Instructions to use HappyBulingling/MyModel-pretrain with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use HappyBulingling/MyModel-pretrain with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="HappyBulingling/MyModel-pretrain", trust_remote_code=True) messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# pip install -U transformers accelerate # Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("HappyBulingling/MyModel-pretrain", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use HappyBulingling/MyModel-pretrain with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "HappyBulingling/MyModel-pretrain" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "HappyBulingling/MyModel-pretrain", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/HappyBulingling/MyModel-pretrain
- SGLang
How to use HappyBulingling/MyModel-pretrain 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 "HappyBulingling/MyModel-pretrain" \ --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": "HappyBulingling/MyModel-pretrain", "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 "HappyBulingling/MyModel-pretrain" \ --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": "HappyBulingling/MyModel-pretrain", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use HappyBulingling/MyModel-pretrain with Docker Model Runner:
docker model run hf.co/HappyBulingling/MyModel-pretrain
File size: 1,148 Bytes
9b53d42 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 | """Rotary position embeddings."""
from __future__ import annotations
import torch
def precompute_rope(
head_dim: int,
max_position_embeddings: int,
rope_theta: float,
) -> tuple[torch.Tensor, torch.Tensor]:
if head_dim % 2 != 0:
raise ValueError("head_dim must be even for RoPE")
inv_freq = 1.0 / (
rope_theta ** (torch.arange(0, head_dim, 2, dtype=torch.float32) / head_dim)
)
positions = torch.arange(max_position_embeddings, dtype=torch.float32)
freqs = torch.outer(positions, inv_freq)
emb = torch.cat((freqs, freqs), dim=-1)
return emb.cos(), emb.sin()
def rotate_half(x: torch.Tensor) -> torch.Tensor:
half = x.shape[-1] // 2
return torch.cat((-x[..., half:], x[..., :half]), dim=-1)
def apply_rotary_pos_emb(
q: torch.Tensor,
k: torch.Tensor,
cos: torch.Tensor,
sin: torch.Tensor,
) -> tuple[torch.Tensor, torch.Tensor]:
cos = cos.to(q.device).unsqueeze(0).unsqueeze(2)
sin = sin.to(q.device).unsqueeze(0).unsqueeze(2)
q_embed = (q * cos) + (rotate_half(q) * sin)
k_embed = (k * cos) + (rotate_half(k) * sin)
return q_embed, k_embed
|