初始化项目，由ModelHub XC社区提供模型
Model: CultriX/Qwen2.5-14B-Unity 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
|
||||||
97
README.md
Normal file
97
README.md
Normal file
@@ -0,0 +1,97 @@
|
|||||||
|
---
|
||||||
|
base_model:
|
||||||
|
- CultriX/Qwen2.5-14B-Wernickev3
|
||||||
|
- qingy2019/Qwen2.5-Math-14B-Instruct
|
||||||
|
- sometimesanotion/Qwen2.5-14B-Vimarckoso
|
||||||
|
- CultriX/Qwen2.5-14B-Emergedv3
|
||||||
|
- allknowingroger/QwenSlerp6-14B
|
||||||
|
- CultriX/SeQwence-14Bv1
|
||||||
|
library_name: transformers
|
||||||
|
tags:
|
||||||
|
- mergekit
|
||||||
|
- merge
|
||||||
|
|
||||||
|
---
|
||||||
|
# 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 [DARE](https://arxiv.org/abs/2311.03099) [TIES](https://arxiv.org/abs/2306.01708) merge method using [CultriX/SeQwence-14Bv1](https://huggingface.co/CultriX/SeQwence-14Bv1) as a base.
|
||||||
|
|
||||||
|
### Models Merged
|
||||||
|
|
||||||
|
The following models were included in the merge:
|
||||||
|
* [CultriX/Qwen2.5-14B-Wernickev3](https://huggingface.co/CultriX/Qwen2.5-14B-Wernickev3)
|
||||||
|
* [qingy2019/Qwen2.5-Math-14B-Instruct](https://huggingface.co/qingy2019/Qwen2.5-Math-14B-Instruct)
|
||||||
|
* [sometimesanotion/Qwen2.5-14B-Vimarckoso](https://huggingface.co/sometimesanotion/Qwen2.5-14B-Vimarckoso)
|
||||||
|
* [CultriX/Qwen2.5-14B-Emergedv3](https://huggingface.co/CultriX/Qwen2.5-14B-Emergedv3)
|
||||||
|
* [allknowingroger/QwenSlerp6-14B](https://huggingface.co/allknowingroger/QwenSlerp6-14B)
|
||||||
|
|
||||||
|
### Configuration
|
||||||
|
|
||||||
|
The following YAML configuration was used to produce this model:
|
||||||
|
|
||||||
|
```yaml
|
||||||
|
base_model: CultriX/SeQwence-14Bv1
|
||||||
|
merge_method: dare_ties
|
||||||
|
parameters:
|
||||||
|
normalize: true
|
||||||
|
int8_mask: true
|
||||||
|
dtype: bfloat16
|
||||||
|
|
||||||
|
models:
|
||||||
|
- model: CultriX/SeQwence-14Bv1
|
||||||
|
parameters:
|
||||||
|
weight: 0.28 # Strong base for multitask benchmarks.
|
||||||
|
density: 0.7 # Retains strong multitask performance.
|
||||||
|
|
||||||
|
- model: CultriX/Qwen2.5-14B-Wernickev3
|
||||||
|
parameters:
|
||||||
|
weight: 0.22 # Balanced to support reasoning-heavy benchmarks like BBH.
|
||||||
|
density: 0.65
|
||||||
|
|
||||||
|
- model: qingy2019/Qwen2.5-Math-14B-Instruct
|
||||||
|
parameters:
|
||||||
|
weight: 0.22 # Optimized for MATH and BBH.
|
||||||
|
density: 0.6
|
||||||
|
|
||||||
|
- model: allknowingroger/QwenSlerp6-14B
|
||||||
|
parameters:
|
||||||
|
weight: 0.18 # Reintegration of the highest scorer for stability across benchmarks.
|
||||||
|
density: 0.65 # Focused on its exceptional multitask and reasoning strengths.
|
||||||
|
|
||||||
|
- model: CultriX/Qwen2.5-14B-Emergedv3
|
||||||
|
parameters:
|
||||||
|
weight: 0.15 # Maintains multitask stability for GPQA and MMLU-PRO.
