Safetensors
GGUF
Turkish
llama
Llama-3
instruct
finetune
chatml
gpt4
synthetic data
distillation
function calling
json mode
axolotl
roleplaying
chat
Instructions to use tda45/TdAI with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- llama-cpp-python
How to use tda45/TdAI with llama-cpp-python:
# !pip install llama-cpp-python from llama_cpp import Llama llm = Llama.from_pretrained( repo_id="tda45/TdAI", filename="llama.cpp/models/ggml-vocab-aquila.gguf", )
output = llm( "Once upon a time,", max_tokens=512, echo=True ) print(output)
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use tda45/TdAI with 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 tda45/TdAI # Run inference directly in the terminal: llama cli -hf tda45/TdAI
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf tda45/TdAI # Run inference directly in the terminal: llama cli -hf tda45/TdAI
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 tda45/TdAI # Run inference directly in the terminal: ./llama-cli -hf tda45/TdAI
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 tda45/TdAI # Run inference directly in the terminal: ./build/bin/llama-cli -hf tda45/TdAI
Use Docker
docker model run hf.co/tda45/TdAI
- LM Studio
- Jan
- Ollama
How to use tda45/TdAI with Ollama:
ollama run hf.co/tda45/TdAI
- Unsloth Studio
How to use tda45/TdAI 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 tda45/TdAI 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 tda45/TdAI to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for tda45/TdAI to start chatting
- Atomic Chat new
- Docker Model Runner
How to use tda45/TdAI with Docker Model Runner:
docker model run hf.co/tda45/TdAI
- Lemonade
How to use tda45/TdAI with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull tda45/TdAI
Run and chat with the model
lemonade run user.TdAI-{{QUANT_TAG}}List all available models
lemonade list
| # Model: Step-3.5-Flash | |
| # n_embd=4096, n_ff=11264, n_vocab=128896, n_layer=45, n_head=64, n_head_kv=8, n_expert=288 | |
| [F32] f32 | |
| [F16] f16 | |
| [Q4_0] q4_0 | |
| output.weight q6_K | |
| [Q4_1] q4_1 | |
| output.weight q6_K | |
| [Q8_0] q8_0 | |
| [Q5_0] q5_0 | |
| output.weight q6_K | |
| [Q5_1] q5_1 | |
| output.weight q6_K | |
| [Q2_K] q2_K | |
| output.weight q6_K | |
| blk.0.attn_output.weight q3_K | |
| blk.0.attn_v.weight q4_K | |
| blk.0.ffn_down.weight q3_K | |
| blk.1.attn_output.weight q3_K | |
| blk.1.attn_v.weight q4_K | |
| blk.1.ffn_down.weight q3_K | |
| blk.2.attn_output.weight q3_K | |
| blk.2.attn_v.weight q4_K | |
| blk.2.ffn_down.weight q3_K | |
| blk.3.attn_output.weight q3_K | |
| blk.3.attn_v.weight q4_K | |
| blk.3.ffn_down_exps.weight q3_K | |
| blk.3.ffn_down_shexp.weight q3_K | |
| blk.4.attn_output.weight q3_K | |
| blk.4.attn_v.weight q4_K | |
| blk.4.ffn_down_exps.weight q3_K | |
| blk.4.ffn_down_shexp.weight q3_K | |
| blk.5.attn_output.weight q3_K | |
| blk.5.attn_v.weight q4_K | |
| blk.5.ffn_down_exps.weight q3_K | |
| blk.5.ffn_down_shexp.weight q3_K | |
| blk.6.attn_output.weight q3_K | |
| blk.6.attn_v.weight q4_K | |
| blk.6.ffn_down_exps.weight q3_K | |
| blk.6.ffn_down_shexp.weight q3_K | |
| blk.7.attn_output.weight q3_K | |
| blk.7.attn_v.weight q4_K | |
| blk.7.ffn_down_exps.weight q3_K | |
| blk.7.ffn_down_shexp.weight q3_K | |
| blk.8.attn_output.weight q3_K | |
| blk.8.attn_v.weight q4_K | |
| blk.8.ffn_down_exps.weight q3_K | |
| blk.8.ffn_down_shexp.weight q3_K | |
| blk.9.attn_output.weight q3_K | |
| blk.9.attn_v.weight q4_K | |
| blk.9.ffn_down_exps.weight q3_K | |
| blk.9.ffn_down_shexp.weight q3_K | |
| blk.10.attn_output.weight q3_K | |
| blk.10.attn_v.weight q4_K | |
| blk.10.ffn_down_exps.weight q3_K | |
| blk.10.ffn_down_shexp.weight q3_K | |
| blk.11.attn_output.weight q3_K | |
| blk.11.attn_v.weight q4_K | |
| blk.11.ffn_down_exps.weight q3_K | |
| blk.11.ffn_down_shexp.weight q3_K | |
| blk.12.attn_output.weight q3_K | |
| blk.12.attn_v.weight q4_K | |
| blk.12.ffn_down_exps.weight q3_K | |
| blk.12.ffn_down_shexp.weight q3_K | |
| blk.13.attn_output.weight q3_K | |
| blk.13.attn_v.weight q4_K | |
| blk.13.ffn_down_exps.weight q3_K | |
| blk.13.ffn_down_shexp.weight q3_K | |
| blk.14.attn_output.weight q3_K | |
| blk.14.attn_v.weight q4_K | |
| blk.14.ffn_down_exps.weight q3_K | |
| blk.14.ffn_down_shexp.weight q3_K | |
| blk.15.attn_output.weight q3_K | |
| blk.15.attn_v.weight q4_K | |
| blk.15.ffn_down_exps.weight q3_K | |
| blk.15.ffn_down_shexp.weight q3_K | |
| blk.16.attn_output.weight q3_K | |
| blk.16.attn_v.weight q4_K | |
| blk.16.ffn_down_exps.weight q3_K | |
| blk.16.ffn_down_shexp.weight q3_K | |
| blk.17.attn_output.weight q3_K | |
| blk.17.attn_v.weight q4_K | |
| blk.17.ffn_down_exps.weight q3_K | |
| blk.17.ffn_down_shexp.weight q3_K | |
| blk.18.attn_output.weight q3_K | |
| blk.18.attn_v.weight q4_K | |
| blk.18.ffn_down_exps.weight q3_K | |
| blk.18.ffn_down_shexp.weight q3_K | |
| blk.19.attn_output.weight q3_K | |
| blk.19.attn_v.weight q4_K | |
| blk.19.ffn_down_exps.weight q3_K | |
| blk.19.ffn_down_shexp.weight q3_K | |
| blk.20.attn_output.weight q3_K | |
| blk.20.attn_v.weight q4_K | |
| blk.20.ffn_down_exps.weight q3_K | |
| blk.20.ffn_down_shexp.weight q3_K | |
| blk.21.attn_output.weight q3_K | |
| blk.21.attn_v.weight q4_K | |
| blk.21.ffn_down_exps.weight q3_K | |
| blk.21.ffn_down_shexp.weight q3_K | |
| blk.22.attn_output.weight q3_K | |
| blk.22.attn_v.weight q4_K | |
| blk.22.ffn_down_exps.weight q3_K | |
| blk.22.ffn_down_shexp.weight q3_K | |
| blk.23.attn_output.weight q3_K | |
| blk.23.attn_v.weight q4_K | |
| blk.23.ffn_down_exps.weight q3_K | |
| blk.23.ffn_down_shexp.weight q3_K | |
| blk.24.attn_output.weight q3_K | |
| blk.24.attn_v.weight q4_K | |
| blk.24.ffn_down_exps.weight q3_K | |
| blk.24.ffn_down_shexp.weight q3_K | |
| blk.25.attn_output.weight q3_K | |
| blk.25.attn_v.weight q4_K | |
| blk.25.ffn_down_exps.weight q3_K | |
| blk.25.ffn_down_shexp.weight q3_K | |
| blk.26.attn_output.weight q3_K | |
| blk.26.attn_v.weight q4_K | |
| blk.26.ffn_down_exps.weight q3_K | |
| blk.26.ffn_down_shexp.weight q3_K | |
| blk.27.attn_output.weight q3_K | |
| blk.27.attn_v.weight q4_K | |
| blk.27.ffn_down_exps.weight q3_K | |
| blk.27.ffn_down_shexp.weight q3_K | |
| blk.28.attn_output.weight q3_K | |
| blk.28.attn_v.weight q4_K | |
| blk.28.ffn_down_exps.weight q3_K | |
| blk.28.ffn_down_shexp.weight q3_K | |
| blk.29.attn_output.weight q3_K | |
| blk.29.attn_v.weight q4_K | |
| blk.29.ffn_down_exps.weight q3_K | |
| blk.29.ffn_down_shexp.weight q3_K | |
| blk.30.attn_output.weight q3_K | |
| blk.30.attn_v.weight q4_K | |
| blk.30.ffn_down_exps.weight q3_K | |
| blk.30.ffn_down_shexp.weight q3_K | |
| blk.31.attn_output.weight q3_K | |
| blk.31.attn_v.weight q4_K | |
| blk.31.ffn_down_exps.weight q3_K | |
| blk.31.ffn_down_shexp.weight q3_K | |
| blk.32.attn_output.weight q3_K | |
| blk.32.attn_v.weight q4_K | |
| blk.32.ffn_down_exps.weight q3_K | |
| blk.32.ffn_down_shexp.weight q3_K | |
| blk.33.attn_output.weight q3_K | |
| blk.33.attn_v.weight q4_K | |
| blk.33.ffn_down_exps.weight q3_K | |
| blk.33.ffn_down_shexp.weight q3_K | |
| blk.34.attn_output.weight q3_K | |
| blk.34.attn_v.weight q4_K | |
| blk.34.ffn_down_exps.weight q3_K | |
| blk.34.ffn_down_shexp.weight q3_K | |
| blk.35.attn_output.weight q3_K | |
| blk.35.attn_v.weight q4_K | |
| blk.35.ffn_down_exps.weight q3_K | |
| blk.35.ffn_down_shexp.weight q3_K | |
| blk.36.attn_output.weight q3_K | |
| blk.36.attn_v.weight q4_K | |
| blk.36.ffn_down_exps.weight q3_K | |
| blk.36.ffn_down_shexp.weight q3_K | |
| blk.37.attn_output.weight q3_K | |
| blk.37.attn_v.weight q4_K | |
| blk.37.ffn_down_exps.weight q3_K | |
| blk.37.ffn_down_shexp.weight q3_K | |
| blk.38.attn_output.weight q3_K | |
| blk.38.attn_v.weight q4_K | |
| blk.38.ffn_down_exps.weight q3_K | |
| blk.38.ffn_down_shexp.weight q3_K | |
| blk.39.attn_output.weight q3_K | |
| blk.39.attn_v.weight q4_K | |
| blk.39.ffn_down_exps.weight q3_K | |
| blk.39.ffn_down_shexp.weight q3_K | |
| blk.40.attn_output.weight q3_K | |
| blk.40.attn_v.weight q4_K | |
| blk.40.ffn_down_exps.weight q3_K | |
| blk.40.ffn_down_shexp.weight q3_K | |
| blk.41.attn_output.weight q3_K | |
| blk.41.attn_v.weight q4_K | |
| blk.41.ffn_down_exps.weight q3_K | |
| blk.41.ffn_down_shexp.weight q3_K | |
| blk.42.attn_output.weight q3_K | |
| blk.42.attn_v.weight q4_K | |
| blk.42.ffn_down_exps.weight q3_K | |
| blk.42.ffn_down_shexp.weight q3_K | |
| blk.43.attn_output.weight q3_K | |
| blk.43.attn_v.weight q4_K | |
| blk.43.ffn_down_exps.weight q3_K | |
| blk.43.ffn_down_shexp.weight q3_K | |
| blk.44.attn_output.weight q3_K | |
| blk.44.attn_v.weight q4_K | |
