Instructions to use MichaelKim/dacon_comp_hansoldeco_v3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use MichaelKim/dacon_comp_hansoldeco_v3 with Transformers:

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

pipe = pipeline("text-generation", model="MichaelKim/dacon_comp_hansoldeco_v3")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("MichaelKim/dacon_comp_hansoldeco_v3")
model = AutoModelForCausalLM.from_pretrained("MichaelKim/dacon_comp_hansoldeco_v3", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use MichaelKim/dacon_comp_hansoldeco_v3 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "MichaelKim/dacon_comp_hansoldeco_v3"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "MichaelKim/dacon_comp_hansoldeco_v3",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/MichaelKim/dacon_comp_hansoldeco_v3

SGLang

How to use MichaelKim/dacon_comp_hansoldeco_v3 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 "MichaelKim/dacon_comp_hansoldeco_v3" \
    --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": "MichaelKim/dacon_comp_hansoldeco_v3",
		"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 "MichaelKim/dacon_comp_hansoldeco_v3" \
        --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": "MichaelKim/dacon_comp_hansoldeco_v3",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use MichaelKim/dacon_comp_hansoldeco_v3 with Docker Model Runner:
```
docker model run hf.co/MichaelKim/dacon_comp_hansoldeco_v3
```

MichaelKim commited on Feb 23, 2024

Commit

94d12dd

verified ·

1 Parent(s): 9e14968

Done

Browse files

Files changed (2) hide show

README.md +4 -2
runs/Feb23_19-12-05_e41a7c5d6343/events.out.tfevents.1708715527.e41a7c5d6343.34.0 +2 -2

README.md CHANGED Viewed

@@ -13,6 +13,8 @@ should probably proofread and complete it, then remove this comment. -->
 # dacon_comp_hansoldeco_v3
 This model is a fine-tuned version of [heegyu/polyglot-ko-1.3b-chat](https://huggingface.co/heegyu/polyglot-ko-1.3b-chat) on an unknown dataset.
 ## Model description
@@ -31,7 +33,7 @@ More information needed
 ### Training hyperparameters
 The following hyperparameters were used during training:
-- learning_rate: 2e-05
 - train_batch_size: 2
 - eval_batch_size: 8
 - seed: 42
@@ -43,7 +45,7 @@ The following hyperparameters were used during training:
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| No log        | 1.0   | 2    | nan             |
 ### Framework versions

 # dacon_comp_hansoldeco_v3
 This model is a fine-tuned version of [heegyu/polyglot-ko-1.3b-chat](https://huggingface.co/heegyu/polyglot-ko-1.3b-chat) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: nan
 ## Model description
 ### Training hyperparameters
 The following hyperparameters were used during training:
+- learning_rate: 5e-05
 - train_batch_size: 2
 - eval_batch_size: 8
 - seed: 42
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
+| 0.0           | 1.0   | 515  | nan             |
 ### Framework versions

runs/Feb23_19-12-05_e41a7c5d6343/events.out.tfevents.1708715527.e41a7c5d6343.34.0 CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fef7a84b4fc82943c126ffe5426b0c3bbb5019f17632e08fd9d067f77b1d036a
-size 12743

 version https://git-lfs.github.com/spec/v1
+oid sha256:4ba724d501018eb42143854aefca561ae90b03d6d330b532807c5ac4e01e1ee7
+size 13097