Text Generation
Transformers
PyTorch
English
llama
alpaca
vicuna
mix
Merge
model merge
roleplay
chat
instruct
text-generation-inference
Instructions to use digitous/13B-HyperMantis with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use digitous/13B-HyperMantis with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="digitous/13B-HyperMantis")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("digitous/13B-HyperMantis") model = AutoModelForCausalLM.from_pretrained("digitous/13B-HyperMantis") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use digitous/13B-HyperMantis with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "digitous/13B-HyperMantis" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "digitous/13B-HyperMantis", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/digitous/13B-HyperMantis
- SGLang
How to use digitous/13B-HyperMantis 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 "digitous/13B-HyperMantis" \ --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": "digitous/13B-HyperMantis", "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 "digitous/13B-HyperMantis" \ --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": "digitous/13B-HyperMantis", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use digitous/13B-HyperMantis with Docker Model Runner:
docker model run hf.co/digitous/13B-HyperMantis
Update README.md
Browse files
README.md
CHANGED
|
@@ -20,6 +20,8 @@ is a weight-sum multi model-merge comprised of:
|
|
| 20 |
|
| 21 |
((MantiCore3E+VicunaCocktail)+(SuperCOT+(StorytellingV2+BluemoonRP))) [All 13B Models]
|
| 22 |
|
|
|
|
|
|
|
| 23 |
Subjective testing shows quality results with KoboldAI (similar results are likely in Text Generation Webui, please disregard KAI-centric settings for that platform); Godlike preset with these tweaks - 2048 context, 800 Output Length, 1.3 Temp, 1.13 Repetition Penalty, AltTextGen:On, AltRepPen:Off, No Prompt Gen:On
|
| 24 |
|
| 25 |
Despite being primarily uncensored Vicuna models at its core, HyperMantis seems to respond best to the Alpaca instruct format. Speculatively due to manticore's eclectic instruct datasets generalizing the model's understanding of following instruct formats to some degree. What is known is HyperMantis responds best to the formality of Alpaca's format, whereas Human/Assistant appears to trigger vestigial traces of moralizing and servitude that aren't conducive for roleplay or freeform instructions.
|
|
|
|
| 20 |
|
| 21 |
((MantiCore3E+VicunaCocktail)+(SuperCOT+(StorytellingV2+BluemoonRP))) [All 13B Models]
|
| 22 |
|
| 23 |
+
(GGML and GPTQ are no longer in this repo and will be migrated to a separate repo for easier git download convenience)
|
| 24 |
+
|
| 25 |
Subjective testing shows quality results with KoboldAI (similar results are likely in Text Generation Webui, please disregard KAI-centric settings for that platform); Godlike preset with these tweaks - 2048 context, 800 Output Length, 1.3 Temp, 1.13 Repetition Penalty, AltTextGen:On, AltRepPen:Off, No Prompt Gen:On
|
| 26 |
|
| 27 |
Despite being primarily uncensored Vicuna models at its core, HyperMantis seems to respond best to the Alpaca instruct format. Speculatively due to manticore's eclectic instruct datasets generalizing the model's understanding of following instruct formats to some degree. What is known is HyperMantis responds best to the formality of Alpaca's format, whereas Human/Assistant appears to trigger vestigial traces of moralizing and servitude that aren't conducive for roleplay or freeform instructions.
|