Instructions to use fbaldassarri/TinyLlama_TinyLlama_v1.1-auto_gptq-int4-gs64-asym with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use fbaldassarri/TinyLlama_TinyLlama_v1.1-auto_gptq-int4-gs64-asym with Transformers:

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

pipe = pipeline("text-generation", model="fbaldassarri/TinyLlama_TinyLlama_v1.1-auto_gptq-int4-gs64-asym")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("fbaldassarri/TinyLlama_TinyLlama_v1.1-auto_gptq-int4-gs64-asym")
model = AutoModelForCausalLM.from_pretrained("fbaldassarri/TinyLlama_TinyLlama_v1.1-auto_gptq-int4-gs64-asym", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use fbaldassarri/TinyLlama_TinyLlama_v1.1-auto_gptq-int4-gs64-asym with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "fbaldassarri/TinyLlama_TinyLlama_v1.1-auto_gptq-int4-gs64-asym"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "fbaldassarri/TinyLlama_TinyLlama_v1.1-auto_gptq-int4-gs64-asym",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/fbaldassarri/TinyLlama_TinyLlama_v1.1-auto_gptq-int4-gs64-asym

SGLang

How to use fbaldassarri/TinyLlama_TinyLlama_v1.1-auto_gptq-int4-gs64-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/TinyLlama_TinyLlama_v1.1-auto_gptq-int4-gs64-asym" \
    --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": "fbaldassarri/TinyLlama_TinyLlama_v1.1-auto_gptq-int4-gs64-asym",
		"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 "fbaldassarri/TinyLlama_TinyLlama_v1.1-auto_gptq-int4-gs64-asym" \
        --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": "fbaldassarri/TinyLlama_TinyLlama_v1.1-auto_gptq-int4-gs64-asym",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use fbaldassarri/TinyLlama_TinyLlama_v1.1-auto_gptq-int4-gs64-asym with Docker Model Runner:
```
docker model run hf.co/fbaldassarri/TinyLlama_TinyLlama_v1.1-auto_gptq-int4-gs64-asym
```

TinyLlama_TinyLlama_v1.1-auto_gptq-int4-gs64-asym / README.md

fbaldassarri

Initial Commit

268bb94 verified about 1 month ago

preview code

Raw

History Blame Contribute Delete

4.93 kB

metadata

language:
  - en
tags:
  - gptq
  - auto-gptq
  - autogptq
  - pytorch
  - causal-lm
  - autoround
  - auto-round
  - intel-autoround
  - intel
  - woq
  - weights-only-quantization
  - tinyllama
  - llama
  - 4-bit
license: apache-2.0
license_link: https://choosealicense.com/licenses/apache-2.0/
library_name: transformers
model_name: TinyLlama_v1.1
base_model:
  - TinyLlama/TinyLlama_v1.1
base_model_relation: quantized
model_type: llama
inference: false
model_creator: fbaldassarri
pipeline_tag: text-generation
prompt_template: '{prompt} '
quantized_by: fbaldassarri
quantization_config:
  method: auto_gptq
  bits: 4
  group_size: 64
  sym: false
  auto_round_version: 0.13.0
  torch_dtype: torch.bfloat16
  device: cpu
  nsamples: 128
  iters: 200
  seqlen: 512
  batch_size: 4

Model Information

Quantized version of TinyLlama/TinyLlama_v1.1 using torch.bfloat16 for quantization tuning.

4 bits (INT4)
group size = 64
Asymmetrical Quantization
Method: WoQ — GPTQ (AutoGPTQ algorithm)

Fast and low memory, 2-3X speedup (slight accuracy drop at W4G64)

Quantization framework: Intel AutoRound v0.13.0

Note: this INT4 version of TinyLlama_v1.1 has been quantized for inference on Intel CPU, Intel iGPU (Arc) via intel-extension-for-pytorch, Intel NPU (AI Boost on Core Ultra series) via OpenVINO.

Usage

This is a base / completion model — prompt it directly with raw text:

from transformers import AutoModelForCausalLM, AutoTokenizer

repo = "fbaldassarri/TinyLlama_TinyLlama_v1.1-auto_gptq-int4-gs64-asym"
model = AutoModelForCausalLM.from_pretrained(repo, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(repo)

prompt = "The quick brown fox"
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, max_new_tokens=64)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Replication Recipe

The recommended way to reproduce this exact quantization is via the auto-round-pipeline — the same orchestration tool that produced this artifact.

Step 1 — Bootstrap the auto-round-pipeline

Set up a dedicated conda environment using the pipeline's setup.sh. Any of the install modes below produces an environment that can reproduce this quantization; pick the one that matches your goals:

git clone https://git.epicdynamic.com/auto-round-pipeline
cd auto-round-pipeline

# Pinned PyPI wheel (fastest; matches what this pipeline used by default):
bash setup.sh --pip-version 0.13.0

# Or build from intel/auto-round at the same tag (byte-identical reproducibility):
bash setup.sh --source-tag v0.13.0

# Intel Arc iGPU acceleration (e.g. Core Ultra 185H) — append to either of the above:
#   ... --intel-xpu
# NVIDIA / AMD opt-in: --cuda / --rocm

The script prints the resulting conda env name (something like auto-round-pipeline-v0.13.0[-src][-xpu|-cuda|-rocm]) at the end.

Step 2 — Quantize just this model

Activate the env that setup.sh created, then invoke the runner with the same job filters that produced this artifact:

conda activate <env-name-printed-by-setup.sh>
python runner.py \
    --model 'TinyLlama/TinyLlama_v1.1' \
    --quant 'INT4-gs64' \
    --format auto_gptq \
    --no-upload      # drop this to also push to HuggingFace Hub

Step 3 — (Optional) standalone Python recipe

If you'd rather call auto-round directly without the orchestration wrapper, this is the exact call the pipeline made:

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
from auto_round import AutoRound

model_name = "TinyLlama/TinyLlama_v1.1"
model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_name)

bits, group_size, sym = 4, 64, False
autoround = AutoRound(
    model, tokenizer,
    bits=bits, group_size=group_size, sym=sym,
    device_map="cpu",
    nsamples=128, iters=200, seqlen=512, batch_size=4,
)
autoround.quantize_and_save("./AutoRound/TinyLlama_TinyLlama_v1.1-auto_gptq-int4-gs64-asym", format="auto_gptq")

Actual Run Conditions

Recorded by the auto-round-pipeline at quantization time:

Field	Value
Intel auto-round version	0.13.0
transformers version	4.55.3
torch version	2.12.0+cpu
torch_dtype (load)	torch.bfloat16
calibration device	`cpu`
calibration samples	128
tuning iterations	200
calibration seq len	512
calibration batch size	4
quantization duration	8018.3s (133.6 min)
completed at (UTC)	2026-06-23T05:23:48.370785+00:00

License

Apache 2.0 License

Disclaimer

This quantized model comes with no warranty. It has been developed only for research purposes.