| blk.44.ffn_down_exps.weight q3_K | |
| blk.44.ffn_down_shexp.weight q3_K | |
| [Q3_K_S] q3_K | |
| output.weight q6_K | |
| [Q3_K_M] q3_K | |
| output.weight q6_K | |
| blk.0.attn_output.weight q4_K | |
| blk.0.attn_v.weight q5_K | |
| blk.0.ffn_down.weight q5_K | |
| blk.1.attn_output.weight q4_K | |
| blk.1.attn_v.weight q5_K | |
| blk.1.ffn_down.weight q5_K | |
| blk.2.attn_output.weight q4_K | |
| blk.2.attn_v.weight q4_K | |
| blk.2.ffn_down.weight q4_K | |
| blk.3.attn_output.weight q4_K | |
| blk.3.attn_v.weight q4_K | |
| blk.3.ffn_down_exps.weight q4_K | |
| blk.3.ffn_down_shexp.weight q4_K | |
| blk.4.attn_output.weight q4_K | |
| blk.4.attn_v.weight q4_K | |
| blk.4.ffn_down_exps.weight q4_K | |
| blk.4.ffn_down_shexp.weight q4_K | |
| blk.5.attn_output.weight q4_K | |
| blk.5.attn_v.weight q4_K | |
| blk.5.ffn_down_exps.weight q4_K | |
| blk.5.ffn_down_shexp.weight q4_K | |
| blk.6.attn_output.weight q4_K | |
| blk.6.attn_v.weight q4_K | |
| blk.6.ffn_down_exps.weight q4_K | |
| blk.6.ffn_down_shexp.weight q4_K | |
| blk.7.attn_output.weight q4_K | |
| blk.7.attn_v.weight q4_K | |
| blk.7.ffn_down_exps.weight q4_K | |
| blk.7.ffn_down_shexp.weight q4_K | |
| blk.8.attn_output.weight q4_K | |
| blk.8.attn_v.weight q4_K | |
| blk.8.ffn_down_exps.weight q4_K | |
| blk.8.ffn_down_shexp.weight q4_K | |
| blk.9.attn_output.weight q4_K | |
| blk.9.attn_v.weight q4_K | |
| blk.9.ffn_down_exps.weight q4_K | |
| blk.9.ffn_down_shexp.weight q4_K | |
| blk.10.attn_output.weight q4_K | |
| blk.10.attn_v.weight q4_K | |
| blk.10.ffn_down_exps.weight q4_K | |
| blk.10.ffn_down_shexp.weight q4_K | |
| blk.11.attn_output.weight q4_K | |
| blk.11.attn_v.weight q4_K | |
| blk.11.ffn_down_exps.weight q4_K | |
| blk.11.ffn_down_shexp.weight q4_K | |
| blk.12.attn_output.weight q4_K | |
| blk.12.attn_v.weight q4_K | |
| blk.12.ffn_down_exps.weight q4_K | |
| blk.12.ffn_down_shexp.weight q4_K | |
| blk.13.attn_output.weight q4_K | |
| blk.13.attn_v.weight q4_K | |
| blk.13.ffn_down_exps.weight q4_K | |
| blk.13.ffn_down_shexp.weight q4_K | |
| blk.14.attn_output.weight q4_K | |
| blk.14.attn_v.weight q4_K | |
| blk.14.ffn_down_exps.weight q4_K | |
| blk.14.ffn_down_shexp.weight q4_K | |
| blk.15.attn_output.weight q4_K | |
| blk.15.attn_v.weight q4_K | |
| blk.15.ffn_down_exps.weight q4_K | |
| blk.15.ffn_down_shexp.weight q4_K | |
| blk.16.attn_output.weight q4_K | |
| blk.16.attn_v.weight q4_K | |
| blk.16.ffn_down_exps.weight q4_K | |
| blk.16.ffn_down_shexp.weight q4_K | |
| blk.17.attn_output.weight q4_K | |
| blk.17.attn_v.weight q4_K | |
| blk.17.ffn_down_exps.weight q4_K | |
| blk.17.ffn_down_shexp.weight q4_K | |
| blk.18.attn_output.weight q4_K | |
| blk.18.attn_v.weight q4_K | |
| blk.18.ffn_down_exps.weight q4_K | |
| blk.18.ffn_down_shexp.weight q4_K | |
| blk.19.attn_output.weight q4_K | |
| blk.19.attn_v.weight q4_K | |
| blk.19.ffn_down_exps.weight q4_K | |
| blk.19.ffn_down_shexp.weight q4_K | |
| blk.20.attn_output.weight q4_K | |
| blk.20.attn_v.weight q4_K | |
| blk.20.ffn_down_exps.weight q4_K | |
| blk.20.ffn_down_shexp.weight q4_K | |
| blk.21.attn_output.weight q4_K | |
| blk.21.attn_v.weight q4_K | |
| blk.21.ffn_down_exps.weight q4_K | |
| blk.21.ffn_down_shexp.weight q4_K | |
| blk.22.attn_output.weight q4_K | |
| blk.22.attn_v.weight q4_K | |
| blk.22.ffn_down_exps.weight q4_K | |
| blk.22.ffn_down_shexp.weight q4_K | |
| blk.23.attn_output.weight q4_K | |
| blk.23.attn_v.weight q4_K | |
| blk.23.ffn_down_exps.weight q4_K | |
| blk.23.ffn_down_shexp.weight q4_K | |
| blk.24.attn_output.weight q4_K | |
| blk.24.attn_v.weight q4_K | |
| blk.24.ffn_down_exps.weight q4_K | |
| blk.24.ffn_down_shexp.weight q4_K | |
| blk.25.attn_output.weight q4_K | |
| blk.25.attn_v.weight q4_K | |
| blk.25.ffn_down_exps.weight q4_K | |
| blk.25.ffn_down_shexp.weight q4_K | |
| blk.26.attn_output.weight q4_K | |
| blk.26.attn_v.weight q4_K | |
| blk.26.ffn_down_exps.weight q4_K | |
| blk.26.ffn_down_shexp.weight q4_K | |
| blk.27.attn_output.weight q4_K | |
| blk.27.attn_v.weight q4_K | |
| blk.27.ffn_down_exps.weight q4_K | |
| blk.27.ffn_down_shexp.weight q4_K | |
| blk.28.attn_output.weight q4_K | |
| blk.28.attn_v.weight q4_K | |
| blk.28.ffn_down_exps.weight q4_K | |
| blk.28.ffn_down_shexp.weight q4_K | |
| blk.29.attn_output.weight q4_K | |
| blk.29.attn_v.weight q4_K | |
| blk.29.ffn_down_exps.weight q4_K | |
| blk.29.ffn_down_shexp.weight q4_K | |
| blk.30.attn_output.weight q4_K | |
| blk.30.attn_v.weight q4_K | |
| blk.30.ffn_down_exps.weight q4_K | |
| blk.30.ffn_down_shexp.weight q4_K | |
| blk.31.attn_output.weight q4_K | |
| blk.31.attn_v.weight q4_K | |
| blk.31.ffn_down_exps.weight q4_K | |
| blk.31.ffn_down_shexp.weight q4_K | |
| blk.32.attn_output.weight q4_K | |
| blk.32.attn_v.weight q4_K | |
| blk.32.ffn_down_exps.weight q4_K | |
| blk.32.ffn_down_shexp.weight q4_K | |
| blk.33.attn_output.weight q4_K | |
| blk.33.attn_v.weight q4_K | |
| blk.33.ffn_down_exps.weight q4_K | |
| blk.33.ffn_down_shexp.weight q4_K | |
| blk.34.attn_output.weight q4_K | |
| blk.34.attn_v.weight q4_K | |
| blk.34.ffn_down_exps.weight q4_K | |
| blk.34.ffn_down_shexp.weight q4_K | |
| blk.35.attn_output.weight q4_K | |
| blk.35.attn_v.weight q4_K | |
| blk.35.ffn_down_exps.weight q4_K | |
| blk.35.ffn_down_shexp.weight q4_K | |
| blk.36.attn_output.weight q4_K | |
| blk.36.attn_v.weight q4_K | |
| blk.36.ffn_down_exps.weight q4_K | |
| blk.36.ffn_down_shexp.weight q4_K | |
| blk.37.attn_output.weight q4_K | |
| blk.37.attn_v.weight q4_K | |
| blk.37.ffn_down_exps.weight q4_K | |
| blk.37.ffn_down_shexp.weight q4_K | |
| blk.38.attn_output.weight q4_K | |
| blk.38.attn_v.weight q4_K | |
| blk.38.ffn_down_exps.weight q4_K | |
| blk.38.ffn_down_shexp.weight q4_K | |
| blk.39.attn_output.weight q4_K | |
| blk.39.attn_v.weight q4_K | |
| blk.39.ffn_down_exps.weight q4_K | |
| blk.39.ffn_down_shexp.weight q4_K | |
| blk.40.attn_output.weight q4_K | |
| blk.40.attn_v.weight q4_K | |
| blk.40.ffn_down_exps.weight q4_K | |
| blk.40.ffn_down_shexp.weight q4_K | |
| blk.41.attn_output.weight q4_K | |
| blk.41.attn_v.weight q4_K | |
| blk.41.ffn_down_exps.weight q4_K | |
| blk.41.ffn_down_shexp.weight q4_K | |
| blk.42.attn_output.weight q4_K | |
| blk.42.attn_v.weight q4_K | |
| blk.42.ffn_down_exps.weight q4_K | |
| blk.42.ffn_down_shexp.weight q4_K | |
| blk.43.attn_output.weight q4_K | |
| blk.43.attn_v.weight q4_K | |
| blk.43.ffn_down_exps.weight q4_K | |
| blk.43.ffn_down_shexp.weight q4_K | |
| blk.44.attn_output.weight q4_K | |
| blk.44.attn_v.weight q4_K | |
| blk.44.ffn_down_exps.weight q4_K | |
| blk.44.ffn_down_shexp.weight q4_K | |
| [Q3_K_L] q3_K | |
| output.weight q6_K | |
| blk.0.attn_output.weight q5_K | |
| blk.0.attn_v.weight q5_K | |
| blk.0.ffn_down.weight q5_K | |
| blk.1.attn_output.weight q5_K | |
| blk.1.attn_v.weight q5_K | |
| blk.1.ffn_down.weight q5_K | |
| blk.2.attn_output.weight q5_K | |
| blk.2.attn_v.weight q5_K | |
| blk.2.ffn_down.weight q5_K | |
| blk.3.attn_output.weight q5_K | |
| blk.3.attn_v.weight q5_K | |
| blk.3.ffn_down_exps.weight q5_K | |
| blk.3.ffn_down_shexp.weight q5_K | |
| blk.4.attn_output.weight q5_K | |
| blk.4.attn_v.weight q5_K | |
| blk.4.ffn_down_exps.weight q5_K | |
| blk.4.ffn_down_shexp.weight q5_K | |
| blk.5.attn_output.weight q5_K | |
| blk.5.attn_v.weight q5_K | |
| blk.5.ffn_down_exps.weight q5_K | |
| blk.5.ffn_down_shexp.weight q5_K | |
| blk.6.attn_output.weight q5_K | |
| blk.6.attn_v.weight q5_K | |
| blk.6.ffn_down_exps.weight q5_K | |
| blk.6.ffn_down_shexp.weight q5_K | |
| blk.7.attn_output.weight q5_K | |
| blk.7.attn_v.weight q5_K | |
| blk.7.ffn_down_exps.weight q5_K | |
| blk.7.ffn_down_shexp.weight q5_K | |
| blk.8.attn_output.weight q5_K | |
| blk.8.attn_v.weight q5_K | |
| blk.8.ffn_down_exps.weight q5_K | |
| blk.8.ffn_down_shexp.weight q5_K | |
| blk.9.attn_output.weight q5_K | |
| blk.9.attn_v.weight q5_K | |
| blk.9.ffn_down_exps.weight q5_K | |
| blk.9.ffn_down_shexp.weight q5_K | |
| blk.10.attn_output.weight q5_K | |
| blk.10.attn_v.weight q5_K | |
| blk.10.ffn_down_exps.weight q5_K | |
| blk.10.ffn_down_shexp.weight q5_K | |
| blk.11.attn_output.weight q5_K | |
| blk.11.attn_v.weight q5_K | |
| blk.11.ffn_down_exps.weight q5_K | |
| blk.11.ffn_down_shexp.weight q5_K | |
| blk.12.attn_output.weight q5_K | |
| blk.12.attn_v.weight q5_K | |
| blk.12.ffn_down_exps.weight q5_K | |
| blk.12.ffn_down_shexp.weight q5_K | |
| blk.13.attn_output.weight q5_K | |
| blk.13.attn_v.weight q5_K | |
| blk.13.ffn_down_exps.weight q5_K | |
| blk.13.ffn_down_shexp.weight q5_K | |
| blk.14.attn_output.weight q5_K | |
| blk.14.attn_v.weight q5_K | |
