Instructions to use horheynm/actoder_autogptq with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use horheynm/actoder_autogptq with Transformers:

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

pipe = pipeline("text-generation", model="horheynm/actoder_autogptq")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("horheynm/actoder_autogptq")
model = AutoModelForCausalLM.from_pretrained("horheynm/actoder_autogptq", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use horheynm/actoder_autogptq with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/horheynm/actoder_autogptq

SGLang

How to use horheynm/actoder_autogptq 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 "horheynm/actoder_autogptq" \
    --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": "horheynm/actoder_autogptq",
		"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 "horheynm/actoder_autogptq" \
        --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": "horheynm/actoder_autogptq",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use horheynm/actoder_autogptq with Docker Model Runner:
```
docker model run hf.co/horheynm/actoder_autogptq
```

actoder_autogptq / config.json

horheynm

Upload of AutoGPTQ quantized model

6146358 verified over 2 years ago

Raw History Blame Contribute Delete

1.09 kB

{
  "_name_or_path": "opt-125m-4bit",
  "_remove_final_layer_norm": false,
  "activation_dropout": 0.0,
  "activation_function": "relu",
  "architectures": [
    "OPTForCausalLM"
  ],
  "attention_dropout": 0.0,
  "bos_token_id": 2,
  "do_layer_norm_before": true,
  "dropout": 0.1,
  "enable_bias": true,
  "eos_token_id": 2,
  "ffn_dim": 3072,
  "hidden_size": 768,
  "init_std": 0.02,
  "layer_norm_elementwise_affine": true,
  "layerdrop": 0.0,
  "max_position_embeddings": 2048,
  "model_type": "opt",
  "num_attention_heads": 12,
  "num_hidden_layers": 12,
  "pad_token_id": 1,
  "prefix": "</s>",
  "quantization_config": {
    "bits": 4,
    "checkpoint_format": "gptq",
    "damp_percent": 0.01,
    "desc_act": true,
    "group_size": 128,
    "model_file_base_name": "gptq_model-4bit-128g",
    "model_name_or_path": "opt-125m-4bit",
    "quant_method": "gptq",
    "static_groups": false,
    "sym": true,
    "true_sequential": true
  },
  "torch_dtype": "float16",
  "transformers_version": "4.41.2",
  "use_cache": true,
  "vocab_size": 50272,
  "word_embed_proj_dim": 768
}

	{
	"_name_or_path": "opt-125m-4bit",
	"_remove_final_layer_norm": false,
	"activation_dropout": 0.0,
	"activation_function": "relu",
	"architectures": [
	"OPTForCausalLM"
	],
	"attention_dropout": 0.0,
	"bos_token_id": 2,
	"do_layer_norm_before": true,
	"dropout": 0.1,
	"enable_bias": true,
	"eos_token_id": 2,
	"ffn_dim": 3072,
	"hidden_size": 768,
	"init_std": 0.02,
	"layer_norm_elementwise_affine": true,
	"layerdrop": 0.0,
	"max_position_embeddings": 2048,
	"model_type": "opt",
	"num_attention_heads": 12,
	"num_hidden_layers": 12,
	"pad_token_id": 1,
	"prefix": "</s>",
	"quantization_config": {
	"bits": 4,
	"checkpoint_format": "gptq",
	"damp_percent": 0.01,
	"desc_act": true,
	"group_size": 128,
	"model_file_base_name": "gptq_model-4bit-128g",
	"model_name_or_path": "opt-125m-4bit",
	"quant_method": "gptq",
	"static_groups": false,
	"sym": true,
	"true_sequential": true
	},
	"torch_dtype": "float16",
	"transformers_version": "4.41.2",
	"use_cache": true,
	"vocab_size": 50272,
	"word_embed_proj_dim": 768
	}