arcee-ai/Calme-Instruct-Extended
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/Calme-Instruct-Extended
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-06-03 01:57:14 +08:00
commit 6527487a2e
20 changed files with 91607 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
model-00001-of-00010.safetensors filter=lfs diff=lfs merge=lfs -text
model-00002-of-00010.safetensors filter=lfs diff=lfs merge=lfs -text
model-00003-of-00010.safetensors filter=lfs diff=lfs merge=lfs -text
model-00004-of-00010.safetensors filter=lfs diff=lfs merge=lfs -text
model-00005-of-00010.safetensors filter=lfs diff=lfs merge=lfs -text
model-00006-of-00010.safetensors filter=lfs diff=lfs merge=lfs -text
model-00007-of-00010.safetensors filter=lfs diff=lfs merge=lfs -text
model-00008-of-00010.safetensors filter=lfs diff=lfs merge=lfs -text
model-00009-of-00010.safetensors filter=lfs diff=lfs merge=lfs -text
model-00010-of-00010.safetensors filter=lfs diff=lfs merge=lfs -text

160
README.md Normal file
View File

@@ -0,0 +1,160 @@
---
license: apache-2.0
tags:
- merge
- mergekit
- MaziyarPanahi/Calme-7B-Instruct-v0.1.1
---
# Calme-Instruct-Extended
Calme-Instruct-Extended is a merge of the following models using [mergekit](https://github.com/cg123/mergekit):
* [MaziyarPanahi/Calme-7B-Instruct-v0.1.1](https://huggingface.co/MaziyarPanahi/Calme-7B-Instruct-v0.1.1)
## 🧩 Configuration
```yaml
slices:
- sources:
- model: MaziyarPanahi/Calme-7B-Instruct-v0.1.1
layer_range:
- 0
- 4
- sources:
- model: MaziyarPanahi/Calme-7B-Instruct-v0.1.1
layer_range:
- 3
- 4
parameters:
scale:
- filter: o_proj
value: 0
- filter: down_proj
value: 0
- value: 1
- sources:
- model: MaziyarPanahi/Calme-7B-Instruct-v0.1.1
layer_range:
- 4
- 8
- sources:
- model: MaziyarPanahi/Calme-7B-Instruct-v0.1.1
layer_range:
- 7
- 8
parameters:
scale:
- filter: o_proj
value: 0
- filter: down_proj
value: 0
- value: 1
- sources:
- model: MaziyarPanahi/Calme-7B-Instruct-v0.1.1
layer_range:
- 8
- 12
- sources:
- model: MaziyarPanahi/Calme-7B-Instruct-v0.1.1
layer_range:
- 11
- 12
parameters:
scale:
- filter: o_proj
value: 0
- filter: down_proj
value: 0
- value: 1
- sources:
- model: MaziyarPanahi/Calme-7B-Instruct-v0.1.1
layer_range:
- 12
- 16
- sources:
- model: MaziyarPanahi/Calme-7B-Instruct-v0.1.1
layer_range:
- 15
- 16
parameters:
scale:
- filter: o_proj
value: 0
- filter: down_proj
value: 0
- value: 1
- sources:
- model: MaziyarPanahi/Calme-7B-Instruct-v0.1.1
layer_range:
- 16
- 20
- sources:
- model: MaziyarPanahi/Calme-7B-Instruct-v0.1.1
layer_range:
- 19
- 20
parameters:
scale:
- filter: o_proj
value: 0
- filter: down_proj
value: 0
- value: 1
- sources:
- model: MaziyarPanahi/Calme-7B-Instruct-v0.1.1
layer_range:
- 20
- 24
- sources:
- model: MaziyarPanahi/Calme-7B-Instruct-v0.1.1
layer_range:
- 23
- 24
parameters:
scale:
- filter: o_proj
value: 0
- filter: down_proj
value: 0
- value: 1
- sources:
- model: MaziyarPanahi/Calme-7B-Instruct-v0.1.1
layer_range:
- 24
- 28
- sources:
- model: MaziyarPanahi/Calme-7B-Instruct-v0.1.1
layer_range:
- 27
- 28
parameters:
scale:
- filter: o_proj
value: 0
- filter: down_proj
value: 0
- value: 1
- sources:
- model: MaziyarPanahi/Calme-7B-Instruct-v0.1.1
layer_range:
- 28
- 32
- sources:
- model: MaziyarPanahi/Calme-7B-Instruct-v0.1.1
layer_range:
- 31
- 32
parameters:
scale:
- filter: o_proj
value: 0
- filter: down_proj
value: 0
- value: 1
merge_method: passthrough
dtype: bfloat16
```

26
config.json Normal file
View File

@@ -0,0 +1,26 @@
{
"_name_or_path": "MaziyarPanahi/Calme-7B-Instruct-v0.1.1",
"architectures": [
"MistralForCausalLM"
],
"attention_dropout": 0.0,
"bos_token_id": 1,
"eos_token_id": 2,
"hidden_act": "silu",
"hidden_size": 4096,
"initializer_range": 0.02,
"intermediate_size": 14336,
"max_position_embeddings": 32768,
"model_type": "mistral",
"num_attention_heads": 32,
"num_hidden_layers": 40,
"num_key_value_heads": 8,
"rms_norm_eps": 1e-05,
"rope_theta": 10000.0,
"sliding_window": 4096,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.38.2",
"use_cache": false,
"vocab_size": 32000
}

