初始化项目，由ModelHub XC社区提供模型
Model: Inv/Konstanta-Alpha-V2-7B 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
|
||||
218
README.md
Normal file
218
README.md
Normal file
@@ -0,0 +1,218 @@
|
||||
---
|
||||
language:
|
||||
- en
|
||||
license: apache-2.0
|
||||
library_name: transformers
|
||||
tags:
|
||||
- mergekit
|
||||
- merge
|
||||
- mistralai/Mistral-7B-v0.1
|
||||
- SanjiWatsuki/Kunoichi-DPO-v2-7B
|
||||
- maywell/PiVoT-0.1-Evil-a
|
||||
- mlabonne/ArchBeagle-7B
|
||||
- LakoMoor/Silicon-Alice-7B
|
||||
- roleplay
|
||||
- rp
|
||||
- not-for-all-audiences
|
||||
base_model:
|
||||
- mistralai/Mistral-7B-v0.1
|
||||
- SanjiWatsuki/Kunoichi-DPO-v2-7B
|
||||
- maywell/PiVoT-0.1-Evil-a
|
||||
- mlabonne/ArchBeagle-7B
|
||||
- LakoMoor/Silicon-Alice-7B
|
||||
model-index:
|
||||
- name: Konstanta-Alpha-V2-7B
|
||||
results:
|
||||
- task:
|
||||
type: text-generation
|
||||
name: Text Generation
|
||||
dataset:
|
||||
name: AI2 Reasoning Challenge (25-Shot)
|
||||
type: ai2_arc
|
||||
config: ARC-Challenge
|
||||
split: test
|
||||
args:
|
||||
num_few_shot: 25
|
||||
metrics:
|
||||
- type: acc_norm
|
||||
value: 69.62
|
||||
name: normalized accuracy
|
||||
source:
|
||||
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Inv/Konstanta-Alpha-V2-7B
|
||||
name: Open LLM Leaderboard
|
||||
- task:
|
||||
type: text-generation
|
||||
name: Text Generation
|
||||
dataset:
|
||||
name: HellaSwag (10-Shot)
|
||||
type: hellaswag
|
||||
split: validation
|
||||
args:
|
||||
num_few_shot: 10
|
||||
metrics:
|
||||
- type: acc_norm
|
||||
value: 87.14
|
||||
name: normalized accuracy
|
||||
source:
|
||||
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Inv/Konstanta-Alpha-V2-7B
|
||||
name: Open LLM Leaderboard
|
||||
- task:
|
||||
type: text-generation
|
||||
name: Text Generation
|
||||
dataset:
|
||||
name: MMLU (5-Shot)
|
||||
type: cais/mmlu
|
||||
config: all
|
||||
split: test
|
||||
args:
|
||||
num_few_shot: 5
|
||||
metrics:
|
||||
- type: acc
|
||||
value: 65.11
|
||||
name: accuracy
|
||||
source:
|
||||
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Inv/Konstanta-Alpha-V2-7B
|
||||
name: Open LLM Leaderboard
|
||||
- task:
|
||||
type: text-generation
|
||||
name: Text Generation
|
||||
dataset:
|
||||
name: TruthfulQA (0-shot)
|
||||
type: truthful_qa
|
||||
config: multiple_choice
|
||||
split: validation
|
||||
args:
|
||||
num_few_shot: 0
|
||||
metrics:
|
||||
- type: mc2
|
||||
value: 61.08
|
||||
source:
|
||||
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Inv/Konstanta-Alpha-V2-7B
|
||||
name: Open LLM Leaderboard
|
||||
- task:
|
||||
type: text-generation
|
||||
name: Text Generation
|
||||
dataset:
|
||||
name: Winogrande (5-shot)
|
||||
type: winogrande
|
||||
config: winogrande_xl
|
||||
split: validation
|
||||
args:
|
||||
num_few_shot: 5
|
||||
metrics:
|
||||
- type: acc
|
||||
value: 81.22
|
||||
name: accuracy
|
||||
source:
|
||||
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Inv/Konstanta-Alpha-V2-7B
|
||||
name: Open LLM Leaderboard
|
||||
- task:
|
||||
type: text-generation
|
||||
name: Text Generation
|
||||
dataset:
|
||||
name: GSM8k (5-shot)
|
||||
type: gsm8k
|
||||
config: main
|
||||
split: test
|
||||
args:
|
||||
num_few_shot: 5
|
||||
metrics:
|
||||
- type: acc
|
||||
value: 69.9
|
||||
name: accuracy
|
||||
source:
|
||||
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Inv/Konstanta-Alpha-V2-7B
|
||||
name: Open LLM Leaderboard
|
||||
---
|
||||
# Konstanta-Alpha-V2-7B
|
||||
|
||||
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 DARE TIES to merge Kunoichi with PiVoT Evil and to merge ArchBeagle with Silicon Alice, and then merge the resulting 2 models with the gradient SLERP merge method. ChatML seems to work the best.
