Instructions to use iproskurina/opt-2.7b-GPTQ-4bit-g128 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use iproskurina/opt-2.7b-GPTQ-4bit-g128 with Transformers:

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

pipe = pipeline("text-generation", model="iproskurina/opt-2.7b-GPTQ-4bit-g128")

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

tokenizer = AutoTokenizer.from_pretrained("iproskurina/opt-2.7b-GPTQ-4bit-g128")
model = AutoModelForCausalLM.from_pretrained("iproskurina/opt-2.7b-GPTQ-4bit-g128", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use iproskurina/opt-2.7b-GPTQ-4bit-g128 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "iproskurina/opt-2.7b-GPTQ-4bit-g128"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "iproskurina/opt-2.7b-GPTQ-4bit-g128",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/iproskurina/opt-2.7b-GPTQ-4bit-g128

SGLang

How to use iproskurina/opt-2.7b-GPTQ-4bit-g128 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 "iproskurina/opt-2.7b-GPTQ-4bit-g128" \
    --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": "iproskurina/opt-2.7b-GPTQ-4bit-g128",
		"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 "iproskurina/opt-2.7b-GPTQ-4bit-g128" \
        --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": "iproskurina/opt-2.7b-GPTQ-4bit-g128",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use iproskurina/opt-2.7b-GPTQ-4bit-g128 with Docker Model Runner:
```
docker model run hf.co/iproskurina/opt-2.7b-GPTQ-4bit-g128
```

iproskurina commited on Sep 23, 2024

Commit

70bb27a

verified ·

1 Parent(s): fd9bb4d

AutoGPTQ model for facebook/opt-2.7b: 4bits, gr128, desc_act=False

Browse files

Files changed (2) hide show

README.md +9 -9
tokenizer.json +1 -0

README.md CHANGED Viewed

@@ -1,18 +1,18 @@
 ---
 base_model: facebook/opt-2.7b
-inference: false
-model_creator: facebook
 model_name: opt-2.7b
-model_type: opt
 pipeline_tag: text-generation
-quantized_by: iproskurina
 tags:
 - pretrained
-license: other
-language:
-- en
-datasets:
-- c4
 ---

 ---
 base_model: facebook/opt-2.7b
+datasets:
+- c4
+language:
+- en
+license: other
 model_name: opt-2.7b
 pipeline_tag: text-generation
 tags:
 - pretrained
+inference: false
+model_creator: facebook
+model_type: opt
+quantized_by: iproskurina
 ---

tokenizer.json CHANGED Viewed

@@ -91,6 +91,7 @@
     "end_of_word_suffix": "",
     "fuse_unk": false,
     "byte_fallback": false,
     "vocab": {
       "<s>": 0,
       "<pad>": 1,

     "end_of_word_suffix": "",
     "fuse_unk": false,
     "byte_fallback": false,
+    "ignore_merges": false,
     "vocab": {
       "<s>": 0,
       "<pad>": 1,