Instructions to use Qmed/llama_instruct_ipex-tcm-AMX-bf16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use Qmed/llama_instruct_ipex-tcm-AMX-bf16 with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("/home/qmed-intel/models/meta-llama/Meta-Llama-3-8B-Instruct") model = PeftModel.from_pretrained(base_model, "Qmed/llama_instruct_ipex-tcm-AMX-bf16") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use Qmed/llama_instruct_ipex-tcm-AMX-bf16 with llama.cpp:
Install (macOS, Linux)
curl -LsSf https://llama.app/install.sh | sh # Start a local OpenAI-compatible server with a web UI: llama serve -hf Qmed/llama_instruct_ipex-tcm-AMX-bf16:Q4_K_M # Run inference directly in the terminal: llama cli -hf Qmed/llama_instruct_ipex-tcm-AMX-bf16:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf Qmed/llama_instruct_ipex-tcm-AMX-bf16:Q4_K_M # Run inference directly in the terminal: llama cli -hf Qmed/llama_instruct_ipex-tcm-AMX-bf16:Q4_K_M
Build from source code
git clone https://github.com/ggml-org/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-app # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama serve -hf Qmed/llama_instruct_ipex-tcm-AMX-bf16:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama cli -hf Qmed/llama_instruct_ipex-tcm-AMX-bf16:Q4_K_M
Use Docker
docker model run hf.co/Qmed/llama_instruct_ipex-tcm-AMX-bf16:Q4_K_M
- Llama new
- LM Studio
- Jan
- Ollama
How to use Qmed/llama_instruct_ipex-tcm-AMX-bf16 with Ollama:
ollama run hf.co/Qmed/llama_instruct_ipex-tcm-AMX-bf16:Q4_K_M
- Unsloth Desktop
- Docker Model Runner
How to use Qmed/llama_instruct_ipex-tcm-AMX-bf16 with Docker Model Runner:
docker model run hf.co/Qmed/llama_instruct_ipex-tcm-AMX-bf16:Q4_K_M
- Lemonade
How to use Qmed/llama_instruct_ipex-tcm-AMX-bf16 with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull Qmed/llama_instruct_ipex-tcm-AMX-bf16:Q4_K_M
Run and chat with the model
lemonade run user.llama_instruct_ipex-tcm-AMX-bf16-Q4_K_M
List all available models
lemonade list
- Atomic Chat
Download optimizer.pt from Qmed/llama_instruct_ipex-tcm-AMX-bf16: direct link, hf CLI and curl.
- Browser
- Download file 336 MB
-
https://huggingface.co/Qmed/llama_instruct_ipex-tcm-AMX-bf16/resolve/main/optimizer.pt
- Command line
-
hf download hf://Qmed/llama_instruct_ipex-tcm-AMX-bf16/optimizer.pt
-
curl -L -o optimizer.pt https://huggingface.co/Qmed/llama_instruct_ipex-tcm-AMX-bf16/resolve/main/optimizer.pt
336 MB
- Xet hash:
- 1f41823d2304d924fadf253006db451c45e66e649855dd3824b5b01508509fc3
- Size of remote file:
- 336 MB
- SHA256:
- 2fa8bbb3ac387efa6d68279632a30770cfa5f5bd5f136f1f00ae9a6e446a178b
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.