初始化项目，由ModelHub XC社区提供模型
Model: Alelcv27/Minerva-7B-Breadcrumbs-Math-French Source: Original Platform
This commit is contained in:
ModelHub XC
35
.gitattributes
vendored
Normal file
35
.gitattributes
vendored
Normal 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
|
||||
53
README.md
Normal file
53
README.md
Normal file
@@ -0,0 +1,53 @@
|
||||
---
|
||||
base_model:
|
||||
- Alelcv27/Minerva-7B-French-v2
|
||||
- Alelcv27/Minerva-7B-Math-v2
|
||||
- sapienzanlp/Minerva-7B-instruct-v1.0
|
||||
library_name: transformers
|
||||
tags:
|
||||
- mergekit
|
||||
- merge
|
||||
|
||||
---
|
||||
# Minerva-7B-Breadcrumbs-Math-French
|
||||
|
||||
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 [Model Breadcrumbs](https://arxiv.org/abs/2312.06795) merge method using [sapienzanlp/Minerva-7B-instruct-v1.0](https://huggingface.co/sapienzanlp/Minerva-7B-instruct-v1.0) as a base.
|
||||
|
||||
### Models Merged
|
||||
|
||||
The following models were included in the merge:
|
||||
* [Alelcv27/Minerva-7B-French-v2](https://huggingface.co/Alelcv27/Minerva-7B-French-v2)
|
||||
* [Alelcv27/Minerva-7B-Math-v2](https://huggingface.co/Alelcv27/Minerva-7B-Math-v2)
|
||||
|
||||
### Configuration
|
||||
|
||||
The following YAML configuration was used to produce this model:
|
||||
|
||||
```yaml
|
||||
base_model: sapienzanlp/Minerva-7B-instruct-v1.0
|
||||
dtype: float16
|
||||
merge_method: breadcrumbs
|
||||
modules:
|
||||
default:
|
||||
slices:
|
||||
- sources:
|
||||
- layer_range: [0, 32]
|
||||
model: Alelcv27/Minerva-7B-French-v2
|
||||
parameters:
|
||||
weight: 0.8
|
||||
- layer_range: [0, 32]
|
||||
model: Alelcv27/Minerva-7B-Math-v2
|
||||
parameters:
|
||||
weight: 0.8
|
||||
- layer_range: [0, 32]
|
||||
model: sapienzanlp/Minerva-7B-instruct-v1.0
|
||||
parameters:
|
||||
density: 0.9
|
||||
gamma: 0.01
|
||||
normalize: 1.0
|
||||
```
|
||||
29
config.json
Normal file
29
config.json
Normal file
@@ -0,0 +1,29 @@
|
||||
{
|
||||
"architectures": [
|
||||
"MistralForCausalLM"
|
||||
],
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 1,
|
||||
"dtype": "float16",
|
||||
"eos_token_id": [
|
||||
2,
|
||||
51202
|
||||
],
|
||||
"head_dim": 128,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 4096,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 14336,
|
||||
"max_position_embeddings": 4096,
|
||||
"model_type": "mistral",
|
||||
"num_attention_heads": 32,
|
||||
"num_hidden_layers": 32,
|
||||
"num_key_value_heads": 8,
|
||||
"rms_norm_eps": 1e-05,
|
||||
"rope_theta": 10000.0,
|
||||
"sliding_window": null,
|
||||
"tie_word_embeddings": false,
|
||||
"transformers_version": "4.57.1",
|
||||
"use_cache": false,
|
||||
"vocab_size": 51264
|
||||
}
|
||||
21
mergekit_config.yml
Normal file
21
mergekit_config.yml
Normal file
@@ -0,0 +1,21 @@
|
||||
base_model: sapienzanlp/Minerva-7B-instruct-v1.0
|
||||
dtype: float16
|
||||
merge_method: breadcrumbs
|
||||
modules:
|
||||
default:
|
||||
slices:
|
||||
- sources:
|
||||
- layer_range: [0, 32]
|
||||
model: Alelcv27/Minerva-7B-French-v2
|
||||
parameters:
|
||||
weight: 0.8
|
||||
- layer_range: [0, 32]
|
||||
model: Alelcv27/Minerva-7B-Math-v2
|
||||
parameters:
|
||||
weight: 0.8
|
||||
- layer_range: [0, 32]
|
||||
model: sapienzanlp/Minerva-7B-instruct-v1.0
|
||||
parameters:
|
||||
density: 0.9
|
||||
gamma: 0.01
|
||||
normalize: 1.0
|
||||
3
model-00001-of-00003.safetensors
Normal file
3
model-00001-of-00003.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:4cacde5f700f646248b605e6d32a18039cb255a2dd436239642cfa66b272ce00
|
||||
size 4883383888
|
||||
3
model-00002-of-00003.safetensors
Normal file
3
model-00002-of-00003.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:48161fbc0a2ee5838ec41cb8c79e426ae171df47f5a87adb5cdb1687eb40478c
|
||||
size 4915916080
|
||||
3
model-00003-of-00003.safetensors
Normal file
3
model-00003-of-00003.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:1d1999453605bf32d64f883cc037f2a8b252b1fae338471835d5a166c08a8485
|
||||
size 4999819160
|
||||
1
model.safetensors.index.json
Normal file
1
model.safetensors.index.json
Normal file
File diff suppressed because one or more lines are too long
35
special_tokens_map.json
Normal file
35
special_tokens_map.json
Normal file
@@ -0,0 +1,35 @@
|
||||
{
|
||||
"additional_special_tokens": [
|
||||
"<|start_header_id|>",
|
||||
"<|end_header_id|>",
|
||||
"<|eot_id|>"
|
||||
],
|
||||
"bos_token": {
|
||||
"content": "<s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"eos_token": {
|
||||
"content": "<|eot_id|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": {
|
||||
"content": "<|eot_id|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"unk_token": {
|
||||
"content": "<unk>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
255169
tokenizer.json
Normal file
255169
tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
73
tokenizer_config.json
Normal file
73
tokenizer_config.json
Normal file
@@ -0,0 +1,73 @@
|
||||
{
|
||||
"add_bos_token": true,
|
||||
"add_eos_token": false,
|
||||
"add_prefix_space": null,
|
||||
"added_tokens_decoder": {
|
||||
"0": {
|
||||
"content": "<s>",
|
||||
"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": "<unk>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"51200": {
|
||||
"content": "<|start_header_id|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"51201": {
|
||||
"content": "<|end_header_id|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"51202": {
|
||||
"content": "<|eot_id|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
}
|
||||
},
|
||||
"additional_special_tokens": [
|
||||
"<|start_header_id|>",
|
||||
"<|end_header_id|>",
|
||||
"<|eot_id|>"
|
||||
],
|
||||
"bos_token": "<s>",
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "<|eot_id|>",
|
||||
"legacy": true,
|
||||
"model_max_length": 4096,
|
||||
"pad_token": "<|eot_id|>",
|
||||
"padding_side": "right",
|
||||
"split_special_tokens": false,
|
||||
"tokenizer_class": "LlamaTokenizer",
|
||||
"unk_token": "<unk>",
|
||||
"use_default_system_prompt": false,
|
||||
"vocab_size": 51200,
|
||||
"chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}"
|
||||
}
|
||||
Reference in New Issue
Block a user