初始化项目，由ModelHub XC社区提供模型
Model: cnmoro/Qwen2.5-0.5B-Portuguese-v1 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
|
||||
404
README.md
Normal file
404
README.md
Normal file
@@ -0,0 +1,404 @@
|
||||
---
|
||||
license: mit
|
||||
language:
|
||||
- zho
|
||||
- eng
|
||||
- fra
|
||||
- spa
|
||||
- por
|
||||
- deu
|
||||
- ita
|
||||
- rus
|
||||
- jpn
|
||||
- kor
|
||||
- vie
|
||||
- tha
|
||||
- ara
|
||||
base_model:
|
||||
- Qwen/Qwen2.5-0.5B-Instruct
|
||||
pipeline_tag: text-generation
|
||||
datasets:
|
||||
- adalbertojunior/openHermes_portuguese
|
||||
- cnmoro/smoltalk-555k-ptbr
|
||||
- cnmoro/RagMixPTBR-Legal-Alpaca-2M
|
||||
model-index:
|
||||
- name: Qwen2.5-0.5B-Portuguese-v1
|
||||
results:
|
||||
- task:
|
||||
type: text-generation
|
||||
name: Text Generation
|
||||
dataset:
|
||||
name: ENEM Challenge (No Images)
|
||||
type: eduagarcia/enem_challenge
|
||||
split: train
|
||||
args:
|
||||
num_few_shot: 3
|
||||
metrics:
|
||||
- type: acc
|
||||
value: 37.86
|
||||
name: accuracy
|
||||
source:
|
||||
url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=cnmoro/Qwen2.5-0.5B-Portuguese-v1
|
||||
name: Open Portuguese LLM Leaderboard
|
||||
- task:
|
||||
type: text-generation
|
||||
name: Text Generation
|
||||
dataset:
|
||||
name: BLUEX (No Images)
|
||||
type: eduagarcia-temp/BLUEX_without_images
|
||||
split: train
|
||||
args:
|
||||
num_few_shot: 3
|
||||
metrics:
|
||||
- type: acc
|
||||
value: 34.63
|
||||
name: accuracy
|
||||
source:
|
||||
url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=cnmoro/Qwen2.5-0.5B-Portuguese-v1
|
||||
name: Open Portuguese LLM Leaderboard
|
||||
- task:
|
||||
type: text-generation
|
||||
name: Text Generation
|
||||
dataset:
|
||||
name: OAB Exams
|
||||
type: eduagarcia/oab_exams
|
||||
split: train
|
||||
args:
|
||||
num_few_shot: 3
|
||||
metrics:
|
||||
- type: acc
|
||||
value: 33.12
|
||||
name: accuracy
|
||||
source:
|
||||
url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=cnmoro/Qwen2.5-0.5B-Portuguese-v1
|
||||
name: Open Portuguese LLM Leaderboard
|
||||
- task:
|
||||
type: text-generation
|
||||
name: Text Generation
|
||||
dataset:
|
||||
name: Assin2 RTE
|
||||
type: assin2
|
||||
split: test
|
||||
args:
|
||||
num_few_shot: 15
|
||||
metrics:
|
||||
- type: f1_macro
|
||||
value: 86.3
|
||||
name: f1-macro
|
||||
source:
|
||||
url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=cnmoro/Qwen2.5-0.5B-Portuguese-v1
|
||||
name: Open Portuguese LLM Leaderboard
|
||||
- task:
|
||||
type: text-generation
|
||||
name: Text Generation
|
||||
dataset:
|
||||
name: Assin2 STS
|
||||
type: eduagarcia/portuguese_benchmark
|
||||
split: test
|
||||
args:
|
||||
num_few_shot: 15
|
||||
metrics:
|
||||
- type: pearson
|
||||
value: 54.3
|
||||
name: pearson
|
||||
source:
|
||||
url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=cnmoro/Qwen2.5-0.5B-Portuguese-v1
|
||||
name: Open Portuguese LLM Leaderboard
|
||||
- task:
|
||||
type: text-generation
|
||||
name: Text Generation
