Hugging Face's logo

win10
/
taide-meta-it-16b

Transformers
GGUF
mergekit
Merge
conversational
Model card Files
xet
 Community
How to use from
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 win10/taide-meta-it-16b:Q6_K
# Run inference directly in the terminal:
llama cli -hf win10/taide-meta-it-16b:Q6_K
Install from WinGet (Windows) 
winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf win10/taide-meta-it-16b:Q6_K
# Run inference directly in the terminal:
llama cli -hf win10/taide-meta-it-16b:Q6_K
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 win10/taide-meta-it-16b:Q6_K
# Run inference directly in the terminal:
./llama-cli -hf win10/taide-meta-it-16b:Q6_K
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 win10/taide-meta-it-16b:Q6_K
# Run inference directly in the terminal:
./build/bin/llama-cli -hf win10/taide-meta-it-16b:Q6_K
Use Docker 
docker model run hf.co/win10/taide-meta-it-16b:Q6_K
Quick Links

llama3-15b-v02

This is a merge of pre-trained language models created using mergekit.

Merge Details

Merge Method

This model was merged using the linear merge method.

Models Merged

The following models were included in the merge:

  • D:/text-generation-webui/models/meta-llama_Meta-Llama-3-8B-Instruct
  • D:/text-generation-webui/models/taide_Llama3-TAIDE-LX-8B-Chat-Alpha1

Configuration

The following YAML configuration was used to produce this model:

dtype: bfloat16
merge_method: linear # use linear so we can include multiple models, albeit at a zero weight
parameters:
  weight: 1.0 # weight everything as 1 unless specified otherwise - linear with one model weighted at 1 is a no-op like passthrough
slices:
- sources:
  - layer_range: [0, 1]
    model: D:/text-generation-webui/models/meta-llama_Meta-Llama-3-8B-Instruct
  - layer_range: [0, 1]
    model: D:/text-generation-webui/models/taide_Llama3-TAIDE-LX-8B-Chat-Alpha1
    parameters:
      weight: 0
- sources:
  - layer_range: [1, 24]
    model: D:/text-generation-webui/models/meta-llama_Meta-Llama-3-8B-Instruct
  - layer_range: [1, 24]
    model: D:/text-generation-webui/models/taide_Llama3-TAIDE-LX-8B-Chat-Alpha1   
- sources:
  - layer_range: [24, 32]
    model: D:/text-generation-webui/models/taide_Llama3-TAIDE-LX-8B-Chat-Alpha1
    parameters:
      weight: 0
  - layer_range: [24, 32]
    model: D:/text-generation-webui/models/meta-llama_Meta-Llama-3-8B-Instruct
Downloads last month
8
GGUF
Model size
8B params
Architecture
llama
Hardware compatibility
Log In to add your hardware

6-bit

8-bit

Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Paper for win10/taide-meta-it-16b