Instructions to use PrunaAI/WizardLM-2-7B-GGUF-smashed with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Pruna AI
How to use PrunaAI/WizardLM-2-7B-GGUF-smashed with Pruna AI:
from pruna import PrunaModel model = PrunaModel.from_pretrained("PrunaAI/WizardLM-2-7B-GGUF-smashed") - llama-cpp-python
How to use PrunaAI/WizardLM-2-7B-GGUF-smashed with llama-cpp-python:
# !pip install llama-cpp-python from llama_cpp import Llama llm = Llama.from_pretrained( repo_id="PrunaAI/WizardLM-2-7B-GGUF-smashed", filename="microsoft_WizardLM-2-7B.IQ3_M.gguf", )
llm.create_chat_completion( messages = "No input example has been defined for this model task." )
- Notebooks
- Google Colab
- Kaggle
- Local Apps
- llama.cpp
How to use PrunaAI/WizardLM-2-7B-GGUF-smashed with llama.cpp:
Install from brew
brew install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf PrunaAI/WizardLM-2-7B-GGUF-smashed:Q4_K_M # Run inference directly in the terminal: llama-cli -hf PrunaAI/WizardLM-2-7B-GGUF-smashed:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf PrunaAI/WizardLM-2-7B-GGUF-smashed:Q4_K_M # Run inference directly in the terminal: llama-cli -hf PrunaAI/WizardLM-2-7B-GGUF-smashed:Q4_K_M
Use pre-built binary
# Download pre-built binary from: # https://github.com/ggerganov/llama.cpp/releases # Start a local OpenAI-compatible server with a web UI: ./llama-server -hf PrunaAI/WizardLM-2-7B-GGUF-smashed:Q4_K_M # Run inference directly in the terminal: ./llama-cli -hf PrunaAI/WizardLM-2-7B-GGUF-smashed:Q4_K_M
Build from source code
git clone https://github.com/ggerganov/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-server llama-cli # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama-server -hf PrunaAI/WizardLM-2-7B-GGUF-smashed:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama-cli -hf PrunaAI/WizardLM-2-7B-GGUF-smashed:Q4_K_M
Use Docker
docker model run hf.co/PrunaAI/WizardLM-2-7B-GGUF-smashed:Q4_K_M
- LM Studio
- Jan
- Ollama
How to use PrunaAI/WizardLM-2-7B-GGUF-smashed with Ollama:
ollama run hf.co/PrunaAI/WizardLM-2-7B-GGUF-smashed:Q4_K_M
- Unsloth Studio new
How to use PrunaAI/WizardLM-2-7B-GGUF-smashed with Unsloth Studio:
Install Unsloth Studio (macOS, Linux, WSL)
curl -fsSL https://unsloth.ai/install.sh | sh # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for PrunaAI/WizardLM-2-7B-GGUF-smashed to start chatting
Install Unsloth Studio (Windows)
irm https://unsloth.ai/install.ps1 | iex # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for PrunaAI/WizardLM-2-7B-GGUF-smashed to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for PrunaAI/WizardLM-2-7B-GGUF-smashed to start chatting
- Docker Model Runner
How to use PrunaAI/WizardLM-2-7B-GGUF-smashed with Docker Model Runner:
docker model run hf.co/PrunaAI/WizardLM-2-7B-GGUF-smashed:Q4_K_M
- Lemonade
How to use PrunaAI/WizardLM-2-7B-GGUF-smashed with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull PrunaAI/WizardLM-2-7B-GGUF-smashed:Q4_K_M
Run and chat with the model
lemonade run user.WizardLM-2-7B-GGUF-smashed-Q4_K_M
List all available models
lemonade list
Upload folder using huggingface_hub
