Instructions to use AvoCahDoe/llama-2-7b-rlmpq with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AvoCahDoe/llama-2-7b-rlmpq with Transformers:

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

pipe = pipeline("text-generation", model="AvoCahDoe/llama-2-7b-rlmpq")

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("AvoCahDoe/llama-2-7b-rlmpq")
model = AutoModelForMultimodalLM.from_pretrained("AvoCahDoe/llama-2-7b-rlmpq")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use AvoCahDoe/llama-2-7b-rlmpq with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/AvoCahDoe/llama-2-7b-rlmpq

SGLang

How to use AvoCahDoe/llama-2-7b-rlmpq 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/llama-2-7b-rlmpq" \
    --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": "AvoCahDoe/llama-2-7b-rlmpq",
		"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 "AvoCahDoe/llama-2-7b-rlmpq" \
        --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": "AvoCahDoe/llama-2-7b-rlmpq",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use AvoCahDoe/llama-2-7b-rlmpq with Docker Model Runner:
```
docker model run hf.co/AvoCahDoe/llama-2-7b-rlmpq
```

Llama 2 7B — RL-MPQ Quantized (Thesis Release)

Quantized variant of meta-llama/Llama-2-7b-hf using RL-MPQ (Reinforcement Learning Mixed-Precision Quantization): per-layer bit-width policies trained with PPO, validated on WikiText-2 perplexity.

This repo ships five compression scenarios as subfolders — from near-FP16 fidelity to aggressive survival mode — so you can pick the bits-vs-quality trade-off for your thesis experiments.


Base model	meta-llama/Llama-2-7b-hf
Method	RL-MPQ (PPO per-layer bit policy)
Format	Fake-quant FP16 weights + `rlmpq_policy.json`
Recommended start	`subfolder="Balanced"`

Scenarios

High_Fidelity/ — load with subfolder="High_Fidelity"
Conservative/ — load with subfolder="Conservative"
Balanced/ — load with subfolder="Balanced"
Aggressive/ — load with subfolder="Aggressive"
Extreme_Survival/ — load with subfolder="Extreme_Survival"

Results (WikiText-2)

Scenario	Avg bits	Compression vs FP16	Perplexity
High_Fidelity	6.5	2.4615x	4.9808
Conservative	5.125	3.122x	5.0276
Balanced	4.375	3.6571x	5.0437
Aggressive	3.5938	4.4522x	5.2614
Extreme_Survival	2.9688	5.3895x	10.9577

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

repo = "AvoCahDoe/llama-2-7b-rlmpq"
scenario = "Balanced"  # High_Fidelity | Conservative | Aggressive | Extreme_Survival

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

Important: Always pass subfolder=<scenario>. Root config.json describes the collection; weights and tokenizer live inside each scenario folder.

Method (thesis summary)

Phase 3 — PPO agent selects per-layer bit widths under scenario-specific reward targets.
Phase 4 — Policies replayed on real weights; WikiText-2 PPL measures quality retention.
Export — Fake-quantized FP16 checkpoints (compatible with Hugging Face Transformers).

Citation

@misc{rlmpq2026,
  title  = {RL-MPQ: Reinforcement Learning Mixed-Precision Quantization},
  author = {AvoCahDoe},
  year   = {2026},
  url    = {https://huggingface.co/AvoCahDoe/llama-2-7b-rlmpq}
}

Part of the RL-NMP-Model-Quantasation thesis framework.

Downloads last month: 44

Model tree for AvoCahDoe/llama-2-7b-rlmpq

Base model

meta-llama/Llama-2-7b-hf

Finetuned

(968)

this model

AvoCahDoe
/

llama-2-7b-rlmpq