Instructions to use AvoCahDoe/qwen2-5-7b-rlmpq-balanced with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AvoCahDoe/qwen2-5-7b-rlmpq-balanced with Transformers:

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

pipe = pipeline("text-generation", model="AvoCahDoe/qwen2-5-7b-rlmpq-balanced")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("AvoCahDoe/qwen2-5-7b-rlmpq-balanced")
model = AutoModelForCausalLM.from_pretrained("AvoCahDoe/qwen2-5-7b-rlmpq-balanced", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use AvoCahDoe/qwen2-5-7b-rlmpq-balanced with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "AvoCahDoe/qwen2-5-7b-rlmpq-balanced"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "AvoCahDoe/qwen2-5-7b-rlmpq-balanced",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/AvoCahDoe/qwen2-5-7b-rlmpq-balanced

SGLang

How to use AvoCahDoe/qwen2-5-7b-rlmpq-balanced 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 "AvoCahDoe/qwen2-5-7b-rlmpq-balanced" \
    --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": "AvoCahDoe/qwen2-5-7b-rlmpq-balanced",
		"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 "AvoCahDoe/qwen2-5-7b-rlmpq-balanced" \
        --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": "AvoCahDoe/qwen2-5-7b-rlmpq-balanced",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use AvoCahDoe/qwen2-5-7b-rlmpq-balanced with Docker Model Runner:
```
docker model run hf.co/AvoCahDoe/qwen2-5-7b-rlmpq-balanced
```

qwen2-5-7b-rlmpq-balanced / README.md

AvoCahDoe

RL-MPQ Balanced — 2026-06-11T21:12:44.630377

986dde3 verified about 2 months ago

preview code

Raw

History Blame Contribute Delete

2.71 kB

metadata

license: apache-2.0
base_model: Qwen/Qwen2.5-7B
pipeline_tag: text-generation
language:
  - en
tags:
  - qwen2
  - text-generation
  - rl-mpq
  - mixed-precision
  - quantization
  - fake-quantization
  - balanced
library_name: transformers
datasets:
  - wikitext
widget:
  - text: The capital of France is

Qwen 2.5 7B — RL-MPQ Balanced

Standalone RL-MPQ (Reinforcement Learning Mixed-Precision Quantization) checkpoint for the Balanced scenario — a quantized variant of Qwen/Qwen2.5-7B.

Field	Value
Base model	Qwen/Qwen2.5-7B
Scenario	Balanced
Avg bits / weight	3.3929
Compression vs FP16	4.7158×
WikiText-2 PPL	8.9305
Layers	28
Bit distribution	`{'3': 17, '4': 11}`
Format	Fake-quant FP16 + `rlmpq_policy.json`

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

repo = "AvoCahDoe/qwen2-5-7b-rlmpq-balanced"

model = AutoModelForCausalLM.from_pretrained(repo, torch_dtype="float16")
tokenizer = AutoTokenizer.from_pretrained(repo)

Other Qwen 2.5 7B scenarios

Scenario	Avg bits	Compression	WikiText-2 PPL
Aggressive	3.1429	5.0909x	9.3678
Conservative	3.6786	4.3495x	8.4114
Extreme Survival	2.4643	6.4928x	497.4791
High Fidelity	3.75	4.2667x	8.208

Grouped archive (all scenarios in one repo): AvoCahDoe/qwen2-5-7b-rlmpq

Method

Phase 3 — PPO agent assigns per-layer bit widths under the Balanced reward target.
Phase 4 — Policy replayed on real weights; WikiText-2 perplexity validates quality.
Export — Fake-quantized FP16 weights compatible with Hugging Face Transformers.

Files

File	Description
`config.json`	Llama architecture + RL-MPQ metadata
`model.safetensors`	Fake-quantized weights
`rlmpq_policy.json`	Per-layer bit-width policy
`rlmpq_metrics.json`	Validation & PPL summary

Citation

@misc{rlmpq_qwen2_5_7b_balanced_2026,
  title  = {RL-MPQ Balanced: Qwen 2.5 7B Mixed-Precision Quantization},
  author = {AvoCahDoe},
  year   = {2026},
  url    = {https://huggingface.co/AvoCahDoe/qwen2-5-7b-rlmpq-balanced}
}