How to use from
llama.cppInstall from WinGet (Windows)
winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf QuantFactory/Flammades-Mistral-Nemo-12B-GGUF:# Run inference directly in the terminal:
llama cli -hf QuantFactory/Flammades-Mistral-Nemo-12B-GGUF: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 QuantFactory/Flammades-Mistral-Nemo-12B-GGUF:# Run inference directly in the terminal:
./llama-cli -hf QuantFactory/Flammades-Mistral-Nemo-12B-GGUF: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 QuantFactory/Flammades-Mistral-Nemo-12B-GGUF:# Run inference directly in the terminal:
./build/bin/llama-cli -hf QuantFactory/Flammades-Mistral-Nemo-12B-GGUF:Use Docker
docker model run hf.co/QuantFactory/Flammades-Mistral-Nemo-12B-GGUF:Quick Links
QuantFactory/Flammades-Mistral-Nemo-12B-GGUF
This is quantized version of flammenai/Flammades-Mistral-Nemo-12B created using llama.cpp
Original Model Card
Flammades-Mistral-Nemo-12B
nbeerbower/Mistral-Nemo-Gutenberg-Doppel-12B-v2 finetuned on flammenai/Date-DPO-NoAsterisks and jondurbin/truthy-dpo-v0.1.
Method
ORPO tuned with 2x RTX 3090 for 3 epochs.
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 22.34 |
| IFEval (0-Shot) | 38.42 |
| BBH (3-Shot) | 32.39 |
| MATH Lvl 5 (4-Shot) | 6.19 |
| GPQA (0-shot) | 7.16 |
| MuSR (0-shot) | 20.31 |
| MMLU-PRO (5-shot) | 29.57 |
- Downloads last month
- 65
Hardware compatibility
Log In to add your hardware
2-bit
3-bit
4-bit
5-bit
6-bit
8-bit
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for QuantFactory/Flammades-Mistral-Nemo-12B-GGUF
Base model
winglian/m12b-20240721-test010Datasets used to train QuantFactory/Flammades-Mistral-Nemo-12B-GGUF
Evaluation results
- strict accuracy on IFEval (0-Shot)Open LLM Leaderboard38.420
- normalized accuracy on BBH (3-Shot)Open LLM Leaderboard32.390
- exact match on MATH Lvl 5 (4-Shot)Open LLM Leaderboard6.190
- acc_norm on GPQA (0-shot)Open LLM Leaderboard7.160
- acc_norm on MuSR (0-shot)Open LLM Leaderboard20.310
- accuracy on MMLU-PRO (5-shot)test set Open LLM Leaderboard29.570
Install (macOS, Linux)
# Start a local OpenAI-compatible server with a web UI: llama serve -hf QuantFactory/Flammades-Mistral-Nemo-12B-GGUF:# Run inference directly in the terminal: llama cli -hf QuantFactory/Flammades-Mistral-Nemo-12B-GGUF: