Text Generation
Transformers
Safetensors
PyTorch
English
lamoe
mixture-of-experts
custom-code
conversational
Instructions to use IMvision12/lamoe-247 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use IMvision12/lamoe-247 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="IMvision12/lamoe-247") 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("IMvision12/lamoe-247", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use IMvision12/lamoe-247 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "IMvision12/lamoe-247" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "IMvision12/lamoe-247", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/IMvision12/lamoe-247
- SGLang
How to use IMvision12/lamoe-247 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 "IMvision12/lamoe-247" \ --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": "IMvision12/lamoe-247", "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 "IMvision12/lamoe-247" \ --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": "IMvision12/lamoe-247", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use IMvision12/lamoe-247 with Docker Model Runner:
docker model run hf.co/IMvision12/lamoe-247
Download chat-template.json from IMvision12/lamoe-247: direct link, hf CLI and curl.
- Browser
- Download file 1.27 kB
-
https://huggingface.co/IMvision12/lamoe-247/resolve/main/chat-template.json
- Command line
-
hf download hf://IMvision12/lamoe-247/chat-template.json
-
curl -L -o chat-template.json https://huggingface.co/IMvision12/lamoe-247/resolve/main/chat-template.json
1.27 kB
| { | |
| "version": "IMvision-chat-tools-v1", | |
| "tokenizer_sha256": "557bdc7a6916c3e9c34cec2acd5d1a22325dca0d5ebc9b44c855d8a6443004a2", | |
| "max_sequence_length": 2048, | |
| "start_token": "<|bos|>", | |
| "role_tokens": [ | |
| "<|system|>", | |
| "<|user|>", | |
| "<|assistant|>" | |
| ], | |
| "end_turn": "<|end_turn|>", | |
| "eos_id": 3, | |
| "tool_result_encoding": "Existing user role token with <tool_response> ordinary-text JSON wrapper; always masked.", | |
| "tool_definitions": "Canonical tools JSON appended once to system content in <tools> tags.", | |
| "tool_call_encoding": "Assistant ordinary-text <tool_call> JSON containing id, name, arguments; supervised.", | |
| "call_only_end": "END_TURN only, no EOS; executor must return observations before continuation.", | |
| "labels": "Same length as input_ids, unshifted. Shift exactly once in causal loss. Mask system/user/tool/role/BOS/padding with -100.", | |
| "eos_policy": "EOS supervised only after final assistant text; never append fabricated observations.", | |
| "packing": "No cross-conversation packing. Independent rows; padding labels must be -100.", | |
| "inference": "Use this exact renderer and canonical tool names. Stop on END_TURN or EOS. Never sample tool results.", | |
| "attribution": "This model is developed and trained by IMvision12(Gitesh)" | |
| } | |