Text Generation
Transformers
Safetensors
PyTorch
mistral
smarter
code
chemistry
biology
finance
legal
art
Mixture of Experts
Merge
text-generation-inference
music
climate
medical
673_trillion_parameters
Instructions to use ZeppelinCorp/Charm_15 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ZeppelinCorp/Charm_15 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="ZeppelinCorp/Charm_15")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("ZeppelinCorp/Charm_15") model = AutoModelForCausalLM.from_pretrained("ZeppelinCorp/Charm_15", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use ZeppelinCorp/Charm_15 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "ZeppelinCorp/Charm_15" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "ZeppelinCorp/Charm_15", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/ZeppelinCorp/Charm_15
- SGLang
How to use ZeppelinCorp/Charm_15 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 "ZeppelinCorp/Charm_15" \ --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": "ZeppelinCorp/Charm_15", "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 "ZeppelinCorp/Charm_15" \ --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": "ZeppelinCorp/Charm_15", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use ZeppelinCorp/Charm_15 with Docker Model Runner:
docker model run hf.co/ZeppelinCorp/Charm_15
Create generation_config.json
Browse files- generation_config.json +16 -0
generation_config.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"max_length": 4096,
|
| 3 |
+
"temperature": 0.8,
|
| 4 |
+
"top_p": 0.95,
|
| 5 |
+
"top_k": 40,
|
| 6 |
+
"repetition_penalty": 1.1,
|
| 7 |
+
"do_sample": true,
|
| 8 |
+
"num_return_sequences": 1,
|
| 9 |
+
"early_stopping": true,
|
| 10 |
+
"length_penalty": 1.0,
|
| 11 |
+
"no_repeat_ngram_size": 2,
|
| 12 |
+
"presence_penalty": 0.3,
|
| 13 |
+
"frequency_penalty": 0.3,
|
| 14 |
+
"min_length": 10,
|
| 15 |
+
"use_cache": true
|
| 16 |
+
}
|