Instructions to use kyujinpy/CoT-llama-2k-7b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use kyujinpy/CoT-llama-2k-7b with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="kyujinpy/CoT-llama-2k-7b")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("kyujinpy/CoT-llama-2k-7b")
model = AutoModelForCausalLM.from_pretrained("kyujinpy/CoT-llama-2k-7b")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use kyujinpy/CoT-llama-2k-7b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "kyujinpy/CoT-llama-2k-7b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "kyujinpy/CoT-llama-2k-7b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/kyujinpy/CoT-llama-2k-7b

SGLang

How to use kyujinpy/CoT-llama-2k-7b with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "kyujinpy/CoT-llama-2k-7b" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "kyujinpy/CoT-llama-2k-7b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "kyujinpy/CoT-llama-2k-7b" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "kyujinpy/CoT-llama-2k-7b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use kyujinpy/CoT-llama-2k-7b with Docker Model Runner:
```
docker model run hf.co/kyujinpy/CoT-llama-2k-7b
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

(주)미디어그룹사람과숲과 (주)마커의 LLM 연구 컨소시엄에서 개발된 모델입니다
The license is cc-by-nc-sa-4.0.

CoT-llama2-7B

More detail repo(Github): CoT-llama2

Model Details

Model Developers Kyujin Han (kyujinpy)

Input Models input text only.

Output Models generate text only.

Model Architecture

CoT-llama2 is an auto-regressive language model based on the LLaMA2 transformer architecture.

Base Model Llama-2-ko-7b

Training Dataset

I use KoCoT_2000.
Using DeepL, translate about kaist-CoT.

I use A100 GPU 40GB and COLAB, when trianing.

Training Hyperparameters

Hyperparameters	Value
batch_size	`64`
micro_batch_size	`1`
Epochs	`15`
learning_rate	`1e-5`
cutoff_len	`2048`
lr_scheduler	`linear`
base_model	`beomi/llama-2-ko-7b`

Model Benchmark

LM Eval Harness - Korean (polyglot branch)

Used EleutherAI's lm-evaluation-harness

Question Answering (QA)

COPA (F1)

Model	0-shot	5-shot	10-shot	50-shot
Polyglot-ko-1.3b	0.7196	0.7193	0.7204	0.7206
Polyglot-ko-3.8b	0.7595	0.7608	0.7638	0.7788
Polyglot-ko-5.8b	0.7745	0.7676	0.7775	0.7887
Polyglot-ko-12.8b	0.7937	0.8108	0.8037	0.8369
Llama-2-Ko-7b 20B	0.7388	0.7626	0.7808	0.7979
Llama-2-Ko-7b 40B	0.7436	0.7927	0.8037	0.8259
KO-platypus2-7B-EX	0.7509	0.7899	0.8029	0.8290
CoT-llama2-7B(ours)	0.7528	0.7888	0.7998	0.8210

Natural Language Inference (NLI; 자연어 추론 평가)

HellaSwag (F1)

Model	0-shot	5-shot	10-shot	50-shot
Polyglot-ko-1.3b	0.5247	0.5260	0.5278	0.5427
Polyglot-ko-3.8b	0.5707	0.5830	0.5670	0.5787
Polyglot-ko-5.8b	0.5976	0.5998	0.5979	0.6208
Polyglot-ko-12.8b	0.5954	0.6306	0.6098	0.6118
Llama-2-Ko-7b 20B	0.4518	0.4668	0.4726	0.4828
Llama-2-Ko-7b 40B	0.4562	0.4657	0.4698	0.4774
KO-platypus2-7B-EX	0.4571	0.4461	0.4371	0.4525
CoT-llama2-7B(ours)	0.4543	0.4554	0.4606	0.4579

Question Answering (QA)

BoolQ (F1)

Model	0-shot	5-shot	10-shot	50-shot
Polyglot-ko-1.3b	0.3552	0.4751	0.4109	0.4038
Polyglot-ko-3.8b	0.4320	0.5263	0.4930	0.4038
Polyglot-ko-5.8b	0.4356	0.5698	0.5187	0.5236
Polyglot-ko-12.8b	0.4818	0.6041	0.6289	0.6448
Llama-2-Ko-7b 20B	0.3607	0.6797	0.6801	0.6622
Llama-2-Ko-7b 40B	0.5786	0.6977	0.7084	0.7144
KO-platypus2-7B-EX	0.6028	0.6979	0.7016	0.6988
CoT-llama2-7B(ours)	0.5852	0.6947	0.7059	0.7213

Classification

SentiNeg (F1)

Model	0-shot	5-shot	10-shot	50-shot
Polyglot-ko-1.3b	0.6790	0.6257	0.5514	0.7851
Polyglot-ko-3.8b	0.4858	0.7950	0.7320	0.7851
Polyglot-ko-5.8b	0.3394	0.8841	0.8808	0.9521
Polyglot-ko-12.8b	0.9117	0.9015	0.9345	0.9723
Llama-2-Ko-7b 20B	0.4855	0.8295	0.8711	0.8513
Llama-2-Ko-7b 40B	0.4594	0.7611	0.7276	0.9370
KO-platypus2-7B-EX	0.5821	0.7653	0.7991	0.8643
CoT-llama2-7B(ours)	0.5045	0.8054	0.7942	0.9446

Implementation Code

### KO-Platypus
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

repo = "kyujinpy/CoT-llama-2k-7b"
CoT-llama = AutoModelForCausalLM.from_pretrained(
        repo,
        return_dict=True,
        torch_dtype=torch.float16,
        device_map='auto'
)
CoT-llama_tokenizer = AutoTokenizer.from_pretrained(repo)

Readme format: beomi/llama-2-ko-7b

Downloads last month: 11

Safetensors

Model size

7B params

Tensor type

F16

Model tree for kyujinpy/CoT-llama-2k-7b

Quantizations

2 models

kyujinpy
/

CoT-llama-2k-7b