arcee-ai/Gemma-Zephyr-Dolly-Chat-Slerp
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: arcee-ai/Gemma-Zephyr-Dolly-Chat-Slerp
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-05-05 14:38:47 +08:00
commit 5caea54ca8
18 changed files with 265 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

45
.gitattributes vendored Normal file
View File

@@ -0,0 +1,45 @@
*.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
model-00001-of-00009.safetensors filter=lfs diff=lfs merge=lfs -text
model-00002-of-00009.safetensors filter=lfs diff=lfs merge=lfs -text
model-00003-of-00009.safetensors filter=lfs diff=lfs merge=lfs -text
model-00004-of-00009.safetensors filter=lfs diff=lfs merge=lfs -text
model-00005-of-00009.safetensors filter=lfs diff=lfs merge=lfs -text
model-00006-of-00009.safetensors filter=lfs diff=lfs merge=lfs -text
model-00007-of-00009.safetensors filter=lfs diff=lfs merge=lfs -text
model-00008-of-00009.safetensors filter=lfs diff=lfs merge=lfs -text
model-00009-of-00009.safetensors filter=lfs diff=lfs merge=lfs -text

37
README.md Normal file
View File

@@ -0,0 +1,37 @@
---
license: apache-2.0
tags:
- merge
- mergekit
- HuggingFaceH4/zephyr-7b-gemma-v0.1
- google/gemma-7b+philschmid/gemma-7b-dolly-chatml
---
# Gemma-Zephyr-Dolly-Chat-Slerp
Gemma-Zephyr-Dolly-Chat-Slerp is a merge of the following models using [mergekit](https://github.com/cg123/mergekit):
* [HuggingFaceH4/zephyr-7b-gemma-v0.1](https://huggingface.co/HuggingFaceH4/zephyr-7b-gemma-v0.1)
* [google/gemma-7b+philschmid/gemma-7b-dolly-chatml](https://huggingface.co/google/gemma-7b+philschmid/gemma-7b-dolly-chatml)
## 🧩 Configuration
```yaml
slices:
- sources:
- model: HuggingFaceH4/zephyr-7b-gemma-v0.1
layer_range: [0, 28]
- model: google/gemma-7b+philschmid/gemma-7b-dolly-chatml
layer_range: [0, 28]
merge_method: slerp
base_model: HuggingFaceH4/zephyr-7b-gemma-v0.1
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": "HuggingFaceH4/zephyr-7b-gemma-v0.1",
"architectures": [
"GemmaForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 2,
"eos_token_id": 1,
"head_dim": 256,
"hidden_act": "gelu",
"hidden_size": 3072,
"initializer_range": 0.02,
"intermediate_size": 24576,
"max_position_embeddings": 8192,
"model_type": "gemma",
"num_attention_heads": 16,
"num_hidden_layers": 28,
"num_key_value_heads": 16,
"pad_token_id": 0,
"rms_norm_eps": 1e-06,
"rope_scaling": null,
"rope_theta": 10000.0,
"torch_dtype": "bfloat16",
"transformers_version": "4.38.2",
"use_cache": true,
"vocab_size": 256000
}

1
configuration.json Normal file
View File

@@ -0,0 +1 @@
{"framework": "pytorch", "task": "text-generation", "allow_remote": true}

19
mergekit_config.yml Normal file
View File

@@ -0,0 +1,19 @@
slices:
- sources:
- model: HuggingFaceH4/zephyr-7b-gemma-v0.1
layer_range: [0, 28]
- model: google/gemma-7b+philschmid/gemma-7b-dolly-chatml
layer_range: [0, 28]
merge_method: slerp
base_model: HuggingFaceH4/zephyr-7b-gemma-v0.1
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-00009.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:947467ddea219700c2af7fef002088bb47686fbb95b902f30da32b455936da4a
size 1912643208

3
model-00002-of-00009.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:67b9161269c19544731ff5b6327d1f8868d965ece602fed4280806d797c562d8
size 1509989312

3
model-00003-of-00009.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:c7eb9d542ce539f0375fa63a9ae444b7e70aea8a4f55b2d1d69d1b614c5c0405
size 1975518032

3
model-00004-of-00009.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:d489e86004f58fa15af33f7d00bf3e8df6d3bf1d9fee8e8344bc6a9f2c813fb0
size 1912655752

3
model-00005-of-00009.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ac618541d0f2fc319b0481225112f4dc19675e59c9979e57c9b2ec91e8951276
size 1962974504

3
model-00006-of-00009.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:922b6a9f17c7c64bc7ad076e87c1112818cf4df79170d3ec3f9fee63d8a90c38
size 1912655736

3
model-00007-of-00009.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b4a5fa05b5949ce2965338c0483366eb4bd0e1f5ed02e2656edad86b157d3cc3
size 1962974528

3
model-00008-of-00009.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:4c8c76969e0bae02cff97a80a72f91f7b7acdeac8afc5861440f500a55221465
size 1962993272

3
model-00009-of-00009.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:767855820816b1933a9460d13b25ea0759fbc5304d07c5052ace91b8ebd016e4
size 1962987040

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

File diff suppressed because one or more lines are too long

34
special_tokens_map.json Normal file
View File

@@ -0,0 +1,34 @@
{
"additional_special_tokens": [
"<|im_start|>",
"<|im_end|>"
],
"bos_token": {
"content": "<bos>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"eos_token": {
"content": "<eos>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"pad_token": {
"content": "<pad>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"unk_token": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
}
}

3
tokenizer.json Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:22449cb9ef4bad0db7dd93b46ddff7ab7d6a654dd4f903e130ddb6361eac3af5
size 17477473

70
tokenizer_config.json Normal file
View File

@@ -0,0 +1,70 @@
{
"add_bos_token": false,
"add_eos_token": false,
"added_tokens_decoder": {
"0": {
"content": "<pad>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"1": {
"content": "<eos>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"2": {
"content": "<bos>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"3": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"106": {
"content": "<|im_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"107": {
"content": "<|im_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"additional_special_tokens": [
"<|im_start|>",
"<|im_end|>"
],
"bos_token": "<bos>",
"chat_template": "{% if messages[0]['role'] == 'user' or messages[0]['role'] == 'system' %}{{ bos_token }}{% endif %}{% for message in messages %}{{ '<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n' }}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% elif messages[-1]['role'] == 'assistant' %}{{ eos_token }}{% endif %}",
"clean_up_tokenization_spaces": false,
"eos_token": "<eos>",
"legacy": null,
"model_max_length": 2048,
"pad_token": "<pad>",
"sp_model_kwargs": {},
"spaces_between_special_tokens": false,
"tokenizer_class": "GemmaTokenizer",
"unk_token": "<unk>",
"use_default_system_prompt": false
}