "Spanish",
+    "es-BZ": "Spanish",
+    "es-CL": "Spanish",
+    "es-CO": "Spanish",
+    "es-CR": "Spanish",
+    "es-CU": "Spanish",
+    "es-DO": "Spanish",
+    "es-EA": "Spanish",
+    "es-EC": "Spanish",
+    "es-ES": "Spanish",
+    "es-GQ": "Spanish",
+    "es-GT": "Spanish",
+    "es-HN": "Spanish",
+    "es-IC": "Spanish",
+    "es-MX": "Spanish",
+    "es-NI": "Spanish",
+    "es-PA": "Spanish",
+    "es-PE": "Spanish",
+    "es-PH": "Spanish",
+    "es-PR": "Spanish",
+    "es-PY": "Spanish",
+    "es-SV": "Spanish",
+    "es-US": "Spanish",
+    "es-UY": "Spanish",
+    "es-VE": "Spanish",
+    "et": "Estonian",
+    "et-EE": "Estonian",
+    "eu": "Basque",
+    "fa": "Persian",
+    "fa-AF": "Persian",
+    "fa-IR": "Persian",
+    "ff": "Fulah",
+    "ff-Adlm": "Fulah",
+    "ff-Adlm-BF": "Fulah",
+    "ff-Adlm-CM": "Fulah",
+    "ff-Adlm-GH": "Fulah",
+    "ff-Adlm-GM": "Fulah",
+    "ff-Adlm-GW": "Fulah",
+    "ff-Adlm-LR": "Fulah",
+    "ff-Adlm-MR": "Fulah",
+    "ff-Adlm-NE": "Fulah",
+    "ff-Adlm-NG": "Fulah",
+    "ff-Adlm-SL": "Fulah",
+    "ff-Adlm-SN": "Fulah",
+    "ff-Latn": "Fulah",
+    "ff-Latn-BF": "Fulah",
+    "ff-Latn-CM": "Fulah",
+    "ff-Latn-GH": "Fulah",
+    "ff-Latn-GM": "Fulah",
+    "ff-Latn-GN": "Fulah",
+    "ff-Latn-GW": "Fulah",
+    "ff-Latn-LR": "Fulah",
+    "ff-Latn-MR": "Fulah",
+    "ff-Latn-NE": "Fulah",
+    "ff-Latn-NG": "Fulah",
+    "ff-Latn-SL": "Fulah",
+    "fi": "Finnish",
+    "fi-FI": "Finnish",
+    "fil-PH": "Filipino",
+    "fo": "Faroese",
+    "fo-DK": "Faroese",
+    "fr": "French",
+    "fr-BE": "French",
+    "fr-BF": "French",
+    "fr-BI": "French",
+    "fr-BJ": "French",
+    "fr-BL": "French",
+    "fr-CA": "French",
+    "fr-CD": "French",
+    "fr-CF": "French",
+    "fr-CG": "French",
+    "fr-CH": "French",
+    "fr-CI": "French",
+    "fr-CM": "French",
+    "fr-DJ": "French",
+    "fr-DZ": "French",
+    "fr-FR": "French",
+    "fr-GA": "French",
+    "fr-GF": "French",
+    "fr-GN": "French",
+    "fr-GP": "French",
+    "fr-GQ": "French",
+    "fr-HT": "French",
+    "fr-KM": "French",
+    "fr-LU": "French",
+    "fr-MA": "French",
+    "fr-MC": "French",
+    "fr-MF": "French",
+    "fr-MG": "French",
+    "fr-ML": "French",
+    "fr-MQ": "French",
+    "fr-MR": "French",
+    "fr-MU": "French",
+    "fr-NC": "French",
+    "fr-NE": "French",
+    "fr-PF": "French",
+    "fr-PM": "French",
+    "fr-RE": "French",
+    "fr-RW": "French",
+    "fr-SC": "French",
+    "fr-SN": "French",
+    "fr-SY": "French",
+    "fr-TD": "French",
+    "fr-TG": "French",
+    "fr-TN": "French",
+    "fr-VU": "French",
+    "fr-WF": "French",
+    "fr-YT": "French",
+    "fy": "Western Frisian",
+    "ga": "Irish",
+    "ga-GB": "Irish",
+    "gd": "Scottish Gaelic",
+    "gl": "Galician",
+    "gn": "Guarani",
+    "gu": "Gujarati",
+    "gu-IN": "Gujarati",
+    "gv": "Manx",
+    "ha": "Hausa",
+    "ha-Arab": "Hausa",
+    "ha-Arab-SD": "Hausa",
+    "ha-GH": "Hausa",
+    "ha-NE": "Hausa",
+    "he": "Hebrew",
+    "he-IL": "Hebrew",
+    "hi": "Hindi",
+    "hi-IN": "Hindi",
+    "hi-Latn": "Hindi",
+    "hr": "Croatian",
+    "hr-BA": "Croatian",
+    "hr-HR": "Croatian",
+    "ht": "Haitian",
+    "hu": "Hungarian",
+    "hu-HU": "Hungarian",
+    "hy": "Armenian",
+    "ia": "Interlingua",
+    "id": "Indonesian",
+    "id-ID": "Indonesian",
+    "ie": "Interlingue",
+    "ig": "Igbo",
