初始化项目，由ModelHub XC社区提供模型
Model: codefuse-ai/F2LLM-v2-80M Source: Original Platform
This commit is contained in:
ModelHub XC
35
.gitattributes
vendored
Normal file
35
.gitattributes
vendored
Normal file
@@ -0,0 +1,35 @@
|
|||||||
|
*.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
|
||||||
10
1_Pooling/config.json
Normal file
10
1_Pooling/config.json
Normal file
@@ -0,0 +1,10 @@
|
|||||||
|
{
|
||||||
|
"word_embedding_dimension": 1024,
|
||||||
|
"pooling_mode_cls_token": false,
|
||||||
|
"pooling_mode_mean_tokens": false,
|
||||||
|
"pooling_mode_max_tokens": false,
|
||||||
|
"pooling_mode_mean_sqrt_len_tokens": false,
|
||||||
|
"pooling_mode_weightedmean_tokens": false,
|
||||||
|
"pooling_mode_lasttoken": true,
|
||||||
|
"include_prompt": true
|
||||||
|
}
|
||||||
202
README.md
Normal file
202
README.md
Normal file
@@ -0,0 +1,202 @@
|
|||||||
|
---
|
||||||
|
license: apache-2.0
|
||||||
|
language:
|
||||||
|
- en
|
||||||
|
- zh
|
||||||
|
- ru
|
||||||
|
- es
|
||||||
|
- fr
|
||||||
|
- de
|
||||||
|
- ar
|
||||||
|
- nl
|
||||||
|
- vi
|
||||||
|
- hi
|
||||||
|
- ko
|
||||||
|
- ja
|
||||||
|
- it
|
||||||
|
- id
|
||||||
|
- pt
|
||||||
|
- pl
|
||||||
|
- tr
|
||||||
|
- da
|
||||||
|
- th
|
||||||
|
- sv
|
||||||
|
- fa
|
||||||
|
- uk
|
||||||
|
- cs
|
||||||
|
- 'no'
|
||||||
|
- el
|
||||||
|
- ca
|
||||||
|
- ro
|
||||||
|
- fi
|
||||||
|
- bg
|
||||||
|
- tl
|
||||||
|
- gl
|
||||||
|
- my
|
||||||
|
- hy
|
||||||
|
- km
|
||||||
|
- ne
|
||||||
|
- hu
|
||||||
|
- eu
|
||||||
|
- he
|
||||||
|
- lo
|
||||||
|
- sw
|
||||||
|
- az
|
||||||
|
- lv
|
||||||
|
- si
|
||||||
|
- sk
|
||||||
|
- tg
|
||||||
|
- et
|
||||||
|
- lt
|
||||||
|
- ms
|
||||||
|
- hr
|
||||||
|
- is
|
||||||
|
- sl
|
||||||
|
- sr
|
||||||
|
- ur
|
||||||
|
- bn
|
||||||
|
- af
|
||||||
|
- ta
|
||||||
|
- ka
|
||||||
|
- te
|
||||||
|
- ml
|
||||||
|
- mn
|
||||||
|
- nn
|
||||||
|
- kk
|
||||||
|
- cy
|
||||||
|
- mr
|
||||||
|
- sq
|
||||||
|
- nb
|
||||||
|
- mk
|
||||||
|
- jv
|
||||||
|
- kn
|
||||||
|
- eo
|
||||||
|
- la
|
||||||
|
- gu
|
||||||
|
- uz
|
||||||
|
- am
|
||||||
|
- oc
|
||||||
|
- be
|
||||||
|
- mg
|
||||||
|
- vo
|
||||||
|
- pa
|
||||||
|
- lb
|
||||||
|
- ht
|
||||||
|
- br
|
||||||
|
- ga
|
||||||
|
- xh
|
||||||
|
- tt
|
||||||
|
- bs
|
||||||
|
- yo
|
||||||
|
base_model:
|
||||||
|
- codefuse-ai/F2LLM-v2-0.6B-Preview-Pruned-80M
|
||||||
|
pipeline_tag: feature-extraction
|
||||||
|
library_name: transformers
|
||||||
|
tags:
|
||||||
|
- sentence-transformers
|
||||||
|
datasets:
|
||||||
|
- codefuse-ai/F2LLM-v2
|
||||||
|
---
|
||||||
|
|
||||||
|
# F2LLM-v2-80M
|
||||||
|
|
||||||
|
F2LLM-v2 is a family of general-purpose, multilingual embedding models in 8 distinct sizes ranging from 80M to 14B. Trained on a curated composite of 60 million publicly available high-quality data, F2LLM-v2 supports more than 200 languages, with a particular emphasis on previously underserved mid- and low-resource languages.
|
||||||
|
|
||||||
|
F2LLM-v2 is fully open. We release base models in 5 sizes, instruct models in 8 sizes, the training data, the training code, and intermediate checkpoints. The three smallest instruct models are pruned and trained from the 0.6B base model.
|
||||||
|
|
||||||
|
| Model | Base | Instruct |
|
||||||
|
| ----- | ----------------------------------------------------------------------------------- | ------------------------------------------------------------------- |
|
||||||
|
| 80M | | [🤗F2LLM-v2-80M](https://huggingface.co/codefuse-ai/F2LLM-v2-80M) |
|
||||||
|
| 160M | | [🤗F2LLM-v2-160M](https://huggingface.co/codefuse-ai/F2LLM-v2-160M) |
|
||||||
|
| 330M | | [🤗F2LLM-v2-330M](https://huggingface.co/codefuse-ai/F2LLM-v2-330M) |
|
||||||
|
| 0.6B | [🤗F2LLM-v2-0.6B-Preview](https://huggingface.co/codefuse-ai/F2LLM-v2-0.6B-Preview) | [🤗F2LLM-v2-0.6B](https://huggingface.co/codefuse-ai/F2LLM-v2-0.6B) |
|
||||||
|
| 1.7B | [🤗F2LLM-v2-1.7B-Preview](https://huggingface.co/codefuse-ai/F2LLM-v2-1.7B-Preview) | [🤗F2LLM-v2-1.7B](https://huggingface.co/codefuse-ai/F2LLM-v2-1.7B) |
|
||||||
|
| 4B | [🤗F2LLM-v2-4B-Preview](https://huggingface.co/codefuse-ai/F2LLM-v2-4B-Preview) | [🤗F2LLM-v2-4B](https://huggingface.co/codefuse-ai/F2LLM-v2-4B) |
|
||||||
|
| 8B | [🤗F2LLM-v2-8B-Preview](https://huggingface.co/codefuse-ai/F2LLM-v2-8B-Preview) | [🤗F2LLM-v2-8B](https://huggingface.co/codefuse-ai/F2LLM-v2-8B) |
|
||||||
|
| 14B | [🤗F2LLM-v2-14B-Preview](https://huggingface.co/codefuse-ai/F2LLM-v2-14B-Preview) | [🤗F2LLM-v2-14B](https://huggingface.co/codefuse-ai/F2LLM-v2-14B) |
|
||||||
|
|
||||||
|
## Usage
|
||||||
|
|
||||||
|
### With Sentence Transformers
|
||||||
|
|
||||||
|
To encode text with the [Sentence Transformers](https://www.sbert.net/) library:
|
||||||
|
|
||||||
|
```python
|
||||||
|
from sentence_transformers import SentenceTransformer
|
||||||
|
model = SentenceTransformer("codefuse-ai/F2LLM-v2-80M", device="cuda:0", model_kwargs={"torch_dtype": "bfloat16"})
|
||||||
|
# Some sample query and documents
|
||||||
|
query = "What is F2LLM used for?"
|
||||||
|
documents = [
|
||||||
|
'We present F2LLM, a family of fully open embedding LLMs that achieve a strong balance between model size, training data, and embedding performance.',
|
||||||
|
'F2LLM is a model for computing text embeddings that can be used for various NLP tasks such as information retrieval, semantic search, and text classification.',
|
||||||
|
'F2LLM 是 CodeFuse 开源的系列嵌入模型。',
|
||||||
|
'F2LLM — это модель вычисления встраивания текста, которую можно использовать для различных задач НЛП, таких как поиск информации, семантический поиск и классификация текста.'
|
||||||
|
]
|
||||||
|
# Encode the query and documents separately. The encode_query method uses the query prompt
|
||||||
|
query_embedding = model.encode_query(query)
|
||||||
|
document_embeddings = model.encode_document(documents)
|
||||||
|
print(query_embedding.shape, document_embeddings.shape)
|
||||||
|
# (320,) (4, 320)
|
||||||
|
# Compute cosine similarity between the query and documents
|
||||||
|
similarity = model.similarity(query_embedding, document_embeddings)
|
||||||
|
print(similarity)
|
||||||
|
# tensor([[0.6968, 0.7818, 0.7165, 0.8374]])
|
||||||
|
```
|
||||||
|
|
||||||
|
### With Transformers
|
||||||
|
|
||||||
|
Or directly with the [Transformers](https://huggingface.co/docs/transformers/index) library:
|
||||||
|
|
||||||
|
```python
|
||||||
|
from transformers import AutoModel, AutoTokenizer
|
||||||
|
import torch
|
||||||
|
import torch.nn.functional as F
|
||||||
|
model_path = "codefuse-ai/F2LLM-v2-80M"
|
||||||
|
tokenizer = AutoTokenizer.from_pretrained(model_path)
|
||||||
|
model = AutoModel.from_pretrained(model_path, torch_dtype=torch.bfloat16, device_map={'': 0})
|
||||||
|
query = "What is F2LLM used for?"
|
||||||
|
query_prompt = "Instruct: Given a question, retrieve passages that can help answer the question.\nQuery: "
|
||||||
|
documents = [
|
||||||
|
'We present F2LLM, a family of fully open embedding LLMs that achieve a strong balance between model size, training data, and embedding performance.',
|
||||||
|
'F2LLM is a model for computing text embeddings that can be used for various NLP tasks such as information retrieval, semantic search, and text classification.',
|
||||||
|
'F2LLM 是 CodeFuse 开源的系列嵌入模型。',
|
||||||
|
'F2LLM — это модель вычисления встраивания текста, которую можно использовать для различных задач НЛП, таких как поиск информации, семантический поиск и классификация текста.'
|
||||||
|
]
|
||||||
|
def encode(sentences):
|
||||||
|
batch_size = len(sentences)
|
||||||
|
# the tokenizer will automatically add eos token
|
||||||
|
tokenized_inputs = tokenizer(sentences, padding=True, return_tensors='pt').to(model.device)
|
||||||
|
last_hidden_state = model(**tokenized_inputs).last_hidden_state
|
||||||
|
eos_positions = tokenized_inputs.attention_mask.sum(dim=1) - 1
|
||||||
|
embeddings = last_hidden_state[torch.arange(batch_size, device=model.device), eos_positions]
|
||||||
|
embeddings = F.normalize(embeddings, p=2, dim=1)
|
||||||
|
return embeddings
|
||||||
|
# Encode the query and documents
|
||||||
|
query_embedding = encode([query_prompt + query])
|
||||||
|
document_embeddings = encode(documents)
|
||||||
|
print(query_embedding.shape, document_embeddings.shape)
|
||||||
|
# torch.Size([1, 320]) torch.Size([4, 320])
|
||||||
|
# Compute cosine similarity between the query and documents
|
||||||
|
similarity = query_embedding @ document_embeddings.T
|
||||||
|
print(similarity)
|
||||||
|
# tensor([[0.6914, 0.7812, 0.7148, 0.8359]], device='cuda:0',
|
||||||
|
# dtype=torch.bfloat16, grad_fn=<MmBackward0>)
|
||||||
|
```
|
||||||
|
|
||||||
|
## Intermediate Checkpoints
|
||||||
|
|
||||||
|
To facilitate future research, we release intermediate checkpoints in the `intermediate_checkpoints` branch.
|
||||||
|
|
||||||
|
## Citation
|
||||||
|
|
||||||
|
```
|
||||||
|
@misc{f2llm-v2,
|
||||||
|
title={F2LLM-v2: Inclusive, Performant, and Efficient Embeddings for a Multilingual World},
|
||||||
|
author={Ziyin Zhang and Zihan Liao and Hang Yu and Peng Di and Rui Wang},
|
||||||
|
year={2026},
|
||||||
|
eprint={2603.19223},
|
||||||
|
archivePrefix={arXiv},
|
||||||
|
primaryClass={cs.CL},
|
||||||
|
url={https://arxiv.org/abs/2603.19223},
|
||||||
|
}
|
||||||
|
```
|
||||||
28
added_tokens.json
Normal file
28
added_tokens.json
Normal file
@@ -0,0 +1,28 @@
|
|||||||
|
{
|
||||||
|
"</think>": 151668,
|
||||||
|
"</tool_call>": 151658,
|
||||||
|
"</tool_response>": 151666,
|
||||||
|
"<think>": 151667,
|
||||||
|
"<tool_call>": 151657,
|
||||||
|
"<tool_response>": 151665,
|
||||||
|
"<|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
|
||||||
|
}
|
||||||
41
config.json
Normal file
41
config.json
Normal file
@@ -0,0 +1,41 @@
|
|||||||
|
{
|
||||||
|
"architectures": [
|
||||||
|
"Qwen3Model"
|
||||||
|
],
|
||||||
|
"attention_bias": false,
|
||||||
|
"attention_dropout": 0.0,
|
||||||
|
"bos_token_id": 151643,
|
||||||
|
"dtype": "bfloat16",
|
||||||
|
"eos_token_id": 151645,
|
||||||
|
"head_dim": 128,
|
||||||
|
"hidden_act": "silu",
|
||||||
|
"hidden_size": 320,
|
||||||
|
"initializer_range": 0.02,
|
||||||
|
"intermediate_size": 2048,
|
||||||
|
"layer_types": [
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention"
|
||||||
|
],
|
||||||
|
"max_position_embeddings": 40960,
|
||||||
|
"max_window_layers": 8,
|
||||||
|
"model_type": "qwen3",
|
||||||
|
"num_attention_heads": 16,
|
||||||
|
"num_hidden_layers": 8,
|
||||||
|
"num_key_value_heads": 8,
|
||||||
|
"rms_norm_eps": 1e-06,
|
||||||
|
"rope_scaling": null,
|
||||||
|
"rope_theta": 1000000,
|
||||||
|
"sliding_window": null,
|
||||||
|
"tie_word_embeddings": true,
|
||||||
|
"torch_dtype": "bfloat16",
|
||||||
|
"transformers_version": "4.51.0",
|
||||||
|
"use_cache": false,
|
||||||
|
"use_sliding_window": false,
|
||||||
|
"vocab_size": 151936
|
||||||
|
}
|
||||||
8
config_sentence_transformers.json
Normal file
8
config_sentence_transformers.json
Normal file
@@ -0,0 +1,8 @@
|
|||||||
|
{
|
||||||
|
"prompts": {
|
||||||
|