| blk.14.ffn_down_exps.weight q5_K | |
| blk.14.ffn_down_shexp.weight q5_K | |
| blk.15.attn_output.weight q5_K | |
| blk.15.attn_v.weight q5_K | |
| blk.15.ffn_down_exps.weight q5_K | |
| blk.15.ffn_down_shexp.weight q5_K | |
| blk.16.attn_output.weight q5_K | |
| blk.16.attn_v.weight q5_K | |
| blk.16.ffn_down_exps.weight q5_K | |
| blk.16.ffn_down_shexp.weight q5_K | |
| blk.17.attn_output.weight q5_K | |
| blk.17.attn_v.weight q5_K | |
| blk.17.ffn_down_exps.weight q5_K | |
| blk.17.ffn_down_shexp.weight q5_K | |
| blk.18.attn_output.weight q5_K | |
| blk.18.attn_v.weight q5_K | |
| blk.18.ffn_down_exps.weight q5_K | |
| blk.18.ffn_down_shexp.weight q5_K | |
| blk.19.attn_output.weight q5_K | |
| blk.19.attn_v.weight q5_K | |
| blk.19.ffn_down_exps.weight q5_K | |
| blk.19.ffn_down_shexp.weight q5_K | |
| blk.20.attn_output.weight q5_K | |
| blk.20.attn_v.weight q5_K | |
| blk.20.ffn_down_exps.weight q5_K | |
| blk.20.ffn_down_shexp.weight q5_K | |
| blk.21.attn_output.weight q5_K | |
| blk.21.attn_v.weight q5_K | |
| blk.21.ffn_down_exps.weight q5_K | |
| blk.21.ffn_down_shexp.weight q5_K | |
| blk.22.attn_output.weight q5_K | |
| blk.22.attn_v.weight q5_K | |
| blk.22.ffn_down_exps.weight q5_K | |
| blk.22.ffn_down_shexp.weight q5_K | |
| blk.23.attn_output.weight q5_K | |
| blk.23.attn_v.weight q5_K | |
| blk.23.ffn_down_exps.weight q5_K | |
| blk.23.ffn_down_shexp.weight q5_K | |
| blk.24.attn_output.weight q5_K | |
| blk.24.attn_v.weight q5_K | |
| blk.24.ffn_down_exps.weight q5_K | |
| blk.24.ffn_down_shexp.weight q5_K | |
| blk.25.attn_output.weight q5_K | |
| blk.25.attn_v.weight q5_K | |
| blk.25.ffn_down_exps.weight q5_K | |
| blk.25.ffn_down_shexp.weight q5_K | |
| blk.26.attn_output.weight q5_K | |
| blk.26.attn_v.weight q5_K | |
| blk.26.ffn_down_exps.weight q5_K | |
| blk.26.ffn_down_shexp.weight q5_K | |
| blk.27.attn_output.weight q5_K | |
| blk.27.attn_v.weight q5_K | |
| blk.27.ffn_down_exps.weight q5_K | |
| blk.27.ffn_down_shexp.weight q5_K | |
| blk.28.attn_output.weight q5_K | |
| blk.28.attn_v.weight q5_K | |
| blk.28.ffn_down_exps.weight q5_K | |
| blk.28.ffn_down_shexp.weight q5_K | |
| blk.29.attn_output.weight q5_K | |
| blk.29.attn_v.weight q5_K | |
| blk.29.ffn_down_exps.weight q5_K | |
| blk.29.ffn_down_shexp.weight q5_K | |
| blk.30.attn_output.weight q5_K | |
| blk.30.attn_v.weight q5_K | |
| blk.30.ffn_down_exps.weight q5_K | |
| blk.30.ffn_down_shexp.weight q5_K | |
| blk.31.attn_output.weight q5_K | |
| blk.31.attn_v.weight q5_K | |
| blk.31.ffn_down_exps.weight q5_K | |
| blk.31.ffn_down_shexp.weight q5_K | |
| blk.32.attn_output.weight q5_K | |
| blk.32.attn_v.weight q5_K | |
| blk.32.ffn_down_exps.weight q5_K | |
| blk.32.ffn_down_shexp.weight q5_K | |
| blk.33.attn_output.weight q5_K | |
| blk.33.attn_v.weight q5_K | |
| blk.33.ffn_down_exps.weight q5_K | |
| blk.33.ffn_down_shexp.weight q5_K | |
| blk.34.attn_output.weight q5_K | |
| blk.34.attn_v.weight q5_K | |
| blk.34.ffn_down_exps.weight q5_K | |
| blk.34.ffn_down_shexp.weight q5_K | |
| blk.35.attn_output.weight q5_K | |
| blk.35.attn_v.weight q5_K | |
| blk.35.ffn_down_exps.weight q5_K | |
| blk.35.ffn_down_shexp.weight q5_K | |
| blk.36.attn_output.weight q5_K | |
| blk.36.attn_v.weight q5_K | |
| blk.36.ffn_down_exps.weight q5_K | |
| blk.36.ffn_down_shexp.weight q5_K | |
| blk.37.attn_output.weight q5_K | |
| blk.37.attn_v.weight q5_K | |
| blk.37.ffn_down_exps.weight q5_K | |
| blk.37.ffn_down_shexp.weight q5_K | |
| blk.38.attn_output.weight q5_K | |
| blk.38.attn_v.weight q5_K | |
| blk.38.ffn_down_exps.weight q5_K | |
| blk.38.ffn_down_shexp.weight q5_K | |
| blk.39.attn_output.weight q5_K | |
| blk.39.attn_v.weight q5_K | |
| blk.39.ffn_down_exps.weight q5_K | |
| blk.39.ffn_down_shexp.weight q5_K | |
| blk.40.attn_output.weight q5_K | |
| blk.40.attn_v.weight q5_K | |
| blk.40.ffn_down_exps.weight q5_K | |
| blk.40.ffn_down_shexp.weight q5_K | |
| blk.41.attn_output.weight q5_K | |
| blk.41.attn_v.weight q5_K | |
| blk.41.ffn_down_exps.weight q5_K | |
| blk.41.ffn_down_shexp.weight q5_K | |
| blk.42.attn_output.weight q5_K | |
| blk.42.attn_v.weight q5_K | |
| blk.42.ffn_down_exps.weight q5_K | |
| blk.42.ffn_down_shexp.weight q5_K | |
| blk.43.attn_output.weight q5_K | |
| blk.43.attn_v.weight q5_K | |
| blk.43.ffn_down_exps.weight q5_K | |
| blk.43.ffn_down_shexp.weight q5_K | |
| blk.44.attn_output.weight q5_K | |
| blk.44.attn_v.weight q5_K | |
| blk.44.ffn_down_exps.weight q5_K | |
| blk.44.ffn_down_shexp.weight q5_K | |
| [Q4_K_S] q4_K | |
| output.weight q6_K | |
| blk.0.attn_v.weight q5_K | |
| blk.0.ffn_down.weight q5_K | |
| blk.1.attn_v.weight q5_K | |
| blk.1.ffn_down.weight q5_K | |
| blk.2.attn_v.weight q5_K | |
| blk.2.ffn_down.weight q5_K | |
| blk.3.attn_v.weight q5_K | |
| blk.3.ffn_down_exps.weight q5_K | |
| blk.3.ffn_down_shexp.weight q5_K | |
| blk.4.ffn_down_exps.weight q5_K | |
| blk.4.ffn_down_shexp.weight q5_K | |
| [Q4_K_M] q4_K | |
| output.weight q6_K | |
| blk.0.attn_v.weight q6_K | |
| blk.0.ffn_down.weight q6_K | |
| blk.1.attn_v.weight q6_K | |
| blk.1.ffn_down.weight q6_K | |
| blk.2.attn_v.weight q6_K | |
| blk.2.ffn_down.weight q6_K | |
| blk.3.attn_v.weight q6_K | |
| blk.3.ffn_down_exps.weight q6_K | |
| blk.3.ffn_down_shexp.weight q6_K | |
| blk.4.attn_v.weight q6_K | |
| blk.4.ffn_down_exps.weight q6_K | |
| blk.4.ffn_down_shexp.weight q6_K | |
| blk.7.attn_v.weight q6_K | |
| blk.7.ffn_down_exps.weight q6_K | |
| blk.7.ffn_down_shexp.weight q6_K | |
| blk.10.attn_v.weight q6_K | |
| blk.10.ffn_down_exps.weight q6_K | |
| blk.10.ffn_down_shexp.weight q6_K | |
| blk.13.attn_v.weight q6_K | |
| blk.13.ffn_down_exps.weight q6_K | |
| blk.13.ffn_down_shexp.weight q6_K | |
| blk.16.attn_v.weight q6_K | |
| blk.16.ffn_down_exps.weight q6_K | |
| blk.16.ffn_down_shexp.weight q6_K | |
| blk.19.attn_v.weight q6_K | |
| blk.19.ffn_down_exps.weight q6_K | |
| blk.19.ffn_down_shexp.weight q6_K | |
| blk.22.attn_v.weight q6_K | |
| blk.22.ffn_down_exps.weight q6_K | |
| blk.22.ffn_down_shexp.weight q6_K | |
| blk.25.attn_v.weight q6_K | |
| blk.25.ffn_down_exps.weight q6_K | |
| blk.25.ffn_down_shexp.weight q6_K | |
| blk.28.attn_v.weight q6_K | |
| blk.28.ffn_down_exps.weight q6_K | |
| blk.28.ffn_down_shexp.weight q6_K | |
| blk.31.attn_v.weight q6_K | |
| blk.31.ffn_down_exps.weight q6_K | |
| blk.31.ffn_down_shexp.weight q6_K | |
| blk.34.attn_v.weight q6_K | |
| blk.34.ffn_down_exps.weight q6_K | |
| blk.34.ffn_down_shexp.weight q6_K | |
| blk.37.attn_v.weight q6_K | |
| blk.37.ffn_down_exps.weight q6_K | |
| blk.37.ffn_down_shexp.weight q6_K | |
| blk.39.attn_v.weight q6_K | |
| blk.39.ffn_down_exps.weight q6_K | |
| blk.39.ffn_down_shexp.weight q6_K | |
| blk.40.attn_v.weight q6_K | |
| blk.40.ffn_down_exps.weight q6_K | |
| blk.40.ffn_down_shexp.weight q6_K | |
| blk.41.attn_v.weight q6_K | |
| blk.41.ffn_down_exps.weight q6_K | |
| blk.41.ffn_down_shexp.weight q6_K | |
| blk.42.attn_v.weight q6_K | |
| blk.42.ffn_down_exps.weight q6_K | |
| blk.42.ffn_down_shexp.weight q6_K | |
| blk.43.attn_v.weight q6_K | |
| blk.43.ffn_down_exps.weight q6_K | |
| blk.43.ffn_down_shexp.weight q6_K | |
| blk.44.attn_v.weight q6_K | |
| blk.44.ffn_down_exps.weight q6_K | |
| blk.44.ffn_down_shexp.weight q6_K | |
| [Q5_K_S] q5_K | |
| output.weight q6_K | |
| [Q5_K_M] q5_K | |
| output.weight q6_K | |
| blk.0.attn_v.weight q6_K | |
| blk.0.ffn_down.weight q6_K | |
| blk.1.attn_v.weight q6_K | |
| blk.1.ffn_down.weight q6_K | |
| blk.2.attn_v.weight q6_K | |
| blk.2.ffn_down.weight q6_K | |
| blk.3.attn_v.weight q6_K | |
| blk.3.ffn_down_exps.weight q6_K | |
| blk.3.ffn_down_shexp.weight q6_K | |
| blk.4.attn_v.weight q6_K | |
| blk.4.ffn_down_exps.weight q6_K | |
| blk.4.ffn_down_shexp.weight q6_K | |
| blk.7.attn_v.weight q6_K | |
| blk.7.ffn_down_exps.weight q6_K | |
| blk.7.ffn_down_shexp.weight q6_K | |
| blk.10.attn_v.weight q6_K | |
| blk.10.ffn_down_exps.weight q6_K | |
| blk.10.ffn_down_shexp.weight q6_K | |
| blk.13.attn_v.weight q6_K | |
| blk.13.ffn_down_exps.weight q6_K | |
| blk.13.ffn_down_shexp.weight q6_K | |
| blk.16.attn_v.weight q6_K | |
| blk.16.ffn_down_exps.weight q6_K | |
| blk.16.ffn_down_shexp.weight q6_K | |
| blk.19.attn_v.weight q6_K | |
| blk.19.ffn_down_exps.weight q6_K | |
| blk.19.ffn_down_shexp.weight q6_K | |
| blk.22.attn_v.weight q6_K | |
| blk.22.ffn_down_exps.weight q6_K | |
| blk.22.ffn_down_shexp.weight q6_K | |
| blk.25.attn_v.weight q6_K | |
| blk.25.ffn_down_exps.weight q6_K | |
| blk.25.ffn_down_shexp.weight q6_K | |
| blk.28.attn_v.weight q6_K | |
| blk.28.ffn_down_exps.weight q6_K | |
| blk.28.ffn_down_shexp.weight q6_K | |
