初始化项目，由ModelHub XC社区提供模型
Model: rombodawg/Everyone-LLM-7b-Base 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
|
||||
242
README.md
Normal file
242
README.md
Normal file
@@ -0,0 +1,242 @@
|
||||
---
|
||||
license: unknown
|
||||
tags:
|
||||
- merge
|
||||
model-index:
|
||||
- name: Everyone-LLM-7b-Base
|
||||
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: 66.38
|
||||
name: normalized accuracy
|
||||
source:
|
||||
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=rombodawg/Everyone-LLM-7b-Base
|
||||
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: 86.02
|
||||
name: normalized accuracy
|
||||
source:
|
||||
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=rombodawg/Everyone-LLM-7b-Base
|
||||
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: 64.94
|
||||
name: accuracy
|
||||
source:
|
||||
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=rombodawg/Everyone-LLM-7b-Base
|
||||
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: 57.89
|
||||
source:
|
||||
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=rombodawg/Everyone-LLM-7b-Base
|
||||
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: 80.43
|
||||
name: accuracy
|
||||
source:
|
||||
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=rombodawg/Everyone-LLM-7b-Base
|
||||
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: 65.58
|
||||
name: accuracy
|
||||
source:
|
||||
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=rombodawg/Everyone-LLM-7b-Base
|
||||
name: Open LLM Leaderboard
|
||||
---
|
||||
Everyone-LLM-7b-Base
|
||||
|
||||
|
||||
|
||||
|
||||
EveryoneLLM series of models made by the community, for the community.
|
||||
|
||||
This is the first version of Everyone-LLM, a model that combines the power of the large majority of powerfull fine-tuned LLM's made by the community, to create a vast and knowledgable LLM with various abilities.
|
||||
|
||||
|
||||
Prompt template: Alpaca
|
||||
```
|
||||
Below is an instruction that describes a task. Write a response that appropriately completes the request.
|
||||
### Instruction:
|
||||
{prompt}
|
||||
### Response:
|
||||
```
|
||||
|
||||
The models that were used in this merger were as follow:
|
||||
|
||||
- https://huggingface.co/cognitivecomputations/dolphin-2.6-mistral-7b-dpo
|
||||
|
||||
- https://huggingface.co/jondurbin/bagel-dpo-7b-v0.4
|
||||
|
||||
- https://huggingface.co/Locutusque/Hercules-2.0-Mistral-7B
|
||||
|
||||
|
||||
- https://huggingface.co/Open-Orca/Mistral-7B-OpenOrca
|
||||
|
||||
- https://huggingface.co/teknium/OpenHermes-2.5-Mistral-7B
|
||||
|
||||
- https://huggingface.co/NousResearch/Nous-Capybara-7B-V1.9
|
||||
|
||||
- https://huggingface.co/Intel/neural-chat-7b-v3-3
|
||||
|
||||
- https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2
|
||||
|
||||
- https://huggingface.co/senseable/WestLake-7B-v2
|
||||
|
||||
- https://huggingface.co/defog/sqlcoder-7b
|
||||
|
||||
- https://huggingface.co/meta-math/MetaMath-Mistral-7B
|
||||
|
||||
- https://huggingface.co/nextai-team/apollo-v1-7b
|
||||
|
||||
- https://huggingface.co/WizardLM/WizardMath-7B-V1.1
|
||||
|
||||
- https://huggingface.co/openchat/openchat-3.5-0106
|
||||
|
||||
- https://huggingface.co/mistralai/Mistral-7B-v0.1
|
||||
|
||||
Thank you to the creators of the above ai models, they have full credit for the EveryoneLLM series of models. Without their hard work we wouldnt be able to achieve the great success we have in the open source community. 💗
|
||||
|
||||
You can find the write up for merging models here:
|
||||
|
||||
https://docs.google.com/document/d/1_vOftBnrk9NRk5h10UqrfJ5CDih9KBKL61yvrZtVWPE/edit?usp=sharing
