初始化项目，由ModelHub XC社区提供模型
Model: FallenMerick/Chunky-Lemon-Cookie-11B 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
|
||||
BIN
Chunky-Lemon-Cookie.png
Normal file
BIN
Chunky-Lemon-Cookie.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 722 KiB |
207
README.md
Normal file
207
README.md
Normal file
@@ -0,0 +1,207 @@
|
||||
---
|
||||
license: cc-by-4.0
|
||||
language:
|
||||
- en
|
||||
base_model:
|
||||
- mistralai/Mistral-7B-v0.1
|
||||
- SanjiWatsuki/Kunoichi-7B
|
||||
- SanjiWatsuki/Silicon-Maid-7B
|
||||
- KatyTheCutie/LemonadeRP-4.5.3
|
||||
- Sao10K/Fimbulvetr-11B-v2
|
||||
library_name: transformers
|
||||
tags:
|
||||
- mergekit
|
||||
- merge
|
||||
- mistral
|
||||
- text-generation
|
||||
- roleplay
|
||||
model-index:
|
||||
- name: Smart-Lemon-Cookie-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=FallenMerick/Chunky-Lemon-Cookie-11B
|
||||
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: 86.55
|
||||
name: normalized accuracy
|
||||
source:
|
||||
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=FallenMerick/Chunky-Lemon-Cookie-11B
|
||||
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: 65.35
|
||||
name: accuracy
|
||||
source:
|
||||
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=FallenMerick/Chunky-Lemon-Cookie-11B
|
||||
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: 61.59
|
||||
source:
|
||||
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=FallenMerick/Chunky-Lemon-Cookie-11B
|
||||
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: 79.79
|
||||
name: accuracy
|
||||
source:
|
||||
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=FallenMerick/Chunky-Lemon-Cookie-11B
|
||||
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: 58.45
|
||||
name: accuracy
|
||||
source:
|
||||
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=FallenMerick/Chunky-Lemon-Cookie-11B
|
||||
name: Open LLM Leaderboard
|
||||
---
|
||||
|
||||
|
||||
|
||||
# Chunky-Lemon-Cookie-11B
|
||||
|
||||
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
|
||||
|
||||
GGUF quants:
|
||||
* https://huggingface.co/backyardai/Chunky-Lemon-Cookie-11B-GGUF
|
||||
* https://huggingface.co/mradermacher/Chunky-Lemon-Cookie-11B-GGUF
|
||||
|
||||
## Merge Details
|
||||
### Merge Method
|
||||
|
||||
This model was merged using the following methods:
|
||||
* passthrough
|
||||
* [task arithmetic](https://arxiv.org/abs/2212.04089)
|
||||
|
||||
### Models Merged
|
||||
|
||||
The following models were included in the merge:
|
||||
* [SanjiWatsuki/Kunoichi-7B](https://huggingface.co/SanjiWatsuki/Kunoichi-7B)
|
||||
* [SanjiWatsuki/Silicon-Maid-7B](https://huggingface.co/SanjiWatsuki/Silicon-Maid-7B)
|
||||
* [KatyTheCutie/LemonadeRP-4.5.3](https://huggingface.co/KatyTheCutie/LemonadeRP-4.5.3)
|
||||
* [Sao10K/Fimbulvetr-11B-v2](https://huggingface.co/Sao10K/Fimbulvetr-11B-v2)
|
||||
* [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1)
|
||||
|
||||
### Configuration
|
||||
|
||||
The following YAML configurations were used to produce this model:
|
||||
|
||||
```yaml
|
||||
slices:
|
||||
- sources:
|
||||
- model: mistralai/Mistral-7B-v0.1
|
||||
layer_range: [0, 24]
|
||||
- sources:
|
||||
- model: mistralai/Mistral-7B-v0.1
|
||||
layer_range: [8, 32]
|
||||
merge_method: passthrough
|
||||
dtype: float16
|
||||
name: Mistral-11B
|
||||
|
||||
---
|
||||
|
||||
slices:
|
||||
- sources:
|
||||
- model: SanjiWatsuki/Kunoichi-7B
|
||||
layer_range: [0, 24]
|
||||
- sources:
|
||||
- model: SanjiWatsuki/Silicon-Maid-7B
|
||||
layer_range: [8, 24]
|
||||
- sources:
|
||||
