初始化项目，由ModelHub XC社区提供模型
Model: arcee-ai/patent-evol-merge Source: Original Platform
This commit is contained in:
ModelHub XC
37
.gitattributes
vendored
Normal file
37
.gitattributes
vendored
Normal file
@@ -0,0 +1,37 @@
|
||||
*.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-00002.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
model-00002-of-00002.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
97
README.md
Normal file
97
README.md
Normal file
@@ -0,0 +1,97 @@
|
||||
---
|
||||
base_model: []
|
||||
library_name: transformers
|
||||
tags:
|
||||
- mergekit
|
||||
- merge
|
||||
|
||||
---
|
||||
# best_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 [task arithmetic](https://arxiv.org/abs/2212.04089) merge method using /root/evol_merge_storage/input_models/Llama-2-7B-fp16_227878287 as a base.
|
||||
|
||||
### Models Merged
|
||||
|
||||
The following models were included in the merge:
|
||||
* /root/evol_merge_storage/input_models/Patent-Instruct-7b_60368649
|
||||
* /root/evol_merge_storage/input_models/Orca-2-7b_2312263870
|
||||
* /root/evol_merge_storage/input_models/Barcenas-Orca-2-7b_1478912867
|
||||
|
||||
### Configuration
|
||||
|
||||
The following YAML configuration was used to produce this model:
|
||||
|
||||
```yaml
|
||||
base_model: /root/evol_merge_storage/input_models/Llama-2-7B-fp16_227878287
|
||||
dtype: bfloat16
|
||||
merge_method: task_arithmetic
|
||||
parameters:
|
||||
int8_mask: 1.0
|
||||
normalize: 0.0
|
||||
slices:
|
||||
- sources:
|
||||
- layer_range: [0, 8]
|
||||
model: /root/evol_merge_storage/input_models/Patent-Instruct-7b_60368649
|
||||
parameters:
|
||||
weight: 0.12964183139810131
|
||||
- layer_range: [0, 8]
|
||||
model: /root/evol_merge_storage/input_models/Barcenas-Orca-2-7b_1478912867
|
||||
parameters:
|
||||
weight: 0.6876744008045087
|
||||
- layer_range: [0, 8]
|
||||
model: /root/evol_merge_storage/input_models/Orca-2-7b_2312263870
|
||||
parameters:
|
||||
weight: 0.04984086375373306
|
||||
- layer_range: [0, 8]
|
||||
model: /root/evol_merge_storage/input_models/Llama-2-7B-fp16_227878287
|
||||
- sources:
|
||||
- layer_range: [8, 16]
|
||||
model: /root/evol_merge_storage/input_models/Patent-Instruct-7b_60368649
|
||||
parameters:
|
||||
weight: 0.4744102649337617
|
||||
- layer_range: [8, 16]
|
||||
model: /root/evol_merge_storage/input_models/Barcenas-Orca-2-7b_1478912867
|
||||
parameters:
|
||||
weight: 0.00040582065232951103
|
||||
- layer_range: [8, 16]
|
||||
model: /root/evol_merge_storage/input_models/Orca-2-7b_2312263870
|
||||
parameters:
|
||||
weight: 1.1436607369426315
|
||||
- layer_range: [8, 16]
|
||||
model: /root/evol_merge_storage/input_models/Llama-2-7B-fp16_227878287
|
||||
- sources:
|
||||
- layer_range: [16, 24]
|
||||
model: /root/evol_merge_storage/input_models/Patent-Instruct-7b_60368649
|
||||
parameters:
|
||||
weight: 0.3615157971780197
|
||||
- layer_range: [16, 24]
|
||||
model: /root/evol_merge_storage/input_models/Barcenas-Orca-2-7b_1478912867
|
||||
parameters:
|
||||
weight: 0.11547324542144169
|
||||
- layer_range: [16, 24]
|
||||
model: /root/evol_merge_storage/input_models/Orca-2-7b_2312263870
|
||||
parameters:
|
||||
weight: 0.773494346001556
