初始化项目，由ModelHub XC社区提供模型
Model: mncai/mistral-7b-dpo-v6 Source: Original Platform
This commit is contained in:
ModelHub XC
51
.gitattributes
vendored
Normal file
51
.gitattributes
vendored
Normal file
@@ -0,0 +1,51 @@
|
||||
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.bz2 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
|
||||
*.model filter=lfs diff=lfs merge=lfs -text
|
||||
*.msgpack 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
|
||||
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||
saved_model/**/* 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
|
||||
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||
*.zstandard filter=lfs diff=lfs merge=lfs -text
|
||||
*.tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
*.db* filter=lfs diff=lfs merge=lfs -text
|
||||
*.ark* filter=lfs diff=lfs merge=lfs -text
|
||||
**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
|
||||
**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
|
||||
**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
|
||||
|
||||
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||
*.gguf* filter=lfs diff=lfs merge=lfs -text
|
||||
*.ggml filter=lfs diff=lfs merge=lfs -text
|
||||
*.llamafile* filter=lfs diff=lfs merge=lfs -text
|
||||
*.pt2 filter=lfs diff=lfs merge=lfs -text
|
||||
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||
*.wasm 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
|
||||
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||
model-00002-of-00002.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
124
README.md
Normal file
124
README.md
Normal file
@@ -0,0 +1,124 @@
|
||||
---
|
||||
license: apache-2.0
|
||||
datasets:
|
||||
- Intel/orca_dpo_pairs
|
||||
language:
|
||||
- en
|
||||
---
|
||||
|
||||
# Model Card for mncai/mistral-7b-dpo-v6
|
||||
|
||||
### Introduction of MindsAndCompany
|
||||
|
||||
https://mnc.ai/
|
||||
|
||||
We create various AI models and develop solutions that can be applied to businesses. And as for generative AI, we are developing products like Code Assistant, TOD Chatbot, LLMOps, and are in the process of developing Enterprise AGI (Artificial General Intelligence).
|
||||
|
||||
### Model Summary
|
||||
based mistral-7b, dpo tuned.
|
||||
|
||||
### Detail
|
||||
|
||||
first step ties merge.
|
||||
```
|
||||
models:
|
||||
- model: AIDC-ai-business/Marcoroni-7B-v3
|
||||
# no parameters necessary for base model
|
||||
- model: GreenNode/GreenNodeLM-7B-v1olet # psmathur/orca_mini_v3_13b
|
||||
parameters:
|
||||
density: [1, 0.7, 0.1] # density gradient
|
||||
weight: 1.0
|
||||
- model: viethq188/LeoScorpius-7B-Chat-DPO
|
||||
parameters:
|
||||
density: 0.5
|
||||
weight: [0, 0.3, 0.7, 1] # weight gradient
|
||||
- model: mncai/mistral-7b-dpo-v5
|
||||
parameters:
|
||||
density: 0.33
|
||||
weight:
|
||||
- filter: mlp
|
||||
value: 0.5
|
||||
- value: 0
|
||||
merge_method: ties
|
||||
base_model: AIDC-ai-business/Marcoroni-7B-v3
|
||||
parameters:
|
||||
normalize: true
|
||||
int8_mask: true
|
||||
dtype: float16
|
||||
```
|
||||
second step dpo.
|
||||
```python
|
||||
# Training arguments
|
||||
training_args = TrainingArguments(
|
||||
per_device_train_batch_size=5,
|
||||
gradient_accumulation_steps=4,
|
||||
gradient_checkpointing=True,
|
||||
learning_rate=5e-6,
|
||||
lr_scheduler_type="cosine",
|
||||
max_steps=1000,
|
||||
save_strategy="no",
|
||||
logging_steps=1,
|
||||
output_dir=new_model,
|
||||
optim="paged_adamw_32bit",
|
||||
warmup_steps=100,
|
||||
bf16=True,
|
||||
report_to="wandb",
|
||||
)
|
||||
|
||||
# Create DPO trainer
|
||||
dpo_trainer = DPOTrainer(
|
||||
model,
|
||||
ref_model,
|
||||
args=training_args,
|
||||
train_dataset=dataset,
|
||||
tokenizer=tokenizer,
|
||||
# peft_config=peft_config,
|
||||
beta=0.1,
|
||||
max_prompt_length=1024,
|
||||
max_length=2048,
|
||||
)
|
||||
|
||||
# Fine-tune model with DPO
|
||||
dpo_trainer.train()
|
||||
```
|
||||
|
||||
|
||||
### How to Use
|
||||
Here give some examples of how to use our model.
