Instructions to use AvoCahDoe/llama-2-13b-rlmpq-high-fidelity with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AvoCahDoe/llama-2-13b-rlmpq-high-fidelity with Transformers:

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

pipe = pipeline("text-generation", model="AvoCahDoe/llama-2-13b-rlmpq-high-fidelity")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("AvoCahDoe/llama-2-13b-rlmpq-high-fidelity")
model = AutoModelForCausalLM.from_pretrained("AvoCahDoe/llama-2-13b-rlmpq-high-fidelity", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use AvoCahDoe/llama-2-13b-rlmpq-high-fidelity with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "AvoCahDoe/llama-2-13b-rlmpq-high-fidelity"
# 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-2-13b-rlmpq-high-fidelity",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/AvoCahDoe/llama-2-13b-rlmpq-high-fidelity

SGLang

How to use AvoCahDoe/llama-2-13b-rlmpq-high-fidelity 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-2-13b-rlmpq-high-fidelity" \
    --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-2-13b-rlmpq-high-fidelity",
		"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-2-13b-rlmpq-high-fidelity" \
        --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-2-13b-rlmpq-high-fidelity",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use AvoCahDoe/llama-2-13b-rlmpq-high-fidelity with Docker Model Runner:
```
docker model run hf.co/AvoCahDoe/llama-2-13b-rlmpq-high-fidelity
```

llama-2-13b-rlmpq-high-fidelity / rlmpq_policy.json

AvoCahDoe

RL-MPQ High Fidelity — 2026-06-11T18:51:39.213945

671f392 verified about 2 months ago

Raw

History Blame

1.09 kB

	{
	"slug": "llama_2_13b",
	"hf_id": "meta-llama/Llama-2-13b-hf",
	"scenario": "High_Fidelity",
	"params": {
	"lambda_mse": 1.0,
	"lambda_bit": 0.05,
	"max_mse_clip": 1.0,
	"target_bits": 7.0,
	"lambda_budget": 2.0
	},
	"policy": [
	4,
	4,
	4,
	4,
	4,
	4,
	4,
	4,
	4,
	4,
	4,
	4,
	4,
	8,
	8,
	8,
	8,
	8,
	8,
	8,
	8,
	8,
	8,
	8,
	8,
	8,
	8,
	8,
	8,
	8,
	8,
	8,
	8,
	8,
	8,
	8,
	8,
	8,
	8,
	8
	],
	"num_layers": 40,
	"avg_bits": 6.7,
	"total_reward": -1.984871,
	"compression_ratio": 2.3881,
	"approx_size_gb": 10.887,
	"bit_distribution": {
	"4": 13,
	"8": 27
	},
	"avg_mse_per_bit": {
	"4": 0.43101077,
	"8": 0.00013292
	},
	"validation_elapsed_s": 0.0131,
	"policy_source": "/workspace/RL-NMP-Model-Quantasation/phase3/models/llama_2_13b/results/High_Fidelity_policy.json",
	"policy_path": "/workspace/RL-NMP-Model-Quantasation/phase3/models/llama_2_13b/results/High_Fidelity_policy.json",
	"training_run": "20260610_202902"
	}