+    "ii": "Sichuan Yi",
+    "ik": "Inupiaq",
+    "io": "Ido",
+    "is": "Icelandic",
+    "it": "Italian",
+    "it-CH": "Italian",
+    "it-IT": "Italian",
+    "it-SM": "Italian",
+    "it-VA": "Italian",
+    "iu": "Inuktitut",
+    "iu-Latn": "Inuktitut",
+    "ja": "Japanese",
+    "ja-JP": "Japanese",
+    "jv": "Javanese",
+    "ka": "Georgian",
+    "ki": "Kikuyu",
+    "kk": "Kazakh",
+    "kk-Arab": "Kazakh",
+    "kk-Cyrl": "Kazakh",
+    "kk-KZ": "Kazakh",
+    "kl": "Kalaallisut",
+    "km": "Central Khmer",
+    "kn": "Kannada",
+    "kn-IN": "Kannada",
+    "ko": "Korean",
+    "ko-CN": "Korean",
+    "ko-KP": "Korean",
+    "ko-KR": "Korean",
+    "ks": "Kashmiri",
+    "ks-Arab": "Kashmiri",
+    "ks-Deva": "Kashmiri",
+    "ku": "Kurdish",
+    "kw": "Cornish",
+    "ky": "Kyrgyz",
+    "la": "Latin",
+    "lb": "Luxembourgish",
+    "lg": "Ganda",
+    "ln": "Lingala",
+    "ln-AO": "Lingala",
+    "ln-CF": "Lingala",
+    "ln-CG": "Lingala",
+    "lo": "Lao",
+    "lt": "Lithuanian",
+    "lt-LT": "Lithuanian",
+    "lu": "Luba-Katanga",
+    "lv": "Latvian",
+    "lv-LV": "Latvian",
+    "mg": "Malagasy",
+    "mi": "Maori",
+    "mk": "Macedonian",
+    "ml": "Malayalam",
+    "ml-IN": "Malayalam",
+    "mn": "Mongolian",
+    "mn-Mong": "Mongolian",
+    "mn-Mong-MN": "Mongolian",
+    "mr": "Marathi",
+    "mr-IN": "Marathi",
+    "ms": "Malay",
+    "ms-Arab": "Malay",
+    "ms-Arab-BN": "Malay",
+    "ms-BN": "Malay",
+    "ms-ID": "Malay",
+    "ms-SG": "Malay",
+    "mt": "Maltese",
+    "my": "Burmese",
+    "nb": "Norwegian Bokmål",
+    "nb-SJ": "Norwegian Bokmål",
+    "nd": "North Ndebele",
+    "ne": "Nepali",
+    "ne-IN": "Nepali",
+    "nl": "Dutch",
+    "nl-AW": "Dutch",
+    "nl-BE": "Dutch",
+    "nl-BQ": "Dutch",
+    "nl-CW": "Dutch",
+    "nl-NL": "Dutch",
+    "nl-SR": "Dutch",
+    "nl-SX": "Dutch",
+    "nn": "Norwegian Nynorsk",
+    "no": "Norwegian",
+    "no-NO": "Norwegian",
+    "nr": "South Ndebele",
+    "nv": "Navajo",
+    "ny": "Chichewa",
+    "oc": "Occitan",
+    "oc-ES": "Occitan",
+    "om": "Oromo",
+    "om-KE": "Oromo",
+    "or": "Oriya",
+    "os": "Ossetian",
+    "os-RU": "Ossetian",
+    "pa": "Punjabi",
+    "pa-IN": "Punjabi",
+    "pa-Arab": "Punjabi",
+    "pa-Guru": "Punjabi",
+    "pl": "Polish",
+    "pl-PL": "Polish",
+    "ps": "Pashto",
+    "ps-PK": "Pashto",
+    "pt": "Portuguese",
+    "pt-AO": "Portuguese",
+    "pt-BR": "Portuguese",
+    "pt-CH": "Portuguese",
+    "pt-CV": "Portuguese",
+    "pt-GQ": "Portuguese",
+    "pt-GW": "Portuguese",
+    "pt-LU": "Portuguese",
+    "pt-MO": "Portuguese",
+    "pt-MZ": "Portuguese",
+    "pt-PT": "Portuguese",
+    "pt-ST": "Portuguese",
+    "pt-TL": "Portuguese",
+    "qu": "Quechua",
+    "qu-BO": "Quechua",
+    "qu-EC": "Quechua",
+    "rm": "Romansh",
+    "rn": "Rundi",
+    "ro": "Romanian",
+    "ro-MD": "Romanian",
+    "ro-RO": "Romanian",
+    "ru": "Russian",
+    "ru-BY": "Russian",
+    "ru-KG": "Russian",
+    "ru-KZ": "Russian",
+    "ru-MD": "Russian",
+    "ru-RU": "Russian",
+    "ru-UA": "Russian",
+    "rw": "Kinyarwanda",
+    "sa": "Sanskrit",
+    "sc": "Sardinian",
+    "sd": "Sindhi",
+    "sd-Arab": "Sindhi",
+    "sd-Deva": "Sindhi",
+    "se": "Northern Sami",
+    "se-FI": "Northern Sami",
+    "se-SE": "Northern Sami",
+    "sg": "Sango",
+    "si": "Sinhala",
+    "sk": "Slovak",
+    "sk-SK": "Slovak",
