Text Generation
Transformers
Safetensors
Mongolian
rdt
traditional-mongolian
recurrent-depth-transformer
mamba
causal-lm
custom-code
custom_code
Instructions to use Montlok/DoL-1.2-Base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Montlok/DoL-1.2-Base with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Montlok/DoL-1.2-Base", trust_remote_code=True)# pip install -U transformers accelerate # Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("Montlok/DoL-1.2-Base", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use Montlok/DoL-1.2-Base with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Montlok/DoL-1.2-Base" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Montlok/DoL-1.2-Base", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Montlok/DoL-1.2-Base
- SGLang
How to use Montlok/DoL-1.2-Base 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 "Montlok/DoL-1.2-Base" \ --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": "Montlok/DoL-1.2-Base", "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 "Montlok/DoL-1.2-Base" \ --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": "Montlok/DoL-1.2-Base", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use Montlok/DoL-1.2-Base with Docker Model Runner:
docker model run hf.co/Montlok/DoL-1.2-Base
Download Tokenizer/generic_bpe/byte_fallback.py from Montlok/DoL-1.2-Base: direct link, hf CLI and curl.
- Browser
- Download file 1.53 kB
-
https://huggingface.co/Montlok/DoL-1.2-Base/resolve/main/Tokenizer/generic_bpe/byte_fallback.py
- Command line
-
hf download hf://Montlok/DoL-1.2-Base/Tokenizer/generic_bpe/byte_fallback.py
-
curl -L -o byte_fallback.py https://huggingface.co/Montlok/DoL-1.2-Base/resolve/main/Tokenizer/generic_bpe/byte_fallback.py
1.53 kB
| # -*- coding: utf-8 -*- | |
| """Byte-fallback helpers shared by tokenizer tracks.""" | |
| from __future__ import annotations | |
| from Tokenizer.unified.encoded import EncodedToken | |
| def byte_token(byte: int) -> str: | |
| return f"<0x{byte:02X}>" | |
| def is_byte_token(token: str) -> bool: | |
| return token.startswith("<0x") and token.endswith(">") and len(token) == 6 | |
| def decode_byte_token(token: str) -> int: | |
| return int(token[3:5], 16) | |
| def encode_byte_fallback( | |
| text: str, | |
| vocab: dict[str, int], | |
| unk_id: int, | |
| base_start: int = 0, | |
| track: str = "misc", | |
| ) -> list[EncodedToken]: | |
| tokens: list[EncodedToken] = [] | |
| for rel_pos, ch in enumerate(text): | |
| direct = vocab.get(ch) | |
| start = base_start + rel_pos | |
| end = start + 1 | |
| if direct is not None: | |
| tokens.append(EncodedToken(direct, ch, track, start, end)) | |
| continue | |
| # ``surrogatepass`` keeps encoding from raising on lone surrogates | |
| # (U+D800–U+DFFF), which appear in scraped/raw web text. A strict | |
| # ``encode`` would raise UnicodeEncodeError and abort the whole shard; | |
| # decode mirrors this with ``errors="replace"``. | |
| for byte in ch.encode("utf-8", "surrogatepass"): | |
| tok = byte_token(byte) | |
| tokens.append(EncodedToken(vocab.get(tok, unk_id), tok, track, start, end)) | |
| return tokens | |
| def decode_bytes(byte_tokens: list[str]) -> str: | |
| return bytes(decode_byte_token(token) for token in byte_tokens).decode( | |
| "utf-8", errors="replace" | |
| ) | |