初始化项目,由ModelHub XC社区提供模型
Model: sthenno-com/miscii-14b-1225 Source: Original Platform
This commit is contained in:
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
|
||||||
174
README.md
Normal file
174
README.md
Normal file
@@ -0,0 +1,174 @@
|
|||||||
|
---
|
||||||
|
language:
|
||||||
|
- zho
|
||||||
|
- eng
|
||||||
|
- fra
|
||||||
|
- spa
|
||||||
|
- por
|
||||||
|
- deu
|
||||||
|
- ita
|
||||||
|
- rus
|
||||||
|
- jpn
|
||||||
|
- kor
|
||||||
|
- vie
|
||||||
|
- tha
|
||||||
|
- ara
|
||||||
|
license: apache-2.0
|
||||||
|
library_name: transformers
|
||||||
|
tags:
|
||||||
|
- mergekit
|
||||||
|
- merge
|
||||||
|
- custom-research
|
||||||
|
- miscii
|
||||||
|
base_model:
|
||||||
|
- sthenno-com/miscii-14b-1028
|
||||||
|
- Qwen/Qwen2.5-14B-Instruct
|
||||||
|
metrics:
|
||||||
|
- accuracy
|
||||||
|
model-index:
|
||||||
|
- name: miscii-14b-1225
|
||||||
|
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: 78.78
|
||||||
|
name: strict accuracy
|
||||||
|
source:
|
||||||
|
url: >-
|
||||||
|
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=sthenno-com/miscii-14b-1225
|
||||||
|
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: 50.91
|
||||||
|
name: normalized accuracy
|
||||||
|
source:
|
||||||
|
url: >-
|
||||||
|
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=sthenno-com/miscii-14b-1225
|
||||||
|
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: 31.57
|
||||||
|
name: exact match
|
||||||
|
source:
|
||||||
|
url: >-
|
||||||
|
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=sthenno-com/miscii-14b-1225
|
||||||
|
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: 17
|
||||||
|
name: acc_norm
|
||||||
|
source:
|
||||||
|
url: >-
|
||||||
|
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=sthenno-com/miscii-14b-1225
|
||||||
|
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: 14.77
|
||||||
|
name: acc_norm
|
||||||
|
source:
|
||||||
|
url: >-
|
||||||
|
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=sthenno-com/miscii-14b-1225
|
||||||
|
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: 47.46
|
||||||
|
name: accuracy
|
||||||
|
source:
|
||||||
|
url: >-
|
||||||
|
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=sthenno-com/miscii-14b-1225
|
||||||
|
name: Open LLM Leaderboard
|
||||||
|
---
|
||||||
|
|
||||||
|
# miscii-14b-1225
|
||||||
|
|
||||||
|

|
||||||
|
Image source: [Rrhar'il | Phigros](https://phigros.fandom.com/wiki/Rrhar%27il)
|
||||||
|
|
||||||
|
## Prompting & Usage
|
||||||
|
|
||||||
|
See [miscii-14b-1028](https://huggingface.co/sthenno-com/miscii-14b-1028) for more details.
|
||||||
|
|
||||||
|
## Training Details
|
||||||
|
|
||||||
|
Coming soon
|
||||||
|
|
||||||
|
## Merge Details
|
||||||
|
|
||||||
|
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
|
||||||
|
|
||||||
|
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard)
|
||||||
|
|
||||||
|
Congratulations to the **miscii** series models for surpassing 40 points for the first time!
|
||||||
|
As of **December 25, 2024**, this should be the **best-performing 14B model** in the tests, right?