|
||||||
|
density: 0.6
|
||||||
|
|
||||||
|
- model: sometimesanotion/Qwen2.5-14B-Vimarckoso
|
||||||
|
parameters:
|
||||||
|
weight: 0.1 # Late-layer contributor for MUSR and multi-step reasoning.
|
||||||
|
density: 0.6
|
||||||
|
|
||||||
|
adaptive_merge_parameters:
|
||||||
|
task_weights:
|
||||||
|
IFEval: 1.4 # Balanced to maintain instruction-following benchmarks.
|
||||||
|
BBH: 1.4 # Ensures strong reasoning capabilities.
|
||||||
|
MATH: 1.5 # Prioritizes mathematical reasoning.
|
||||||
|
GPQA: 1.5 # Balanced for factual QA.
|
||||||
|
MUSR: 1.4 # Advanced multi-step reasoning.
|
||||||
|
MMLU-PRO: 1.5 # Emphasized for domain-specific multitask performance.
|
||||||
|
|
||||||
|
smoothing_factor: 0.12 # Smooth transitions between task-specific contributions.
|
||||||
|
|
||||||
|
gradient_clipping:
|
||||||
|
CultriX/SeQwence-14Bv1: 0.8
|
||||||
|
CultriX/Qwen2.5-14B-Wernickev3: 0.8
|
||||||
|
qingy2019/Qwen2.5-Math-14B-Instruct: 0.85
|
||||||
|
allknowingroger/QwenSlerp6-14B: 0.8 # Balanced for high scoring model contributions.
|
||||||
|
CultriX/Qwen2.5-14B-Emergedv3: 0.75
|
||||||
|
sometimesanotion/Qwen2.5-14B-Vimarckoso: 0.75
|
||||||
|
|
||||||
|
tokenizer_source: CultriX/SeQwence-14Bv1
|
||||||
|
|
||||||
|
```
|
||||||
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": "CultriX/SeQwence-14Bv1",
|
||||||
|
"architectures": [
|
||||||
|
"Qwen2ForCausalLM"
|
||||||
|
],
|
||||||
|
"attention_dropout": 0.0,
|
||||||
|
"bos_token_id": 151643,
|
||||||
|
"eos_token_id": 151643,
|
||||||
|
"hidden_act": "silu",
|
||||||
|
"hidden_size": 5120,
|
||||||
|
"initializer_range": 0.02,
|
||||||
|
"intermediate_size": 13824,
|
||||||
|
"max_position_embeddings": 131072,
|
||||||
|
"max_window_layers": 48,
|
||||||
|
"model_type": "qwen2",
|
||||||
|
"num_attention_heads": 40,
|
||||||
|
"num_hidden_layers": 48,
|
||||||
|
"num_key_value_heads": 8,
|
||||||
|
"rms_norm_eps": 1e-05,
|
||||||
|
"rope_scaling": null,
|
||||||
|
"rope_theta": 1000000.0,
|
||||||
|
"sliding_window": null,
|
||||||
|
"tie_word_embeddings": false,
|
||||||
|
"torch_dtype": "bfloat16",
|
||||||
|
"transformers_version": "4.46.2",
|
||||||
|
"use_cache": true,
|
||||||
|
"use_sliding_window": false,
|
||||||
|
"vocab_size": 151665
|
||||||
|
}
|
||||||
58
mergekit_config.yml
Normal file
58
mergekit_config.yml
Normal file
@@ -0,0 +1,58 @@
|
|||||||
|
base_model: CultriX/SeQwence-14Bv1
|
||||||
|
merge_method: dare_ties
|
||||||
|
parameters:
|
||||||
|
normalize: true
|
||||||
|
int8_mask: true
|
||||||
|
dtype: bfloat16
|
||||||
|
|
||||||
|
models:
|
||||||
|
- model: CultriX/SeQwence-14Bv1
|
||||||
|
parameters:
|
||||||
|
weight: 0.28 # Strong base for multitask benchmarks.
|
||||||
|
density: 0.7 # Retains strong multitask performance.