1
configuration.json Normal file
View File

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

143
mergekit_config.yml Normal file
View File

@@ -0,0 +1,143 @@
slices:
- sources:
- model: MaziyarPanahi/Calme-7B-Instruct-v0.1.1
layer_range:
- 0
- 4
- sources:
- model: MaziyarPanahi/Calme-7B-Instruct-v0.1.1
layer_range:
- 3
- 4
parameters:
scale:
- filter: o_proj
value: 0
- filter: down_proj
value: 0
- value: 1
- sources:
- model: MaziyarPanahi/Calme-7B-Instruct-v0.1.1
layer_range:
- 4
- 8
- sources:
- model: MaziyarPanahi/Calme-7B-Instruct-v0.1.1
layer_range:
- 7
- 8
parameters:
scale:
- filter: o_proj
value: 0
- filter: down_proj
value: 0
- value: 1
- sources:
- model: MaziyarPanahi/Calme-7B-Instruct-v0.1.1
layer_range:
- 8
- 12
- sources:
- model: MaziyarPanahi/Calme-7B-Instruct-v0.1.1
layer_range:
- 11
- 12
parameters:
scale:
- filter: o_proj
value: 0
- filter: down_proj
value: 0
- value: 1
- sources:
- model: MaziyarPanahi/Calme-7B-Instruct-v0.1.1
layer_range:
- 12
- 16
- sources:
- model: MaziyarPanahi/Calme-7B-Instruct-v0.1.1
layer_range:
- 15
- 16
parameters:
scale:
- filter: o_proj
value: 0
- filter: down_proj
value: 0
- value: 1
- sources:
- model: MaziyarPanahi/Calme-7B-Instruct-v0.1.1
layer_range:
- 16
- 20
- sources:
- model: MaziyarPanahi/Calme-7B-Instruct-v0.1.1
layer_range:
- 19
- 20
parameters:
scale:
- filter: o_proj
value: 0
- filter: down_proj
value: 0
- value: 1
- sources:
- model: MaziyarPanahi/Calme-7B-Instruct-v0.1.1
layer_range:
- 20
- 24
- sources:
- model: MaziyarPanahi/Calme-7B-Instruct-v0.1.1
layer_range:
- 23
- 24
parameters:
scale:
- filter: o_proj
value: 0
- filter: down_proj
value: 0
- value: 1
- sources:
- model: MaziyarPanahi/Calme-7B-Instruct-v0.1.1
layer_range:
- 24
- 28
- sources:
- model: MaziyarPanahi/Calme-7B-Instruct-v0.1.1
layer_range:
- 27
- 28
parameters:
scale:
- filter: o_proj
value: 0
- filter: down_proj
value: 0
- value: 1
- sources:
- model: MaziyarPanahi/Calme-7B-Instruct-v0.1.1
layer_range:
- 28
- 32
- sources:
- model: MaziyarPanahi/Calme-7B-Instruct-v0.1.1
layer_range:
- 31
- 32
parameters:
scale:
- filter: o_proj
value: 0
- filter: down_proj
value: 0
- value: 1
merge_method: passthrough
dtype: bfloat16

3
model-00001-of-00010.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:3d010c40690e3376e27a65568a4529622d1e00ca278349e7fa284fa892e16886
size 1996542272

3
model-00002-of-00010.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:1abc5445e1992ff0899cdd36aa91aacabda04277c97672b3011ce1e7ec8cc9ed
size 1963003976

3
model-00003-of-00010.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ea01f2c80dcc95558771622d0d5e3d4782829a083325cc451236cf2a2660daa6
size 1939952744

3
model-00004-of-00010.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:9e7273b56929c1ca027b2d75b67b12682c402d8b617b3cc068a4b146eb5457e4
size 1979781464

3
model-00005-of-00010.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:fdee5c310ccc02a994101140391188d3d3849c9f3da7a233ff2ca84e01db9c9d
size 1946243984

3
model-00006-of-00010.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:7cc0fa844edcf1615d48e03618b5560d1911b1cdfabd653111d07e774e0601d6
size 1895878304

3
model-00007-of-00010.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:5135ba6925385812637f832cba04ca54f65a031ffb2d31dfd90814595e575923
size 1973531736

3
model-00008-of-00010.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:2915a9b4f00bc4cde9c21301d4be1974e3390de054da263a70eb4aa4e62e7350
size 1979781464

3
model-00009-of-00010.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:c172543bec78071369a1ad5539e378ce04d756c6de227ee6ada45d9f1c8270bf
size 1946243984

3
model-00010-of-00010.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a0177b0fe2d7adc655b15868da1451e9d3168b8e2edc1beec72da1f33014baaf
size 352338512

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": "<s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"eos_token": {
"content": "</s>",
"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
}
}

91122
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.

46
tokenizer_config.json Normal file
View File

@@ -0,0 +1,46 @@
{
"add_bos_token": true,
"add_eos_token": false,
"add_prefix_space": true,
"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
}
},
"additional_special_tokens": [],
"bos_token": "<s>",
"chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token}}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
"clean_up_tokenization_spaces": false,
"eos_token": "</s>",
"legacy": true,
"model_max_length": 32768,
"pad_token": "<unk>",
"padding_side": "right",
"sp_model_kwargs": {},
"spaces_between_special_tokens": false,
"tokenizer_class": "LlamaTokenizer",
"unk_token": "<unk>",
"use_default_system_prompt": false,
"use_fast": true
}