Instructions to use ISTA-DASLab/Llama-2-7b-AQLM-2Bit-2x8-hf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ISTA-DASLab/Llama-2-7b-AQLM-2Bit-2x8-hf with Transformers:

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

pipe = pipeline("text-generation", model="ISTA-DASLab/Llama-2-7b-AQLM-2Bit-2x8-hf")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ISTA-DASLab/Llama-2-7b-AQLM-2Bit-2x8-hf")
model = AutoModelForCausalLM.from_pretrained("ISTA-DASLab/Llama-2-7b-AQLM-2Bit-2x8-hf", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ISTA-DASLab/Llama-2-7b-AQLM-2Bit-2x8-hf with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ISTA-DASLab/Llama-2-7b-AQLM-2Bit-2x8-hf"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ISTA-DASLab/Llama-2-7b-AQLM-2Bit-2x8-hf",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/ISTA-DASLab/Llama-2-7b-AQLM-2Bit-2x8-hf

SGLang

How to use ISTA-DASLab/Llama-2-7b-AQLM-2Bit-2x8-hf 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 "ISTA-DASLab/Llama-2-7b-AQLM-2Bit-2x8-hf" \
    --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": "ISTA-DASLab/Llama-2-7b-AQLM-2Bit-2x8-hf",
		"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 "ISTA-DASLab/Llama-2-7b-AQLM-2Bit-2x8-hf" \
        --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": "ISTA-DASLab/Llama-2-7b-AQLM-2Bit-2x8-hf",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use ISTA-DASLab/Llama-2-7b-AQLM-2Bit-2x8-hf with Docker Model Runner:
```
docker model run hf.co/ISTA-DASLab/Llama-2-7b-AQLM-2Bit-2x8-hf
```

Llama-2-7b-AQLM-2Bit-2x8-hf

Commit History

Update README.md

017ede1
verified

BlackSamorez commited on Mar 11, 2024

Update README.md

b1548d0
verified

BlackSamorez commited on Mar 1, 2024

tokenizer

48c304f

BlackSamorez commited on Feb 21, 2024

new dispatch

e242f23

BlackSamorez commited on Feb 21, 2024

safetensors

fbffe28

BlackSamorez commited on Feb 21, 2024

Upload finetuned Llama-2-7b models (#1)

d966725
verified

BlackSamorez

SpiridonSunRotator commited on Feb 20, 2024

Upload pytorch_model.bin with huggingface_hub

7e96183
verified

BlackSamorez commited on Feb 20, 2024

Update README.md

2df1b7a
verified

BlackSamorez commited on Feb 8, 2024

Create README.md

45d67dd
verified

BlackSamorez commited on Feb 8, 2024

better checkpoint

f6db3f5

Andrei Panferov commited on Feb 6, 2024

try except import

400eeaa

Andrei Panferov commited on Jan 30, 2024

everythin

aebd979

Andrei Panferov commited on Jan 30, 2024

initial commit

aecf9d3
verified

BlackSamorez commited on Jan 30, 2024

Commit History

Update README.md 017ede1 verified

Update README.md b1548d0 verified

tokenizer 48c304f

new dispatch e242f23

safetensors fbffe28

Upload finetuned Llama-2-7b models (#1) d966725 verified

Upload pytorch_model.bin with huggingface_hub 7e96183 verified

Update README.md 2df1b7a verified

Create README.md 45d67dd verified

better checkpoint f6db3f5

try except import 400eeaa

everythin aebd979

initial commit aecf9d3 verified

Update README.md

017ede1
verified

Update README.md

b1548d0
verified

tokenizer

48c304f

new dispatch

e242f23

safetensors

fbffe28

Upload finetuned Llama-2-7b models (#1)

d966725
verified

Upload pytorch_model.bin with huggingface_hub

7e96183
verified

Update README.md

2df1b7a
verified

Create README.md

45d67dd
verified

better checkpoint

f6db3f5

try except import

400eeaa

everythin

aebd979

initial commit

aecf9d3
verified