| blk.31.attn_v.weight q6_K | |
| blk.31.ffn_down_exps.weight q6_K | |
| blk.31.ffn_down_shexp.weight q6_K | |
| blk.34.attn_v.weight q6_K | |
| blk.34.ffn_down_exps.weight q6_K | |
| blk.34.ffn_down_shexp.weight q6_K | |
| blk.37.attn_v.weight q6_K | |
| blk.37.ffn_down_exps.weight q6_K | |
| blk.37.ffn_down_shexp.weight q6_K | |
| blk.39.attn_v.weight q6_K | |
| blk.39.ffn_down_exps.weight q6_K | |
| blk.39.ffn_down_shexp.weight q6_K | |
| blk.40.attn_v.weight q6_K | |
| blk.40.ffn_down_exps.weight q6_K | |
| blk.40.ffn_down_shexp.weight q6_K | |
| blk.41.attn_v.weight q6_K | |
| blk.41.ffn_down_exps.weight q6_K | |
| blk.41.ffn_down_shexp.weight q6_K | |
| blk.42.attn_v.weight q6_K | |
| blk.42.ffn_down_exps.weight q6_K | |
| blk.42.ffn_down_shexp.weight q6_K | |
| blk.43.attn_v.weight q6_K | |
| blk.43.ffn_down_exps.weight q6_K | |
| blk.43.ffn_down_shexp.weight q6_K | |
| blk.44.attn_v.weight q6_K | |
| blk.44.ffn_down_exps.weight q6_K | |
| blk.44.ffn_down_shexp.weight q6_K | |
| [Q6_K] q6_K | |
| [IQ2_XXS] iq2_xxs | |
| output.weight q5_K | |
| token_embd.weight q2_K | |
| blk.0.attn_v.weight q4_K | |
| blk.0.ffn_down.weight q2_K | |
| blk.1.attn_v.weight q4_K | |
| blk.1.ffn_down.weight q2_K | |
| blk.2.attn_v.weight q4_K | |
| blk.2.ffn_down.weight q2_K | |
| blk.3.attn_v.weight q4_K | |
| blk.3.ffn_down_exps.weight q2_K | |
| blk.3.ffn_down_shexp.weight q2_K | |
| blk.4.attn_v.weight q4_K | |
| blk.5.attn_v.weight q4_K | |
| blk.6.attn_v.weight q4_K | |
| blk.7.attn_v.weight q4_K | |
| blk.8.attn_v.weight q4_K | |
| blk.9.attn_v.weight q4_K | |
| blk.10.attn_v.weight q4_K | |
| blk.11.attn_v.weight q4_K | |
| blk.12.attn_v.weight q4_K | |
| blk.13.attn_v.weight q4_K | |
| blk.14.attn_v.weight q4_K | |
| blk.15.attn_v.weight q4_K | |
| blk.16.attn_v.weight q4_K | |
| blk.17.attn_v.weight q4_K | |
| blk.18.attn_v.weight q4_K | |
| blk.19.attn_v.weight q4_K | |
| blk.20.attn_v.weight q4_K | |
| blk.21.attn_v.weight q4_K | |
| blk.22.attn_v.weight q4_K | |
| blk.23.attn_v.weight q4_K | |
| blk.24.attn_v.weight q4_K | |
| blk.25.attn_v.weight q4_K | |
| blk.26.attn_v.weight q4_K | |
| blk.27.attn_v.weight q4_K | |
| blk.28.attn_v.weight q4_K | |
| blk.29.attn_v.weight q4_K | |
| blk.30.attn_v.weight q4_K | |
| blk.31.attn_v.weight q4_K | |
| blk.32.attn_v.weight q4_K | |
| blk.33.attn_v.weight q4_K | |
| blk.34.attn_v.weight q4_K | |
| blk.35.attn_v.weight q4_K | |
| blk.36.attn_v.weight q4_K | |
| blk.37.attn_v.weight q4_K | |
| blk.38.attn_v.weight q4_K | |
| blk.39.attn_v.weight q4_K | |
| blk.40.attn_v.weight q4_K | |
| blk.41.attn_v.weight q4_K | |
| blk.42.attn_v.weight q4_K | |
| blk.43.attn_v.weight q4_K | |
| blk.44.attn_v.weight q4_K | |
| [IQ2_XS] iq2_xs | |
| output.weight q5_K | |
| token_embd.weight q2_K | |
| blk.0.attn_v.weight q4_K | |
| blk.0.ffn_down.weight q2_K | |
| blk.1.attn_v.weight q4_K | |
| blk.1.ffn_down.weight q2_K | |
| blk.2.attn_v.weight q4_K | |
| blk.2.ffn_down.weight q2_K | |
| blk.3.attn_v.weight q4_K | |
| blk.3.ffn_down_exps.weight q2_K | |
| blk.3.ffn_down_shexp.weight q2_K | |
| blk.4.attn_v.weight q4_K | |
| blk.5.attn_v.weight q4_K | |
| blk.6.attn_v.weight q4_K | |
| blk.7.attn_v.weight q4_K | |
| blk.8.attn_v.weight q4_K | |
| blk.9.attn_v.weight q4_K | |
| blk.10.attn_v.weight q4_K | |
| blk.11.attn_v.weight q4_K | |
| blk.12.attn_v.weight q4_K | |
| blk.13.attn_v.weight q4_K | |
| blk.14.attn_v.weight q4_K | |
| blk.15.attn_v.weight q4_K | |
| blk.16.attn_v.weight q4_K | |
| blk.17.attn_v.weight q4_K | |
| blk.18.attn_v.weight q4_K | |
| blk.19.attn_v.weight q4_K | |
| blk.20.attn_v.weight q4_K | |
| blk.21.attn_v.weight q4_K | |
| blk.22.attn_v.weight q4_K | |
| blk.23.attn_v.weight q4_K | |
| blk.24.attn_v.weight q4_K | |
| blk.25.attn_v.weight q4_K | |
| blk.26.attn_v.weight q4_K | |
| blk.27.attn_v.weight q4_K | |
| blk.28.attn_v.weight q4_K | |
| blk.29.attn_v.weight q4_K | |
| blk.30.attn_v.weight q4_K | |
| blk.31.attn_v.weight q4_K | |
| blk.32.attn_v.weight q4_K | |
| blk.33.attn_v.weight q4_K | |
| blk.34.attn_v.weight q4_K | |
| blk.35.attn_v.weight q4_K | |
| blk.36.attn_v.weight q4_K | |
| blk.37.attn_v.weight q4_K | |
| blk.38.attn_v.weight q4_K | |
| blk.39.attn_v.weight q4_K | |
| blk.40.attn_v.weight q4_K | |
| blk.41.attn_v.weight q4_K | |
| blk.42.attn_v.weight q4_K | |
| blk.43.attn_v.weight q4_K | |
| blk.44.attn_v.weight q4_K | |
| [Q2_K_S] q2_K | |
| output.weight q6_K | |
| blk.0.attn_v.weight q4_K | |
| blk.0.ffn_down.weight q4_K | |
| blk.1.attn_v.weight q4_K | |
| blk.1.ffn_down.weight q4_K | |
| blk.2.attn_v.weight q4_K | |
| blk.2.ffn_down.weight q4_K | |
| blk.3.attn_v.weight q4_K | |
| blk.3.ffn_down_exps.weight q4_K | |
| blk.3.ffn_down_shexp.weight q4_K | |
| blk.4.attn_v.weight q4_K | |
| blk.4.ffn_down_exps.weight q4_K | |
| blk.4.ffn_down_shexp.weight q4_K | |
| blk.5.attn_v.weight q4_K | |
| blk.6.attn_v.weight q4_K | |
| blk.7.attn_v.weight q4_K | |
| blk.8.attn_v.weight q4_K | |
| blk.9.attn_v.weight q4_K | |
| blk.10.attn_v.weight q4_K | |
| blk.11.attn_v.weight q4_K | |
| blk.12.attn_v.weight q4_K | |
| blk.13.attn_v.weight q4_K | |
| blk.14.attn_v.weight q4_K | |
| blk.15.attn_v.weight q4_K | |
| blk.16.attn_v.weight q4_K | |
| blk.17.attn_v.weight q4_K | |
| blk.18.attn_v.weight q4_K | |
| blk.19.attn_v.weight q4_K | |
| blk.20.attn_v.weight q4_K | |
| blk.21.attn_v.weight q4_K | |
| blk.22.attn_v.weight q4_K | |
| blk.23.attn_v.weight q4_K | |
| blk.24.attn_v.weight q4_K | |
| blk.25.attn_v.weight q4_K | |
| blk.26.attn_v.weight q4_K | |
| blk.27.attn_v.weight q4_K | |
| blk.28.attn_v.weight q4_K | |
| blk.29.attn_v.weight q4_K | |
| blk.30.attn_v.weight q4_K | |
| blk.31.attn_v.weight q4_K | |
| blk.32.attn_v.weight q4_K | |
| blk.33.attn_v.weight q4_K | |
| blk.34.attn_v.weight q4_K | |
| blk.35.attn_v.weight q4_K | |
| blk.36.attn_v.weight q4_K | |
| blk.37.attn_v.weight q4_K | |
| blk.38.attn_v.weight q4_K | |
| blk.39.attn_v.weight q4_K | |
| blk.40.attn_v.weight q4_K | |
| blk.41.attn_v.weight q4_K | |
| blk.42.attn_v.weight q4_K | |
| blk.43.attn_v.weight q4_K | |
| blk.44.attn_v.weight q4_K | |
| [IQ3_XS] iq3_s | |
| output.weight q6_K | |
| blk.0.attn_k.weight iq3_xxs | |
| blk.0.attn_q.weight iq3_xxs | |
| blk.0.attn_v.weight q4_K | |
| blk.1.attn_k.weight iq3_xxs | |
| blk.1.attn_q.weight iq3_xxs | |
| blk.1.attn_v.weight q4_K | |
| blk.2.attn_k.weight iq3_xxs | |
| blk.2.attn_q.weight iq3_xxs | |
| blk.2.attn_v.weight q4_K | |
| blk.3.attn_k.weight iq3_xxs | |
| blk.3.attn_q.weight iq3_xxs | |
| blk.3.attn_v.weight q4_K | |
| blk.4.attn_k.weight iq3_xxs | |
| blk.4.attn_q.weight iq3_xxs | |
| blk.4.attn_v.weight q4_K | |
| blk.5.attn_k.weight iq3_xxs | |
| blk.5.attn_q.weight iq3_xxs | |
| blk.5.attn_v.weight q4_K | |
| blk.5.ffn_gate_exps.weight iq3_xxs | |
| blk.5.ffn_gate_shexp.weight iq3_xxs | |
| blk.5.ffn_up_exps.weight iq3_xxs | |
| blk.5.ffn_up_shexp.weight iq3_xxs | |
| blk.6.attn_k.weight iq3_xxs | |
| blk.6.attn_q.weight iq3_xxs | |
| blk.6.attn_v.weight q4_K | |
| blk.6.ffn_gate_exps.weight iq3_xxs | |
| blk.6.ffn_gate_shexp.weight iq3_xxs | |
| blk.6.ffn_up_exps.weight iq3_xxs | |
| blk.6.ffn_up_shexp.weight iq3_xxs | |
| blk.7.attn_k.weight iq3_xxs | |
| blk.7.attn_q.weight iq3_xxs | |
| blk.7.attn_v.weight q4_K | |
| blk.7.ffn_gate_exps.weight iq3_xxs | |
| blk.7.ffn_gate_shexp.weight iq3_xxs | |
| blk.7.ffn_up_exps.weight iq3_xxs | |
| blk.7.ffn_up_shexp.weight iq3_xxs | |
| blk.8.attn_k.weight iq3_xxs | |
| blk.8.attn_q.weight iq3_xxs | |
| blk.8.attn_v.weight q4_K | |
| blk.8.ffn_gate_exps.weight iq3_xxs | |
| blk.8.ffn_gate_shexp.weight iq3_xxs | |
| blk.8.ffn_up_exps.weight iq3_xxs | |
| blk.8.ffn_up_shexp.weight iq3_xxs | |
| blk.9.attn_k.weight iq3_xxs | |
| blk.9.attn_q.weight iq3_xxs | |
| blk.9.attn_v.weight q4_K | |
| blk.9.ffn_gate_exps.weight iq3_xxs | |
| blk.9.ffn_gate_shexp.weight iq3_xxs | |
| blk.9.ffn_up_exps.weight iq3_xxs | |
| blk.9.ffn_up_shexp.weight iq3_xxs | |
| blk.10.attn_k.weight iq3_xxs | |
| blk.10.attn_q.weight iq3_xxs | |
| blk.10.attn_v.weight q4_K | |
| blk.10.ffn_gate_exps.weight iq3_xxs | |
| blk.10.ffn_gate_shexp.weight iq3_xxs | |
| blk.10.ffn_up_exps.weight iq3_xxs | |
| blk.10.ffn_up_shexp.weight iq3_xxs | |
| blk.11.attn_k.weight iq3_xxs | |
| blk.11.attn_q.weight iq3_xxs | |
| blk.11.attn_v.weight q4_K | |
| blk.11.ffn_gate_exps.weight iq3_xxs | |
| blk.11.ffn_gate_shexp.weight iq3_xxs | |
| blk.11.ffn_up_exps.weight iq3_xxs | |
| blk.11.ffn_up_shexp.weight iq3_xxs | |
| blk.12.attn_k.weight iq3_xxs | |
| blk.12.attn_q.weight iq3_xxs | |
| blk.12.attn_v.weight q4_K | |
| blk.12.ffn_gate_exps.weight iq3_xxs | |
| blk.12.ffn_gate_shexp.weight iq3_xxs | |