|
||||||
|
|
||||||
|
- model: CultriX/Qwen2.5-14B-Wernickev3
|
||||||
|
parameters:
|
||||||
|
weight: 0.22 # Balanced to support reasoning-heavy benchmarks like BBH.
|
||||||
|
density: 0.65
|
||||||
|
|
||||||
|
- model: qingy2019/Qwen2.5-Math-14B-Instruct
|
||||||
|
parameters:
|
||||||
|
weight: 0.22 # Optimized for MATH and BBH.
|
||||||
|
density: 0.6
|
||||||
|
|
||||||
|
- model: allknowingroger/QwenSlerp6-14B
|
||||||
|
parameters:
|
||||||
|
weight: 0.18 # Reintegration of the highest scorer for stability across benchmarks.
|
||||||
|
density: 0.65 # Focused on its exceptional multitask and reasoning strengths.
|
||||||
|
|
||||||
|
- model: CultriX/Qwen2.5-14B-Emergedv3
|
||||||
|
parameters:
|
||||||
|
weight: 0.15 # Maintains multitask stability for GPQA and MMLU-PRO.
|
||||||
|
density: 0.6
|
||||||
|
|
||||||
|
- model: sometimesanotion/Qwen2.5-14B-Vimarckoso
|
||||||
|
parameters:
|
||||||
|
weight: 0.1 # Late-layer contributor for MUSR and multi-step reasoning.
|
||||||
|
density: 0.6
|
||||||
|
|
||||||
|
adaptive_merge_parameters:
|
||||||
|
task_weights:
|
||||||
|
IFEval: 1.4 # Balanced to maintain instruction-following benchmarks.
|
||||||
|
BBH: 1.4 # Ensures strong reasoning capabilities.
|
||||||
|
MATH: 1.5 # Prioritizes mathematical reasoning.
|
||||||
|
GPQA: 1.5 # Balanced for factual QA.
|
||||||
|
MUSR: 1.4 # Advanced multi-step reasoning.
|
||||||
|
MMLU-PRO: 1.5 # Emphasized for domain-specific multitask performance.
|
||||||
|
|
||||||
|
smoothing_factor: 0.12 # Smooth transitions between task-specific contributions.
|
||||||
|
|
||||||
|
gradient_clipping:
|
||||||
|
CultriX/SeQwence-14Bv1: 0.8
|
||||||
|
CultriX/Qwen2.5-14B-Wernickev3: 0.8
|
||||||
|
qingy2019/Qwen2.5-Math-14B-Instruct: 0.85
|
||||||
|
allknowingroger/QwenSlerp6-14B: 0.8 # Balanced for high scoring model contributions.
|
||||||
|
CultriX/Qwen2.5-14B-Emergedv3: 0.75
|
||||||
|
sometimesanotion/Qwen2.5-14B-Vimarckoso: 0.75
|
||||||
|
|
||||||
|
tokenizer_source: CultriX/SeQwence-14Bv1
|
||||||
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 sha256:6880b91bc7b28fa196f11122c9782af4f4f13d1a137ce515758125de4c1e8a58
|
||||||
|
size 4899283440
|
||||||
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 sha256:2c4e97adb6cbe4a3a8d2a5ec62378b99157ccef814dcd29848800df9bb4f31bd
|
||||||
|
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 sha256:987ba2c2e451b98ea7f8cd8b52ea68c388763e04d4e8c5d9b69fc42b7006f868
|
||||||
|
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 sha256:8fd08ca06203a9819b9c3765200aed5bda91b9d8130a1a4ad7ed3fe94e41b604
|
||||||
|
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 sha256:2341acae7ff82aa02399673f843a6136661366890253a009b7683c2c258114fa
|
||||||
|
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 sha256:10636666a25a391fb96fc9cec6cdf9ce06950a5977f90f8c638326836506cb4c
|
||||||
|
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
|
||||||
207
tokenizer_config.json
Normal file
207
tokenizer_config.json
Normal file
@@ -0,0 +1,207 @@
|
|||||||
|
{
|
||||||
|
"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",
|
||||||
|
"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