|
||||
dataset:
|
||||
name: FaQuAD NLI
|
||||
type: ruanchaves/faquad-nli
|
||||
split: test
|
||||
args:
|
||||
num_few_shot: 15
|
||||
metrics:
|
||||
- type: f1_macro
|
||||
value: 65.33
|
||||
name: f1-macro
|
||||
source:
|
||||
url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=cnmoro/Qwen2.5-0.5B-Portuguese-v1
|
||||
name: Open Portuguese LLM Leaderboard
|
||||
- task:
|
||||
type: text-generation
|
||||
name: Text Generation
|
||||
dataset:
|
||||
name: HateBR Binary
|
||||
type: ruanchaves/hatebr
|
||||
split: test
|
||||
args:
|
||||
num_few_shot: 25
|
||||
metrics:
|
||||
- type: f1_macro
|
||||
value: 44.06
|
||||
name: f1-macro
|
||||
source:
|
||||
url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=cnmoro/Qwen2.5-0.5B-Portuguese-v1
|
||||
name: Open Portuguese LLM Leaderboard
|
||||
- task:
|
||||
type: text-generation
|
||||
name: Text Generation
|
||||
dataset:
|
||||
name: PT Hate Speech Binary
|
||||
type: hate_speech_portuguese
|
||||
split: test
|
||||
args:
|
||||
num_few_shot: 25
|
||||
metrics:
|
||||
- type: f1_macro
|
||||
value: 55.1
|
||||
name: f1-macro
|
||||
source:
|
||||
url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=cnmoro/Qwen2.5-0.5B-Portuguese-v1
|
||||
name: Open Portuguese LLM Leaderboard
|
||||
- task:
|
||||
type: text-generation
|
||||
name: Text Generation
|
||||
dataset:
|
||||
name: tweetSentBR
|
||||
type: eduagarcia/tweetsentbr_fewshot
|
||||
split: test
|
||||
args:
|
||||
num_few_shot: 25
|
||||
metrics:
|
||||
- type: f1_macro
|
||||
value: 45.96
|
||||
name: f1-macro
|
||||
source:
|
||||
url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=cnmoro/Qwen2.5-0.5B-Portuguese-v1
|
||||
name: Open Portuguese LLM Leaderboard
|
||||
---
|
||||
|
||||
Qwen2.5-0.5B finetuned for proficiency in Portuguese language and increased intelligence.
|
||||
|
||||
```text
|
||||
https://ollama.com/cnmoro/Qwen2.5-0.5B-Portuguese-v1
|
||||
```
|
||||
|
||||
```python
|
||||
from transformers import AutoModelForCausalLM, AutoTokenizer
|
||||
|
||||
model_name = "cnmoro/Qwen2.5-0.5B-Portuguese-v1"
|
||||
|
||||
model = AutoModelForCausalLM.from_pretrained(
|
||||
model_name,
|
||||
torch_dtype="auto",
|
||||
device_map="auto"
|
||||
)
|
||||
tokenizer = AutoTokenizer.from_pretrained(model_name)
|
||||
|
||||
prompt = "Escreva uma breve introdução sobre LLMs (Large Language Models) e suas aplicações."
|
||||
|
||||
# System prompt is always injected and hardcoded automatically
|
||||
# for ideal performance in portuguese language.
|
||||
# No need to write it again.
|
||||
messages = [
|
||||
{"role": "user", "content": prompt}
|
||||
]
|
||||
text = tokenizer.apply_chat_template(
|
||||
messages,
|
||||
tokenize=False,
|
||||
add_generation_prompt=True
|
||||
)
|
||||
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)
|
||||
|
||||
generated_ids = model.generate(
|
||||
**model_inputs,
|
||||
max_new_tokens=512
|
||||
)
|
||||
generated_ids = [
|
||||
output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
|
||||
]