| blk.12.ffn_up_exps.weight iq3_xxs | |
| blk.12.ffn_up_shexp.weight iq3_xxs | |
| blk.13.attn_k.weight iq3_xxs | |
| blk.13.attn_q.weight iq3_xxs | |
| blk.13.attn_v.weight q4_K | |
| blk.13.ffn_gate_exps.weight iq3_xxs | |
| blk.13.ffn_gate_shexp.weight iq3_xxs | |
| blk.13.ffn_up_exps.weight iq3_xxs | |
| blk.13.ffn_up_shexp.weight iq3_xxs | |
| blk.14.attn_k.weight iq3_xxs | |
| blk.14.attn_q.weight iq3_xxs | |
| blk.14.attn_v.weight q4_K | |
| blk.14.ffn_gate_exps.weight iq3_xxs | |
| blk.14.ffn_gate_shexp.weight iq3_xxs | |
| blk.14.ffn_up_exps.weight iq3_xxs | |
| blk.14.ffn_up_shexp.weight iq3_xxs | |
| blk.15.attn_k.weight iq3_xxs | |
| blk.15.attn_q.weight iq3_xxs | |
| blk.15.attn_v.weight q4_K | |
| blk.15.ffn_gate_exps.weight iq3_xxs | |
| blk.15.ffn_gate_shexp.weight iq3_xxs | |
| blk.15.ffn_up_exps.weight iq3_xxs | |
| blk.15.ffn_up_shexp.weight iq3_xxs | |
| blk.16.attn_k.weight iq3_xxs | |
| blk.16.attn_q.weight iq3_xxs | |
| blk.16.attn_v.weight q4_K | |
| blk.16.ffn_gate_exps.weight iq3_xxs | |
| blk.16.ffn_gate_shexp.weight iq3_xxs | |
| blk.16.ffn_up_exps.weight iq3_xxs | |
| blk.16.ffn_up_shexp.weight iq3_xxs | |
| blk.17.attn_k.weight iq3_xxs | |
| blk.17.attn_q.weight iq3_xxs | |
| blk.17.attn_v.weight q4_K | |
| blk.17.ffn_gate_exps.weight iq3_xxs | |
| blk.17.ffn_gate_shexp.weight iq3_xxs | |
| blk.17.ffn_up_exps.weight iq3_xxs | |
| blk.17.ffn_up_shexp.weight iq3_xxs | |
| blk.18.attn_k.weight iq3_xxs | |
| blk.18.attn_q.weight iq3_xxs | |
| blk.18.attn_v.weight q4_K | |
| blk.18.ffn_gate_exps.weight iq3_xxs | |
| blk.18.ffn_gate_shexp.weight iq3_xxs | |
| blk.18.ffn_up_exps.weight iq3_xxs | |
| blk.18.ffn_up_shexp.weight iq3_xxs | |
| blk.19.attn_k.weight iq3_xxs | |
| blk.19.attn_q.weight iq3_xxs | |
| blk.19.attn_v.weight q4_K | |
| blk.19.ffn_gate_exps.weight iq3_xxs | |
| blk.19.ffn_gate_shexp.weight iq3_xxs | |
| blk.19.ffn_up_exps.weight iq3_xxs | |
| blk.19.ffn_up_shexp.weight iq3_xxs | |
| blk.20.attn_k.weight iq3_xxs | |
| blk.20.attn_q.weight iq3_xxs | |
| blk.20.attn_v.weight q4_K | |
| blk.20.ffn_gate_exps.weight iq3_xxs | |
| blk.20.ffn_gate_shexp.weight iq3_xxs | |
| blk.20.ffn_up_exps.weight iq3_xxs | |
| blk.20.ffn_up_shexp.weight iq3_xxs | |
| blk.21.attn_k.weight iq3_xxs | |
| blk.21.attn_q.weight iq3_xxs | |
| blk.21.attn_v.weight q4_K | |
| blk.21.ffn_gate_exps.weight iq3_xxs | |
| blk.21.ffn_gate_shexp.weight iq3_xxs | |
| blk.21.ffn_up_exps.weight iq3_xxs | |
| blk.21.ffn_up_shexp.weight iq3_xxs | |
| blk.22.attn_k.weight iq3_xxs | |
| blk.22.attn_q.weight iq3_xxs | |
| blk.22.attn_v.weight q4_K | |
| blk.22.ffn_gate_exps.weight iq3_xxs | |
| blk.22.ffn_gate_shexp.weight iq3_xxs | |
| blk.22.ffn_up_exps.weight iq3_xxs | |
| blk.22.ffn_up_shexp.weight iq3_xxs | |
| blk.23.attn_k.weight iq3_xxs | |
| blk.23.attn_q.weight iq3_xxs | |
| blk.23.attn_v.weight q4_K | |
| blk.23.ffn_gate_exps.weight iq3_xxs | |
| blk.23.ffn_gate_shexp.weight iq3_xxs | |
| blk.23.ffn_up_exps.weight iq3_xxs | |
| blk.23.ffn_up_shexp.weight iq3_xxs | |
| blk.24.attn_k.weight iq3_xxs | |
| blk.24.attn_q.weight iq3_xxs | |
| blk.24.attn_v.weight q4_K | |
| blk.24.ffn_gate_exps.weight iq3_xxs | |
| blk.24.ffn_gate_shexp.weight iq3_xxs | |
| blk.24.ffn_up_exps.weight iq3_xxs | |
| blk.24.ffn_up_shexp.weight iq3_xxs | |
| blk.25.attn_k.weight iq3_xxs | |
| blk.25.attn_q.weight iq3_xxs | |
| blk.25.attn_v.weight q4_K | |
| blk.25.ffn_gate_exps.weight iq3_xxs | |
| blk.25.ffn_gate_shexp.weight iq3_xxs | |
| blk.25.ffn_up_exps.weight iq3_xxs | |
| blk.25.ffn_up_shexp.weight iq3_xxs | |
| blk.26.attn_k.weight iq3_xxs | |
| blk.26.attn_q.weight iq3_xxs | |
| blk.26.attn_v.weight q4_K | |
| blk.26.ffn_gate_exps.weight iq3_xxs | |
| blk.26.ffn_gate_shexp.weight iq3_xxs | |
| blk.26.ffn_up_exps.weight iq3_xxs | |
| blk.26.ffn_up_shexp.weight iq3_xxs | |
| blk.27.attn_k.weight iq3_xxs | |
| blk.27.attn_q.weight iq3_xxs | |
| blk.27.attn_v.weight q4_K | |
| blk.27.ffn_gate_exps.weight iq3_xxs | |
| blk.27.ffn_gate_shexp.weight iq3_xxs | |
| blk.27.ffn_up_exps.weight iq3_xxs | |
| blk.27.ffn_up_shexp.weight iq3_xxs | |
| blk.28.attn_k.weight iq3_xxs | |
| blk.28.attn_q.weight iq3_xxs | |
| blk.28.attn_v.weight q4_K | |
| blk.28.ffn_gate_exps.weight iq3_xxs | |
| blk.28.ffn_gate_shexp.weight iq3_xxs | |
| blk.28.ffn_up_exps.weight iq3_xxs | |
| blk.28.ffn_up_shexp.weight iq3_xxs | |
| blk.29.attn_k.weight iq3_xxs | |
| blk.29.attn_q.weight iq3_xxs | |
| blk.29.attn_v.weight q4_K | |
| blk.29.ffn_gate_exps.weight iq3_xxs | |
| blk.29.ffn_gate_shexp.weight iq3_xxs | |
| blk.29.ffn_up_exps.weight iq3_xxs | |
| blk.29.ffn_up_shexp.weight iq3_xxs | |
| blk.30.attn_k.weight iq3_xxs | |
| blk.30.attn_q.weight iq3_xxs | |
| blk.30.attn_v.weight q4_K | |
| blk.30.ffn_gate_exps.weight iq3_xxs | |
| blk.30.ffn_gate_shexp.weight iq3_xxs | |
| blk.30.ffn_up_exps.weight iq3_xxs | |
| blk.30.ffn_up_shexp.weight iq3_xxs | |
| blk.31.attn_k.weight iq3_xxs | |
| blk.31.attn_q.weight iq3_xxs | |
| blk.31.attn_v.weight q4_K | |
| blk.31.ffn_gate_exps.weight iq3_xxs | |
| blk.31.ffn_gate_shexp.weight iq3_xxs | |
| blk.31.ffn_up_exps.weight iq3_xxs | |
| blk.31.ffn_up_shexp.weight iq3_xxs | |
| blk.32.attn_k.weight iq3_xxs | |
| blk.32.attn_q.weight iq3_xxs | |
| blk.32.attn_v.weight q4_K | |
| blk.32.ffn_gate_exps.weight iq3_xxs | |
| blk.32.ffn_gate_shexp.weight iq3_xxs | |
| blk.32.ffn_up_exps.weight iq3_xxs | |
| blk.32.ffn_up_shexp.weight iq3_xxs | |
| blk.33.attn_k.weight iq3_xxs | |
| blk.33.attn_q.weight iq3_xxs | |
| blk.33.attn_v.weight q4_K | |
| blk.33.ffn_gate_exps.weight iq3_xxs | |
| blk.33.ffn_gate_shexp.weight iq3_xxs | |
| blk.33.ffn_up_exps.weight iq3_xxs | |
| blk.33.ffn_up_shexp.weight iq3_xxs | |
| blk.34.attn_k.weight iq3_xxs | |
| blk.34.attn_q.weight iq3_xxs | |
| blk.34.attn_v.weight q4_K | |
| blk.34.ffn_gate_exps.weight iq3_xxs | |
| blk.34.ffn_gate_shexp.weight iq3_xxs | |
| blk.34.ffn_up_exps.weight iq3_xxs | |
| blk.34.ffn_up_shexp.weight iq3_xxs | |
| blk.35.attn_k.weight iq3_xxs | |
| blk.35.attn_q.weight iq3_xxs | |
| blk.35.attn_v.weight q4_K | |
| blk.35.ffn_gate_exps.weight iq3_xxs | |
| blk.35.ffn_gate_shexp.weight iq3_xxs | |
| blk.35.ffn_up_exps.weight iq3_xxs | |
| blk.35.ffn_up_shexp.weight iq3_xxs | |
| blk.36.attn_k.weight iq3_xxs | |
| blk.36.attn_q.weight iq3_xxs | |
| blk.36.attn_v.weight q4_K | |
| blk.36.ffn_gate_exps.weight iq3_xxs | |
| blk.36.ffn_gate_shexp.weight iq3_xxs | |
| blk.36.ffn_up_exps.weight iq3_xxs | |
| blk.36.ffn_up_shexp.weight iq3_xxs | |
| blk.37.attn_k.weight iq3_xxs | |
| blk.37.attn_q.weight iq3_xxs | |
| blk.37.attn_v.weight q4_K | |
| blk.37.ffn_gate_exps.weight iq3_xxs | |
| blk.37.ffn_gate_shexp.weight iq3_xxs | |
| blk.37.ffn_up_exps.weight iq3_xxs | |
| blk.37.ffn_up_shexp.weight iq3_xxs | |
| blk.38.attn_k.weight iq3_xxs | |
| blk.38.attn_q.weight iq3_xxs | |
| blk.38.attn_v.weight q4_K | |
| blk.38.ffn_gate_exps.weight iq3_xxs | |
| blk.38.ffn_gate_shexp.weight iq3_xxs | |
| blk.38.ffn_up_exps.weight iq3_xxs | |
| blk.38.ffn_up_shexp.weight iq3_xxs | |
| blk.39.attn_k.weight iq3_xxs | |
| blk.39.attn_q.weight iq3_xxs | |
| blk.39.attn_v.weight q4_K | |
| blk.40.attn_k.weight iq3_xxs | |
| blk.40.attn_q.weight iq3_xxs | |
| blk.40.attn_v.weight q4_K | |
| blk.41.attn_k.weight iq3_xxs | |
| blk.41.attn_q.weight iq3_xxs | |
| blk.41.attn_v.weight q4_K | |
| blk.42.attn_k.weight iq3_xxs | |
| blk.42.attn_q.weight iq3_xxs | |
| blk.42.attn_v.weight q4_K | |
| blk.43.attn_k.weight iq3_xxs | |
| blk.43.attn_q.weight iq3_xxs | |
| blk.43.attn_v.weight q4_K | |
| blk.44.attn_k.weight iq3_xxs | |
| blk.44.attn_q.weight iq3_xxs | |
| blk.44.attn_v.weight q4_K | |
| [IQ3_XXS] iq3_xxs | |
| output.weight q5_K | |
| token_embd.weight iq3_s | |
| blk.0.attn_k.weight iq2_s | |
| blk.0.attn_output.weight iq3_s | |
| blk.0.attn_q.weight iq2_s | |
| blk.0.attn_v.weight q4_K | |
| blk.0.ffn_down.weight q4_K | |
| blk.1.attn_k.weight iq2_s | |
| blk.1.attn_output.weight iq3_s | |
| blk.1.attn_q.weight iq2_s | |
| blk.1.attn_v.weight q4_K | |
| blk.1.ffn_down.weight q4_K | |
| blk.2.attn_k.weight iq2_s | |
| blk.2.attn_output.weight iq3_s | |
| blk.2.attn_q.weight iq2_s | |
| blk.2.attn_v.weight q4_K | |
| blk.2.ffn_down.weight q4_K | |
| blk.3.attn_k.weight iq2_s | |
| blk.3.attn_output.weight iq3_s | |
| blk.3.attn_q.weight iq2_s | |
| blk.3.attn_v.weight q4_K | |
| blk.3.ffn_down_exps.weight q4_K | |
| blk.3.ffn_down_shexp.weight q4_K | |
| blk.4.attn_k.weight iq2_s | |
| blk.4.attn_output.weight iq3_s | |
| blk.4.attn_q.weight iq2_s | |
| blk.4.attn_v.weight q4_K | |
| blk.4.ffn_down_exps.weight q4_K | |
| blk.4.ffn_down_shexp.weight q4_K | |
| blk.5.attn_k.weight iq2_s | |