|
||||
- layer_range: [16, 24]
|
||||
model: /root/evol_merge_storage/input_models/Llama-2-7B-fp16_227878287
|
||||
- sources:
|
||||
- layer_range: [24, 32]
|
||||
model: /root/evol_merge_storage/input_models/Patent-Instruct-7b_60368649
|
||||
parameters:
|
||||
weight: 0.027506217667945004
|
||||
- layer_range: [24, 32]
|
||||
model: /root/evol_merge_storage/input_models/Barcenas-Orca-2-7b_1478912867
|
||||
parameters:
|
||||
weight: 0.4112043376249425
|
||||
- layer_range: [24, 32]
|
||||
model: /root/evol_merge_storage/input_models/Orca-2-7b_2312263870
|
||||
parameters:
|
||||
weight: 0.48967743702922145
|
||||
- layer_range: [24, 32]
|
||||
model: /root/evol_merge_storage/input_models/Llama-2-7B-fp16_227878287
|
||||
```
|
||||
29
config.json
Normal file
29
config.json
Normal file
@@ -0,0 +1,29 @@
|
||||
{
|
||||
"_name_or_path": "/root/evol_merge_storage/input_models/Llama-2-7B-fp16_227878287",
|
||||
"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": 4096,
|
||||
"model_type": "llama",
|
||||
"num_attention_heads": 32,
|
||||
"num_hidden_layers": 32,
|
||||
"num_key_value_heads": 32,
|
||||
"pad_token_id": 0,
|
||||
"pretraining_tp": 1,
|
||||
"rms_norm_eps": 1e-05,
|
||||
"rope_scaling": null,
|
||||
"rope_theta": 10000.0,
|
||||
"tie_word_embeddings": false,
|
||||
"torch_dtype": "bfloat16",
|
||||
"transformers_version": "4.39.3",
|
||||
"use_cache": true,
|
||||
"vocab_size": 32000
|
||||
}
|
||||
1
configuration.json
Normal file
1
configuration.json
Normal file
@@ -0,0 +1 @@
|
||||
{"framework": "pytorch", "task": "text-generation", "allow_remote": true}
|
||||
3193
eval_results.json
Normal file
3193
eval_results.json
Normal file
File diff suppressed because it is too large
Load Diff
67
mergekit_config.yml
Normal file
67
mergekit_config.yml
Normal file
@@ -0,0 +1,67 @@
|
||||
base_model: /root/evol_merge_storage/input_models/Llama-2-7B-fp16_227878287
|
||||
dtype: bfloat16
|
||||
merge_method: task_arithmetic
|
||||
parameters:
|
||||
int8_mask: 1.0
|
||||
normalize: 0.0
|
||||
slices:
|
||||
- sources:
|
||||
- layer_range: [0, 8]
|
||||
model: /root/evol_merge_storage/input_models/Patent-Instruct-7b_60368649
|
||||
parameters:
|
||||
weight: 0.12964183139810131
|
||||
- layer_range: [0, 8]
|
||||
model: /root/evol_merge_storage/input_models/Barcenas-Orca-2-7b_1478912867
|
||||
parameters:
|
||||
weight: 0.6876744008045087
|
||||
- layer_range: [0, 8]
|
||||
model: /root/evol_merge_storage/input_models/Orca-2-7b_2312263870
|
||||
parameters:
|
||||
weight: 0.04984086375373306
|
||||
- layer_range: [0, 8]
|
||||
model: /root/evol_merge_storage/input_models/Llama-2-7B-fp16_227878287
|
||||
- sources:
|
||||
- layer_range: [8, 16]
|
||||
model: /root/evol_merge_storage/input_models/Patent-Instruct-7b_60368649
|
||||
parameters:
|
||||
weight: 0.4744102649337617
|
||||
- layer_range: [8, 16]
|
||||
model: /root/evol_merge_storage/input_models/Barcenas-Orca-2-7b_1478912867
|
||||
parameters:
|
||||
weight: 0.00040582065232951103
|
||||
- layer_range: [8, 16]
|
||||
model: /root/evol_merge_storage/input_models/Orca-2-7b_2312263870
|
||||
parameters:
|
||||
weight: 1.1436607369426315
|
||||
- layer_range: [8, 16]
|
||||
