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/Q2.5-Veltha-14B-GGUF:# Run inference directly in the terminal:
llama cli -hf QuantFactory/Q2.5-Veltha-14B-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/Q2.5-Veltha-14B-GGUF:# Run inference directly in the terminal:
./llama-cli -hf QuantFactory/Q2.5-Veltha-14B-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/Q2.5-Veltha-14B-GGUF:# Run inference directly in the terminal:
./build/bin/llama-cli -hf QuantFactory/Q2.5-Veltha-14B-GGUF:Use Docker
docker model run hf.co/QuantFactory/Q2.5-Veltha-14B-GGUF:Quick Links
A newer version of this model is available: djuna/Q2.5-Veltha-14B-0.5
QuantFactory/Q2.5-Veltha-14B-GGUF
This is quantized version of djuna/Q2.5-Veltha-14B created using llama.cpp
Original Model Card
merge
This is a merge of pre-trained language models created using mergekit.
Merge Details
Merge Method
This model was merged using the della_linear merge method using qwen/Qwen2.5-14b as a base.
Models Merged
The following models were included in the merge:
- huihui-ai/Qwen2.5-14B-Instruct-abliterated-v2
- EVA-UNIT-01/EVA-Qwen2.5-14B-v0.2
- v000000/Qwen2.5-Lumen-14B
- arcee-ai/SuperNova-Medius
- allura-org/TQ2.5-14B-Aletheia-v1
Configuration
The following YAML configuration was used to produce this model:
merge_method: della_linear
dtype: float32
out_dtype: bfloat16
parameters:
epsilon: 0.04
lambda: 1.05
normalize: true
base_model: qwen/Qwen2.5-14b
tokenizer_source: arcee-ai/SuperNova-Medius
models:
- model: arcee-ai/SuperNova-Medius
parameters:
weight: 10
density: 1
- model: EVA-UNIT-01/EVA-Qwen2.5-14B-v0.2
parameters:
weight: 7
density: 0.5
- model: v000000/Qwen2.5-Lumen-14B
parameters:
weight: 7
density: 0.4
- model: allura-org/TQ2.5-14B-Aletheia-v1
parameters:
weight: 8
density: 0.4
- model: huihui-ai/Qwen2.5-14B-Instruct-abliterated-v2
parameters:
weight: 8
density: 0.45
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 39.21 |
| IFEval (0-Shot) | 82.92 |
| BBH (3-Shot) | 49.75 |
| MATH Lvl 5 (4-Shot) | 28.02 |
| GPQA (0-shot) | 14.54 |
| MuSR (0-shot) | 12.26 |
| MMLU-PRO (5-shot) | 47.76 |
- Downloads last month
- 112
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/Q2.5-Veltha-14B-GGUF
Merge model
this model
Evaluation results
- strict accuracy on IFEval (0-Shot)Open LLM Leaderboard82.920
- normalized accuracy on BBH (3-Shot)Open LLM Leaderboard49.750
- exact match on MATH Lvl 5 (4-Shot)Open LLM Leaderboard28.020
- acc_norm on GPQA (0-shot)Open LLM Leaderboard14.540
- acc_norm on MuSR (0-shot)Open LLM Leaderboard12.260
- accuracy on MMLU-PRO (5-shot)test set Open LLM Leaderboard47.760
Install (macOS, Linux)
# Start a local OpenAI-compatible server with a web UI: llama serve -hf QuantFactory/Q2.5-Veltha-14B-GGUF:# Run inference directly in the terminal: llama cli -hf QuantFactory/Q2.5-Veltha-14B-GGUF: