初始化项目，由ModelHub XC社区提供模型
Model: wanlige/li-14b-v0.4 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
|
||||||
303
README.md
Normal file
303
README.md
Normal file
@@ -0,0 +1,303 @@
|
|||||||
|
---
|
||||||
|
library_name: transformers
|
||||||
|
tags:
|
||||||
|
- mergekit
|
||||||
|
- merge
|
||||||
|
base_model:
|
||||||
|
- Qwen/Qwen2.5-14B-Instruct
|
||||||
|
- Qwen/Qwen2.5-Coder-14B
|
||||||
|
- deepseek-ai/DeepSeek-R1-Distill-Qwen-14B
|
||||||
|
- huihui-ai/DeepSeek-R1-Distill-Qwen-14B-abliterated-v2
|
||||||
|
- tanliboy/lambda-qwen2.5-14b-dpo-test
|
||||||
|
- SicariusSicariiStuff/Impish_QWEN_14B-1M
|
||||||
|
- Qwen/Qwen2.5-14B
|
||||||
|
model-index:
|
||||||
|
- name: li-14b-v0.4
|
||||||
|
results:
|
||||||
|
- task:
|
||||||
|
type: text-generation
|
||||||
|
name: Text Generation
|
||||||
|
dataset:
|
||||||
|
name: IFEval (0-Shot)
|
||||||
|
type: HuggingFaceH4/ifeval
|
||||||
|
args:
|
||||||
|
num_few_shot: 0
|
||||||
|
metrics:
|
||||||
|
- type: inst_level_strict_acc and prompt_level_strict_acc
|
||||||
|
value: 81.33
|
||||||
|
name: strict accuracy
|
||||||
|
source:
|
||||||
|
url: >-
|
||||||
|
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=wanlige/li-14b-v0.4
|
||||||
|
name: Open LLM Leaderboard
|
||||||
|
- task:
|
||||||
|
type: text-generation
|
||||||
|
name: Text Generation
|
||||||
|
dataset:
|
||||||
|
name: BBH (3-Shot)
|
||||||
|
type: BBH
|
||||||
|
args:
|
||||||
|
num_few_shot: 3
|
||||||
|
metrics:
|
||||||
|
- type: acc_norm
|
||||||
|
value: 50.38
|
||||||
|
name: normalized accuracy
|
||||||
|
source:
|
||||||
|
url: >-
|
||||||
|
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=wanlige/li-14b-v0.4
|
||||||
|
name: Open LLM Leaderboard
|
||||||
|
- task:
|
||||||
|
type: text-generation
|
||||||
|
name: Text Generation
|
||||||
|
dataset:
|
||||||
|
name: MATH Lvl 5 (4-Shot)
|
||||||
|
type: hendrycks/competition_math
|
||||||
|
args:
|
||||||
|
num_few_shot: 4
|
||||||
|
metrics:
|
||||||
|
- type: exact_match
|
||||||
|
value: 55.74
|
||||||
|
name: exact match
|
||||||
|
source:
|
||||||
|
url: >-
|
||||||
|
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=wanlige/li-14b-v0.4
|
||||||
|
name: Open LLM Leaderboard
|
||||||
|
- task:
|
||||||
|
type: text-generation
|
||||||
|
name: Text Generation
|
||||||
|
dataset:
|
||||||
|
name: GPQA (0-shot)
|
||||||
|
type: Idavidrein/gpqa
|
||||||
|
args:
|
||||||
|
num_few_shot: 0
|
||||||
|
metrics:
|
||||||
|
- type: acc_norm
|
||||||
|
value: 11.86
|
||||||
|
name: acc_norm
|
||||||
|
source:
|
||||||
|
url: >-
|
||||||
|
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=wanlige/li-14b-v0.4
|
||||||
|
name: Open LLM Leaderboard
|
||||||
|
- task:
|
||||||
|
type: text-generation
|
||||||
|
name: Text Generation
|
||||||
|
dataset:
|
||||||
|
name: MuSR (0-shot)
|
||||||
|
type: TAUR-Lab/MuSR
|
||||||
|
args:
|
||||||
|
num_few_shot: 0
|
||||||
|
metrics:
|
||||||
|
- type: acc_norm
|
||||||
|
value: 16.35
|
||||||
|
name: acc_norm
|
||||||
|
source:
|
||||||
|
url: >-
|
||||||
|
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=wanlige/li-14b-v0.4
|
||||||
|
name: Open LLM Leaderboard
|
||||||
|
- task:
|
||||||
|
type: text-generation
|
||||||
|
name: Text Generation
|
||||||
|
dataset:
|
||||||
|
name: MMLU-PRO (5-shot)
|
||||||
|
type: TIGER-Lab/MMLU-Pro
|
||||||
|
config: main
|
||||||
|
split: test
|
||||||
|
args:
|
||||||
|
num_few_shot: 5
|
||||||
|
metrics:
|
||||||
|
- type: acc
|
||||||
|
value: 46.3
|
||||||
|
name: accuracy
|
||||||
|
source:
|
||||||
|
url: >-
|
||||||
|
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=wanlige/li-14b-v0.4
|
||||||
|
name: Open LLM Leaderboard
|
||||||
|
license: apache-2.0
|
||||||
|
language:
|
||||||
|
- zh
|
||||||
|
- en
|
||||||
|
- fr
|
||||||
|
- sa
|
||||||
|
- de
|
||||||
|
pipeline_tag: text-generation
|
||||||
|
---
|
||||||
|
|
||||||
|
> [!TIP] This model is currently ranked #1 among the models up to 15B parameters and #50 among all models on the [Open LLM Leaderboard](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard).
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
<a href="https://www.36588.com.cn/">
|
||||||
|
|
||||||
|
<img src="./sjky.png" alt="关于我们" />
|
||||||
|
|
||||||
|
</a>
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
世纪开元智印互联科技集团股份有限公司创立于2001年3月9日，总部位于山东省济南市。历经20余年发展，世纪开元以技术创新为核心，实现互联网与传统印刷行业的深度融合，探索出了区别于传统印刷行业的新模式、新业态。
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
世纪开元主要从事定制化影像、商务印刷及包装印刷类产品的研发、设计、生产及销售，通过将互联网、数字化、自动化和智能化等新模式和新技术与包装印刷行业相结合的方式，使小批量个性化定制产品订单得以相对标准化、规模化生产，旨在满足个人消费者及各类企业用户的小批量定制化需求，为用户提供一站式场景化定制印刷服务，实现全流程智能制造，已成长为业内领先的“工业互联网”印刷企业。
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
在未来发展中，世纪开元将一如既往地加大技术研发投入，深度融合互联网、大数据、人工智能等新一代信息技术，注重专项技术人才的培养，积极引进数字化、智能化手段优化创新业务流程和实现用户体验的提升，并通过多维度的企业发展，带动行业协同发展，促进印刷行业新旧动能转换，开拓印刷行业发展新方向。
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
了解更多，请访问我们的官网：[世纪开元](https://www.36588.com.cn/)
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
Established on March 9, 2001, and headquartered in Jinan, Shandong Province, **Century Innovation** has grown over the past two decades by focusing on technological innovation. The company has achieved deep integration of the Internet with the traditional printing industry, pioneering new models and business formats distinct from conventional printing practices.
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
**Century Innovation** specializes in the research, design, production, and sales of customized imaging, commercial printing, and packaging products. By combining the Internet, digitalization, automation, and intelligent technologies with the printing industry, the company enables relatively standardized and scalable production for small-batch personalized custom orders. This approach aims to meet the needs of individual consumers and various enterprise users for small-batch customization, providing users with one-stop, scenario-based custom printing services and achieving full-process intelligent manufacturing. As a result, **Century Innovation** has become a leading "Industrial Internet" printing enterprise.
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
In the future, **Century Innovation** will continue to increase investment in technology R&D, deeply integrate the Internet, big data, artificial intelligence, and other next-generation information technologies, and focus on cultivating specialized technical talent. The company will actively adopt digital and intelligent means to optimize innovative business processes and enhance user experience. Through multi-dimensional development, it aims to drive industry collaboration, promote the transformation of old and new drivers in the printing industry, and explore new directions for its growth.
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
To learn more, visit our official website: [Century Innovation](https://www.36588.com.cn/)
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
# merge
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
## Merge Details
|
||||||
|
|
||||||
|
### Merge Method
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
This model was merged using the [Model Stock](https://arxiv.org/abs/2403.19522) merge method using [Qwen/Qwen2.5-14B-Instruct](https://huggingface.co/Qwen/Qwen2.5-14B-Instruct) as a base.
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
### Models Merged
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
The following models were included in the merge:
|
||||||
|
|
||||||
|
* [Qwen/Qwen2.5-Coder-14B](https://huggingface.co/Qwen/Qwen2.5-Coder-14B)
|
||||||
|
|
||||||
|
* [deepseek-ai/DeepSeek-R1-Distill-Qwen-14B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-14B)
|
||||||
|
|
||||||
|
* [huihui-ai/DeepSeek-R1-Distill-Qwen-14B-abliterated-v2](https://huggingface.co/huihui-ai/DeepSeek-R1-Distill-Qwen-14B-abliterated-v2)
|
||||||
|
|
||||||
|
* [tanliboy/lambda-qwen2.5-14b-dpo-test](https://huggingface.co/tanliboy/lambda-qwen2.5-14b-dpo-test)
|
||||||
|
|
||||||
|
* [SicariusSicariiStuff/Impish_QWEN_14B-1M](https://huggingface.co/SicariusSicariiStuff/Impish_QWEN_14B-1M)
|
||||||
|
|
||||||
|
* [Qwen/Qwen2.5-14B](https://huggingface.co/Qwen/Qwen2.5-14B)
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
### Configuration
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
The following YAML configuration was used to produce this model:
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
```yaml
|
||||||
|
|
||||||
|
models:
|
||||||
|
|
||||||
|
- model: deepseek-ai/DeepSeek-R1-Distill-Qwen-14B #logic
|
||||||
|
|
||||||
|
- model: huihui-ai/DeepSeek-R1-Distill-Qwen-14B-abliterated-v2 #uncensored
|
||||||
|
|
||||||
|
- model: Qwen/Qwen2.5-14B #text generation
|
||||||
|
|
||||||
|
- model: Qwen/Qwen2.5-14B-Instruct #chat assistant
|
||||||
|
|
||||||
|
- model: Qwen/Qwen2.5-Coder-14B #coding
|
||||||
|
|
||||||
|
- model: SicariusSicariiStuff/Impish_QWEN_14B-1M #math
|
||||||
|
|
||||||
|
- model: tanliboy/lambda-qwen2.5-14b-dpo-test #dpo
|
||||||
|
|
||||||
|
merge_method: model_stock
|
||||||
|
|
||||||
|
base_model: Qwen/Qwen2.5-14B-Instruct
|
||||||
|
|
||||||
|
normalize: true
|
||||||
|
|
||||||
|
int8_mask: true
|
||||||
|
|
||||||
|
dtype: bfloat16
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
```
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard)
|
||||||
|
|
||||||
|
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/wanlige__li-14b-v0.4-details)
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
| Metric |Value|
|
||||||
|
|
||||||
|
|-------------------|----:|
|
||||||
|
|
||||||
|
|Avg. |43.66|
|
||||||
|
|
||||||
|
|IFEval (0-Shot) |81.33|
|
||||||
|
|
||||||
|
|BBH (3-Shot) |50.38|
|
||||||
|
|
||||||
|
|MATH Lvl 5 (4-Shot)|55.74|
|
||||||
|
|
||||||
|
|GPQA (0-shot) |11.86|
|
||||||
|
|
||||||
|
|MuSR (0-shot) |16.35|
|
||||||
|
|
||||||
|
|MMLU-PRO (5-shot) |46.30|
|
||||||
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
|
||||||
|
}
|
||||||
29
config.json
Normal file
29
config.json
Normal file
@@ -0,0 +1,29 @@
|
|||||||
|
{
|
||||||
|
"_name_or_path": "Qwen/Qwen2.5-14B-Instruct",
|
||||||
|
"architectures": [
|
||||||
|
"Qwen2ForCausalLM"
|
||||||
|
],
|
||||||
|
"attention_dropout": 0.0,
|
||||||
|
"bos_token_id": 151643,
|
||||||
|
"eos_token_id": 151645,
|
||||||
|
"hidden_act": "silu",
|
||||||
|
"hidden_size": 5120,
|
||||||
|