|
||||
|
||||
```python
|
||||
from transformers import AutoConfig, AutoModel, AutoTokenizer
|
||||
import transformers
|
||||
import torch
|
||||
hf_model = 'mncai/mistral-7b-dpo-v6'
|
||||
message = "<|user|>\n두 개의 구가 있는데 각각 지름이 1, 2일때 구의 부피는 몇배 차이가 나지? 설명도 같이 해줘.\n<|assistant|>\n"
|
||||
|
||||
sequences = pipeline(
|
||||
message,
|
||||
do_sample=True,
|
||||
top_k=10,
|
||||
num_return_sequences=1,
|
||||
eos_token_id=tokenizer.eos_token_id,
|
||||
max_length=2048,
|
||||
)
|
||||
for seq in sequences:
|
||||
print(f"Result: {seq['generated_text']}")
|
||||
```
|
||||
|
||||
### Warnings
|
||||
Currently, the leaderboard is overfitted. It is inevitable because, unlike Kaggle, where there's private scoring followed by the end of the competition, here the scores are continuously open.
|
||||
Even among my models, some received lower scores in internal data evaluations. mncai/agiin-13.6B-v0.1 > mncai/agiin-11.1B-v0.1 > mncai/mistral-7b-dpo-v6. However, on the leaderboard, mncai/mistral-7b-dpo-v6 has the highest score.
|
||||
When choosing a model to use on the open LLM leaderboard, it would be best to evaluate with your own private dataset that is not publicly available.
|
||||
|
||||
### Detect-Pretrain-Code-Contamination Result Share
|
||||
|
||||
use https://github.com/Mihaiii/detect-pretrain-code-contamination
|
||||
|
||||
DATASET=truthful_qa
|
||||
python src/run.py --target_model mncai/mistral-7b-dpo-v6 --data $DATASET --output_dir out/$DATASET --ratio_gen 0.4
|
||||
|
||||
result < 0.1, %: 0.76
|
||||
|
||||
|
||||
### Contact
|
||||
If you have any questions, please raise an issue or contact us at dwmyoung@mnc.ai
|
||||
26
config.json
Normal file
26
config.json
Normal file
@@ -0,0 +1,26 @@
|
||||
{
|
||||
"_name_or_path": "mncai/mistral-7b-dpo-v6",
|
||||
"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": "bfloat16",
|
||||
"transformers_version": "4.35.2",
|
||||
"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}
|
||||
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:ff084805f3a21b19b4a87ab3ba580d11405fc017f630e6c2b92e0e7fe3a8c86c
|
||||
size 9942981496
|
||||
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 sha256:33e643cde13e2a4e68e6785b3d212f695653aa55fcf861a927a0367f346fc327
|
||||
size 4540516256
|
||||
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
28
special_tokens_map.json
Normal file
28
special_tokens_map.json
Normal file
@@ -0,0 +1,28 @@
|
||||
{
|
||||
"additional_special_tokens": [
|
||||
"<unk>",
|
||||
"<s>",
|
||||
"</s>"
|
||||
],
|
||||
"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
|
||||
}
|
||||
}
|
||||
BIN
tokenizer.json
(Stored with Git LFS)
Normal file
BIN
tokenizer.json
(Stored with Git LFS)
Normal file
Binary file not shown.
46
tokenizer_config.json
Normal file
46
tokenizer_config.json
Normal file
@@ -0,0 +1,46 @@
|
||||
{
|
||||
"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": [
|
||||
"<unk>",
|
||||
"<s>",
|
||||
"</s>"
|
||||
],
|
||||
"bos_token": "<s>",
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "</s>",
|
||||
"legacy": true,
|
||||
"model_max_length": 1000000000000000019884624838656,
|
||||
"pad_token": null,
|
||||
"padding_side": "left",
|
||||
"sp_model_kwargs": {},
|
||||
"spaces_between_special_tokens": false,
|
||||
"split_special_tokens": false,
|
||||
"tokenizer_class": "LlamaTokenizer",
|
||||
"unk_token": "<unk>",
|
||||
"use_default_system_prompt": true
|
||||
}
|
||||
Reference in New Issue
Block a user