|
||||
### Models Merged
|
||||
|
||||
The following models were included in the merge:
|
||||
* [SanjiWatsuki/Kunoichi-DPO-v2-7B](https://huggingface.co/SanjiWatsuki/Kunoichi-DPO-v2-7B)
|
||||
* [maywell/PiVoT-0.1-Evil-a](https://huggingface.co/maywell/PiVoT-0.1-Evil-a)
|
||||
* [mlabonne/ArchBeagle-7B](https://huggingface.co/mlabonne/ArchBeagle-7B)
|
||||
* [LakoMoor/Silicon-Alice-7B](https://huggingface.co/LakoMoor/Silicon-Alice-7B)
|
||||
|
||||
### Configuration
|
||||
|
||||
The following YAML configuration was used to produce this model (to reproduce use mergekit-mega command):
|
||||
|
||||
```yaml
|
||||
base_model: mistralai/Mistral-7B-v0.1
|
||||
dtype: float16
|
||||
merge_method: dare_ties
|
||||
parameters:
|
||||
int8_mask: true
|
||||
slices:
|
||||
- sources:
|
||||
- layer_range: [0, 32]
|
||||
model: mistralai/Mistral-7B-v0.1
|
||||
- layer_range: [0, 32]
|
||||
model: : SanjiWatsuki/Kunoichi-DPO-v2-7B
|
||||
parameters:
|
||||
density: 0.8
|
||||
weight: 0.5
|
||||
- layer_range: [0, 32]
|
||||
model: : maywell/PiVoT-0.1-Evil-a
|
||||
parameters:
|
||||
density: 0.3
|
||||
weight: 0.15
|
||||
name: first-step
|
||||
---
|
||||
base_model: mistralai/Mistral-7B-v0.1
|
||||
dtype: float16
|
||||
merge_method: dare_ties
|
||||
parameters:
|
||||
int8_mask: true
|
||||
slices:
|
||||
- sources:
|
||||
- layer_range: [0, 32]
|
||||
model: mistralai/Mistral-7B-v0.1
|
||||
- layer_range: [0, 32]
|
||||
model: mlabonne/ArchBeagle-7B
|
||||
parameters:
|
||||
density: 0.8
|
||||
weight: 0.75
|
||||
- layer_range: [0, 32]
|
||||
model: LakoMoor/Silicon-Alice-7B
|
||||
parameters:
|
||||
density: 0.6
|
||||
weight: 0.30
|
||||
name: second-step
|
||||
---
|
||||
models:
|
||||
- model: first-step
|
||||
- model: second-step
|
||||
merge_method: slerp
|
||||
base_model: first-step
|
||||
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
|
||||
int8_mask: true
|
||||
normalize: true
|
||||
dtype: float16
|
||||
```
|
||||
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
||||
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_Inv__Konstanta-Alpha-V2-7B)
|
||||
|
||||
| Metric |Value|
|
||||
|---------------------------------|----:|
|
||||
|Avg. |72.35|
|
||||
|AI2 Reasoning Challenge (25-Shot)|69.62|
|
||||
|HellaSwag (10-Shot) |87.14|
|
||||
|MMLU (5-Shot) |65.11|
|
||||
|TruthfulQA (0-shot) |61.08|
|
||||
|Winogrande (5-shot) |81.22|
|
||||
|GSM8k (5-shot) |69.90|
|
||||
|
||||
25
config.json
Normal file
25
config.json
Normal file
@@ -0,0 +1,25 @@
|
||||
{
|
||||
"_name_or_path": "Konstanta-V2-Alpha-7B",
|
||||
"architectures": [
|
||||
"MistralForCausalLM"
|
||||
],
|
||||
"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": 32,
|
||||
"num_key_value_heads": 8,
|
||||
"rms_norm_eps": 1e-05,
|
||||
"rope_theta": 10000.0,
|
||||
"sliding_window": 4096,
|
||||
"tie_word_embeddings": false,
|
||||
"torch_dtype": "float16",
|
||||
"transformers_version": "4.35.2",
|
||||
"use_cache": true,
|
||||
"vocab_size": 32000
|
||||
}
|
||||
16
mergekit_config.yml
Normal file
16
mergekit_config.yml
Normal file
@@ -0,0 +1,16 @@
|
||||
|
||||
models:
