初始化项目，由ModelHub XC社区提供模型
Model: ai-for-good-lab/byol-mri-12b-it Source: Original Platform
This commit is contained in:
ModelHub XC
36
.gitattributes
vendored
Normal file
36
.gitattributes
vendored
Normal file
@@ -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
|
||||
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||
65
README.md
Normal file
65
README.md
Normal file
@@ -0,0 +1,65 @@
|
||||
---
|
||||
license: gemma
|
||||
language:
|
||||
- mi
|
||||
- en
|
||||
base_model: google/gemma-3-12b-pt
|
||||
tags:
|
||||
- byol
|
||||
- low-resource
|
||||
- māori
|
||||
- gemma3
|
||||
library_name: transformers
|
||||
pipeline_tag: text-generation
|
||||
---
|
||||
|
||||
# BYOL Māori 12B IT
|
||||
|
||||
This model was produced by the [BYOL framework](https://github.com/microsoft/byol)
|
||||
for extending LLMs to low-resource languages.
|
||||
|
||||
- **Base model:** [google/gemma-3-12b-pt](https://huggingface.co/google/gemma-3-12b-pt)
|
||||
- **Language:** Māori (mri)
|
||||
- **Training stage:** Instruction Tuning (SFT)
|
||||
- **License:** [Gemma Terms of Use](https://ai.google.dev/gemma/terms) (derived from Gemma 3)
|
||||
- **Paper:** [BYOL: Bring Your Own Language Into LLMs](https://arxiv.org/abs/2601.10804)
|
||||
- **Code:** [github.com/microsoft/byol](https://github.com/microsoft/byol)
|
||||
|
||||
## Model Description
|
||||
|
||||
This is an **instruction-tuned (SFT)** language model for Māori (mri). It was created by applying supervised fine-tuning on top of the [BYOL Māori 12b CPT](https://huggingface.co/ai-for-good-lab/byol-mri-12b-cpt) checkpoint, using translated instruction-following data (SmolTalk2 + AYA) generated via the [BYOL framework](https://github.com/microsoft/byol).
|
||||
|
||||
This is an intermediate checkpoint used to produce the merged model. For best results, use the [merged variant](https://huggingface.co/ai-for-good-lab/byol-mri-12b-merged) instead, which combines the language knowledge from CPT with the instruction-following ability from this model.
|
||||
|
||||
## Usage
|
||||
|
||||
```bash
|
||||
pip install -U transformers
|
||||
```
|
||||
|
||||
```python
|
||||
from transformers import AutoModelForCausalLM, AutoTokenizer
|
||||
import torch
|
||||
|
||||
model_id = "ai-for-good-lab/byol-mri-12b-it"
|
||||
tokenizer = AutoTokenizer.from_pretrained(model_id)
|
||||
model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto", dtype=torch.bfloat16)
|
||||
|
||||
# Chat inference
|
||||
messages = [{"role": "user", "content": "Kōrerotia mai mō Aotearoa."}]
|
||||
inputs = tokenizer.apply_chat_template(messages, return_tensors="pt", add_generation_prompt=True, return_dict=True).to(model.device)
|
||||
outputs = model.generate(**inputs, max_new_tokens=256)
|
||||
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
|
||||
```
|
||||
|
||||
## Citation
|
||||
|
||||
```bibtex
|
||||
@article{zamir2026byolbringlanguagellms,
|
||||
title={BYOL: Bring Your Own Language Into LLMs},
|
||||
author={Syed Waqas Zamir and Wassim Hamidouche and Boulbaba Ben Amor and Luana Marotti and Inbal Becker-Reshef and Juan Lavista Ferres},
|
||||
year={2026},
|
||||
journal={arXiv:2601.10804},
|
||||
url={https://arxiv.org/abs/2601.10804},
|
||||
}
|
||||
```
|
||||
3
added_tokens.json