"query": "Instruct: Given a question, retrieve passages that can help answer the question.\nQuery: ",
|
||||||
|
"document": ""
|
||||||
|
},
|
||||||
|
"default_prompt_name": null,
|
||||||
|
"similarity_fn_name": "cosine"
|
||||||
|
}
|
||||||
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 sha256:2177fbd79bd6259904a54514e0e313efd28704acd98bfe276a06b2c638f2e4c1
|
||||||
|
size 160178064
|
||||||
20
modules.json
Normal file
20
modules.json
Normal file
@@ -0,0 +1,20 @@
|
|||||||
|
[
|
||||||
|
{
|
||||||
|
"idx": 0,
|
||||||
|
"name": "0",
|
||||||
|
"path": "",
|
||||||
|
"type": "sentence_transformers.models.Transformer"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"idx": 1,
|
||||||
|
"name": "1",
|
||||||
|
"path": "1_Pooling",
|
||||||
|
"type": "sentence_transformers.models.Pooling"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"idx": 2,
|
||||||
|
"name": "2",
|
||||||
|
"path": "2_Normalize",
|
||||||
|
"type": "sentence_transformers.models.Normalize"
|
||||||
|
}
|
||||||
|
]
|
||||||
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": "<|endoftext|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false
|
||||||
|
}
|
||||||
|
}
|
||||||
303688
tokenizer.json
Normal file
303688
tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
240
tokenizer_config.json
Normal file
240
tokenizer_config.json
Normal file
@@ -0,0 +1,240 @@
|
|||||||
|
{
|
||||||
|
"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
|
||||||
|
},
|
||||||
|
"151665": {
|
||||||
|
"content": "<tool_response>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151666": {
|
||||||
|
"content": "</tool_response>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151667": {
|
||||||
|
"content": "<think>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151668": {
|
||||||
|
"content": "</think>",
|
||||||
|
"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 {%- if messages[0].role == 'system' %}\n {{- messages[0].content + '\\n\\n' }}\n {%- endif %}\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 {%- if messages[0].role == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0].content + '<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n {%- set index = (messages|length - 1) - loop.index0 %}\n {%- if ns.multi_step_tool and message.role == \"user\" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}\n {%- set ns.multi_step_tool = false %}\n {%- set ns.last_query_index = index %}\n {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n {%- if message.content is string %}\n {%- set content = message.content %}\n {%- else %}\n {%- set content = '' %}\n {%- endif %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n {{- '<|im_start|>' + message.role + '\\n' + content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {%- set reasoning_content = '' %}\n {%- if message.reasoning_content is string %}\n {%- set reasoning_content = message.reasoning_content %}\n {%- else %}\n {%- if '</think>' in content %}\n {%- set reasoning_content = content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n {%- set content = content.split('</think>')[-1].lstrip('\\n') %}\n {%- endif %}\n {%- endif %}\n {%- if loop.index0 > ns.last_query_index %}\n {%- if loop.last or (not loop.last and reasoning_content) %}\n {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content.strip('\\n') + '\\n</think>\\n\\n' + content.lstrip('\\n') }}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- if message.tool_calls %}\n {%- for tool_call in message.tool_calls %}\n {%- if (loop.first and content) or (not loop.first) %}\n {{- '\\n' }}\n {%- endif %}\n {%- if tool_call.function %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {%- if tool_call.arguments is string %}\n {{- tool_call.arguments }}\n {%- else %}\n {{- tool_call.arguments | tojson }}\n {%- endif %}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- 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 {%- if enable_thinking is defined and enable_thinking is false %}\n {{- '<think>\\n\\n</think>\\n\\n' }}\n {%- endif %}\n{%- endif %}",
|
||||||
|
"clean_up_tokenization_spaces": false,
|
||||||
|
"eos_token": "<|im_end|>",
|
||||||
|
"errors": "replace",
|
||||||
|
"extra_special_tokens": {},
|
||||||
|
"model_max_length": 131072,
|
||||||
|
"pad_token": "<|endoftext|>",
|
||||||
|
"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