Text Generation
Transformers
Safetensors
falcon
text-generation-inference
8-bit precision
bitsandbytes
Instructions to use MeoChrist/YA with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use MeoChrist/YA with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="MeoChrist/YA")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("MeoChrist/YA") model = AutoModelForCausalLM.from_pretrained("MeoChrist/YA") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use MeoChrist/YA with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "MeoChrist/YA" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "MeoChrist/YA", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/MeoChrist/YA
- SGLang
How to use MeoChrist/YA 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 "MeoChrist/YA" \ --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": "MeoChrist/YA", "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 "MeoChrist/YA" \ --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": "MeoChrist/YA", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use MeoChrist/YA with Docker Model Runner:
docker model run hf.co/MeoChrist/YA
Upload /adapter_config.json with huggingface_hub
Browse files- adapter_config.json +2 -2
adapter_config.json
CHANGED
|
@@ -16,10 +16,10 @@
|
|
| 16 |
"rank_pattern": {},
|
| 17 |
"revision": null,
|
| 18 |
"target_modules": [
|
|
|
|
| 19 |
"query_key_value",
|
| 20 |
"dense_h_to_4h",
|
| 21 |
-
"dense"
|
| 22 |
-
"dense_4h_to_h"
|
| 23 |
],
|
| 24 |
"task_type": "CAUSAL_LM"
|
| 25 |
}
|
|
|
|
| 16 |
"rank_pattern": {},
|
| 17 |
"revision": null,
|
| 18 |
"target_modules": [
|
| 19 |
+
"dense_4h_to_h",
|
| 20 |
"query_key_value",
|
| 21 |
"dense_h_to_4h",
|
| 22 |
+
"dense"
|
|
|
|
| 23 |
],
|
| 24 |
"task_type": "CAUSAL_LM"
|
| 25 |
}
|