+    "sl": "Slovenian",
+    "sl-SI": "Slovenian",
+    "sn": "Shona",
+    "so": "Somali",
+    "so-DJ": "Somali",
+    "so-ET": "Somali",
+    "so-KE": "Somali",
+    "sq": "Albanian",
+    "sq-MK": "Albanian",
+    "sq-XK": "Albanian",
+    "sr": "Serbian",
+    "sr-RS": "Serbian",
+    "sr-Cyrl": "Serbian",
+    "sr-Cyrl-BA": "Serbian",
+    "sr-Cyrl-ME": "Serbian",
+    "sr-Cyrl-XK": "Serbian",
+    "sr-Latn": "Serbian",
+    "sr-Latn-BA": "Serbian",
+    "sr-Latn-ME": "Serbian",
+    "sr-Latn-XK": "Serbian",
+    "ss": "Swati",
+    "ss-SZ": "Swati",
+    "st": "Southern Sotho",
+    "st-LS": "Southern Sotho",
+    "su": "Sundanese",
+    "su-Latn": "Sundanese",
+    "sv": "Swedish",
+    "sv-AX": "Swedish",
+    "sv-FI": "Swedish",
+    "sv-SE": "Swedish",
+    "sw": "Swahili",
+    "sw-CD": "Swahili",
+    "sw-KE": "Swahili",
+    "sw-TZ": "Swahili",
+    "sw-UG": "Swahili",
+    "ta": "Tamil",
+    "ta-IN": "Tamil",
+    "ta-LK": "Tamil",
+    "ta-MY": "Tamil",
+    "ta-SG": "Tamil",
+    "te": "Telugu",
+    "te-IN": "Telugu",
+    "tg": "Tajik",
+    "th": "Thai",
+    "th-TH": "Thai",
+    "ti": "Tigrinya",
+    "ti-ER": "Tigrinya",
+    "tk": "Turkmen",
+    "tl": "Tagalog",
+    "tn": "Tswana",
+    "tn-BW": "Tswana",
+    "to": "Tonga",
+    "tr": "Turkish",
+    "tr-CY": "Turkish",
+    "tr-TR": "Turkish",
+    "ts": "Tsonga",
+    "tt": "Tatar",
+    "ug": "Uyghur",
+    "uk": "Ukrainian",
+    "uk-UA": "Ukrainian",
+    "ur": "Urdu",
+    "ur-IN": "Urdu",
+    "ur-PK": "Urdu",
+    "uz": "Uzbek",
+    "uz-Arab": "Uzbek",
+    "uz-Cyrl": "Uzbek",
+    "uz-Latn": "Uzbek",
+    "ve": "Venda",
+    "vi": "Vietnamese",
+    "vi-VN": "Vietnamese",
+    "vo": "Volapük",
+    "wa": "Walloon",
+    "wo": "Wolof",
+    "xh": "Xhosa",
+    "yi": "Yiddish",
+    "yo": "Yoruba",
+    "yo-BJ": "Yoruba",
+    "za": "Zhuang",
+    "zh": "Chinese",
+    "zh-CH": "Chinese",
+    "zh-TW": "Chinese",
+    "zh-Hans": "Chinese",
+    "zh-Hans-HK": "Chinese",
+    "zh-Hans-MO": "Chinese",
+    "zh-Hans-MY": "Chinese",
+    "zh-Hans-SG": "Chinese",
+    "zh-Hant": "Chinese",
+    "zh-Hant-HK": "Chinese",
+    "zh-Hant-MO": "Chinese",
+    "zh-Hant-MY": "Chinese",
+    "zh-Latn": "Chinese",
+    "zu": "Zulu",
+    "zu-ZA": "Zulu",
+}
+-%}
+{{ bos_token }}
+{%- if (messages[0]['role'] != 'user') -%}
+    {{ raise_exception("Conversations must start with a user prompt.") }}
+{%- endif -%}
+{%- for message in messages -%}
+    {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}
+        {{ raise_exception("Conversation roles must alternate user/assistant/user/assistant/...") }}
+    {%- endif -%}
+    {%- if (message['role'] == 'assistant') -%}
+        {%- if message['content'] is none or message['content'] is not string -%}
+            {{ raise_exception("Assistant role must provide content as a string") }}
+        {%- endif -%}
+        {{ '<start_of_turn>model\n'}}
+        {{ message["content"] | trim }}
+    {%- elif (message['role'] == 'user') -%}
+        {%- if message['content'] is none or message['content'] is not iterable or message['content'] | length != 1 -%}
+            {{ raise_exception(
+                "User role must provide `content` as an iterable with exactly one item. That item must be a " +
+                "`mapping(type:'text' | 'image', source_lang_code:string, target_lang_code:string, " +
+                "text:string | none, image:string | none)`."