|
||||
|
||||
response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
|
||||
response
|
||||
# LLM significa Large Language Models, que são modelos de linguagem computacional
|
||||
# projetados para simular a inteligência humana no processamento e geração de texto.
|
||||
# Esses modelos usam técnicas avançadas de aprendizado de máquina e redes neurais para
|
||||
# compreender e gerar texto com base em dados de entrada. As aplicações de LLM incluem
|
||||
# tradução automática, análise de sentimento, modelagem de tópicos e resposta a perguntas
|
||||
# automatizadas. Eles estão sendo cada vez mais utilizados em diversas áreas, como
|
||||
# saúde, educação e finanças, para melhorar a comunicação, as experiências dos clientes
|
||||
# e os resultados da pesquisa.
|
||||
```
|
||||
|
||||
## Overall Results
|
||||
|
||||
| Task | Metric | Value | Stdev |
|
||||
| ------------------------ | --------------- | ------- | ------- |
|
||||
| assin2_rte | f1_macro | 0.391 | 0.006 |
|
||||
| assin2_rte | acc | 0.527 | 0.007 |
|
||||
| assin2_sts | pearson | 0.115 | 0.014 |
|
||||
| assin2_sts | mse | 1.011 | N/A |
|
||||
| bluex | acc | 0.349 | 0.010 |
|
||||
| enem_challenge | acc | 0.363 | 0.007 |
|
||||
| faquad_nli | f1_macro | 0.595 | 0.017 |
|
||||
| faquad_nli | acc | 0.791 | 0.011 |
|
||||
| hatebr_offensive | f1_macro | 0.338 | 0.005 |
|
||||
| hatebr_offensive | acc | 0.502 | 0.009 |
|
||||
| oab_exams | acc | 0.326 | 0.006 |
|
||||
| portuguese_hate_speech | f1_macro | 0.412 | 0.004 |
|
||||
| portuguese_hate_speech | acc | 0.702 | 0.011 |
|
||||
| tweetsentbr | f1_macro | 0.455 | 0.005 |
|
||||
| tweetsentbr | acc | 0.594 | 0.008 |
|
||||
|
||||
## Detailed Results
|
||||
|
||||
### assin2_rte
|
||||
|
||||
| Metric | Value | Stdev |
|
||||
| --------- | ----- | ----- |
|
||||
| f1_macro | 0.391 | 0.006 |
|
||||
| acc | 0.527 | 0.007 |
|
||||
|
||||
### assin2_sts
|
||||
|
||||
| Metric | Value | Stdev |
|
||||
| --------- | ----- | ----- |
|
||||
| pearson | 0.115 | 0.014 |
|
||||
| mse | 1.011 | N/A |
|
||||
|
||||
### bluex
|
||||
|
||||
| Exam ID | Metric | Value | Stdev |
|
||||
| ----------------------- | ------ | -------- | -------- |
|
||||
| all | acc | 0.349 | 0.010 |
|
||||
| USP_2019 | acc | 0.225 | 0.038 |
|
||||
| USP_2024 | acc | 0.293 | 0.041 |
|
||||
| USP_2021 | acc | 0.423 | 0.040 |
|
||||
| UNICAMP_2018 | acc | 0.241 | 0.034 |
|
||||
| UNICAMP_2024 | acc | 0.444 | 0.043 |
|
||||
| USP_2020 | acc | 0.393 | 0.038 |
|
||||
| UNICAMP_2020 | acc | 0.291 | 0.035 |
|
||||
| UNICAMP_2021_1 | acc | 0.326 | 0.040 |
|
||||
| UNICAMP_2022 | acc | 0.487 | 0.046 |
|
||||
| USP_2022 | acc | 0.388 | 0.040 |
|
||||
| UNICAMP_2019 | acc | 0.280 | 0.037 |
|
||||
| UNICAMP_2021_2 | acc | 0.294 | 0.037 |
|
||||
| UNICAMP_2023 | acc | 0.558 | 0.044 |
|
||||
| USP_2023 | acc | 0.364 | 0.042 |
|
||||
| USP_2018 | acc | 0.278 | 0.035 |
|
||||
|
||||
### enem_challenge
|
||||
|
||||
| Exam ID | Metric | Value | Stdev |
|
||||
| --------- | ------ | ----- | ----- |
|
||||
| all | acc | 0.363 | 0.007 |
|
||||
| 2016_2 | acc | 0.390 | 0.025 |
|
||||
| 2015 | acc | 0.319 | 0.025 |
|
||||
| 2011 | acc | 0.410 | 0.026 |
|
||||
| 2013 | acc | 0.398 | 0.027 |
|
||||
| 2017 | acc | 0.319 | 0.025 |
|
||||
| 2022 | acc | 0.376 | 0.024 |
|
||||
| 2009 | acc | 0.226 | 0.023 |
|
||||
| 2010 | acc | 0.444 | 0.026 |
|
||||
| 2012 | acc | 0.345 | 0.025 |
|
||||
| 2014 | acc | 0.339 | 0.026 |
|
||||
| 2016 | acc | 0.397 | 0.026 |
|
||||
| 2023 | acc | 0.385 | 0.024 |