|
||||||
|
|
||||||
|
| Metric |Value|
|
||||||
|
|-------------------|----:|
|
||||||
|
|Avg. |40.08|
|
||||||
|
|IFEval (0-Shot) |78.78|
|
||||||
|
|BBH (3-Shot) |50.91|
|
||||||
|
|MATH Lvl 5 (4-Shot)|31.57|
|
||||||
|
|GPQA (0-shot) |17.00|
|
||||||
|
|MuSR (0-shot) |14.77|
|
||||||
|
|MMLU-PRO (5-shot) |47.46|
|
||||||
|
|
||||||
|
|
||||||
|
## Refined since 2025-02-15
|
||||||
|
|
||||||
|
| Metric |Value|
|
||||||
|
|-------------------|----:|
|
||||||
|
|Avg. |42.35|
|
||||||
|
|IFEval (0-Shot) |78.78|
|
||||||
|
|BBH (3-Shot) |50.91|
|
||||||
|
|MATH Lvl 5 (4-Shot)|45.17|
|
||||||
|
|GPQA (0-shot) |17.00|
|
||||||
|
|MuSR (0-shot) |14.77|
|
||||||
|
|MMLU-PRO (5-shot) |47.46|
|
||||||
BIN
Rrharil.png
Normal file
BIN
Rrharil.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 742 KiB |
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": "/home/neoheartbeats/endpoint/models/miscii-1028",
|
||||||
|
"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": "4.47.1",
|
||||||
|
"use_cache": true,
|
||||||
|
"use_sliding_window": false,
|
||||||
|
"vocab_size": 151665
|
||||||
|
}
|
||||||
1
configuration.json
Normal file
1
configuration.json
Normal file
@@ -0,0 +1 @@
|
|||||||
|
{"framework": "pytorch", "task": "text-generation", "allow_remote": true}
|
||||||
28
mergekit_config.yml
Normal file
28
mergekit_config.yml
Normal file
@@ -0,0 +1,28 @@
|
|||||||
|
tokenizer_source: "base"
|
||||||
|
chat_template: "chatml"
|
||||||
|
|
||||||
|
merge_method: ties
|
||||||
|
dtype: bfloat16
|
||||||
|
|
||||||
|
parameters:
|
||||||
|
normalize: true
|
||||||
|
|
||||||
|
base_model: sthenno-com/miscii-14b-1028
|
||||||
|
|
||||||
|
models:
|
||||||
|
- model: sthenno-com/miscii-14b-1028
|
||||||
|
parameters:
|
||||||
|
weight: 1
|
||||||
|
density: 0.5
|
||||||
|
- model: sthenno/miscii-1218
|
||||||
|
parameters:
|
||||||
|
weight: 1
|
||||||
|
density: 0.5
|
||||||
|
- model: sthenno/exp-002
|
||||||
|
parameters:
|
||||||
|
weight: 0.9
|
||||||
|
density: 0.5
|
||||||
|
- model: sthenno/miscii-1218
|
||||||
|
parameters:
|
||||||
|
weight: 0.6
|
||||||
|
density: 0.5
|
||||||
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:cd2c1526920ac3cfa7a0d6c5bef6e0872c2ac8f079f04ec63cdfa15e4dc205a5
|
||||||
|
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:da59aef13b183fb9db8e98b2ac31cef8b06c19519518cf86b58d212488db638f
|
||||||
|
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 sha256:667ec0c4c8d5f96a9380b3346e5c32772f6f07f886e0967ade5f78e54a77ff44
|
||||||
|
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 sha256:151b2bedb7a0d043f32d01f2d98705b6af64bdb46e856d0f10449cfcfd9d38a4
|
||||||
|
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 sha256:293a68f9ceac0517deb087a9f6e724bf73d2aa3ebc3b9eee445eee00f525bc89
|
||||||
|
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 sha256:81b6dfa70f16169ff9dff3eac388ce3bfd894955d33f4f783677480662c1efb2
|
||||||
|
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
|
||||||
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": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\\n' + message['content'] + '<|im_end|>' + '\\n'}}{% endfor %}\n{% if add_generation_prompt %}{{ '<|im_start|>assistant\\n' }}{% endif %}\n",
|
||||||
|
"clean_up_tokenization_spaces": false,
|
||||||
|
"eos_token": "<|im_end|>",
|
||||||
|
"errors": "replace",
|
||||||
|
"extra_special_tokens": {},
|
||||||
|
"model_max_length": 131072,
|
||||||
|
"pad_token": "<|endoftext|>",
|
||||||
|
"padding_side": "left",
|
||||||
|
"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