Instructions to use Dans-DiscountModels/Dans-RetroRodeo-13b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Dans-DiscountModels/Dans-RetroRodeo-13b with Transformers:

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

pipe = pipeline("text-generation", model="Dans-DiscountModels/Dans-RetroRodeo-13b")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Dans-DiscountModels/Dans-RetroRodeo-13b")
model = AutoModelForCausalLM.from_pretrained("Dans-DiscountModels/Dans-RetroRodeo-13b")

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Dans-DiscountModels/Dans-RetroRodeo-13b with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Dans-DiscountModels/Dans-RetroRodeo-13b

SGLang

How to use Dans-DiscountModels/Dans-RetroRodeo-13b 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 "Dans-DiscountModels/Dans-RetroRodeo-13b" \
    --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": "Dans-DiscountModels/Dans-RetroRodeo-13b",
		"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 "Dans-DiscountModels/Dans-RetroRodeo-13b" \
        --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": "Dans-DiscountModels/Dans-RetroRodeo-13b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Dans-DiscountModels/Dans-RetroRodeo-13b with Docker Model Runner:
```
docker model run hf.co/Dans-DiscountModels/Dans-RetroRodeo-13b
```

PocketDoc commited on Sep 20, 2023

Commit

49c8828

1 Parent(s): 0bf2a0f

Update README.md

Browse files

Files changed (1) hide show

README.md +4 -2

README.md CHANGED Viewed

@@ -10,8 +10,10 @@ This model is proficient in crafting text-based adventure games. It can both con
 This model was trained on [Holodeck-1](https://huggingface.co/KoboldAI/LLAMA2-13B-Holodeck-1) using a the floyd and cys datasets from the skein text adventure dataset. The dataset has been improved over what was used in my previous model "Dans-CreepingSenseOfDoom" and this time presented in the more traditional adventure mode format.
 ## PROMPT FORMAT AND EXAMPLES:
-#### For shorter responses:
 Traditional adventure format with a description of the genre, tags, and other misc information at the top followed by an optional introductory message. User messages are prefixed with two new lines and "> "
 ```
 [Genres: Science Fiction]
 [Tags: humor, old school]
@@ -57,7 +59,7 @@ The man looks up from his writing. "Who are you?" he asks suspiciously.
 > You ask where people are getting sent
 "To the future, obviously."
 ```
-#### For longer novel like responses:
 ```
 [Genres: grimdark fantasy] [Tags: Fantasy, Grimdark, Serious, Villain Protagonist, War] [Description: This story is definitely more "story" than "game", however there are two distinct paths that can be followed, each with their own pitfalls and additional choices. This story can get long, and assuming you're surviving, years do pass in it and you and your environment will change.] [First message intro] [Mode: Interactive Storyteller]
 It was a dark night when I received my first letter from my father. It had been sent by messenger bird and delivered to me at midnight. As I read through its contents, I could feel myself growing numb as I realized what he had asked of me. My father wanted me to go to war.

 This model was trained on [Holodeck-1](https://huggingface.co/KoboldAI/LLAMA2-13B-Holodeck-1) using a the floyd and cys datasets from the skein text adventure dataset. The dataset has been improved over what was used in my previous model "Dans-CreepingSenseOfDoom" and this time presented in the more traditional adventure mode format.
 ## PROMPT FORMAT AND EXAMPLES:
+#### Format description:
 Traditional adventure format with a description of the genre, tags, and other misc information at the top followed by an optional introductory message. User messages are prefixed with two new lines and "> "
+#### Examples of shorter responses:
 ```
 [Genres: Science Fiction]
 [Tags: humor, old school]
 > You ask where people are getting sent
 "To the future, obviously."
 ```
+#### Examples of longer novel like responses:
 ```
 [Genres: grimdark fantasy] [Tags: Fantasy, Grimdark, Serious, Villain Protagonist, War] [Description: This story is definitely more "story" than "game", however there are two distinct paths that can be followed, each with their own pitfalls and additional choices. This story can get long, and assuming you're surviving, years do pass in it and you and your environment will change.] [First message intro] [Mode: Interactive Storyteller]
 It was a dark night when I received my first letter from my father. It had been sent by messenger bird and delivered to me at midnight. As I read through its contents, I could feel myself growing numb as I realized what he had asked of me. My father wanted me to go to war.