Instructions to use prithivMLmods/Calcium-20B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use prithivMLmods/Calcium-20B with Transformers:

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

pipe = pipeline("text-generation", model="prithivMLmods/Calcium-20B")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("prithivMLmods/Calcium-20B")
model = AutoModelForCausalLM.from_pretrained("prithivMLmods/Calcium-20B")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use prithivMLmods/Calcium-20B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "prithivMLmods/Calcium-20B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "prithivMLmods/Calcium-20B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/prithivMLmods/Calcium-20B

SGLang

How to use prithivMLmods/Calcium-20B 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 "prithivMLmods/Calcium-20B" \
    --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": "prithivMLmods/Calcium-20B",
		"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 "prithivMLmods/Calcium-20B" \
        --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": "prithivMLmods/Calcium-20B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use prithivMLmods/Calcium-20B with Docker Model Runner:
```
docker model run hf.co/prithivMLmods/Calcium-20B
```

prithivMLmods commited on Jan 15, 2025

Commit

6439237

verified ·

1 Parent(s): c03ff4a

Update README.md

Browse files

Files changed (1) hide show

README.md +2 -0

README.md CHANGED Viewed

@@ -11,5 +11,7 @@ tags:
 ---
 ![fghfghf.png](https://cdn-uploads.huggingface.co/production/uploads/65bb837dbfb878f46c77de4c/zcI6XhYs9oKapZxWDkVQJ.png)
 Calcium 20B, based on the Llama 3.1 collection of multilingual large language models (LLMs), is a collection of pretrained and instruction-tuned generative models optimized for multilingual dialogue use cases. These models outperform many available open-source alternatives.
 Model Architecture: Llama 3.1 is an auto-regressive language model that uses an optimized transformer architecture. The tuned versions are fine-tuned using supervised fine-tuning (SFT) and reinforcement learning with human feedback (RLHF) to align with human preferences for helpfulness and safety. Calcium 20B is trained on synthetic reasoning datasets for mathematical reasoning and science-based problem solving, focusing on following instructions or keywords embedded in the input.

 ---
 ![fghfghf.png](https://cdn-uploads.huggingface.co/production/uploads/65bb837dbfb878f46c77de4c/zcI6XhYs9oKapZxWDkVQJ.png)
+# **Calcium 20B**
 Calcium 20B, based on the Llama 3.1 collection of multilingual large language models (LLMs), is a collection of pretrained and instruction-tuned generative models optimized for multilingual dialogue use cases. These models outperform many available open-source alternatives.
 Model Architecture: Llama 3.1 is an auto-regressive language model that uses an optimized transformer architecture. The tuned versions are fine-tuned using supervised fine-tuning (SFT) and reinforcement learning with human feedback (RLHF) to align with human preferences for helpfulness and safety. Calcium 20B is trained on synthetic reasoning datasets for mathematical reasoning and science-based problem solving, focusing on following instructions or keywords embedded in the input.