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 / config.json

AvoCahDoe

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

671f392 verified about 2 months ago

Raw

History Blame

1.32 kB

	{
	"architectures": [
	"LlamaForCausalLM"
	],
	"attention_bias": false,
	"attention_dropout": 0.0,
	"bos_token_id": 1,
	"dtype": "float16",
	"eos_token_id": 2,
	"head_dim": 128,
	"hidden_act": "silu",
	"hidden_size": 5120,
	"initializer_range": 0.02,
	"intermediate_size": 13824,
	"max_position_embeddings": 4096,
	"mlp_bias": false,
	"model_type": "llama",
	"num_attention_heads": 40,
	"num_hidden_layers": 40,
	"num_key_value_heads": 40,
	"pad_token_id": null,
	"pretraining_tp": 1,
	"rms_norm_eps": 1e-05,
	"rope_parameters": {
	"rope_theta": 10000.0,
	"rope_type": "default",
	"type": "default"
	},
	"tie_word_embeddings": false,
	"transformers_version": "5.11.0",
	"use_cache": true,
	"vocab_size": 32000,
	"base_model": "meta-llama/Llama-2-13b-hf",
	"quantization": {
	"method": "rl-mpq",
	"format": "fake-quant-fp16",
	"scenario": "High_Fidelity",
	"avg_bits": 6.7,
	"description": "Per-layer mixed bit-width via PPO-trained policy (not GPTQ/AWQ)"
	},
	"rlmpq": {
	"framework": "RL-NMP-Model-Quantasation",
	"scenario": "High_Fidelity",
	"scenario_label": "High Fidelity",
	"repo_id": "AvoCahDoe/llama-2-13b-rlmpq-high-fidelity",
	"grouped_repo": "AvoCahDoe/llama-2-13b-rlmpq",
	"collection_title": "RL-MPQ \u2014 Llama 2 13B"
	}
	}