Instructions to use turtle170/MicroAtlas-V1-F16-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries
PEFT
How to use turtle170/MicroAtlas-V1-F16-GGUF with PEFT:
```
Task type is invalid.
```

How to use turtle170/MicroAtlas-V1-F16-GGUF with Transformers:

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

pipe = pipeline("text-generation", model="turtle170/MicroAtlas-V1-F16-GGUF")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("turtle170/MicroAtlas-V1-F16-GGUF", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use turtle170/MicroAtlas-V1-F16-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "turtle170/MicroAtlas-V1-F16-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "turtle170/MicroAtlas-V1-F16-GGUF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/turtle170/MicroAtlas-V1-F16-GGUF

SGLang

How to use turtle170/MicroAtlas-V1-F16-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 "turtle170/MicroAtlas-V1-F16-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": "turtle170/MicroAtlas-V1-F16-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 "turtle170/MicroAtlas-V1-F16-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": "turtle170/MicroAtlas-V1-F16-GGUF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use turtle170/MicroAtlas-V1-F16-GGUF with Docker Model Runner:
```
docker model run hf.co/turtle170/MicroAtlas-V1-F16-GGUF
```

turtle170 commited on Jan 14

Commit

acca4e0

verified ·

1 Parent(s): 7ca3e5b

Upload README.md with huggingface_hub

Browse files

Files changed (1) hide show

README.md +33 -0

README.md ADDED Viewed

	@@ -0,0 +1,33 @@

+---
+base_model: turtle170/MicroAtlas-V1
+datasets:
+- teknium/OpenHermes-2.5
+- Magpie-Align/Magpie-Phi3-Pro-300K-Filtered
+language:
+- en
+library_name: peft
+license: apache-2.0
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:microsoft/Phi-3-mini-4k-instruct
+- lora
+- transformers
+- llama-cpp
+- gguf-my-lora
+---
+# turtle170/MicroAtlas-V1-F16-GGUF
+This LoRA adapter was converted to GGUF format from [`turtle170/MicroAtlas-V1`](https://huggingface.co/turtle170/MicroAtlas-V1) via the ggml.ai's [GGUF-my-lora](https://huggingface.co/spaces/ggml-org/gguf-my-lora) space.
+Refer to the [original adapter repository](https://huggingface.co/turtle170/MicroAtlas-V1) for more details.
+## Use with llama.cpp
+```bash
+# with cli
+llama-cli -m base_model.gguf --lora MicroAtlas-V1-f16.gguf (...other args)
+# with server
+llama-server -m base_model.gguf --lora MicroAtlas-V1-f16.gguf (...other args)
+```
+To know more about LoRA usage with llama.cpp server, refer to the [llama.cpp server documentation](https://github.com/ggerganov/llama.cpp/blob/master/examples/server/README.md).