|
||||
|
||||
### faquad_nli
|
||||
|
||||
| Metric | Value | Stdev |
|
||||
| --------- | ----- | ----- |
|
||||
| f1_macro | 0.595 | 0.017 |
|
||||
| acc | 0.791 | 0.011 |
|
||||
|
||||
### hatebr_offensive
|
||||
|
||||
| Metric | Value | Stdev |
|
||||
| --------- | ----- | ----- |
|
||||
| f1_macro | 0.338 | 0.005 |
|
||||
| acc | 0.502 | 0.009 |
|
||||
|
||||
### oab_exams
|
||||
|
||||
| Exam ID | Metric | Value | Stdev |
|
||||
| ------------- | ------ | ----- | ----- |
|
||||
| all | acc | 0.326 | 0.006 |
|
||||
| 2018-25 | acc | 0.400 | 0.032 |
|
||||
| 2016-20a | acc | 0.238 | 0.027 |
|
||||
| 2011-05 | acc | 0.400 | 0.032 |
|
||||
| 2012-08 | acc | 0.325 | 0.030 |
|
||||
| 2012-09 | acc | 0.260 | 0.029 |
|
||||
| 2014-13 | acc | 0.325 | 0.030 |
|
||||
| 2011-03 | acc | 0.313 | 0.027 |
|
||||
| 2016-20 | acc | 0.275 | 0.029 |
|
||||
| 2012-06a | acc | 0.325 | 0.030 |
|
||||
| 2017-22 | acc | 0.338 | 0.031 |
|
||||
| 2015-16 | acc | 0.325 | 0.030 |
|
||||
| 2013-12 | acc | 0.300 | 0.030 |
|
||||
| 2017-24 | acc | 0.250 | 0.028 |
|
||||
| 2012-06 | acc | 0.238 | 0.027 |
|
||||
| 2014-14 | acc | 0.325 | 0.030 |
|
||||
| 2013-11 | acc | 0.325 | 0.030 |
|
||||
| 2013-10 | acc | 0.413 | 0.032 |
|
||||
| 2010-02 | acc | 0.390 | 0.028 |
|
||||
| 2016-21 | acc | 0.375 | 0.031 |
|
||||
| 2015-18 | acc | 0.300 | 0.030 |
|
||||
| 2015-17 | acc | 0.282 | 0.029 |
|
||||
| 2016-19 | acc | 0.333 | 0.031 |
|
||||
| 2012-07 | acc | 0.388 | 0.031 |
|
||||
| 2017-23 | acc | 0.325 | 0.030 |
|
||||
| 2011-04 | acc | 0.350 | 0.031 |
|
||||
| 2010-01 | acc | 0.282 | 0.028 |
|
||||
| 2014-15 | acc | 0.385 | 0.032 |
|
||||
|
||||
### portuguese_hate_speech
|
||||
|
||||
| Metric | Value | Stdev |
|
||||
| --------- | ----- | ----- |
|
||||
| f1_macro | 0.412 | 0.004 |
|
||||
| acc | 0.702 | 0.011 |
|
||||
|
||||
### tweetsentbr
|
||||
|
||||
| Metric | Value | Stdev |
|
||||
| --------- | ----- | ----- |
|
||||
| f1_macro | 0.455 | 0.005 |
|
||||
| acc | 0.594 | 0.008 |
|
||||
|
||||
## Model Meta Information
|
||||
|
||||
* **Truncated Samples:** 3863
|
||||
* **Non-Truncated Samples:** 10287
|
||||
* **Padded Samples:** 0
|
||||
* **Non-Padded Samples:** 14150
|
||||
* **Fewshots Truncated:** 3863
|
||||
* **Has Chat Template:** True
|
||||
* **Chat Type:** system\_user\_assistant
|
||||
* **Number of GPUs:** 1
|
||||
* **Accelerate Number of Processes:** N/A
|
||||
* **Model SHA:** None
|
||||
* **Model Data Type:** torch.bfloat16
|
||||
* **Model Memory Footprint:** 988065664 bytes
|
||||
* **Model Number of Parameters:** 494032768
|
||||
* **Model is Loaded in 4bit:** N/A
|
||||
* **Model is Loaded in 8bit:** N/A
|
||||
* **Model is Quantized:** N/A
|
||||
* **Model Device:** cuda:0
|
||||
* **Batch Size:** 1
|
||||
* **Max Length:** 512
|
||||
* **Max Context Length** 480
|
||||
* **Max Generation Tokens:** 32
|
||||
* **Effective Batch Size:** 1.0
|
||||
|
||||
|
||||
# Open Portuguese LLM Leaderboard Evaluation Results
|
||||
|
||||
Detailed results can be found [here](https://huggingface.co/datasets/eduagarcia-temp/llm_pt_leaderboard_raw_results/tree/main/cnmoro/Qwen2.5-0.5B-Portuguese-v1) and on the [🚀 Open Portuguese LLM Leaderboard](https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard)
|
||||
|
||||
| Metric | Value |
|
||||
|--------------------------|---------|
|
||||
|Average |**50.74**|
|
||||
|ENEM Challenge (No Images)| 37.86|
|
||||
|BLUEX (No Images) | 34.63|
|
||||
|OAB Exams | 33.12|
|
||||
|Assin2 RTE | 86.30|
|
||||
