Text Generation
Transformers
Safetensors
NeMo
mistral
mergekit
Merge
nuslerp
conversational
text-generation-inference
Instructions to use DarkArtsForge/Protocol-Phantom-12B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use DarkArtsForge/Protocol-Phantom-12B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="DarkArtsForge/Protocol-Phantom-12B") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("DarkArtsForge/Protocol-Phantom-12B") model = AutoModelForCausalLM.from_pretrained("DarkArtsForge/Protocol-Phantom-12B") messages = [ {"role": "user", "content": "Who are you?"}, ] inputs = tokenizer.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt", ).to(model.device) outputs = model.generate(**inputs, max_new_tokens=40) print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - NeMo
How to use DarkArtsForge/Protocol-Phantom-12B with NeMo:
# tag did not correspond to a valid NeMo domain.
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use DarkArtsForge/Protocol-Phantom-12B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "DarkArtsForge/Protocol-Phantom-12B" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "DarkArtsForge/Protocol-Phantom-12B", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/DarkArtsForge/Protocol-Phantom-12B
- SGLang
How to use DarkArtsForge/Protocol-Phantom-12B 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 "DarkArtsForge/Protocol-Phantom-12B" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "DarkArtsForge/Protocol-Phantom-12B", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'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 "DarkArtsForge/Protocol-Phantom-12B" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "DarkArtsForge/Protocol-Phantom-12B", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use DarkArtsForge/Protocol-Phantom-12B with Docker Model Runner:
docker model run hf.co/DarkArtsForge/Protocol-Phantom-12B
Upload mergekit_config.yml with huggingface_hub
Browse files- mergekit_config.yml +17 -0
mergekit_config.yml
ADDED
|
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
architecture: MistralForCausalLM
|
| 2 |
+
base_model: B:/12B/mistralai--Mistral-Nemo-Instruct-2407
|
| 3 |
+
models:
|
| 4 |
+
- model: B:/12B/LatitudeGames--Wayfarer-2-12B
|
| 5 |
+
parameters:
|
| 6 |
+
weight: 0.5
|
| 7 |
+
- model: B:/12B/WokeAI--Tankie-DPE-12b-SFT-v2
|
| 8 |
+
parameters:
|
| 9 |
+
weight: 0.5
|
| 10 |
+
merge_method: nuslerp
|
| 11 |
+
parameters:
|
| 12 |
+
nuslerp_flatten: false # Flattens tensors to treat them as high-dimensional vectors
|
| 13 |
+
nuslerp_row_wise: true # Set to true if you want to interpolate per-row instead of per-tensor
|
| 14 |
+
dtype: float32
|
| 15 |
+
out_dtype: bfloat16
|
| 16 |
+
tokenizer:
|
| 17 |
+
source: union
|