model: /root/evol_merge_storage/input_models/Llama-2-7B-fp16_227878287
|
||||
- sources:
|
||||
- layer_range: [16, 24]
|
||||
model: /root/evol_merge_storage/input_models/Patent-Instruct-7b_60368649
|
||||
parameters:
|
||||
weight: 0.3615157971780197
|
||||
- layer_range: [16, 24]
|
||||
model: /root/evol_merge_storage/input_models/Barcenas-Orca-2-7b_1478912867
|
||||
parameters:
|
||||
weight: 0.11547324542144169
|
||||
- layer_range: [16, 24]
|
||||
model: /root/evol_merge_storage/input_models/Orca-2-7b_2312263870
|
||||
parameters:
|
||||
weight: 0.773494346001556
|
||||
- layer_range: [16, 24]
|
||||
model: /root/evol_merge_storage/input_models/Llama-2-7B-fp16_227878287
|
||||
- sources:
|
||||
- layer_range: [24, 32]
|
||||
model: /root/evol_merge_storage/input_models/Patent-Instruct-7b_60368649
|
||||
parameters:
|
||||
weight: 0.027506217667945004
|
||||
- layer_range: [24, 32]
|
||||
model: /root/evol_merge_storage/input_models/Barcenas-Orca-2-7b_1478912867
|
||||
parameters:
|
||||
weight: 0.4112043376249425
|
||||
- layer_range: [24, 32]
|
||||
model: /root/evol_merge_storage/input_models/Orca-2-7b_2312263870
|
||||
parameters:
|
||||
weight: 0.48967743702922145
|
||||
- layer_range: [24, 32]
|
||||
model: /root/evol_merge_storage/input_models/Llama-2-7B-fp16_227878287
|
||||
3
model-00001-of-00002.safetensors
Normal file
3
model-00001-of-00002.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:3671629e9f42bc8f1af9ecc604ba1d66dd33a7907b20f0ac8b4318c3888bfca8
|
||||
size 9924132872
|
||||
3
model-00002-of-00002.safetensors
Normal file
3
model-00002-of-00002.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:ab857c3306d002aa9a886aa27833d20911ad14879caa861a1e522b040fe38ee9
|
||||
size 3552732192
|
||||
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
23
special_tokens_map.json
Normal file
23
special_tokens_map.json
Normal file
@@ -0,0 +1,23 @@
|
||||
{
|
||||
"bos_token": {
|
||||
"content": "<s>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"eos_token": {
|
||||
"content": "</s>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"unk_token": {
|
||||
"content": "<unk>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
93391
tokenizer.json
Normal file
93391
tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
3
tokenizer.model
Normal file
3
tokenizer.model
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
||||
size 499723
|
||||
39
tokenizer_config.json
Normal file
39
tokenizer_config.json
Normal file
@@ -0,0 +1,39 @@
|
||||
{
|
||||
"add_bos_token": true,
|
||||
"add_eos_token": false,
|
||||
"added_tokens_decoder": {
|
||||
"0": {
|
||||
"content": "<unk>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"1": {
|
||||
"content": "<s>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"2": {
|
||||
"content": "</s>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
}
|
||||
},
|
||||
"bos_token": "<s>",
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "</s>",
|
||||
"model_max_length": 1000000000000000019884624838656,
|
||||
"pad_token": null,
|
||||
"sp_model_kwargs": {},
|
||||
"tokenizer_class": "LlamaTokenizer",
|
||||
"unk_token": "<unk>",
|
||||
"use_default_system_prompt": false
|
||||
}
|
||||
Reference in New Issue
Block a user