Instructions to use fbaldassarri/iGeniusAI_Italia-9B-Instruct-v0.1-autogptq-int8-gs128-auto-asym with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Local Apps Settings

How to use fbaldassarri/iGeniusAI_Italia-9B-Instruct-v0.1-autogptq-int8-gs128-auto-asym with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "fbaldassarri/iGeniusAI_Italia-9B-Instruct-v0.1-autogptq-int8-gs128-auto-asym"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "fbaldassarri/iGeniusAI_Italia-9B-Instruct-v0.1-autogptq-int8-gs128-auto-asym",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/fbaldassarri/iGeniusAI_Italia-9B-Instruct-v0.1-autogptq-int8-gs128-auto-asym

SGLang

How to use fbaldassarri/iGeniusAI_Italia-9B-Instruct-v0.1-autogptq-int8-gs128-auto-asym 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 "fbaldassarri/iGeniusAI_Italia-9B-Instruct-v0.1-autogptq-int8-gs128-auto-asym" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "fbaldassarri/iGeniusAI_Italia-9B-Instruct-v0.1-autogptq-int8-gs128-auto-asym",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "fbaldassarri/iGeniusAI_Italia-9B-Instruct-v0.1-autogptq-int8-gs128-auto-asym" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "fbaldassarri/iGeniusAI_Italia-9B-Instruct-v0.1-autogptq-int8-gs128-auto-asym",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use fbaldassarri/iGeniusAI_Italia-9B-Instruct-v0.1-autogptq-int8-gs128-auto-asym with Docker Model Runner:
```
docker model run hf.co/fbaldassarri/iGeniusAI_Italia-9B-Instruct-v0.1-autogptq-int8-gs128-auto-asym
```

iGeniusAI_Italia-9B-Instruct-v0.1-autogptq-int8-gs128-auto-asym / quantize_config.json

fbaldassarri

Initial Upload

516807f verified over 1 year ago

Raw

History Blame Contribute Delete

565 Bytes

	{
	"bits": 8,
	"group_size": 128,
	"sym": false,
	"data_type": "int",
	"enable_quanted_input": true,
	"enable_minmax_tuning": true,
	"seqlen": 512,
	"batch_size": 4,
	"scale_dtype": "torch.float16",
	"lr": 0.005,
	"minmax_lr": 0.005,
	"gradient_accumulate_steps": 1,
	"iters": 200,
	"amp": false,
	"nsamples": 128,
	"low_gpu_mem_usage": false,
	"enable_norm_bias_tuning": false,
	"autoround_version": "0.4.6",
	"block_name_to_quantize": "layers",
	"quant_method": "gptq",
	"desc_act": false,
	"true_sequential": false,
	"damp_percent": 0.01
	}