Instructions to use UncleanCode/anacondia-70m with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use UncleanCode/anacondia-70m with Transformers:

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

pipe = pipeline("text-generation", model="UncleanCode/anacondia-70m")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("UncleanCode/anacondia-70m")
model = AutoModelForCausalLM.from_pretrained("UncleanCode/anacondia-70m")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use UncleanCode/anacondia-70m with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "UncleanCode/anacondia-70m"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "UncleanCode/anacondia-70m",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/UncleanCode/anacondia-70m

SGLang

How to use UncleanCode/anacondia-70m 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 "UncleanCode/anacondia-70m" \
    --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": "UncleanCode/anacondia-70m",
		"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 "UncleanCode/anacondia-70m" \
        --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": "UncleanCode/anacondia-70m",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use UncleanCode/anacondia-70m with Docker Model Runner:
```
docker model run hf.co/UncleanCode/anacondia-70m
```

UncleanCode commited on Aug 20, 2023

Commit

89226f9

1 Parent(s): db23c20

Update README.md

Browse files

Files changed (1) hide show

README.md +2 -3

README.md CHANGED Viewed

@@ -1,6 +1,5 @@
 ---
-library_name: peft
-license: bigscience-bloom-rail-1.0
 datasets:
 - timdettmers/openassistant-guanaco
 language:
@@ -11,7 +10,7 @@ pipeline_tag: text-generation
 Anacondia-70m is a Pythia-70m-deduped model fine-tuned with QLoRA on [timdettmers/openassistant-guanaco](https://huggingface.co/datasets/timdettmers/openassistant-guanaco)
 ## Usage
-Anacondia is not intended for any real usage and was trained for educational purposes. Please consider more serious models for inference.
 ## Training procedure

 ---
+license: apache-2.0
 datasets:
 - timdettmers/openassistant-guanaco
 language:
 Anacondia-70m is a Pythia-70m-deduped model fine-tuned with QLoRA on [timdettmers/openassistant-guanaco](https://huggingface.co/datasets/timdettmers/openassistant-guanaco)
 ## Usage
+Anacondia is not intended for any downstream usage and was trained for educational purposes. Please consider more serious models for inference if this doesn't fall into your usage aim.
 ## Training procedure