Instructions to use dvitvaai/pothana-sp-base-300M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use dvitvaai/pothana-sp-base-300M with Transformers:

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

pipe = pipeline("text-generation", model="dvitvaai/pothana-sp-base-300M")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("dvitvaai/pothana-sp-base-300M")
model = AutoModelForCausalLM.from_pretrained("dvitvaai/pothana-sp-base-300M", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use dvitvaai/pothana-sp-base-300M with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "dvitvaai/pothana-sp-base-300M"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "dvitvaai/pothana-sp-base-300M",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/dvitvaai/pothana-sp-base-300M

SGLang

How to use dvitvaai/pothana-sp-base-300M 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 "dvitvaai/pothana-sp-base-300M" \
    --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": "dvitvaai/pothana-sp-base-300M",
		"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 "dvitvaai/pothana-sp-base-300M" \
        --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": "dvitvaai/pothana-sp-base-300M",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use dvitvaai/pothana-sp-base-300M with Docker Model Runner:
```
docker model run hf.co/dvitvaai/pothana-sp-base-300M
```

pothana-sp-base-300M / config.json

neshkatrapati

Upload folder using huggingface_hub

8da140c verified 7 months ago

Raw

History Blame Contribute Delete

693 Bytes

	{
	"architectures": [
	"LlamaForCausalLM"
	],
	"model_type": "llama",
	"torch_dtype": "float32",
	"hidden_size": 1024,
	"intermediate_size": 2816,
	"num_hidden_layers": 60,
	"num_attention_heads": 16,
	"num_key_value_heads": 4,
	"head_dim": 64,
	"max_position_embeddings": 2048,
	"rope_theta": 10000.0,
	"rope_scaling": null,
	"rms_norm_eps": 1e-06,
	"hidden_act": "silu",
	"attention_bias": false,
	"mlp_bias": false,
	"vocab_size": 48000,
	"tie_word_embeddings": true,
	"pad_token_id": 0,
	"bos_token_id": 2,
	"eos_token_id": 3,
	"attention_dropout": 0.0,
	"initializer_range": 0.02,
	"pretraining_tp": 1,
	"use_cache": true,
	"transformers_version": "4.40.0"
	}