|
||||
- model: /content/drive/MyDrive/output_model2/konstanta-first-step
|
||||
- model: /content/drive/MyDrive/output_model2/konstanta-second-step
|
||||
merge_method: slerp
|
||||
base_model: /content/drive/MyDrive/output_model2/konstanta-first-step
|
||||
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 # fallback for rest of tensors
|
||||
int8_mask: true
|
||||
normalize: true
|
||||
dtype: float16
|
||||
3
model-00001-of-00008.safetensors
Normal file
3
model-00001-of-00008.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:39cd0bd2a4b1e110ce224cdce85b0e8a921ee9f16f66d7d9f09a13ca08b09866
|
||||
size 1946210712
|
||||
3
model-00002-of-00008.safetensors
Normal file
3
model-00002-of-00008.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:bbe6bbb8f825bca3db8e9b45511aa4b8314d07469afa81423ee5a8c7bc83cb1b
|
||||
size 1912681080
|
||||
3
model-00003-of-00008.safetensors
Normal file
3
model-00003-of-00008.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:87b568eb3bfcf7b2e231599601c2877226a0ba783b9fc9eb9875668d848f826c
|
||||
size 1979781392
|
||||
3
model-00004-of-00008.safetensors
Normal file
3
model-00004-of-00008.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:a60c520ba9602ae10d38f19dc595fd7596971b7bf74a9237b4955c2f3bc820dd
|
||||
size 1979798504
|
||||
3
model-00005-of-00008.safetensors
Normal file
3
model-00005-of-00008.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:339f577eebb5778c5ca2fb59420e6c5d54a209d2b1cd3905a4a4e9d423b0ce70
|
||||
size 1889603616
|
||||
3
model-00006-of-00008.safetensors
Normal file
3
model-00006-of-00008.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:ca17aa52c7743564688a9837e3b9a6388ff76466245158af10d06ff9749d1199
|
||||
size 1973489704
|
||||
3
model-00007-of-00008.safetensors
Normal file
3
model-00007-of-00008.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:601ae631bca9ed36dbc3d71a869a5925dadb4d3f78e45e22b3453feb078c77a7
|
||||
size 1895903640
|
||||
3
model-00008-of-00008.safetensors
Normal file
3
model-00008-of-00008.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:0e9781fa7e9456709e384975a37b313871918941cd17b219a42bac224fad52b7
|
||||
size 906029072
|
||||
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": 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
|
||||
}
|
||||
}
|
||||
91122
tokenizer.json
Normal file
91122
tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
BIN
tokenizer.model
(Stored with Git LFS)
Normal file
BIN
tokenizer.model
(Stored with Git LFS)
Normal file
Binary file not shown.
40
tokenizer_config.json
Normal file
40
tokenizer_config.json
Normal file
@@ -0,0 +1,40 @@
|
||||
{
|
||||
"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>",
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "</s>",
|
||||
"legacy": true,
|
||||
"model_max_length": 1000000000000000019884624838656,
|
||||
"pad_token": null,
|
||||
"sp_model_kwargs": {},
|
||||
"spaces_between_special_tokens": false,
|
||||
"tokenizer_class": "LlamaTokenizer",
|
||||
"unk_token": "<unk>",
|
||||
"use_default_system_prompt": false
|
||||
}
|
||||
Reference in New Issue
Block a user