Text Generation
Transformers
PyTorch
Safetensors
Korean
English
llama
KoLLAMA
KoreanGPT
text-generation-inference
Instructions to use beomi/kollama-7b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use beomi/kollama-7b with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="beomi/kollama-7b")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("beomi/kollama-7b") model = AutoModelForCausalLM.from_pretrained("beomi/kollama-7b", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use beomi/kollama-7b with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "beomi/kollama-7b" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "beomi/kollama-7b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/beomi/kollama-7b
- SGLang
How to use beomi/kollama-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 "beomi/kollama-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": "beomi/kollama-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 "beomi/kollama-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": "beomi/kollama-7b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use beomi/kollama-7b with Docker Model Runner:
docker model run hf.co/beomi/kollama-7b
Add 140k model
Browse files
pytorch_model-00001-of-00002.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2e2c7412c40a94fe0119f768691bd8b6a586354ba43ab3d1be2bd2ee0f9e89b0
|
| 3 |
+
size 9960101722
|
pytorch_model-00002-of-00002.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7cfd356b5f358403dac538ef0d3a87a3ce4be9c05ad1d157cf60a7062836bce1
|
| 3 |
+
size 3844528347
|
pytorch_model.bin.index.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
| 1 |
{
|
| 2 |
"metadata": {
|
| 3 |
-
"total_size":
|
| 4 |
},
|
| 5 |
"weight_map": {
|
| 6 |
"lm_head.weight": "pytorch_model-00002-of-00002.bin",
|
|
|
|
| 1 |
{
|
| 2 |
"metadata": {
|
| 3 |
+
"total_size": 13804519424
|
| 4 |
},
|
| 5 |
"weight_map": {
|
| 6 |
"lm_head.weight": "pytorch_model-00002-of-00002.bin",
|
tokenizer_config.json
CHANGED
|
@@ -1,4 +1,8 @@
|
|
| 1 |
{
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
"model_max_length": 1000000000000000019884624838656,
|
| 3 |
"tokenizer_class": "PreTrainedTokenizerFast"
|
| 4 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"name_or_path": "beomi/KoLLAMA",
|
| 3 |
+
"eos_token": "<|endoftext|>",
|
| 4 |
+
"bos_token": "<|sep|>",
|
| 5 |
+
"pad_token": "<|endoftext|>",
|
| 6 |
"model_max_length": 1000000000000000019884624838656,
|
| 7 |
"tokenizer_class": "PreTrainedTokenizerFast"
|
| 8 |
}
|