Hugging Face's logo

AlekseiPravdin
/
Seamaiiza-7B-v2-128k-gguf

GGUF
Merge
mergekit
lazymergekit
AlekseiPravdin/KSI-RP-NSK-128k-7B
AlekseiPravdin/Seamaiiza-7B-v1
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 AlekseiPravdin/Seamaiiza-7B-v2-128k-gguf:
# Run inference directly in the terminal:
llama cli -hf AlekseiPravdin/Seamaiiza-7B-v2-128k-gguf:
Install from WinGet (Windows) 
winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf AlekseiPravdin/Seamaiiza-7B-v2-128k-gguf:
# Run inference directly in the terminal:
llama cli -hf AlekseiPravdin/Seamaiiza-7B-v2-128k-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 AlekseiPravdin/Seamaiiza-7B-v2-128k-gguf:
# Run inference directly in the terminal:
./llama-cli -hf AlekseiPravdin/Seamaiiza-7B-v2-128k-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 AlekseiPravdin/Seamaiiza-7B-v2-128k-gguf:
# Run inference directly in the terminal:
./build/bin/llama-cli -hf AlekseiPravdin/Seamaiiza-7B-v2-128k-gguf:
Use Docker 
docker model run hf.co/AlekseiPravdin/Seamaiiza-7B-v2-128k-gguf:
Quick Links

Seamaiiza-7B-v2-128k ⭐️⭐️⭐️❤️‍🔥(Story Streaming)

Seamaiiza-7B-v2-128k is a merge of the following models using mergekit:

🧩 Configuration 

slices:
  - sources:
      - model: AlekseiPravdin/Seamaiiza-7B-v1
        layer_range: [0, 32]
      - model: AlekseiPravdin/KSI-RP-NSK-128k-7B
        layer_range: [0, 32]
merge_method: slerp
base_model: AlekseiPravdin/KSI-RP-NSK-128k-7B
parameters:
  t:
    - filter: self_attn
      value: [0, 0.57, 0.33, 0.73, 1]
    - filter: mlp
      value: [1, 0.53, 0.77, 0.37, 0]
    - value: 0.53
dtype: bfloat16
Downloads last month
73
GGUF
Model size
7B params
Architecture
llama
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

Collection including AlekseiPravdin/Seamaiiza-7B-v2-128k-gguf