| blk.5.attn_output.weight iq3_s | |
| blk.5.attn_q.weight iq2_s | |
| blk.5.attn_v.weight q4_K | |
| blk.5.ffn_down_exps.weight q3_K | |
| blk.5.ffn_down_shexp.weight q3_K | |
| blk.6.attn_k.weight iq2_s | |
| blk.6.attn_output.weight iq3_s | |
| blk.6.attn_q.weight iq2_s | |
| blk.6.attn_v.weight q4_K | |
| blk.6.ffn_down_exps.weight q3_K | |
| blk.6.ffn_down_shexp.weight q3_K | |
| blk.7.attn_k.weight iq2_s | |
| blk.7.attn_output.weight iq3_s | |
| blk.7.attn_q.weight iq2_s | |
| blk.7.attn_v.weight q4_K | |
| blk.7.ffn_down_exps.weight q3_K | |
| blk.7.ffn_down_shexp.weight q3_K | |
| blk.8.attn_k.weight iq2_s | |
| blk.8.attn_output.weight iq3_s | |
| blk.8.attn_q.weight iq2_s | |
| blk.8.attn_v.weight q4_K | |
| blk.8.ffn_down_exps.weight q3_K | |
| blk.8.ffn_down_shexp.weight q3_K | |
| blk.9.attn_k.weight iq2_s | |
| blk.9.attn_output.weight iq3_s | |
| blk.9.attn_q.weight iq2_s | |
| blk.9.attn_v.weight q4_K | |
| blk.9.ffn_down_exps.weight q3_K | |
| blk.9.ffn_down_shexp.weight q3_K | |
| blk.10.attn_k.weight iq2_s | |
| blk.10.attn_output.weight iq3_s | |
| blk.10.attn_q.weight iq2_s | |
| blk.10.attn_v.weight q4_K | |
| blk.10.ffn_down_exps.weight q3_K | |
| blk.10.ffn_down_shexp.weight q3_K | |
| blk.11.attn_k.weight iq2_s | |
| blk.11.attn_output.weight iq3_s | |
| blk.11.attn_q.weight iq2_s | |
| blk.11.attn_v.weight q4_K | |
| blk.11.ffn_down_exps.weight q3_K | |
| blk.11.ffn_down_shexp.weight q3_K | |
| blk.12.attn_k.weight iq2_s | |
| blk.12.attn_output.weight iq3_s | |
| blk.12.attn_q.weight iq2_s | |
| blk.12.attn_v.weight q4_K | |
| blk.12.ffn_down_exps.weight q3_K | |
| blk.12.ffn_down_shexp.weight q3_K | |
| blk.13.attn_k.weight iq2_s | |
| blk.13.attn_output.weight iq3_s | |
| blk.13.attn_q.weight iq2_s | |
| blk.13.attn_v.weight q4_K | |
| blk.13.ffn_down_exps.weight q3_K | |
| blk.13.ffn_down_shexp.weight q3_K | |
| blk.14.attn_k.weight iq2_s | |
| blk.14.attn_output.weight iq3_s | |
| blk.14.attn_q.weight iq2_s | |
| blk.14.attn_v.weight q4_K | |
| blk.14.ffn_down_exps.weight q3_K | |
| blk.14.ffn_down_shexp.weight q3_K | |
| blk.15.attn_k.weight iq2_s | |
| blk.15.attn_output.weight iq3_s | |
| blk.15.attn_q.weight iq2_s | |
| blk.15.attn_v.weight q4_K | |
| blk.15.ffn_down_exps.weight q3_K | |
| blk.15.ffn_down_shexp.weight q3_K | |
| blk.16.attn_k.weight iq2_s | |
| blk.16.attn_output.weight iq3_s | |
| blk.16.attn_q.weight iq2_s | |
| blk.16.attn_v.weight q4_K | |
| blk.16.ffn_down_exps.weight q3_K | |
| blk.16.ffn_down_shexp.weight q3_K | |
| blk.17.attn_k.weight iq2_s | |
| blk.17.attn_output.weight iq3_s | |
| blk.17.attn_q.weight iq2_s | |
| blk.17.attn_v.weight q4_K | |
| blk.17.ffn_down_exps.weight q3_K | |
| blk.17.ffn_down_shexp.weight q3_K | |
| blk.18.attn_k.weight iq2_s | |
| blk.18.attn_output.weight iq3_s | |
| blk.18.attn_q.weight iq2_s | |
| blk.18.attn_v.weight q4_K | |
| blk.18.ffn_down_exps.weight q3_K | |
| blk.18.ffn_down_shexp.weight q3_K | |
| blk.19.attn_k.weight iq2_s | |
| blk.19.attn_output.weight iq3_s | |
| blk.19.attn_q.weight iq2_s | |
| blk.19.attn_v.weight q4_K | |
| blk.19.ffn_down_exps.weight q3_K | |
| blk.19.ffn_down_shexp.weight q3_K | |
| blk.20.attn_k.weight iq2_s | |
| blk.20.attn_output.weight iq3_s | |
| blk.20.attn_q.weight iq2_s | |
| blk.20.attn_v.weight q4_K | |
| blk.20.ffn_down_exps.weight q3_K | |
| blk.20.ffn_down_shexp.weight q3_K | |
| blk.21.attn_k.weight iq2_s | |
| blk.21.attn_output.weight iq3_s | |
| blk.21.attn_q.weight iq2_s | |
| blk.21.attn_v.weight q4_K | |
| blk.21.ffn_down_exps.weight q3_K | |
| blk.21.ffn_down_shexp.weight q3_K | |
| blk.22.attn_k.weight iq2_s | |
| blk.22.attn_output.weight iq3_s | |
| blk.22.attn_q.weight iq2_s | |
| blk.22.attn_v.weight q4_K | |
| blk.22.ffn_down_exps.weight q3_K | |
| blk.22.ffn_down_shexp.weight q3_K | |
| blk.23.attn_k.weight iq2_s | |
| blk.23.attn_output.weight iq3_s | |
| blk.23.attn_q.weight iq2_s | |
| blk.23.attn_v.weight q4_K | |
| blk.23.ffn_down_exps.weight q3_K | |
| blk.23.ffn_down_shexp.weight q3_K | |
| blk.24.attn_k.weight iq2_s | |
| blk.24.attn_output.weight iq3_s | |
| blk.24.attn_q.weight iq2_s | |
| blk.24.attn_v.weight q4_K | |
| blk.24.ffn_down_exps.weight q3_K | |
| blk.24.ffn_down_shexp.weight q3_K | |
| blk.25.attn_k.weight iq2_s | |
| blk.25.attn_output.weight iq3_s | |
| blk.25.attn_q.weight iq2_s | |
| blk.25.attn_v.weight q4_K | |
| blk.25.ffn_down_exps.weight q3_K | |
| blk.25.ffn_down_shexp.weight q3_K | |
| blk.26.attn_k.weight iq2_s | |
| blk.26.attn_output.weight iq3_s | |
| blk.26.attn_q.weight iq2_s | |
| blk.26.attn_v.weight q4_K | |
| blk.26.ffn_down_exps.weight q3_K | |
| blk.26.ffn_down_shexp.weight q3_K | |
| blk.27.attn_k.weight iq2_s | |
| blk.27.attn_output.weight iq3_s | |
| blk.27.attn_q.weight iq2_s | |
| blk.27.attn_v.weight q4_K | |
| blk.27.ffn_down_exps.weight q3_K | |
| blk.27.ffn_down_shexp.weight q3_K | |
| blk.28.attn_k.weight iq2_s | |
| blk.28.attn_output.weight iq3_s | |
| blk.28.attn_q.weight iq2_s | |
| blk.28.attn_v.weight q4_K | |
| blk.28.ffn_down_exps.weight q3_K | |
| blk.28.ffn_down_shexp.weight q3_K | |
| blk.29.attn_k.weight iq2_s | |
| blk.29.attn_output.weight iq3_s | |
| blk.29.attn_q.weight iq2_s | |
| blk.29.attn_v.weight q4_K | |
| blk.29.ffn_down_exps.weight q3_K | |
| blk.29.ffn_down_shexp.weight q3_K | |
| blk.30.attn_k.weight iq2_s | |
| blk.30.attn_output.weight iq3_s | |
| blk.30.attn_q.weight iq2_s | |
| blk.30.attn_v.weight q4_K | |
| blk.30.ffn_down_exps.weight q3_K | |
| blk.30.ffn_down_shexp.weight q3_K | |
| blk.31.attn_k.weight iq2_s | |
| blk.31.attn_output.weight iq3_s | |
| blk.31.attn_q.weight iq2_s | |
| blk.31.attn_v.weight q4_K | |
| blk.31.ffn_down_exps.weight q3_K | |
| blk.31.ffn_down_shexp.weight q3_K | |
| blk.32.attn_k.weight iq2_s | |
| blk.32.attn_output.weight iq3_s | |
| blk.32.attn_q.weight iq2_s | |
| blk.32.attn_v.weight q4_K | |
| blk.32.ffn_down_exps.weight q3_K | |
| blk.32.ffn_down_shexp.weight q3_K | |
| blk.33.attn_k.weight iq2_s | |
| blk.33.attn_output.weight iq3_s | |
| blk.33.attn_q.weight iq2_s | |
| blk.33.attn_v.weight q4_K | |
| blk.33.ffn_down_exps.weight q3_K | |
| blk.33.ffn_down_shexp.weight q3_K | |
| blk.34.attn_k.weight iq2_s | |
| blk.34.attn_output.weight iq3_s | |
| blk.34.attn_q.weight iq2_s | |
| blk.34.attn_v.weight q4_K | |
| blk.34.ffn_down_exps.weight q3_K | |
| blk.34.ffn_down_shexp.weight q3_K | |
| blk.35.attn_k.weight iq2_s | |
| blk.35.attn_output.weight iq3_s | |
| blk.35.attn_q.weight iq2_s | |
| blk.35.attn_v.weight q4_K | |
| blk.35.ffn_down_exps.weight q3_K | |
| blk.35.ffn_down_shexp.weight q3_K | |
| blk.36.attn_k.weight iq2_s | |
| blk.36.attn_output.weight iq3_s | |
| blk.36.attn_q.weight iq2_s | |
| blk.36.attn_v.weight q4_K | |
| blk.36.ffn_down_exps.weight q3_K | |
| blk.36.ffn_down_shexp.weight q3_K | |
| blk.37.attn_k.weight iq2_s | |
| blk.37.attn_output.weight iq3_s | |
| blk.37.attn_q.weight iq2_s | |
| blk.37.attn_v.weight q4_K | |
| blk.37.ffn_down_exps.weight q3_K | |
| blk.37.ffn_down_shexp.weight q3_K | |
| blk.38.attn_k.weight iq2_s | |
| blk.38.attn_output.weight iq3_s | |
| blk.38.attn_q.weight iq2_s | |
| blk.38.attn_v.weight q4_K | |
| blk.38.ffn_down_exps.weight q3_K | |
| blk.38.ffn_down_shexp.weight q3_K | |
| blk.39.attn_k.weight iq2_s | |
| blk.39.attn_output.weight iq3_s | |
| blk.39.attn_q.weight iq2_s | |
| blk.39.attn_v.weight q4_K | |
| blk.39.ffn_down_exps.weight q3_K | |
| blk.39.ffn_down_shexp.weight q3_K | |
| blk.40.attn_k.weight iq2_s | |
| blk.40.attn_output.weight iq3_s | |
| blk.40.attn_q.weight iq2_s | |
| blk.40.attn_v.weight q4_K | |
| blk.40.ffn_down_exps.weight q3_K | |
| blk.40.ffn_down_shexp.weight q3_K | |
| blk.41.attn_k.weight iq2_s | |
| blk.41.attn_output.weight iq3_s | |
| blk.41.attn_q.weight iq2_s | |
| blk.41.attn_v.weight q4_K | |
| blk.41.ffn_down_exps.weight q3_K | |
| blk.41.ffn_down_shexp.weight q3_K | |
| blk.42.attn_k.weight iq2_s | |
| blk.42.attn_output.weight iq3_s | |
| blk.42.attn_q.weight iq2_s | |
| blk.42.attn_v.weight q4_K | |
| blk.42.ffn_down_exps.weight q3_K | |
| blk.42.ffn_down_shexp.weight q3_K | |
| blk.43.attn_k.weight iq2_s | |
| blk.43.attn_output.weight iq3_s | |
| blk.43.attn_q.weight iq2_s | |
| blk.43.attn_v.weight q4_K | |
| blk.43.ffn_down_exps.weight q3_K | |
| blk.43.ffn_down_shexp.weight q3_K | |
| blk.44.attn_k.weight iq2_s | |
| blk.44.attn_output.weight iq3_s | |
| blk.44.attn_q.weight iq2_s | |
| blk.44.attn_v.weight q4_K | |
| blk.44.ffn_down_exps.weight q3_K | |
| blk.44.ffn_down_shexp.weight q3_K | |
| [IQ1_S] iq1_s | |
| output.weight q5_K | |
| token_embd.weight q2_K | |
| blk.0.attn_output.weight iq2_xxs | |