Upload folder using huggingface_hub
Multi commit ID: 5c430011c78d12207812feed15f3981cc36a2b2e98f121e0d65571c7bfa2b845
Scheduled commits:
- Upload 1 file(s) totalling 3.3G (2befca1a07a468f9063e9e08006cc0bc30e50a68b2d4df1f8e230fbd513f2d5a)
- Upload 1 file(s) totalling 3.2G (8cfb4d9750250c32899be0f313134ec784a40f04f1553258b43f4be878389f75)
- Upload 1 file(s) totalling 3.0G (1d5414afc699c11b8f02a4c98b1517ef6172d556a2be7faa9d2882771e42c4e1)
- Upload 1 file(s) totalling 4.2G (9b5fbb4db7cfd24c38977ff618123ebb9b3e33a7936dd61a287d8e823c28c503)
- Upload 1 file(s) totalling 3.9G (98d6c0af735e9ac9f89bebd7f4aea3bc65f26a010ccd6c67114a72c00eba9521)
- Upload 1 file(s) totalling 2.7G (63a863c48dda84756120d7a432686bdf58ab787851d415e2ec9263d3afc141a7)
- Upload 1 file(s) totalling 3.8G (2da95da32d278f7c1627d8c690050c16443091993e44c2c0b9c7ae7a821ee5aa)
- Upload 1 file(s) totalling 3.5G (ff8430e6875a9fd1fcc06124aa8e85ecff5c4ffacc355ce9de52ba08d6a4433c)
- Upload 1 file(s) totalling 3.2G (2ee10ca3c80c22ae0d67dadcff23f93d5e9a80c755784a11b3f30f6864b68557)
- Upload 1 file(s) totalling 4.1G (ba14a0ce99906cbd2fd9400537e401edc30a62440f46d302325ef21ddbff9494)
- Upload 1 file(s) totalling 4.6G (2dc167d2ca11632cb3672c4cc5ed8ba2dd9cc27feb93d02c751d4eb7f3b0501c)
- Upload 1 file(s) totalling 4.4G (447d974b332b9d43b8c9d7e0a954741aed42dc0ffb16da2a77afa4274b6b3384)
- Upload 1 file(s) totalling 4.1G (fd92ba04089d33b10c35605a2bcd358f589ef2989b00d388da0331702e0b4347)
- Upload 1 file(s) totalling 5.0G (8837fe5e157027c56258d65dfd42529f2516b53e2a080112ac0c3709bdf96bb7)
- Upload 1 file(s) totalling 5.4G (030d19120f313b86974b7b31f5fcdaa07d0d7f0faaa8267ed724d1c5ce423e7c)
- Upload 1 file(s) totalling 5.1G (c1a9d7591f0d976dca9e06f516fd7714ce899923267ec7c2553028cc9c0307aa)
- Upload 1 file(s) totalling 5.0G (fd1e8e31bef983b51162cd8f242bfdaa8d19e93554c652f722016a2780e84ad0)
- Upload 1 file(s) totalling 5.9G (b077fb17fdf6b6fd38cb8ff99de4b10fdea7cd09e6bab556d3d75c36136078ea)
- Upload 1 file(s) totalling 7.7G (6ade10ac637fd19c05d4b046eafc3f28c38c877e29da133ba6dc32a9113840dc)
- Upload 1 file(s) totalling 14.5G (6db2ff41958013d5e9f5dcd020bd16e4adb40887aba4a7cecfee5e8014b82f8f)
- Upload 1 file(s) totalling 12.1K (e2831ce9d8d8b3d1461100b88a073d0c5344135f04db9fd61584b29ae53f00bb)
This is a PR opened using the huggingface_hub library in the context of a multi-commit. PR can be commented as a usual PR. However, please be aware that manually updating the PR description, changing the PR status, or pushing new commits, is not recommended as it might corrupt the commit process. Learn more about multi-commits in this guide.
create_pr=False has been passed so PR is automatically merged.
This is a comment posted using the huggingface_hub library in the context of a multi-commit. Learn more about multi-commits in this guide.
Multi-commit is now completed! You can ping the repo owner to review the changes. This PR can now be commented or modified without risking to corrupt it.
This is a comment posted using the huggingface_hub library in the context of a multi-commit. Learn more about multi-commits in this guide.