Instructions to use santhosh97/gpt-pythia-6.9b-quantized with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use santhosh97/gpt-pythia-6.9b-quantized with Transformers:

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

pipe = pipeline("text-generation", model="santhosh97/gpt-pythia-6.9b-quantized")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("santhosh97/gpt-pythia-6.9b-quantized")
model = AutoModelForCausalLM.from_pretrained("santhosh97/gpt-pythia-6.9b-quantized")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use santhosh97/gpt-pythia-6.9b-quantized with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "santhosh97/gpt-pythia-6.9b-quantized"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "santhosh97/gpt-pythia-6.9b-quantized",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/santhosh97/gpt-pythia-6.9b-quantized

SGLang

How to use santhosh97/gpt-pythia-6.9b-quantized 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 "santhosh97/gpt-pythia-6.9b-quantized" \
    --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": "santhosh97/gpt-pythia-6.9b-quantized",
		"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 "santhosh97/gpt-pythia-6.9b-quantized" \
        --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": "santhosh97/gpt-pythia-6.9b-quantized",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use santhosh97/gpt-pythia-6.9b-quantized with Docker Model Runner:
```
docker model run hf.co/santhosh97/gpt-pythia-6.9b-quantized
```

gpt-pythia-6.9b-quantized / config.json

santhosh97

Upload GPTNeoXForCausalLM

92565fb about 3 years ago

raw

history blame contribute delete

820 Bytes

	{
	"_name_or_path": "EleutherAI/pythia-6.9b",
	"architectures": [
	"GPTNeoXForCausalLM"
	],
	"bos_token_id": 0,
	"classifier_dropout": 0.1,
	"eos_token_id": 0,
	"hidden_act": "gelu",
	"hidden_size": 4096,
	"initializer_range": 0.02,
	"intermediate_size": 16384,
	"layer_norm_eps": 1e-05,
	"max_position_embeddings": 2048,
	"model_type": "gpt_neox",
	"num_attention_heads": 32,
	"num_hidden_layers": 32,
	"quantization_config": {
	"llm_int8_enable_fp32_cpu_offload": false,
	"llm_int8_skip_modules": null,
	"llm_int8_threshold": 6.0,
	"load_in_8bit": true
	},
	"rotary_emb_base": 10000,
	"rotary_pct": 0.25,
	"tie_word_embeddings": false,
	"torch_dtype": "float16",
	"transformers_version": "4.29.0.dev0",
	"use_cache": true,
	"use_parallel_residual": true,
	"vocab_size": 50432
	}