|Assin2 STS | 54.30|
|
||||
|FaQuAD NLI | 65.33|
|
||||
|HateBR Binary | 44.06|
|
||||
|PT Hate Speech Binary | 55.10|
|
||||
|tweetSentBR | 45.96|
|
||||
|
||||
24
added_tokens.json
Normal file
24
added_tokens.json
Normal file
@@ -0,0 +1,24 @@
|
||||
{
|
||||
"</tool_call>": 151658,
|
||||
"<tool_call>": 151657,
|
||||
"<|box_end|>": 151649,
|
||||
"<|box_start|>": 151648,
|
||||
"<|endoftext|>": 151643,
|
||||
"<|file_sep|>": 151664,
|
||||
"<|fim_middle|>": 151660,
|
||||
"<|fim_pad|>": 151662,
|
||||
"<|fim_prefix|>": 151659,
|
||||
"<|fim_suffix|>": 151661,
|
||||
"<|im_end|>": 151645,
|
||||
"<|im_start|>": 151644,
|
||||
"<|image_pad|>": 151655,
|
||||
"<|object_ref_end|>": 151647,
|
||||
"<|object_ref_start|>": 151646,
|
||||
"<|quad_end|>": 151651,
|
||||
"<|quad_start|>": 151650,
|
||||
"<|repo_name|>": 151663,
|
||||
"<|video_pad|>": 151656,
|
||||
"<|vision_end|>": 151653,
|
||||
"<|vision_pad|>": 151654,
|
||||
"<|vision_start|>": 151652
|
||||
}
|
||||
31
config.json
Normal file
31
config.json
Normal file
@@ -0,0 +1,31 @@
|
||||
{
|
||||
"_name_or_path": "cnmoro/Qwen2.5-0.5B-Portuguese-v1",
|
||||
"architectures": [
|
||||
"Qwen2ForCausalLM"
|
||||
],
|
||||
"attention_dropout": 0.0,
|
||||
"eos_token_id": 151645,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 896,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 4864,
|
||||
"max_position_embeddings": 32768,
|
||||
"max_window_layers": 21,
|
||||
"model_type": "qwen2",
|
||||
"num_attention_heads": 14,
|
||||
"num_hidden_layers": 24,
|
||||
"num_key_value_heads": 2,
|
||||
"pad_token_id": 151654,
|
||||
"rms_norm_eps": 1e-06,
|
||||
"rope_scaling": null,
|
||||
"rope_theta": 1000000.0,
|
||||
"sliding_window": null,
|
||||
"tie_word_embeddings": true,
|
||||
"torch_dtype": "bfloat16",
|
||||
"transformers_version": "4.47.1",
|
||||
"unsloth_fixed": true,
|
||||
"unsloth_version": "2024.12.12",
|
||||
"use_cache": true,
|
||||
"use_sliding_window": false,
|
||||
"vocab_size": 151936
|
||||
}
|
||||
15
generation_config.json
Normal file
15
generation_config.json
Normal file
@@ -0,0 +1,15 @@
|
||||
{
|
||||
"bos_token_id": 151643,
|
||||
"do_sample": true,
|
||||
"eos_token_id": [
|
||||
151645,
|
||||
151643
|
||||
],
|
||||
"max_length": 32768,
|
||||
"pad_token_id": 151654,
|
||||
"repetition_penalty": 1.1,
|
||||
"temperature": 0.7,
|
||||
"top_k": 20,
|
||||
"top_p": 0.8,
|
||||
"transformers_version": "4.47.1"
|
||||
}
|
||||
151388
merges.txt
Normal file
151388
merges.txt
Normal file
File diff suppressed because it is too large
Load Diff
3
model.safetensors
Normal file
3
model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:8c34b7e110bd2f8f2e9f2ec6ff35e5953cce9ad54fee7dd9c3af2f64febb2fd3
|
||||
size 988097824
|
||||
31
special_tokens_map.json
Normal file
31
special_tokens_map.json
Normal file
@@ -0,0 +1,31 @@
|
||||
{
|
||||
"additional_special_tokens": [
|
||||
"<|im_start|>",
|
||||
"<|im_end|>",
|
||||
"<|object_ref_start|>",
|
||||
"<|object_ref_end|>",
|
||||
"<|box_start|>",
|
||||
"<|box_end|>",
|
||||
"<|quad_start|>",
|
||||
"<|quad_end|>",
|
||||
"<|vision_start|>",
|
||||
"<|vision_end|>",
|
||||
"<|vision_pad|>",
|
||||
"<|image_pad|>",
|
||||
"<|video_pad|>"
|
||||
],
|
||||
"eos_token": {
|
||||
"content": "<|im_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": {
|
||||
"content": "<|vision_pad|>",
|
||||
"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 sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
|
||||
size 11421896
|
||||
209
