初始化项目，由ModelHub XC社区提供模型
Model: nuinashco/gemma-3-1b-it-xlsum-ua-sft 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
|
||||
72
README.md
Normal file
72
README.md
Normal file
@@ -0,0 +1,72 @@
|
||||
---
|
||||
language:
|
||||
- uk
|
||||
license: gemma
|
||||
base_model: unsloth/gemma-3-1b-it
|
||||
datasets:
|
||||
- csebuetnlp/xlsum
|
||||
tags:
|
||||
- summarization
|
||||
- ukrainian
|
||||
- unsloth
|
||||
- gemma3
|
||||
- sft
|
||||
metrics:
|
||||
- rouge
|
||||
pipeline_tag: text-generation
|
||||
---
|
||||
|
||||
# gemma-3-1b-ua-safe-summarization
|
||||
|
||||
Full fine-tune of [**unsloth/gemma-3-1b-it**](https://huggingface.co/unsloth/gemma-3-1b-it) on Ukrainian news summarization.
|
||||
Trained with [Unsloth](https://github.com/unslothai/unsloth) + TRL SFT on the
|
||||
[**csebuetnlp/xlsum**](https://huggingface.co/datasets/csebuetnlp/xlsum) dataset
|
||||
(Ukrainian split of XL-Sum with safety filtering).
|
||||
|
||||
## Training details
|
||||
|
||||
| | |
|
||||
|---|---|
|
||||
| Base model | [unsloth/gemma-3-1b-it](https://huggingface.co/unsloth/gemma-3-1b-it) |
|
||||
| Dataset | [csebuetnlp/xlsum](https://huggingface.co/datasets/csebuetnlp/xlsum) |
|
||||
| Fine-tuning | Full SFT (no LoRA) |
|
||||
| Framework | [Unsloth](https://github.com/unslothai/unsloth) + TRL |
|
||||
| Epochs | ~1.48 (checkpoint-4000, best val ROUGE-L) |
|
||||
| Max seq length | 3072 |
|
||||
| Batch size | 8 per device |
|
||||
| Learning rate | 2e-5 (cosine decay, warmup 3 %) |
|
||||
| Precision | bfloat16 |
|
||||
| Optimizer | adamw_8bit |
|
||||
| Best eval ROUGE-L | **22.23** |
|
||||
|
||||
Response-only masking was applied — loss is computed on the model turn only.
|
||||
|
||||
## Usage
|
||||
|
||||
```python
|
||||
from transformers import AutoTokenizer, AutoModelForCausalLM
|
||||
import torch
|
||||
|
||||
model_id = "nuinashco/gemma-3-1b-it-xlsum-ua-sft"
|
||||
tokenizer = AutoTokenizer.from_pretrained(model_id)
|
||||
model = AutoModelForCausalLM.from_pretrained(
|
||||
model_id, torch_dtype=torch.bfloat16, device_map="auto"
|
||||
)
|
||||
|
||||
article = "Ваш текст новини тут..."
|
||||
prompt = [
|
||||
{"role": "user", "content": f"Зроби короткий переказ наступного тексту:\n{article}"}
|
||||
]
|
||||
inputs = tokenizer.apply_chat_template(
|
||||
prompt, add_generation_prompt=True, return_tensors="pt"
|
||||
).to(model.device)
|
||||
|
||||
out = model.generate(inputs, max_new_tokens=128, do_sample=False)
|
||||
print(tokenizer.decode(out[0][inputs.shape[-1]:], skip_special_tokens=True))
|
||||
```
|
||||
|
||||
## Limitations
|
||||
|
||||
- Trained for **Ukrainian** only; performance on other languages is undefined.
|
||||
- Inherits any biases present in the base model and training corpus.
|
||||
- Summaries may occasionally be factually inaccurate; always verify against the source.
