Instructions to use EleutherAI/polyglot-ko-12.8b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use EleutherAI/polyglot-ko-12.8b with Transformers:

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

pipe = pipeline("text-generation", model="EleutherAI/polyglot-ko-12.8b")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("EleutherAI/polyglot-ko-12.8b")
model = AutoModelForCausalLM.from_pretrained("EleutherAI/polyglot-ko-12.8b")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use EleutherAI/polyglot-ko-12.8b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "EleutherAI/polyglot-ko-12.8b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "EleutherAI/polyglot-ko-12.8b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/EleutherAI/polyglot-ko-12.8b

SGLang

How to use EleutherAI/polyglot-ko-12.8b 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 "EleutherAI/polyglot-ko-12.8b" \
    --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": "EleutherAI/polyglot-ko-12.8b",
		"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 "EleutherAI/polyglot-ko-12.8b" \
        --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": "EleutherAI/polyglot-ko-12.8b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use EleutherAI/polyglot-ko-12.8b with Docker Model Runner:
```
docker model run hf.co/EleutherAI/polyglot-ko-12.8b
```

jason9693 commited on Nov 11, 2022

Commit

4fc0002

1 Parent(s): 10b882d

Upload with huggingface_hub

Browse files

Files changed (3) hide show

config.json +1 -1
pytorch_model.bin +1 -1
tokenizer_config.json +1 -1

config.json CHANGED Viewed

@@ -1 +1 @@

- {"hidden_act": "gelu", "architectures": ["GPTNeoXForCausalLM"], "bos_token_id": 0, "eos_token_id": 0, "initializer_range": 0.02, "layer_norm_eps": 1e-05, "model_type": "gpt_neox", "hidden_size": 5120, "intermediate_size": 20480, "num_attention_heads": 40, "num_hidden_layers": 40, "max_position_embeddings": 2048, "rotary_pct": 0.5, "rotary_emb_base": 10000, "torch_dtype": "float16", "use_cache": true, "vocab_size": 30080, "num_steps": "~~global_step250000~~"}

+ {"hidden_act": "gelu", "architectures": ["GPTNeoXForCausalLM"], "bos_token_id": 0, "eos_token_id": 0, "initializer_range": 0.02, "layer_norm_eps": 1e-05, "model_type": "gpt_neox", "hidden_size": 5120, "intermediate_size": 20480, "num_attention_heads": 40, "num_hidden_layers": 40, "max_position_embeddings": 2048, "rotary_pct": 0.5, "rotary_emb_base": 10000, "torch_dtype": "float16", "use_cache": true, "vocab_size": 30080, "num_steps": "global_step301000"}

pytorch_model.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2cf9eac2285df9c52c9993b68b109c3a5df1d008b9af61c3e53a37f1573c5846
 size 25955180945

 version https://git-lfs.github.com/spec/v1
+oid sha256:4c73c3524c705f333b73f47f4bd60eb3cde2998860d03d67c90e262ec1bb9f4c
 size 25955180945

tokenizer_config.json CHANGED Viewed

@@ -1,5 +1,5 @@
 {
-    "name_or_path": "EleutherAI/polyglot-ko-12.8b",
     "eos_token": "<|endoftext|>",
     "pad_token": "<|endoftext|>",
     "tokenizer_class": "PreTrainedTokenizerFast"

 {
+    "name_or_path": "EleutherAI/polyglot-ko-1.3b",
     "eos_token": "<|endoftext|>",
     "pad_token": "<|endoftext|>",
     "tokenizer_class": "PreTrainedTokenizerFast"