Instructions to use retronic/Colox_The1st-LORA_GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use retronic/Colox_The1st-LORA_GGUF with Transformers:

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

pipe = pipeline("text-generation", model="retronic/Colox_The1st-LORA_GGUF")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("retronic/Colox_The1st-LORA_GGUF", dtype="auto")

PEFT
How to use retronic/Colox_The1st-LORA_GGUF with PEFT:
```
Task type is invalid.
```
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use retronic/Colox_The1st-LORA_GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "retronic/Colox_The1st-LORA_GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "retronic/Colox_The1st-LORA_GGUF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/retronic/Colox_The1st-LORA_GGUF

SGLang

How to use retronic/Colox_The1st-LORA_GGUF 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 "retronic/Colox_The1st-LORA_GGUF" \
    --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": "retronic/Colox_The1st-LORA_GGUF",
		"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 "retronic/Colox_The1st-LORA_GGUF" \
        --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": "retronic/Colox_The1st-LORA_GGUF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use retronic/Colox_The1st-LORA_GGUF with Docker Model Runner:
```
docker model run hf.co/retronic/Colox_The1st-LORA_GGUF
```

retronic commited on Mar 4

Commit

81742aa

verified ·

1 Parent(s): f78608a

Update README.md

Browse files

Files changed (1) hide show

README.md +4 -1

README.md CHANGED Viewed

@@ -21,4 +21,7 @@ This is the Colox-v1 GGUF Lora adapter.
 This is compatible with any service that supports GGUF Lora adpaters plus base model. (ex: llama-cpp, ollama, etc.)
 # What is the base model?
-Llama 3.1 8B Instruct

 This is compatible with any service that supports GGUF Lora adpaters plus base model. (ex: llama-cpp, ollama, etc.)
 # What is the base model?
+Llama 3.1 8B Instruct
+# How is this Lora adapter quanitized?
+This has been quanitized to F16.