+            ) }}
+        {%- endif -%}
+        {%- set content = message["content"][0] -%}
+        {%- set source_lang_code = content["source_lang_code"] | replace("_", "-")  -%}
+        {%- set source_lang = languages[source_lang_code] -%}
+        {%- set target_lang_code = content["target_lang_code"] | replace("_", "-") -%}
+        {%- set target_lang = languages[target_lang_code] -%}
+        {{ '<start_of_turn>user\nYou are a professional ' + source_lang + ' (' + source_lang_code + ') to ' +
+           target_lang + ' (' + target_lang_code + ') translator. Your goal is to accurately convey the meaning and '
+           'nuances of the original ' + source_lang + ' text while adhering to ' + target_lang + ' grammar, '
+           'vocabulary, and cultural sensitivities.\n'
+        }}
+        {%- if content["type"] == 'text' -%}
+            {{
+                'Produce only the ' + target_lang + ' translation, without any additional explanations or ' +
+                'commentary. Please translate the following ' + source_lang + ' text into ' + target_lang + ':\n\n\n' +
+                content["text"] | trim
+            }}
+        {%- elif content["type"] == 'image' -%}
+            {{
+                'Please translate the ' + source_lang + ' text in the provided image into ' + target_lang + '. ' +
+                'Produce only the ' + target_lang + ' translation, without any additional explanations, ' +
+                'alternatives or commentary. Focus only on the text, do not output where the text is located, ' +
+                'surrounding objects or any other explanation about the picture. Ignore symbols, pictogram, and ' +
+                'arrows!\n\n\n<start_of_image>'
+            }}
+        {%- else -%}
+            {{ raise_exception("User role `content` can contain either `text` or `image` data.") }}
+        {%- endif -%}
+    {%- else -%}
+        {{ raise_exception("Conversations must only contain user or assistant roles.") }}
+    {%- endif -%}
+    {{ '<end_of_turn>\n' }}
+{%- endfor -%}
+{%- if add_generation_prompt -%}
+    {{'<start_of_turn>model\n'}}
+{%- endif -%}

config.json

@@ -0,0 +1,90 @@
+{
+  "_sliding_window_pattern": 6,
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "attn_logit_softcapping": null,
+  "bos_token_id": 2,
+  "dtype": "bfloat16",
+  "eos_token_id": 1,
+  "final_logit_softcapping": null,
+  "head_dim": 256,
+  "hidden_activation": "gelu_pytorch_tanh",
+  "hidden_size": 3840,
+  "initializer_range": 0.02,
+  "intermediate_size": 15360,
+  "layer_types": [
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 131072,
+  "model_type": "gemma3_text",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 48,
+  "num_key_value_heads": 8,
+  "pad_token_id": 0,
+  "query_pre_attn_scalar": 256,
+  "rms_norm_eps": 1e-06,
+  "rope_local_base_freq": 10000,
+  "rope_parameters": {
+    "full_attention": {
+      "factor": 8.0,
+      "rope_type": "linear"
+    },
+    "sliding_attention": {
+      "rope_type": "default"
+    }
+  },
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "sliding_window": 1024,
+  "transformers_version": "4.57.6",
+  "use_bidirectional_attention": false,
+  "use_cache": false,
+  "vocab_size": 262208
+}

special_tokens_map.json

@@ -0,0 +1,33 @@
+{
+  "boi_token": "<start_of_image>",
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eoi_token": "<end_of_image>",
+  "eos_token": {
+    "content": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "image_token": "<image_soft_token>",
+  "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.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4667f2089529e8e7657cfb6d1c19910ae71ff5f28aa7ab2ff2763330affad795
+size 33384568

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1299c11d7cf632ef3b4e11937501358ada021bbdf7c47638d13c0ee982f2e79c
+size 4689074