- model: KatyTheCutie/LemonadeRP-4.5.3
|
||||
layer_range: [24, 32]
|
||||
merge_method: passthrough
|
||||
dtype: float16
|
||||
name: Big-Lemon-Cookie-11B
|
||||
|
||||
---
|
||||
|
||||
models:
|
||||
- model: Big-Lemon-Cookie-11B
|
||||
parameters:
|
||||
weight: 0.85
|
||||
- model: Sao10K/Fimbulvetr-11B-v2
|
||||
parameters:
|
||||
weight: 0.15
|
||||
merge_method: task_arithmetic
|
||||
base_model: Mistral-11B
|
||||
dtype: float16
|
||||
name: Chunky-Lemon-Cookie-11B
|
||||
```
|
||||
|
||||
# [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_FallenMerick__Chunky-Lemon-Cookie-11B)
|
||||
|
||||
| Metric |Value|
|
||||
|---------------------------------|----:|
|
||||
|Avg. |70.23|
|
||||
|AI2 Reasoning Challenge (25-Shot)|69.62|
|
||||
|HellaSwag (10-Shot) |86.55|
|
||||
|MMLU (5-Shot) |65.35|
|
||||
|TruthfulQA (0-shot) |61.59|
|
||||
|Winogrande (5-shot) |79.79|
|
||||
|GSM8k (5-shot) |58.45|
|
||||
26
config.json
Normal file
26
config.json
Normal file
@@ -0,0 +1,26 @@
|
||||
{
|
||||
"_name_or_path": "Chunky-Lemon-Cookie-11B",
|
||||
"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": 48,
|
||||
"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": "4.40.1",
|
||||
"use_cache": true,
|
||||
"vocab_size": 32000
|
||||
}
|
||||
40
mergekit_config.yml
Normal file
40
mergekit_config.yml
Normal file
@@ -0,0 +1,40 @@
|
||||
slices:
|
||||
- sources:
|
||||
- model: mistralai/Mistral-7B-v0.1
|
||||
layer_range: [0, 24]
|
||||
- sources:
|
||||
- model: mistralai/Mistral-7B-v0.1
|
||||
layer_range: [8, 32]
|
||||
merge_method: passthrough
|
||||
dtype: float16
|
||||
name: Mistral-11B
|
||||
|
||||
---
|
||||
|
||||
slices:
|
||||
- sources:
|
||||
- model: SanjiWatsuki/Kunoichi-7B
|
||||
layer_range: [0, 24]
|
||||
- sources:
|
||||
- model: SanjiWatsuki/Silicon-Maid-7B
|
||||
layer_range: [8, 24]
|
||||
- sources:
|
||||
- model: KatyTheCutie/LemonadeRP-4.5.3
|
||||
layer_range: [24, 32]
|
||||
merge_method: passthrough
|
||||
dtype: float16
|
||||
name: Big-Lemon-Cookie-11B
|
||||
|
||||
---
|
||||
|
||||
models:
|
||||
- model: Big-Lemon-Cookie-11B
|
||||
parameters:
|
||||
weight: 0.85
|
||||
- model: Sao10K/Fimbulvetr-11B-v2
|
||||
parameters:
|
||||
weight: 0.15
|
||||
merge_method: task_arithmetic
|
||||
base_model: Mistral-11B
|
||||
dtype: float16
|
||||
name: Chunky-Lemon-Cookie-11B
|
||||
3
model-00001-of-00005.safetensors
Normal file
3
model-00001-of-00005.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:4e9a1b1b85e8681999c037eb70fce68da30e9665baf5909152a9c5221b5afe40
|
||||
size 4886546912
|
||||
3
model-00002-of-00005.safetensors
Normal file
3
model-00002-of-00005.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:8072382205d543191f337e90bd8fe0ceb52bf8b46eea635b5a7e27a3886d4513
|
||||
size 4915916080
|
||||
3
model-00003-of-00005.safetensors
Normal file
3
model-00003-of-00005.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:ccd692a264a6b0dbc5a3db0b1cdb7e0bcb5da8771961f76acdb53a5f4d502a94
|
||||
size 4915916080
|
||||
3
model-00004-of-00005.safetensors
Normal file
3
model-00004-of-00005.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:b6fb350128b760710da47534ea97275ab26a23b32dcb36e15f2c1245fdfe343d
|
||||
size 4999819224
|
||||
3
model-00005-of-00005.safetensors
Normal file
3
model-00005-of-00005.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:19d217fbe716563e3b2c0d63908b0e878f9fb21079db1ab25cd898dc6258848b
|
||||
size 1744900112
|
||||
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
|
||||
}
|
||||
}
|
||||
91123
tokenizer.json
Normal file
91123
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