Normal file
3
added_tokens.json
Normal file
@@ -0,0 +1,3 @@
|
||||
{
|
||||
"<image_soft_token>": 262144
|
||||
}
|
||||
3
chat_template.json
Normal file
3
chat_template.json
Normal file
@@ -0,0 +1,3 @@
|
||||
{
|
||||
"chat_template": "{{ bos_token }}\n{%- if messages[0]['role'] == 'system' -%}\n {%- if messages[0]['content'] is string -%}\n {%- set first_user_prefix = messages[0]['content'] + '\n\n' -%}\n {%- else -%}\n {%- set first_user_prefix = messages[0]['content'][0]['text'] + '\n\n' -%}\n {%- endif -%}\n {%- set loop_messages = messages[1:] -%}\n{%- else -%}\n {%- set first_user_prefix = \"\" -%}\n {%- set loop_messages = messages -%}\n{%- endif -%}\n{%- for message in loop_messages -%}\n {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}\n {{ raise_exception(\"Conversation roles must alternate user/assistant/user/assistant/...\") }}\n {%- endif -%}\n {%- if (message['role'] == 'assistant') -%}\n {%- set role = \"model\" -%}\n {%- else -%}\n {%- set role = message['role'] -%}\n {%- endif -%}\n {{ '<start_of_turn>' + role + '\n' + (first_user_prefix if loop.first else \"\") }}\n {%- if message['content'] is string -%}\n {{ message['content'] | trim }}\n {%- elif message['content'] is iterable -%}\n {%- for item in message['content'] -%}\n {%- if item['type'] == 'image' -%}\n {{ '<start_of_image>' }}\n {%- elif item['type'] == 'text' -%}\n {{ item['text'] | trim }}\n {%- endif -%}\n {%- endfor -%}\n {%- else -%}\n {{ raise_exception(\"Invalid content type\") }}\n {%- endif -%}\n {{ '<end_of_turn>\n' }}\n{%- endfor -%}\n{%- if add_generation_prompt -%}\n {{'<start_of_turn>model\n'}}\n{%- endif -%}\n"
|
||||
}
|
||||
109
config.json
Normal file
109
config.json
Normal file
@@ -0,0 +1,109 @@
|
||||
{
|
||||
"architectures": [
|
||||
"Gemma3ForConditionalGeneration"
|
||||
],
|
||||
"boi_token_index": 255999,
|
||||
"dtype": "bfloat16",
|
||||
"eoi_token_index": 256000,
|
||||
"image_token_index": 262144,
|
||||
"initializer_range": 0.02,
|
||||
"mm_tokens_per_image": 256,
|
||||
"model_type": "gemma3",
|
||||
"text_config": {
|
||||
"_sliding_window_pattern": 6,
|
||||
"attention_bias": false,
|
||||
"attention_dropout": 0.0,
|
||||
"attn_logit_softcapping": null,
|
||||
"dtype": "bfloat16",
|
||||
"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,
|
||||
"query_pre_attn_scalar": 256,
|
||||
"rms_norm_eps": 1e-06,
|
||||
"rope_local_base_freq": 10000.0,
|
||||
"rope_scaling": {
|
||||
"factor": 8.0,
|
||||
"rope_type": "linear"
|
||||
},
|
||||
"rope_theta": 1000000.0,
|
||||
"sliding_window": 1024,
|
||||
"use_bidirectional_attention": false,
|
||||
"use_cache": true,
|
||||
"vocab_size": 262208
|
||||
},
|
||||
"transformers_version": "4.57.6",
|
||||
"vision_config": {
|
||||
"attention_dropout": 0.0,
|
||||
"dtype": "bfloat16",
|
||||
"hidden_act": "gelu_pytorch_tanh",
|
||||
"hidden_size": 1152,
|
||||
"image_size": 896,
|
||||
"intermediate_size": 4304,
|
||||
"layer_norm_eps": 1e-06,
|
||||
"model_type": "siglip_vision_model",
|
||||
"num_attention_heads": 16,
|
||||
"num_channels": 3,
|
||||
"num_hidden_layers": 27,
|
||||
"patch_size": 14,
|
||||
"vision_use_head": false
|
||||
},
|
||||
"torch_dtype": "bfloat16"
|
||||
}
|
||||
13
generation_config.json
Normal file
13
