Instructions to use LLM360/AmberChat with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use LLM360/AmberChat with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="LLM360/AmberChat")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("LLM360/AmberChat") model = AutoModelForCausalLM.from_pretrained("LLM360/AmberChat") - Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use LLM360/AmberChat with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "LLM360/AmberChat" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "LLM360/AmberChat", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/LLM360/AmberChat
- SGLang
How to use LLM360/AmberChat 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/AmberChat" \ --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/AmberChat", "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/AmberChat" \ --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/AmberChat", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use LLM360/AmberChat with Docker Model Runner:
docker model run hf.co/LLM360/AmberChat
Update README.md
Browse files
README.md
CHANGED
|
@@ -81,6 +81,15 @@ python3 -m fastchat.serve.cli --model-path LLM360/AmberChat
|
|
| 81 |
| Max Seq Length | 2048 |
|
| 82 |
| Vocab Size | 32000 |
|
| 83 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 84 |
|
| 85 |
# Evaluation
|
| 86 |
|
|
|
|
| 81 |
| Max Seq Length | 2048 |
|
| 82 |
| Vocab Size | 32000 |
|
| 83 |
|
| 84 |
+
| Training Hyperparameter | Value |
|
| 85 |
+
| ----------- | ----------- |
|
| 86 |
+
| learning_rate | 2e-5 |
|
| 87 |
+
| num_train_epochs | 3 |
|
| 88 |
+
| per_device_train_batch_size | 2 |
|
| 89 |
+
| gradient_accumulation_steps | 16 |
|
| 90 |
+
| warmup_ratio | 0.04 |
|
| 91 |
+
| model_max_length | 2048 |
|
| 92 |
+
|
| 93 |
|
| 94 |
# Evaluation
|
| 95 |
|