Weyaxi/Luban-Marcoroni-13B-v2
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: Weyaxi/Luban-Marcoroni-13B-v2
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-04-27 20:47:58 +08:00
commit 5d1f269c26
13 changed files with 93590 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

35
.gitattributes vendored Normal file
View 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

37
README.md Normal file
View File

@@ -0,0 +1,37 @@
---
license: cc-by-nc-4.0
datasets:
- Open-Orca/OpenOrca
language:
- en
---
<a href="https://www.buymeacoffee.com/PulsarAI" target="_blank"><img src="https://cdn.buymeacoffee.com/buttons/v2/default-yellow.png" alt="Buy Me A Coffee" style="height: 60px !important;width: 217px !important;" ></a>
Merge of [Marcoroni-13B](https://huggingface.co/AIDC-ai-business/Marcoroni-13B) and [Luban-13B](https://huggingface.co/AIDC-ai-business/Luban-13B) using ties merge.
### *Weights*
- [Marcoroni-13B](https://huggingface.co/AIDC-ai-business/Marcoroni-13B): 0.6
- [Luban-13B](https://huggingface.co/AIDC-ai-business/Luban-13B): 0.4
### *Density*
- [Marcoroni-13B](https://huggingface.co/AIDC-ai-business/Marcoroni-13B): 0.5
- [Luban-13B](https://huggingface.co/AIDC-ai-business/Luban-13B): 0.5
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_Weyaxi__Luban-Marcoroni-13B-v2)
| Metric | Value |
|-----------------------|---------------------------|
| Avg. | 51.11 |
| ARC (25-shot) | 63.48 |
| HellaSwag (10-shot) | 82.89 |
| MMLU (5-shot) | 58.72 |
| TruthfulQA (0-shot) | 55.56 |
| Winogrande (5-shot) | 76.95 |
| GSM8K (5-shot) | 9.93 |
| DROP (3-shot) | 10.25 |

4
added_tokens.json Normal file
View File

@@ -0,0 +1,4 @@
{
"<|PAD|>": 32001,
"<|end_of_turn|>": 32000
}

27
config.json Normal file
View File

@@ -0,0 +1,27 @@
{
"_name_or_path": "/root/.cache/huggingface/hub/models--Open-Orca--OpenOrcaxOpenChat-Preview2-13B/snapshots/6643bd620204fa22cc9cff1d1586c29591e13c0b",
"architectures": [
"LlamaForCausalLM"
],
"bos_token_id": 1,
"eos_token_id": 2,
"hidden_act": "silu",
"hidden_size": 5120,
"initializer_range": 0.02,
"intermediate_size": 13824,
"max_position_embeddings": 4096,
"model_type": "llama",
"num_attention_heads": 40,
"num_hidden_layers": 40,
"num_key_value_heads": 40,
"pad_token_id": 0,
"pretraining_tp": 1,
"rms_norm_eps": 1e-05,
"rope_scaling": null,
"rope_theta": 10000.0,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.33.1",
"use_cache": false,
"vocab_size": 32002
}

8
generation_config.json Normal file
View File

@@ -0,0 +1,8 @@
{
"_from_model_config": true,
"bos_token_id": 1,
"eos_token_id": 2,
"pad_token_id": 0,
"transformers_version": "4.31.0",
"use_cache": false
}

3
model-00001-of-00003.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:07a0eaee8757882fbfa305e571e1a9e7b3fae4bdccf8b962820f856e753ff3c3
size 10276409240

3
model-00002-of-00003.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b0882873fb6d9dc036b26b41ef6040a8d1536f2e818979ab5ab5e4828a6c57e1
size 9904123752

3
model-00003-of-00003.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:86adb10585a1dd77a9a4b401b33b759aad708d79c425472828eda9f84b3b83ab
size 6506680096

1
model.safetensors.index.json Normal file
View File

File diff suppressed because one or more lines are too long

21
special_tokens_map.json Normal file
View File

@@ -0,0 +1,21 @@
{
"additional_special_tokens": [
"<|end_of_turn|>",
"<|PAD|>"
],
"bos_token": {
"content": "<s>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"eos_token": "<|end_of_turn|>",
"unk_token": {
"content": "<unk>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
}
}

93409
tokenizer.json Normal file
View File

File diff suppressed because it is too large Load Diff

3
tokenizer.model Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
size 499723

36
tokenizer_config.json Normal file
View File

@@ -0,0 +1,36 @@
{
"add_bos_token": true,
"add_eos_token": false,
"bos_token": {
"__type": "AddedToken",
"content": "<s>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"clean_up_tokenization_spaces": false,
"eos_token": {
"__type": "AddedToken",
"content": "</s>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"legacy": true,
"model_max_length": 1000000000000000019884624838656,
"pad_token": null,
"sp_model_kwargs": {},
"spaces_between_special_tokens": false,
"tokenizer_class": "LlamaTokenizer",
"unk_token": {
"__type": "AddedToken",
"content": "<unk>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"use_default_system_prompt": true
}