Text Generation
Transformers
Safetensors
English
Arabic
quasar_long
silx-ai
quasar-preview
quasar
foundation-model
Mixture of Experts
18b
2b-active
long-context
bittensor
sn24
decentralized-training
distillation
hybrid-transformer
loop-transformer
safe-nope
drope
conversational
custom_code
Instructions to use mainline777/base_IIXIV with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use mainline777/base_IIXIV with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="mainline777/base_IIXIV", trust_remote_code=True) messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("mainline777/base_IIXIV", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use mainline777/base_IIXIV with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "mainline777/base_IIXIV" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "mainline777/base_IIXIV", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/mainline777/base_IIXIV
- SGLang
How to use mainline777/base_IIXIV 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 "mainline777/base_IIXIV" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "mainline777/base_IIXIV", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'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 "mainline777/base_IIXIV" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "mainline777/base_IIXIV", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use mainline777/base_IIXIV with Docker Model Runner:
docker model run hf.co/mainline777/base_IIXIV
| import warnings | |
| from transformers.configuration_utils import PretrainedConfig | |
| class BitNetConfig(PretrainedConfig): | |
| model_type = 'bitnet' | |
| keys_to_ignore_at_inference = ['past_key_values'] | |
| def __init__( | |
| self, | |
| hidden_size: int = 2048, | |
| num_hidden_layers: int = 24, | |
| num_heads: int = 32, | |
| num_kv_heads: int | None = None, | |
| window_size: int | None = None, | |
| rope_theta: float | None = 10000., | |
| max_position_embeddings: int = 2048, | |
| hidden_ratio: int | None = 4, | |
| intermediate_size: int | None = None, | |
| hidden_act: str = "swish", | |
| initializer_range: float = 0.02, | |
| elementwise_affine: bool | None = True, | |
| norm_eps: float = 1e-6, | |
| use_cache: bool = True, | |
| pad_token_id: int | None = None, | |
| bos_token_id: int = 1, | |
| eos_token_id: int = 2, | |
| tie_word_embeddings: bool = False, | |
| fuse_norm: bool = True, | |
| fuse_swiglu: bool = True, | |
| fuse_cross_entropy: bool = True, | |
| fuse_linear_cross_entropy: bool = False, | |
| use_l2warp: bool = False, | |
| vocab_size: int = 32000, | |
| **kwargs, | |
| ): | |
| self.hidden_size = hidden_size | |
| self.num_hidden_layers = num_hidden_layers | |
| self.num_heads = num_heads | |
| self.num_kv_heads = num_kv_heads | |
| self.window_size = window_size | |
| self.rope_theta = rope_theta | |
| self.max_position_embeddings = max_position_embeddings | |
| self.hidden_ratio = hidden_ratio | |
| self.intermediate_size = intermediate_size | |
| self.hidden_act = hidden_act | |
| self.initializer_range = initializer_range | |
| self.elementwise_affine = elementwise_affine | |
| self.norm_eps = norm_eps | |
| self.use_cache = use_cache | |
| self.fuse_norm = fuse_norm | |
| self.fuse_swiglu = fuse_swiglu | |
| self.fuse_cross_entropy = fuse_cross_entropy | |
| self.fuse_linear_cross_entropy = fuse_linear_cross_entropy | |
| self.use_l2warp = use_l2warp | |
| self.vocab_size = vocab_size | |
| if fuse_cross_entropy and fuse_linear_cross_entropy: | |
| raise ValueError( | |
| "`fuse_cross_entropy` and `fuse_linear_cross_entropy` cannot be True at the same time.", | |
| ) | |
| if fuse_linear_cross_entropy: | |
| warnings.warn( | |
| "`fuse_linear_cross_entropy` is enabled, which can improves memory efficiency " | |
| "at the potential cost of reduced precision. " | |
| "If you observe issues like loss divergence, consider disabling this setting.", | |
| ) | |
| super().__init__( | |
| pad_token_id=pad_token_id, | |
| bos_token_id=bos_token_id, | |
| eos_token_id=eos_token_id, | |
| tie_word_embeddings=tie_word_embeddings, | |
| **kwargs, | |
| ) | |