axxd/wizardllama-7b
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: axxd/wizardllama-7b
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-05-06 22:50:54 +08:00
commit c61bc84b87
16 changed files with 93694 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

50
README.md Normal file
View File

@@ -0,0 +1,50 @@
---
base_model:
- codellama/CodeLlama-7b-Python-hf
- WizardLM/WizardCoder-Python-7B-V1.0
library_name: transformers
tags:
- mergekit
- merge
- code
license: apache-2.0
---
# 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 SLERP merge method.
### Models Merged
The following models were included in the merge:
* [codellama/CodeLlama-7b-Python-hf](https://huggingface.co/codellama/CodeLlama-7b-Python-hf)
* [WizardLM/WizardCoder-Python-7B-V1.0](https://huggingface.co/WizardLM/WizardCoder-Python-7B-V1.0)
### Configuration
The following YAML configuration was used to produce this model:
```yaml
slices:
- sources:
- model: WizardLM/WizardCoder-Python-7B-V1.0
layer_range: [0, 32]
- model: codellama/CodeLlama-7b-Python-hf
layer_range: [0, 32]
merge_method: slerp
base_model: codellama/CodeLlama-7b-Python-hf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: bfloat16
```

28
config.json Normal file
View File

@@ -0,0 +1,28 @@
{
"_name_or_path": "codellama/CodeLlama-7b-Python-hf",
"architectures": [
"LlamaForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 1,
"eos_token_id": 2,
"hidden_act": "silu",
"hidden_size": 4096,
"initializer_range": 0.02,
"intermediate_size": 11008,
"max_position_embeddings": 16384,
"model_type": "llama",
"num_attention_heads": 32,
"num_hidden_layers": 32,
"num_key_value_heads": 32,
"pretraining_tp": 1,
"rms_norm_eps": 1e-05,
"rope_scaling": null,
"rope_theta": 1000000,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.38.2",
"use_cache": true,
"vocab_size": 32000
}

17
mergekit_config.yml Normal file
View File

@@ -0,0 +1,17 @@
slices:
- sources:
- model: WizardLM/WizardCoder-Python-7B-V1.0
layer_range: [0, 32]
- model: codellama/CodeLlama-7b-Python-hf
layer_range: [0, 32]
merge_method: slerp
base_model: codellama/CodeLlama-7b-Python-hf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: bfloat16

3
model-00001-of-00007.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:80318d865953f3a31118b027fa2bfd70bb103da472e6f0bbd4e12a1b5a6af887
size 1990275992

3
model-00002-of-00007.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:8c98767470d98822dc5b1b588a88d419c11c8fe6d9daaa743267eeea8e8fdc93
size 1990284304

3
model-00003-of-00007.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:46e1105fffc3ad8b568ebdff5fef516f9600665a10153bf23262068547cc6aeb
size 1990284280

3
model-00004-of-00007.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a612f7e998e9c548177d477ddeba6adfbeacc0d852c045e478e6129d99cc4867
size 1990284256

3
model-00005-of-00007.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:55d2e8f2e2bf4fc3d2b33dd6976383fa44ef502e6909cafbbff55833685cb69a
size 1753297528

3
model-00006-of-00007.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:982a081a9b4b1531c85815858d12ceb0a589a3d4c0475e921068c05e55902031
size 1918955112

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

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:005d3fee1dfb955afc595d50c330062a89950de64cefa952ab022f7f9687547b
size 1843483528

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

File diff suppressed because one or more lines are too long

29
special_tokens_map.json Normal file
View File

@@ -0,0 +1,29 @@
{
"additional_special_tokens": [
"▁<PRE>",
"▁<MID>",
"▁<SUF>",
"▁<EOT>"
],
"bos_token": {
"content": "<s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"eos_token": {
"content": "</s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"unk_token": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
}
}

93427
tokenizer.json Normal file
View File

File diff suppressed because it is too large Load Diff

BIN
tokenizer.model (Stored with Git LFS) Normal file
View File

Binary file not shown.

83
tokenizer_config.json Normal file
View File

@@ -0,0 +1,83 @@
{
"add_bos_token": true,
"add_eos_token": false,
"added_tokens_decoder": {
"0": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"1": {
"content": "<s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"2": {
"content": "</s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32000": {
"content": "▁<PRE>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32001": {
"content": "▁<MID>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32002": {
"content": "▁<SUF>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32003": {
"content": "▁<EOT>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"additional_special_tokens": [
"▁<PRE>",
"▁<MID>",
"▁<SUF>",
"▁<EOT>"
],
"bos_token": "<s>",
"clean_up_tokenization_spaces": false,
"eos_token": "</s>",
"eot_token": "▁<EOT>",
"fill_token": "<FILL_ME>",
"legacy": null,
"middle_token": "▁<MID>",
"model_max_length": 1000000000000000019884624838656,
"pad_token": null,
"prefix_token": "▁<PRE>",
"sp_model_kwargs": {},
"suffix_token": "▁<SUF>",
"tokenizer_class": "CodeLlamaTokenizer",
"unk_token": "<unk>",
"use_default_system_prompt": false
}