"initializer_range": 0.02,
|
||||||
|
"intermediate_size": 13824,
|
||||||
|
"max_position_embeddings": 32768,
|
||||||
|
"max_window_layers": 70,
|
||||||
|
"model_type": "qwen2",
|
||||||
|
"num_attention_heads": 40,
|
||||||
|
"num_hidden_layers": 48,
|
||||||
|
"num_key_value_heads": 8,
|
||||||
|
"rms_norm_eps": 1e-06,
|
||||||
|
"rope_scaling": null,
|
||||||
|
"rope_theta": 1000000.0,
|
||||||
|
"sliding_window": null,
|
||||||
|
"tie_word_embeddings": false,
|
||||||
|
"torch_dtype": "bfloat16",
|
||||||
|
"transformers_version": "4.48.2",
|
||||||
|
"use_cache": true,
|
||||||
|
"use_sliding_window": false,
|
||||||
|
"vocab_size": 152064
|
||||||
|
}
|
||||||
13
mergekit_config.yml
Normal file
13
mergekit_config.yml
Normal file
@@ -0,0 +1,13 @@
|
|||||||
|
models:
|
||||||
|
- model: deepseek-ai/DeepSeek-R1-Distill-Qwen-14B #logic
|
||||||
|
- model: huihui-ai/DeepSeek-R1-Distill-Qwen-14B-abliterated-v2 #uncensored
|
||||||
|
- model: Qwen/Qwen2.5-14B #text generation
|
||||||
|
- model: Qwen/Qwen2.5-14B-Instruct #chat assistant
|
||||||
|
- model: Qwen/Qwen2.5-Coder-14B #coding
|
||||||
|
- model: SicariusSicariiStuff/Impish_QWEN_14B-1M #math
|
||||||
|
- model: tanliboy/lambda-qwen2.5-14b-dpo-test #dpo
|
||||||
|
merge_method: model_stock
|
||||||
|
base_model: Qwen/Qwen2.5-14B-Instruct
|
||||||
|
normalize: true
|
||||||
|
int8_mask: true
|
||||||
|
dtype: bfloat16
|
||||||
151388
merges.txt
Normal file
151388
merges.txt
Normal file
File diff suppressed because it is too large
Load Diff
3
model-00001-of-00006.safetensors
Normal file
3
model-00001-of-00006.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:c27c70746336391cc2551a87b9415c020478a2b00d08436723b2b4b805cc588f
|
||||||
|
size 4907454960
|
||||||
3
model-00002-of-00006.safetensors
Normal file
3
model-00002-of-00006.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:106f16cc01373428e68d91567fbbf32299ad7b06be13e26c76d31f3c885143c7
|
||||||
|
size 4954847384
|
||||||
3
model-00003-of-00006.safetensors
Normal file
3
model-00003-of-00006.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:31e85d4799b48ca708a088e9513a1e47f717c3984f11f5f86cf62452c5d2c27b
|
||||||
|
size 4954847376
|
||||||
3
model-00004-of-00006.safetensors
Normal file
3
model-00004-of-00006.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:4541467b34a1c371ba4214217edfd4750e2544326c39291c5bc4f3e0ea17f60e
|
||||||
|
size 4954847376
|
||||||
3
model-00005-of-00006.safetensors
Normal file
3
model-00005-of-00006.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:be155eb9bc6356101be2e9aebce47979ca872ec8baca4959b32a439c2538b0fd
|
||||||
|
size 4954847376
|
||||||
3
model-00006-of-00006.safetensors
Normal file
3
model-00006-of-00006.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:43e49540acea5f752e5d550bf77bed08c7d0e319d6659a175983061d1a96ec00
|
||||||
|
size 4813289432
|
||||||
1
model.safetensors.index.json
Normal file
1
model.safetensors.index.json
Normal file
File diff suppressed because one or more lines are too long
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
|
||||||
|
}
|
||||||
|
}
|
||||||
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
|
||||||
208
tokenizer_config.json
Normal file
208
tokenizer_config.json
Normal file
@@ -0,0 +1,208 @@
|
|||||||
|
{
|
||||||
|
"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 {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n {%- endif %}\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 {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n {%- endif %}\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": 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