generation_config.json
Normal file
@@ -0,0 +1,13 @@
|
||||
{
|
||||
"bos_token_id": 2,
|
||||
"cache_implementation": "hybrid",
|
||||
"do_sample": true,
|
||||
"eos_token_id": [
|
||||
1,
|
||||
106
|
||||
],
|
||||
"pad_token_id": 0,
|
||||
"top_k": 64,
|
||||
"top_p": 0.95,
|
||||
"transformers_version": "4.57.6"
|
||||
}
|
||||
3
model-00001-of-00005.safetensors
Normal file
3
model-00001-of-00005.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:1d51fb5f9c3e205fb91f1244d6024ebd8e67e68601e7ff4fb98a61c3178b326d
|
||||
size 4979902192
|
||||
3
model-00002-of-00005.safetensors
Normal file
3
model-00002-of-00005.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:6f01c0b16fcd6b88b813306f7f0c19d28f57a36cfaf78af376cf287f29f9c876
|
||||
size 4931296592
|
||||
3
model-00003-of-00005.safetensors
Normal file
3
model-00003-of-00005.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:a40b18f68476ed8804b78c5fe17303d154236cf330b68422d0f5451747ae0c85
|
||||
size 4931296656
|
||||
3
model-00004-of-00005.safetensors
Normal file
3
model-00004-of-00005.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:241d3e61ba0e3f8f2bce5255ead56a1ce787abd6d70f03cc275d2dabbdfb385a
|
||||
size 4931296656
|
||||
3
model-00005-of-00005.safetensors
Normal file
3
model-00005-of-00005.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:17f3aa4bb87c61d5a97a9531ed324f048a9f17b5e74be61de3b3704066d19275
|
||||
size 4601000928
|
||||
1073
model.safetensors.index.json
Normal file
1073
model.safetensors.index.json
Normal file
File diff suppressed because it is too large
Load Diff
29
preprocessor_config.json
Normal file
29
preprocessor_config.json
Normal file
@@ -0,0 +1,29 @@
|
||||
{
|
||||
"do_convert_rgb": null,
|
||||
"do_normalize": true,
|
||||
"do_pan_and_scan": null,
|
||||
"do_rescale": true,
|
||||
"do_resize": true,
|
||||
"image_mean": [
|
||||
0.5,
|
||||
0.5,
|
||||
0.5
|
||||
],
|
||||
"image_processor_type": "Gemma3ImageProcessor",
|
||||
"image_seq_length": 256,
|
||||
"image_std": [
|
||||
0.5,
|
||||
0.5,
|
||||
0.5
|
||||
],
|
||||
"pan_and_scan_max_num_crops": null,
|
||||
"pan_and_scan_min_crop_size": null,
|
||||
"pan_and_scan_min_ratio_to_activate": null,
|
||||
"processor_class": "Gemma3Processor",
|
||||
"resample": 2,
|
||||
"rescale_factor": 0.00392156862745098,
|
||||
"size": {
|
||||
"height": 896,
|
||||
"width": 896
|
||||
}
|
||||
}
|
||||
4
processor_config.json
Normal file
4
processor_config.json
Normal file
@@ -0,0 +1,4 @@
|
||||
{
|
||||
"image_seq_length": 256,
|
||||
"processor_class": "Gemma3Processor"
|
||||
}
|
||||
33
special_tokens_map.json
Normal file
33
special_tokens_map.json
Normal file
@@ -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
|
||||
}
|
||||
}
|
||||
3
tokenizer.json
Normal file
3
tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:4667f2089529e8e7657cfb6d1c19910ae71ff5f28aa7ab2ff2763330affad795
|
||||
size 33384568
|
||||
3
tokenizer.model
Normal file
3
tokenizer.model
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:1299c11d7cf632ef3b4e11937501358ada021bbdf7c47638d13c0ee982f2e79c
|
||||
size 4689074
|
||||
51346
tokenizer_config.json
Normal file
51346
tokenizer_config.json
Normal file
File diff suppressed because it is too large
Load Diff
Reference in New Issue
Block a user