Instructions to use eugenepentland/Minotaur-13b-Landmark with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use eugenepentland/Minotaur-13b-Landmark with Transformers:

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

pipe = pipeline("text-generation", model="eugenepentland/Minotaur-13b-Landmark", trust_remote_code=True)

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("eugenepentland/Minotaur-13b-Landmark", trust_remote_code=True)
model = AutoModelForMultimodalLM.from_pretrained("eugenepentland/Minotaur-13b-Landmark", trust_remote_code=True)

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use eugenepentland/Minotaur-13b-Landmark with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "eugenepentland/Minotaur-13b-Landmark"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "eugenepentland/Minotaur-13b-Landmark",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/eugenepentland/Minotaur-13b-Landmark

SGLang

How to use eugenepentland/Minotaur-13b-Landmark 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 "eugenepentland/Minotaur-13b-Landmark" \
    --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": "eugenepentland/Minotaur-13b-Landmark",
		"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 "eugenepentland/Minotaur-13b-Landmark" \
        --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": "eugenepentland/Minotaur-13b-Landmark",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use eugenepentland/Minotaur-13b-Landmark with Docker Model Runner:
```
docker model run hf.co/eugenepentland/Minotaur-13b-Landmark
```

Minotaur-13b-Landmark / configuration_landmark_llama.py

eugenepentland

added automap & landmark code

6d3e318 about 3 years ago

raw

history blame contribute delete

1.58 kB

	# coding=utf-8
	# Copyright 2022 EleutherAI and the HuggingFace Inc. team. All rights reserved.
	#
	# This code is based on EleutherAI's GPT-NeoX library and the GPT-NeoX
	# and OPT implementations in this library. It has been modified from its
	# original forms to accommodate minor architectural differences compared
	# to GPT-NeoX and OPT used by the Meta AI team that trained the model.
	#
	# Licensed under the Apache License, Version 2.0 (the "License");
	# you may not use this file except in compliance with the License.
	# You may obtain a copy of the License at
	#
	# http://www.apache.org/licenses/LICENSE-2.0
	#
	# Unless required by applicable law or agreed to in writing, software
	# distributed under the License is distributed on an "AS IS" BASIS,
	# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
	# See the License for the specific language governing permissions and
	# limitations under the License.
	""" LLaMA model configuration"""

	from transformers import LlamaConfig as HFLlamaConfig
	from transformers.utils import logging


	logger = logging.get_logger(__name__)


	class LlamaConfig(HFLlamaConfig):
	model_type = "llama"

	def __init__(
	self,
	mem_id=32001,
	mem_freq=50,
	mem_top_k=5,
	mem_max_seq_len=255,
	mem_max_cache_size=None,
	**kwargs,
	):
	self.mem_id = mem_id
	self.mem_freq = mem_freq
	self.mem_top_k = mem_top_k
	self.mem_max_seq_len = mem_max_seq_len
	self.mem_max_cache_size = mem_max_cache_size
	super().__init__(**kwargs)