Instructions to use breadlicker45/MuseRizz with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use breadlicker45/MuseRizz with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="breadlicker45/MuseRizz")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("breadlicker45/MuseRizz") model = AutoModelForCausalLM.from_pretrained("breadlicker45/MuseRizz") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use breadlicker45/MuseRizz with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "breadlicker45/MuseRizz" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "breadlicker45/MuseRizz", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/breadlicker45/MuseRizz
- SGLang
How to use breadlicker45/MuseRizz 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 "breadlicker45/MuseRizz" \ --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": "breadlicker45/MuseRizz", "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 "breadlicker45/MuseRizz" \ --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": "breadlicker45/MuseRizz", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use breadlicker45/MuseRizz with Docker Model Runner:
docker model run hf.co/breadlicker45/MuseRizz
Commit ·
2b190b2
1
Parent(s): 466444b
Upload 4 files
Browse files- config.json +21 -0
- generation_config.json +6 -0
- pytorch_model (6).bin +3 -0
- tokenizer (5).json +0 -0
config.json
ADDED
|
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "breadlicker45/MuseBan",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"RwkvForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_hidden_size": 1024,
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"context_length": 1024,
|
| 9 |
+
"eos_token_id": 0,
|
| 10 |
+
"hidden_size": 1024,
|
| 11 |
+
"intermediate_size": 4096,
|
| 12 |
+
"layer_norm_epsilon": 1e-05,
|
| 13 |
+
"model_type": "rwkv",
|
| 14 |
+
"num_hidden_layers": 24,
|
| 15 |
+
"rescale_every": 6,
|
| 16 |
+
"tie_word_embeddings": false,
|
| 17 |
+
"torch_dtype": "float32",
|
| 18 |
+
"transformers_version": "4.31.0.dev0",
|
| 19 |
+
"use_cache": true,
|
| 20 |
+
"vocab_size": 50279
|
| 21 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 0,
|
| 4 |
+
"eos_token_id": 2,
|
| 5 |
+
"transformers_version": "4.31.0.dev0"
|
| 6 |
+
}
|
pytorch_model (6).bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:653ec3b99f655eac0fe7145424cef96b28e1793d3a26306083973694ef656d43
|
| 3 |
+
size 1721752485
|
tokenizer (5).json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|