tokenizer_config.json
Normal file
209
tokenizer_config.json
Normal file
@@ -0,0 +1,209 @@
|
||||
{
|
||||
"add_bos_token": false,
|
||||
"add_prefix_space": false,
|
||||
"added_tokens_decoder": {
|
||||
"151643": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151644": {
|
||||
"content": "<|im_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151645": {
|
||||
"content": "<|im_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151646": {
|
||||
"content": "<|object_ref_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151647": {
|
||||
"content": "<|object_ref_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151648": {
|
||||
"content": "<|box_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151649": {
|
||||
"content": "<|box_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151650": {
|
||||
"content": "<|quad_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151651": {
|
||||
"content": "<|quad_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151652": {
|
||||
"content": "<|vision_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151653": {
|
||||
"content": "<|vision_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151654": {
|
||||
"content": "<|vision_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151655": {
|
||||
"content": "<|image_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151656": {
|
||||
"content": "<|video_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151657": {
|
||||
"content": "<tool_call>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151658": {
|
||||
"content": "</tool_call>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151659": {
|
||||
"content": "<|fim_prefix|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151660": {
|
||||
"content": "<|fim_middle|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151661": {
|
||||
"content": "<|fim_suffix|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151662": {
|
||||
"content": "<|fim_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151663": {
|
||||
"content": "<|repo_name|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151664": {
|
||||
"content": "<|file_sep|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
}
|
||||
},
|
||||
"additional_special_tokens": [
|
||||
"<|im_start|>",
|
||||
"<|im_end|>",
|
||||
"<|object_ref_start|>",
|
||||
"<|object_ref_end|>",
|
||||
"<|box_start|>",
|
||||
"<|box_end|>",
|
||||
"<|quad_start|>",
|
||||
"<|quad_end|>",
|
||||
"<|vision_start|>",
|
||||
"<|vision_end|>",
|
||||
"<|vision_pad|>",
|
||||
"<|image_pad|>",
|
||||
"<|video_pad|>"
|
||||
],
|
||||
"bos_token": null,
|
||||
"chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {{- 'Você é um assistente que sempre responde em português brasileiro, fornecendo respostas de qualidade para o usuário.' }}\n {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {{- '<|im_start|>system\\nVocê é um assistente que sempre responde em português brasileiro, fornecendo respostas de qualidade para o usuário.<|im_end|>\\n' }}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "<|im_end|>",
|
||||
"errors": "replace",
|
||||
"extra_special_tokens": {},
|
||||
"model_max_length": 32768,
|
||||
"pad_token": "<|vision_pad|>",
|
||||
"padding_side": "right",
|
||||
"split_special_tokens": false,
|
||||
"tokenizer_class": "Qwen2Tokenizer",
|
||||
"unk_token": null
|
||||
}
|
||||
1
vocab.json
Normal file
1
vocab.json
Normal file
File diff suppressed because one or more lines are too long
Reference in New Issue
Block a user