|
||||
3
added_tokens.json
Normal file
3
added_tokens.json
Normal file
@@ -0,0 +1,3 @@
|
||||
{
|
||||
"<image_soft_token>": 262144
|
||||
}
|
||||
47
chat_template.jinja
Normal file
47
chat_template.jinja
Normal file
@@ -0,0 +1,47 @@
|
||||
{{ bos_token }}
|
||||
{%- if messages[0]['role'] == 'system' -%}
|
||||
{%- if messages[0]['content'] is string -%}
|
||||
{%- set first_user_prefix = messages[0]['content'] + '
|
||||
|
||||
' -%}
|
||||
{%- else -%}
|
||||
{%- set first_user_prefix = messages[0]['content'][0]['text'] + '
|
||||
|
||||
' -%}
|
||||
{%- endif -%}
|
||||
{%- set loop_messages = messages[1:] -%}
|
||||
{%- else -%}
|
||||
{%- set first_user_prefix = "" -%}
|
||||
{%- set loop_messages = messages -%}
|
||||
{%- endif -%}
|
||||
{%- for message in loop_messages -%}
|
||||
{%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}
|
||||
{{ raise_exception("Conversation roles must alternate user/assistant/user/assistant/...") }}
|
||||
{%- endif -%}
|
||||
{%- if (message['role'] == 'assistant') -%}
|
||||
{%- set role = "model" -%}
|
||||
{%- else -%}
|
||||
{%- set role = message['role'] -%}
|
||||
{%- endif -%}
|
||||
{{ '<start_of_turn>' + role + '
|
||||
' + (first_user_prefix if loop.first else "") }}
|
||||
{%- if message['content'] is string -%}
|
||||
{{ message['content'] | trim }}
|
||||
{%- elif message['content'] is iterable -%}
|
||||
{%- for item in message['content'] -%}
|
||||
{%- if item['type'] == 'image' -%}
|
||||
{{ '<start_of_image>' }}
|
||||
{%- elif item['type'] == 'text' -%}
|
||||
{{ item['text'] | trim }}
|
||||
{%- endif -%}
|
||||
{%- endfor -%}
|
||||
{%- else -%}
|
||||
{{ raise_exception("Invalid content type") }}
|
||||
{%- endif -%}
|
||||
{{ '<end_of_turn>
|
||||
' }}
|
||||
{%- endfor -%}
|
||||
{%- if add_generation_prompt -%}
|
||||
{{ '<start_of_turn>model
|
||||
' }}
|
||||
{%- endif -%}
|
||||
67
config.json
Normal file
67
config.json
Normal file
@@ -0,0 +1,67 @@
|
||||
{
|
||||
"_sliding_window_pattern": 6,
|
||||
"architectures": [
|
||||
"Gemma3ForCausalLM"
|
||||
],
|
||||
"attention_bias": false,
|
||||
"attention_dropout": 0.0,
|
||||
"attn_logit_softcapping": null,
|
||||
"bos_token_id": 2,
|
||||
"cache_implementation": "hybrid",
|
||||
"dtype": "bfloat16",
|
||||
"eos_token_id": 106,
|
||||
"final_logit_softcapping": null,
|
||||
"head_dim": 256,
|
||||
"hidden_activation": "gelu_pytorch_tanh",
|
||||
"hidden_size": 1152,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 6912,
|
||||
"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"
|
||||
],
|
||||
"max_position_embeddings": 32768,
|
||||
"model_name": "unsloth/gemma-3-1b-it",
|
||||
"model_type": "gemma3_text",
|
||||
"num_attention_heads": 4,
|
||||
"num_hidden_layers": 26,
|
||||
"num_key_value_heads": 1,
|
||||
"pad_token_id": 0,
|
||||
"query_pre_attn_scalar": 256,
|
||||
"rms_norm_eps": 1e-06,
|
||||
"rope_local_base_freq": 10000,
|
||||
"rope_scaling": null,
|
||||
"rope_theta": 1000000,
|
||||
"sliding_window": 512,
|
||||
"sliding_window_pattern": 6,
|
||||
"transformers_version": "4.57.6",
|
||||
"unsloth_fixed": true,
|
||||
"unsloth_version": "2026.4.7",
|
||||
"use_bidirectional_attention": false,
|
||||
"use_cache": true,
|
||||
"vocab_size": 262144
|
||||
}
|
||||
14
generation_config.json
Normal file
14
generation_config.json
Normal file
@@ -0,0 +1,14 @@
|
||||
{
|
||||
"bos_token_id": 2,
|
||||
"cache_implementation": "hybrid",
|
||||
"do_sample": true,
|
||||
"eos_token_id": [
|
||||
1,
|
||||
106
|
||||
],
|
||||
"max_length": 32768,
|
||||
"pad_token_id": 0,
|
||||
"top_k": 64,
|
||||
"top_p": 0.95,
|
||||
"transformers_version": "4.57.6"
|
||||
}
|
||||
3
model.safetensors
Normal file
3
model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:e3a7eca4482e6202c542e09aed6d17b75ad59f9587e489e9212d850761352b8d
|
||||
size 1999811208
|
||||
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": "<end_of_turn>",
|
||||
"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
2898
trainer_state.json
Normal file
2898
trainer_state.json
Normal file
File diff suppressed because it is too large
Load Diff
Reference in New Issue
Block a user