brucethemoose/CaPlatTessDolXaBoros-Yi-34B-200K-DARE-Ties
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: brucethemoose/CaPlatTessDolXaBoros-Yi-34B-200K-DARE-Ties
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-07-21 21:50:52 +08:00
commit 7112d03a97
16 changed files with 174359 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

54
README.md Normal file
View File

@@ -0,0 +1,54 @@
---
license: other
license_name: yi-license
license_link: https://huggingface.co/01-ai/Yi-34B/blob/main/LICENSE
language:
- en
library_name: transformers
pipeline_tag: text-generation
tags:
- text-generation-inference
- merge
---
A low density DARE ties merge, for benchmarking on the open llm leaderboard.
**You probably shouldn't use this model. Use this higher density merge instead, which is scoring much better on the llm leaderboard and perplexity tests:** https://huggingface.co/brucethemoose/CaPlatTessDolXaBoros-Yi-34B-200K-DARE-Ties-HighDensity
mergekit config:
```
models:
- model: /home/alpha/Storage/Models/Raw/chargoddard_Yi-34B-200K-Llama
# no parameters necessary for base model
- model: /home/alpha/Storage/Models/Raw/migtissera_Tess-34B-v1.4
parameters:
weight: 0.19
density: 0.44
- model: /home/alpha//Storage/Models/Raw/bhenrym14_airoboros-3_1-yi-34b-200k
parameters:
weight: 0.14
density: 0.34
- model: /home/alpha/Storage/Models/Raw/Nous-Capybara-34B
parameters:
weight: 0.19
density: 0.44
- model: /home/alpha/Storage/Models/Raw/kyujinpy_PlatYi-34B-200K-Q
parameters:
weight: 0.14
density: 0.34
- model: /home/alpha/FastModels/ehartford_dolphin-2.2-yi-34b-200k
parameters:
weight: 0.19
density: 0.44
- model: /home/alpha/FastModels/fblgit_una-xaberius-34b-v1beta
parameters:
weight: 0.15
density: 0.08
merge_method: dare_ties
base_model: /home/alpha/Storage/Models/Raw/chargoddard_Yi-34B-200K-Llama
parameters:
int8_mask: true
dtype: bfloat16
```

28
config.json Normal file
View File

@@ -0,0 +1,28 @@
{
"_name_or_path": "/home/alpha/Storage/Models/Raw/chargoddard_Yi-34B-200K-Llama",
"architectures": [
"LlamaForCausalLM"
],
"attention_bias": false,
"bos_token_id": 1,
"eos_token_id": 2,
"hidden_act": "silu",
"hidden_size": 7168,
"initializer_range": 0.02,
"intermediate_size": 20480,
"max_position_embeddings": 200000,
"model_type": "llama",
"num_attention_heads": 56,
"num_hidden_layers": 60,
"num_key_value_heads": 8,
"pad_token_id": 0,
"pretraining_tp": 1,
"rms_norm_eps": 1e-05,
"rope_scaling": null,
"rope_theta": 5000000.0,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.35.2",
"use_cache": true,
"vocab_size": 64000
}

3
model-00001-of-00008.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:aa1579329c539f976dd45ad60bf03144b44b2b68c302495d4b8f57510e1292c2
size 9843206304

3
model-00002-of-00008.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:04af5b93d4b4ffca3905657fe51299c02f592d2a6cc3b756ab890e8a4840211e
size 9747829888

3
model-00003-of-00008.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:082807bcc669ff3ec960114bbfcec1373dc7fa49eadb1542912d7b89d4eb86be
size 9747829912

3
model-00004-of-00008.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:4d81f39e8774523d1c3040dd1ff120b9c79eec80ba7084eca5ae9ae4931166f2
size 9806549808

3
model-00005-of-00008.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:5d04c544c0fa3b0ebec933483aceb2954e156d18e476526bfb7967d95e772718
size 9747829904

3
model-00006-of-00008.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:9e920e2ac524dd2013af1e857a3beded3173b24a3f2b7a6fd6e29afe967629e1
size 9747801008

3
model-00007-of-00008.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:041ba478832bf6e5d69f24267a37af7833a35a1cf3834ab793d2ad491605462a
size 9843220824

3
model-00008-of-00008.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:33097d72dc678652bd9d513c1deaf4e6c719117912c80876617dae7e4ee7aa9f
size 293630312

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

File diff suppressed because one or more lines are too long

30
special_tokens_map.json Normal file
View File

@@ -0,0 +1,30 @@
{
"bos_token": {
"content": "<|startoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"eos_token": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"pad_token": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"unk_token": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
}
}

174143
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 sha256:386c49cf943d71aa110361135338c50e38beeff0a66593480421f37b319e1a39
size 1033105

41
tokenizer_config.json Normal file
View File

@@ -0,0 +1,41 @@
{
"added_tokens_decoder": {
"0": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"1": {
"content": "<|startoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"2": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"bos_token": "<|startoftext|>",
"clean_up_tokenization_spaces": false,
"eos_token": "<|endoftext|>",
"legacy": false,
"model_max_length": 200000,
"pad_token": "<unk>",
"padding_side": "right",
"sp_model_kwargs": {},
"spaces_between_special_tokens": false,
"tokenizer_class": "LlamaTokenizer",
"truncation_side": "right",
"unk_token": "<unk>",
"use_default_system_prompt": false
}