Edentns/DataVortexS-10.7B-dpo-v1.11

Model

4

stars

5

commits

1

repos using this model

2

linked in READMEs

Feb 24, 2024

updated

endpoints_compatible
llama
safetensors
text-generation
text-generation-inference
transformers

README

DataVortexS-10.7B-dpo-v1.11

DataVortex

Our Team

Research & EngineeringProduct Management
Kwangseok YangSeunghyun Choi
Jeongwon ChoiHyoseok Choi

Model Details

Base Model

LDCC/LDCC-SOLAR-10.7B

Trained On

  • OS: Ubuntu 22.04
  • GPU: H100 80GB 4ea
  • transformers: v4.36.2

Instruction format

It follows Alpaca (Chat) format.

E.g.

text = """\
### System:
당신은 사람들이 정보를 찾을 수 있도록 도와주는 인공지능 비서입니다.

### User:
대한민국의 수도는 어디야?

### Assistant:
대한민국의 수도는 서울입니다.

### User:
서울 인구는 총 몇 명이야?
"""

Model Benchmark

Ko LM Eval Harness

Task0-shot5-shot10-shot50-shot
kobest_boolq0.9201010.9280180.9330250.928754
kobest_copa0.7217820.8019360.8177370.84093
kobest_hellaswag0.445020.4827830.4839780.48978
kobest_sentineg0.513980.9319280.9445560.934475
Average0.6502210.7861660.7948240.798485

Ko-LLM-Leaderboard

AverageKo-ARCKo-HellaSwagKo-MMLUKo-TruthfulQAKo-CommonGen V2
59.5655.9768.6852.6766.7453.72

Implementation Code

This model contains the chat_template instruction format.
You can use the code below.

from transformers import AutoModelForCausalLM, AutoTokenizer

device = "cuda" # the device to load the model onto

model = AutoModelForCausalLM.from_pretrained("Edentns/DataVortexS-10.7B-dpo-v1.11")
tokenizer = AutoTokenizer.from_pretrained("Edentns/DataVortexS-10.7B-dpo-v1.11")

messages = [
    {"role": "system", "content": "당신은 사람들이 정보를 찾을 수 있도록 도와주는 인공지능 비서입니다."},
    {"role": "user", "content": "대한민국의 수도는 어디야?"},
    {"role": "assistant", "content": "대한민국의 수도는 서울입니다."},
    {"role": "user", "content": "서울 인구는 총 몇 명이야?"}
]

encodeds = tokenizer.apply_chat_template(messages, return_tensors="pt")

model_inputs = encodeds.to(device)
model.to(device)

generated_ids = model.generate(model_inputs, max_new_tokens=1000, do_sample=True)
decoded = tokenizer.batch_decode(generated_ids)
print(decoded[0])

License

This model is licensed under the cc-by-nc-4.0. which allows others to share and adapt the model for non-commercial purposes.

Contributors

JC
Jeongwon Choi

5 commits

Edentns/DataVortexS-10.7B-dpo-v1.11

Model

4

stars

5

commits

1

repos using this model

2

linked in READMEs

Feb 24, 2024

updated

endpoints_compatible
llama
safetensors
text-generation
text-generation-inference
transformers

README

DataVortexS-10.7B-dpo-v1.11

DataVortex

Our Team

Research & EngineeringProduct Management
Kwangseok YangSeunghyun Choi
Jeongwon ChoiHyoseok Choi

Model Details

Base Model

LDCC/LDCC-SOLAR-10.7B

Trained On

  • OS: Ubuntu 22.04
  • GPU: H100 80GB 4ea
  • transformers: v4.36.2

Instruction format

It follows Alpaca (Chat) format.

E.g.

text = """\
### System:
당신은 사람들이 정보를 찾을 수 있도록 도와주는 인공지능 비서입니다.

### User:
대한민국의 수도는 어디야?

### Assistant:
대한민국의 수도는 서울입니다.

### User:
서울 인구는 총 몇 명이야?
"""

Model Benchmark

Ko LM Eval Harness

Task0-shot5-shot10-shot50-shot
kobest_boolq0.9201010.9280180.9330250.928754
kobest_copa0.7217820.8019360.8177370.84093
kobest_hellaswag0.445020.4827830.4839780.48978
kobest_sentineg0.513980.9319280.9445560.934475
Average0.6502210.7861660.7948240.798485

Ko-LLM-Leaderboard

AverageKo-ARCKo-HellaSwagKo-MMLUKo-TruthfulQAKo-CommonGen V2
59.5655.9768.6852.6766.7453.72

Implementation Code

This model contains the chat_template instruction format.
You can use the code below.

from transformers import AutoModelForCausalLM, AutoTokenizer

device = "cuda" # the device to load the model onto

model = AutoModelForCausalLM.from_pretrained("Edentns/DataVortexS-10.7B-dpo-v1.11")
tokenizer = AutoTokenizer.from_pretrained("Edentns/DataVortexS-10.7B-dpo-v1.11")

messages = [
    {"role": "system", "content": "당신은 사람들이 정보를 찾을 수 있도록 도와주는 인공지능 비서입니다."},
    {"role": "user", "content": "대한민국의 수도는 어디야?"},
    {"role": "assistant", "content": "대한민국의 수도는 서울입니다."},
    {"role": "user", "content": "서울 인구는 총 몇 명이야?"}
]

encodeds = tokenizer.apply_chat_template(messages, return_tensors="pt")

model_inputs = encodeds.to(device)
model.to(device)

generated_ids = model.generate(model_inputs, max_new_tokens=1000, do_sample=True)
decoded = tokenizer.batch_decode(generated_ids)
print(decoded[0])

License

This model is licensed under the cc-by-nc-4.0. which allows others to share and adapt the model for non-commercial purposes.

Contributors

JC
Jeongwon Choi

5 commits