|
||||
|
||||
|
||||
# Open LLM Leaderboard Scores
|
||||
```
|
||||
| Model | Average | ARC | HellaSwag | MMLU | TruthfulQA | Winogrande | GSM8K |
|
||||
|------------------------------------|---------|---------|-----------|---------|------------|------------|---------|
|
||||
| rombodawg/Everyone-LLM-7b-Base | 70.21 | 66.38 | 86.02 | 64.94 | 57.89 | 80.43 | 65.58 |
|
||||
```
|
||||
|
||||
Config for the merger can be found bellow:
|
||||
|
||||
```yaml
|
||||
models:
|
||||
- model: cognitivecomputations_dolphin-2.6-mistral-7b-dpo
|
||||
parameters:
|
||||
weight: 1
|
||||
- model: jondurbin_bagel-dpo-7b-v0.4
|
||||
parameters:
|
||||
weight: 1
|
||||
- model: Locutusque_Hercules-2.0-Mistral-7B
|
||||
parameters:
|
||||
weight: 1
|
||||
- model: Open-Orca_Mistral-7B-OpenOrca
|
||||
parameters:
|
||||
weight: 1
|
||||
- model: teknium_OpenHermes-2.5-Mistral-7B
|
||||
parameters:
|
||||
weight: 1
|
||||
- model: NousResearch_Nous-Capybara-7B-V1.9
|
||||
|
||||
parameters:
|
||||
weight: 1
|
||||
- model: Intel_neural-chat-7b-v3-3
|
||||
parameters:
|
||||
weight: 1
|
||||
- model: mistralai_Mistral-7B-Instruct-v0.2
|
||||
parameters:
|
||||
weight: 1
|
||||
- model: senseable_WestLake-7B-v2
|
||||
parameters:
|
||||
weight: 1
|
||||
- model: defog_sqlcoder-7b
|
||||
parameters:
|
||||
weight: 1
|
||||
- model: meta-math_MetaMath-Mistral-7B
|
||||
parameters:
|
||||
weight: 1
|
||||
- model: nextai-team_apollo-v1-7b
|
||||
parameters:
|
||||
weight: 1
|
||||
- model: WizardLM_WizardMath-7B-V1.1
|
||||
parameters:
|
||||
weight: 1
|
||||
- model: openchat_openchat-3.5-0106
|
||||
parameters:
|
||||
weight: 1
|
||||
merge_method: task_arithmetic
|
||||
base_model: mistralai_Mistral-7B-v0.1
|
||||
parameters:
|
||||
normalize: true
|
||||
int8_mask: 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_rombodawg__Everyone-LLM-7b-Base)
|
||||
|
||||
| Metric |Value|
|
||||
|---------------------------------|----:|
|
||||
|Avg. |70.21|
|
||||
|AI2 Reasoning Challenge (25-Shot)|66.38|
|
||||
|HellaSwag (10-Shot) |86.02|
|
||||
|MMLU (5-Shot) |64.94|
|
||||
|TruthfulQA (0-shot) |57.89|
|
||||
|Winogrande (5-shot) |80.43|
|
||||
|GSM8k (5-shot) |65.58|
|
||||
|
||||
26
config.json
Normal file
26
config.json
Normal file
@@ -0,0 +1,26 @@
|
||||
{
|
||||
"_name_or_path": "Everyone-LLM-7b",
|
||||
"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": 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": "4.36.2",
|
||||
"use_cache": true,
|
||||
"vocab_size": 32000
|
||||
}
|
||||
6
generation_config.json
Normal file
6
generation_config.json
Normal file
@@ -0,0 +1,6 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 1,
|
||||
"eos_token_id": 2,
|
||||
"transformers_version": "4.34.0.dev0"
|
||||
}
|
||||
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:b1696b00f3c924ff7e9073262649d8f9b6c1be8049ecd57a01629132cb388840
|
||||
size 9976543880
|
||||
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:ffed85d649df653919149f84133ab40006b6fa343b8e01620772086b32b1879e
|
||||
size 4506953872
|
||||
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
5
special_tokens_map.json
Normal file
5
special_tokens_map.json
Normal file
@@ -0,0 +1,5 @@
|
||||
{
|
||||
"bos_token": "<s>",
|
||||
"eos_token": "</s>",
|
||||
"unk_token": "<unk>"
|
||||
}
|
||||
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.
42
tokenizer_config.json
Normal file
42
tokenizer_config.json
Normal file
@@ -0,0 +1,42 @@
|
||||
{
|
||||
"add_bos_token": true,
|
||||
"add_eos_token": false,
|
||||
"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