| blk.0.attn_v.weight q4_K | |
| blk.0.ffn_down.weight q2_K | |
| blk.1.attn_output.weight iq2_xxs | |
| blk.1.attn_v.weight q4_K | |
| blk.1.ffn_down.weight q2_K | |
| blk.2.attn_output.weight iq2_xxs | |
| blk.2.attn_v.weight q4_K | |
| blk.2.ffn_down.weight q2_K | |
| blk.3.attn_output.weight iq2_xxs | |
| blk.3.attn_v.weight q4_K | |
| blk.3.ffn_down_exps.weight q2_K | |
| blk.3.ffn_down_shexp.weight q2_K | |
| blk.4.attn_output.weight iq2_xxs | |
| blk.4.attn_v.weight q4_K | |
| blk.5.attn_output.weight iq2_xxs | |
| blk.5.attn_v.weight q4_K | |
| blk.6.attn_output.weight iq2_xxs | |
| blk.6.attn_v.weight q4_K | |
| blk.7.attn_output.weight iq2_xxs | |
| blk.7.attn_v.weight q4_K | |
| blk.8.attn_output.weight iq2_xxs | |
| blk.8.attn_v.weight q4_K | |
| blk.9.attn_output.weight iq2_xxs | |
| blk.9.attn_v.weight q4_K | |
| blk.10.attn_output.weight iq2_xxs | |
| blk.10.attn_v.weight q4_K | |
| blk.11.attn_output.weight iq2_xxs | |
| blk.11.attn_v.weight q4_K | |
| blk.12.attn_output.weight iq2_xxs | |
| blk.12.attn_v.weight q4_K | |
| blk.13.attn_output.weight iq2_xxs | |
| blk.13.attn_v.weight q4_K | |
| blk.14.attn_output.weight iq2_xxs | |
| blk.14.attn_v.weight q4_K | |
| blk.15.attn_output.weight iq2_xxs | |
| blk.15.attn_v.weight q4_K | |
| blk.16.attn_output.weight iq2_xxs | |
| blk.16.attn_v.weight q4_K | |
| blk.17.attn_output.weight iq2_xxs | |
| blk.17.attn_v.weight q4_K | |
| blk.18.attn_output.weight iq2_xxs | |
| blk.18.attn_v.weight q4_K | |
| blk.19.attn_output.weight iq2_xxs | |
| blk.19.attn_v.weight q4_K | |
| blk.20.attn_output.weight iq2_xxs | |
| blk.20.attn_v.weight q4_K | |
| blk.21.attn_output.weight iq2_xxs | |
| blk.21.attn_v.weight q4_K | |
| blk.22.attn_output.weight iq2_xxs | |
| blk.22.attn_v.weight q4_K | |
| blk.23.attn_output.weight iq2_xxs | |
| blk.23.attn_v.weight q4_K | |
| blk.24.attn_output.weight iq2_xxs | |
| blk.24.attn_v.weight q4_K | |
| blk.25.attn_output.weight iq2_xxs | |
| blk.25.attn_v.weight q4_K | |
| blk.26.attn_output.weight iq2_xxs | |
| blk.26.attn_v.weight q4_K | |
| blk.27.attn_output.weight iq2_xxs | |
| blk.27.attn_v.weight q4_K | |
| blk.28.attn_output.weight iq2_xxs | |
| blk.28.attn_v.weight q4_K | |
| blk.29.attn_output.weight iq2_xxs | |
| blk.29.attn_v.weight q4_K | |
| blk.30.attn_output.weight iq2_xxs | |
| blk.30.attn_v.weight q4_K | |
| blk.31.attn_output.weight iq2_xxs | |
| blk.31.attn_v.weight q4_K | |
| blk.32.attn_output.weight iq2_xxs | |
| blk.32.attn_v.weight q4_K | |
| blk.33.attn_output.weight iq2_xxs | |
| blk.33.attn_v.weight q4_K | |
| blk.34.attn_output.weight iq2_xxs | |
| blk.34.attn_v.weight q4_K | |
| blk.35.attn_output.weight iq2_xxs | |
| blk.35.attn_v.weight q4_K | |
| blk.36.attn_output.weight iq2_xxs | |
| blk.36.attn_v.weight q4_K | |
| blk.37.attn_output.weight iq2_xxs | |
| blk.37.attn_v.weight q4_K | |
| blk.38.attn_output.weight iq2_xxs | |
| blk.38.attn_v.weight q4_K | |
| blk.39.attn_output.weight iq2_xxs | |
| blk.39.attn_v.weight q4_K | |
| blk.40.attn_output.weight iq2_xxs | |
| blk.40.attn_v.weight q4_K | |
| blk.41.attn_output.weight iq2_xxs | |
| blk.41.attn_v.weight q4_K | |
| blk.42.attn_output.weight iq2_xxs | |
| blk.42.attn_v.weight q4_K | |
| blk.43.attn_output.weight iq2_xxs | |
| blk.43.attn_v.weight q4_K | |
| blk.44.attn_output.weight iq2_xxs | |
| blk.44.attn_v.weight q4_K | |
| [IQ4_NL] iq4_nl | |
| output.weight q6_K | |
| blk.0.attn_v.weight q5_K | |
| blk.0.ffn_down.weight q5_K | |
| blk.1.attn_v.weight q5_K | |
| blk.1.ffn_down.weight q5_K | |
| blk.2.attn_v.weight q5_K | |
| blk.2.ffn_down.weight q5_K | |
| blk.3.attn_v.weight q5_K | |
| blk.3.ffn_down_exps.weight q5_K | |
| blk.3.ffn_down_shexp.weight q5_K | |
| blk.4.attn_v.weight q5_K | |
| blk.4.ffn_down_exps.weight q5_K | |
| blk.4.ffn_down_shexp.weight q5_K | |
| blk.5.attn_v.weight q5_K | |
| blk.6.attn_v.weight q5_K | |
| blk.7.attn_v.weight q5_K | |
| blk.8.attn_v.weight q5_K | |
| blk.9.attn_v.weight q5_K | |
| blk.10.attn_v.weight q5_K | |
| blk.11.attn_v.weight q5_K | |
| blk.12.attn_v.weight q5_K | |
| blk.13.attn_v.weight q5_K | |
| blk.14.attn_v.weight q5_K | |
| blk.15.attn_v.weight q5_K | |
| blk.16.attn_v.weight q5_K | |
| blk.17.attn_v.weight q5_K | |
| blk.18.attn_v.weight q5_K | |
| blk.19.attn_v.weight q5_K | |
| blk.20.attn_v.weight q5_K | |
| blk.21.attn_v.weight q5_K | |
| blk.22.attn_v.weight q5_K | |
| blk.23.attn_v.weight q5_K | |
| blk.24.attn_v.weight q5_K | |
| blk.25.attn_v.weight q5_K | |
| blk.26.attn_v.weight q5_K | |
| blk.27.attn_v.weight q5_K | |
| blk.28.attn_v.weight q5_K | |
| blk.29.attn_v.weight q5_K | |
| blk.30.attn_v.weight q5_K | |
| blk.31.attn_v.weight q5_K | |
| blk.32.attn_v.weight q5_K | |
| blk.33.attn_v.weight q5_K | |
| blk.34.attn_v.weight q5_K | |
| blk.35.attn_v.weight q5_K | |
| blk.36.attn_v.weight q5_K | |
| blk.37.attn_v.weight q5_K | |
| blk.38.attn_v.weight q5_K | |
| blk.39.attn_v.weight q5_K | |
| blk.40.attn_v.weight q5_K | |
| blk.41.attn_v.weight q5_K | |
| blk.42.attn_v.weight q5_K | |
| blk.43.attn_v.weight q5_K | |
| blk.44.attn_v.weight q5_K | |
| [IQ3_S] iq3_s | |
| output.weight q6_K | |
| blk.0.attn_v.weight q4_K | |
| blk.1.attn_v.weight q4_K | |
| blk.2.attn_v.weight q4_K | |
| blk.3.attn_v.weight q4_K | |
| blk.4.attn_v.weight q4_K | |
| blk.5.attn_v.weight q4_K | |
| blk.6.attn_v.weight q4_K | |
| blk.7.attn_v.weight q4_K | |
| blk.8.attn_v.weight q4_K | |
| blk.9.attn_v.weight q4_K | |
| blk.10.attn_v.weight q4_K | |
| blk.11.attn_v.weight q4_K | |
| blk.12.attn_v.weight q4_K | |
| blk.13.attn_v.weight q4_K | |
| blk.14.attn_v.weight q4_K | |
| blk.15.attn_v.weight q4_K | |
| blk.16.attn_v.weight q4_K | |
| blk.17.attn_v.weight q4_K | |
| blk.18.attn_v.weight q4_K | |
| blk.19.attn_v.weight q4_K | |
| blk.20.attn_v.weight q4_K | |
| blk.21.attn_v.weight q4_K | |
| blk.22.attn_v.weight q4_K | |
| blk.23.attn_v.weight q4_K | |
| blk.24.attn_v.weight q4_K | |
| blk.25.attn_v.weight q4_K | |
| blk.26.attn_v.weight q4_K | |
| blk.27.attn_v.weight q4_K | |
| blk.28.attn_v.weight q4_K | |
| blk.29.attn_v.weight q4_K | |
| blk.30.attn_v.weight q4_K | |
| blk.31.attn_v.weight q4_K | |
| blk.32.attn_v.weight q4_K | |
| blk.33.attn_v.weight q4_K | |
| blk.34.attn_v.weight q4_K | |
| blk.35.attn_v.weight q4_K | |
| blk.36.attn_v.weight q4_K | |
| blk.37.attn_v.weight q4_K | |
| blk.38.attn_v.weight q4_K | |
| blk.39.attn_v.weight q4_K | |
| blk.40.attn_v.weight q4_K | |
| blk.41.attn_v.weight q4_K | |
| blk.42.attn_v.weight q4_K | |
| blk.43.attn_v.weight q4_K | |
| blk.44.attn_v.weight q4_K | |
| [IQ3_M] iq3_s | |
| output.weight q6_K | |
| blk.0.attn_output.weight q4_K | |
| blk.0.attn_v.weight q4_K | |
| blk.0.ffn_down.weight q4_K | |
| blk.1.attn_output.weight q4_K | |
| blk.1.attn_v.weight q4_K | |
| blk.1.ffn_down.weight q4_K | |
| blk.2.attn_output.weight q4_K | |
| blk.2.attn_v.weight q4_K | |
| blk.2.ffn_down.weight q4_K | |
| blk.3.attn_output.weight q4_K | |
| blk.3.attn_v.weight q4_K | |
| blk.3.ffn_down_exps.weight q4_K | |
| blk.3.ffn_down_shexp.weight q4_K | |
| blk.4.attn_output.weight q4_K | |
| blk.4.attn_v.weight q4_K | |
| blk.4.ffn_down_exps.weight q4_K | |
| blk.4.ffn_down_shexp.weight q4_K | |
| blk.5.attn_output.weight q4_K | |
| blk.5.attn_v.weight q4_K | |
| blk.6.attn_output.weight q4_K | |
| blk.6.attn_v.weight q4_K | |
| blk.7.attn_output.weight q4_K | |
| blk.7.attn_v.weight q4_K | |
| blk.8.attn_output.weight q4_K | |
| blk.8.attn_v.weight q4_K | |
| blk.9.attn_output.weight q4_K | |
| blk.9.attn_v.weight q4_K | |
| blk.10.attn_output.weight q4_K | |
| blk.10.attn_v.weight q4_K | |
| blk.11.attn_output.weight q4_K | |
| blk.11.attn_v.weight q4_K | |
| blk.12.attn_output.weight q4_K | |
| blk.12.attn_v.weight q4_K | |
| blk.13.attn_output.weight q4_K | |
| blk.13.attn_v.weight q4_K | |
| blk.14.attn_output.weight q4_K | |
| blk.14.attn_v.weight q4_K | |
| blk.15.attn_output.weight q4_K | |
| blk.15.attn_v.weight q4_K | |
| blk.16.attn_output.weight q4_K | |
| blk.16.attn_v.weight q4_K | |
| blk.17.attn_output.weight q4_K | |
| blk.17.attn_v.weight q4_K | |
| blk.18.attn_output.weight q4_K | |
| blk.18.attn_v.weight q4_K | |
| blk.19.attn_output.weight q4_K | |
| blk.19.attn_v.weight q4_K | |
| blk.20.attn_output.weight q4_K | |
| blk.20.attn_v.weight q4_K | |
| blk.21.attn_output.weight q4_K | |
| blk.21.attn_v.weight q4_K | |
| blk.22.attn_output.weight q4_K | |
| blk.22.attn_v.weight q4_K | |
| blk.23.attn_output.weight q4_K | |
| blk.23.attn_v.weight q4_K | |
| blk.24.attn_output.weight q4_K | |
| blk.24.attn_v.weight q4_K | |
| blk.25.attn_output.weight q4_K | |
| blk.25.attn_v.weight q4_K | |
| blk.26.attn_output.weight q4_K | |
