Instructions to use LLM360/K2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use LLM360/K2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="LLM360/K2")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("LLM360/K2") model = AutoModelForCausalLM.from_pretrained("LLM360/K2") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use LLM360/K2 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "LLM360/K2" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "LLM360/K2", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/LLM360/K2
- SGLang
How to use LLM360/K2 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 "LLM360/K2" \ --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": "LLM360/K2", "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 "LLM360/K2" \ --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": "LLM360/K2", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use LLM360/K2 with Docker Model Runner:
docker model run hf.co/LLM360/K2
Update config.json
Browse files- config.json +3 -3
config.json
CHANGED
|
@@ -11,8 +11,8 @@
|
|
| 11 |
"hidden_size": 8192,
|
| 12 |
"initializer_range": 0.02,
|
| 13 |
"intermediate_size": 22016,
|
| 14 |
-
"max_position_embeddings":
|
| 15 |
-
"max_sequence_length":
|
| 16 |
"model_type": "llama",
|
| 17 |
"num_attention_heads": 64,
|
| 18 |
"num_hidden_layers": 80,
|
|
@@ -21,7 +21,7 @@
|
|
| 21 |
"pretraining_tp": 1,
|
| 22 |
"rms_norm_eps": 1e-05,
|
| 23 |
"rope_scaling": null,
|
| 24 |
-
"rope_theta":
|
| 25 |
"tie_word_embeddings": false,
|
| 26 |
"torch_dtype": "float16",
|
| 27 |
"transformers_version": "4.39.3",
|
|
|
|
| 11 |
"hidden_size": 8192,
|
| 12 |
"initializer_range": 0.02,
|
| 13 |
"intermediate_size": 22016,
|
| 14 |
+
"max_position_embeddings": 8192,
|
| 15 |
+
"max_sequence_length": 8192,
|
| 16 |
"model_type": "llama",
|
| 17 |
"num_attention_heads": 64,
|
| 18 |
"num_hidden_layers": 80,
|
|
|
|
| 21 |
"pretraining_tp": 1,
|
| 22 |
"rms_norm_eps": 1e-05,
|
| 23 |
"rope_scaling": null,
|
| 24 |
+
"rope_theta": 500000.0,
|
| 25 |
"tie_word_embeddings": false,
|
| 26 |
"torch_dtype": "float16",
|
| 27 |
"transformers_version": "4.39.3",
|