| blk.26.attn_v.weight q4_K | |
| blk.27.attn_output.weight q4_K | |
| blk.27.attn_v.weight q4_K | |
| blk.28.attn_output.weight q4_K | |
| blk.28.attn_v.weight q4_K | |
| blk.29.attn_output.weight q4_K | |
| blk.29.attn_v.weight q4_K | |
| blk.30.attn_output.weight q4_K | |
| blk.30.attn_v.weight q4_K | |
| blk.31.attn_output.weight q4_K | |
| blk.31.attn_v.weight q4_K | |
| blk.32.attn_output.weight q4_K | |
| blk.32.attn_v.weight q4_K | |
| blk.33.attn_output.weight q4_K | |
| blk.33.attn_v.weight q4_K | |
| blk.34.attn_output.weight q4_K | |
| blk.34.attn_v.weight q4_K | |
| blk.35.attn_output.weight q4_K | |
| blk.35.attn_v.weight q4_K | |
| blk.36.attn_output.weight q4_K | |
| blk.36.attn_v.weight q4_K | |
| blk.37.attn_output.weight q4_K | |
| blk.37.attn_v.weight q4_K | |
| blk.38.attn_output.weight q4_K | |
| blk.38.attn_v.weight q4_K | |
| blk.39.attn_output.weight q4_K | |
| blk.39.attn_v.weight q4_K | |
| blk.40.attn_output.weight q4_K | |
| blk.40.attn_v.weight q4_K | |
| blk.41.attn_output.weight q4_K | |
| blk.41.attn_v.weight q4_K | |
| blk.42.attn_output.weight q4_K | |
| blk.42.attn_v.weight q4_K | |
| blk.43.attn_output.weight q4_K | |
| blk.43.attn_v.weight q4_K | |
| blk.44.attn_output.weight q4_K | |
| blk.44.attn_v.weight q4_K | |
| [IQ2_S] iq2_xs | |
| output.weight q5_K | |
| token_embd.weight iq3_s | |
| blk.0.attn_output.weight iq3_s | |
| blk.0.attn_v.weight q4_K | |
| blk.0.ffn_down.weight iq3_s | |
| blk.1.attn_output.weight iq3_s | |
| blk.1.attn_v.weight q4_K | |
| blk.1.ffn_down.weight iq3_s | |
| blk.2.attn_output.weight iq3_s | |
| blk.2.attn_v.weight q4_K | |
| blk.2.ffn_down.weight iq3_s | |
| blk.3.attn_output.weight iq3_s | |
| blk.3.attn_v.weight q4_K | |
| blk.3.ffn_down_exps.weight iq3_s | |
| blk.3.ffn_down_shexp.weight iq3_s | |
| blk.4.attn_output.weight iq3_s | |
| blk.4.attn_v.weight q4_K | |
| blk.5.attn_output.weight iq3_s | |
| blk.5.attn_v.weight q4_K | |
| blk.6.attn_output.weight iq3_s | |
| blk.6.attn_v.weight q4_K | |
| blk.7.attn_output.weight iq3_s | |
| blk.7.attn_v.weight q4_K | |
| blk.8.attn_output.weight iq3_s | |
| blk.8.attn_v.weight q4_K | |
| blk.9.attn_output.weight iq3_s | |
| blk.9.attn_v.weight q4_K | |
| blk.10.attn_output.weight iq3_s | |
| blk.10.attn_v.weight q4_K | |
| blk.11.attn_output.weight iq3_s | |
| blk.11.attn_v.weight q4_K | |
| blk.12.attn_output.weight iq3_s | |
| blk.12.attn_v.weight q4_K | |
| blk.13.attn_output.weight iq3_s | |
| blk.13.attn_v.weight q4_K | |
| blk.14.attn_output.weight iq3_s | |
| blk.14.attn_v.weight q4_K | |
| blk.15.attn_output.weight iq3_s | |
| blk.15.attn_v.weight q4_K | |
| blk.16.attn_output.weight iq3_s | |
| blk.16.attn_v.weight q4_K | |
| blk.17.attn_output.weight iq3_s | |
| blk.17.attn_v.weight q4_K | |
| blk.18.attn_output.weight iq3_s | |
| blk.18.attn_v.weight q4_K | |
| blk.19.attn_output.weight iq3_s | |
| blk.19.attn_v.weight q4_K | |
| blk.20.attn_output.weight iq3_s | |
| blk.20.attn_v.weight q4_K | |
| blk.21.attn_output.weight iq3_s | |
| blk.21.attn_v.weight q4_K | |
| blk.22.attn_output.weight iq3_s | |
| blk.22.attn_v.weight q4_K | |
| blk.23.attn_output.weight iq3_s | |
| blk.23.attn_v.weight q4_K | |
| blk.24.attn_output.weight iq3_s | |
| blk.24.attn_v.weight q4_K | |
| blk.25.attn_output.weight iq3_s | |
| blk.25.attn_v.weight q4_K | |
| blk.26.attn_output.weight iq3_s | |
| blk.26.attn_v.weight q4_K | |
| blk.27.attn_output.weight iq3_s | |
| blk.27.attn_v.weight q4_K | |
| blk.28.attn_output.weight iq3_s | |
| blk.28.attn_v.weight q4_K | |
| blk.29.attn_output.weight iq3_s | |
| blk.29.attn_v.weight q4_K | |
| blk.30.attn_output.weight iq3_s | |
| blk.30.attn_v.weight q4_K | |
| blk.31.attn_output.weight iq3_s | |
| blk.31.attn_v.weight q4_K | |
| blk.32.attn_output.weight iq3_s | |
| blk.32.attn_v.weight q4_K | |
| blk.33.attn_output.weight iq3_s | |
| blk.33.attn_v.weight q4_K | |
| blk.34.attn_output.weight iq3_s | |
| blk.34.attn_v.weight q4_K | |
| blk.35.attn_output.weight iq3_s | |
| blk.35.attn_v.weight q4_K | |
| blk.36.attn_output.weight iq3_s | |
| blk.36.attn_v.weight q4_K | |
| blk.37.attn_output.weight iq3_s | |
| blk.37.attn_v.weight q4_K | |
| blk.38.attn_output.weight iq3_s | |
| blk.38.attn_v.weight q4_K | |
| blk.39.attn_output.weight iq3_s | |
| blk.39.attn_v.weight q4_K | |
| blk.40.attn_output.weight iq3_s | |
| blk.40.attn_v.weight q4_K | |
| blk.41.attn_output.weight iq3_s | |
| blk.41.attn_v.weight q4_K | |
| blk.42.attn_output.weight iq3_s | |
| blk.42.attn_v.weight q4_K | |
| blk.43.attn_output.weight iq3_s | |
| blk.43.attn_v.weight q4_K | |
| blk.44.attn_output.weight iq3_s | |
| blk.44.attn_v.weight q4_K | |
| [IQ2_M] iq2_s | |
| output.weight q5_K | |
| token_embd.weight iq3_s | |
| blk.0.attn_output.weight iq3_s | |
| blk.0.attn_v.weight q4_K | |
| blk.0.ffn_down.weight iq3_s | |
| blk.1.attn_output.weight iq3_s | |
| blk.1.attn_v.weight q4_K | |
| blk.1.ffn_down.weight iq3_s | |
| blk.2.attn_output.weight iq3_s | |
| blk.2.attn_v.weight q4_K | |
| blk.2.ffn_down.weight iq3_s | |
| blk.3.attn_output.weight iq3_s | |
| blk.3.attn_v.weight q4_K | |
| blk.3.ffn_down_exps.weight iq3_s | |
| blk.3.ffn_down_shexp.weight iq3_s | |
| blk.4.attn_output.weight iq3_s | |
| blk.4.attn_v.weight q4_K | |
| blk.5.attn_output.weight iq3_s | |
| blk.5.attn_v.weight q4_K | |
| blk.6.attn_output.weight iq3_s | |
| blk.6.attn_v.weight q4_K | |
| blk.7.attn_output.weight iq3_s | |
| blk.7.attn_v.weight q4_K | |
| blk.8.attn_output.weight iq3_s | |
| blk.8.attn_v.weight q4_K | |
| blk.9.attn_output.weight iq3_s | |
| blk.9.attn_v.weight q4_K | |
| blk.10.attn_output.weight iq3_s | |
| blk.10.attn_v.weight q4_K | |
| blk.11.attn_output.weight iq3_s | |
| blk.11.attn_v.weight q4_K | |
| blk.12.attn_output.weight iq3_s | |
| blk.12.attn_v.weight q4_K | |
| blk.13.attn_output.weight iq3_s | |
| blk.13.attn_v.weight q4_K | |
| blk.14.attn_output.weight iq3_s | |
| blk.14.attn_v.weight q4_K | |
| blk.15.attn_output.weight iq3_s | |
| blk.15.attn_v.weight q4_K | |
| blk.16.attn_output.weight iq3_s | |
| blk.16.attn_v.weight q4_K | |
| blk.17.attn_output.weight iq3_s | |
| blk.17.attn_v.weight q4_K | |
| blk.18.attn_output.weight iq3_s | |
| blk.18.attn_v.weight q4_K | |
| blk.19.attn_output.weight iq3_s | |
| blk.19.attn_v.weight q4_K | |
| blk.20.attn_output.weight iq3_s | |
| blk.20.attn_v.weight q4_K | |
| blk.21.attn_output.weight iq3_s | |
| blk.21.attn_v.weight q4_K | |
| blk.22.attn_output.weight iq3_s | |
| blk.22.attn_v.weight q4_K | |
| blk.23.attn_output.weight iq3_s | |
| blk.23.attn_v.weight q4_K | |
| blk.24.attn_output.weight iq3_s | |
| blk.24.attn_v.weight q4_K | |
| blk.25.attn_output.weight iq3_s | |
| blk.25.attn_v.weight q4_K | |
| blk.26.attn_output.weight iq3_s | |
| blk.26.attn_v.weight q4_K | |
| blk.27.attn_output.weight iq3_s | |
| blk.27.attn_v.weight q4_K | |
| blk.28.attn_output.weight iq3_s | |
| blk.28.attn_v.weight q4_K | |
| blk.29.attn_output.weight iq3_s | |
| blk.29.attn_v.weight q4_K | |
| blk.30.attn_output.weight iq3_s | |
| blk.30.attn_v.weight q4_K | |
| blk.31.attn_output.weight iq3_s | |
| blk.31.attn_v.weight q4_K | |
| blk.32.attn_output.weight iq3_s | |
| blk.32.attn_v.weight q4_K | |
| blk.33.attn_output.weight iq3_s | |
| blk.33.attn_v.weight q4_K | |
| blk.34.attn_output.weight iq3_s | |
| blk.34.attn_v.weight q4_K | |
| blk.35.attn_output.weight iq3_s | |
| blk.35.attn_v.weight q4_K | |
| blk.36.attn_output.weight iq3_s | |
| blk.36.attn_v.weight q4_K | |
| blk.37.attn_output.weight iq3_s | |
| blk.37.attn_v.weight q4_K | |
| blk.38.attn_output.weight iq3_s | |
| blk.38.attn_v.weight q4_K | |
| blk.39.attn_output.weight iq3_s | |
| blk.39.attn_v.weight q4_K | |
| blk.40.attn_output.weight iq3_s | |
| blk.40.attn_v.weight q4_K | |
| blk.41.attn_output.weight iq3_s | |
| blk.41.attn_v.weight q4_K | |
| blk.42.attn_output.weight iq3_s | |
| blk.42.attn_v.weight q4_K | |
| blk.43.attn_output.weight iq3_s | |
| blk.43.attn_v.weight q4_K | |
| blk.44.attn_output.weight iq3_s | |
| blk.44.attn_v.weight q4_K | |
| [IQ4_XS] iq4_xs | |
| output.weight q6_K | |
| blk.0.attn_v.weight q5_K | |
| blk.0.ffn_down.weight q5_K | |
| blk.1.attn_v.weight q5_K | |
| blk.1.ffn_down.weight q5_K | |
| blk.2.attn_v.weight q5_K | |
| blk.2.ffn_down.weight q5_K | |
| blk.3.attn_v.weight q5_K | |
| blk.3.ffn_down_exps.weight q5_K | |
| blk.3.ffn_down_shexp.weight q5_K | |
| blk.4.attn_v.weight q5_K | |
| blk.4.ffn_down_exps.weight q5_K | |
| blk.4.ffn_down_shexp.weight q5_K | |
| blk.5.attn_v.weight q5_K | |
| blk.6.attn_v.weight q5_K | |
| blk.7.attn_v.weight q5_K | |
| blk.8.attn_v.weight q5_K | |
| blk.9.attn_v.weight q5_K | |
| blk.10.attn_v.weight q5_K | |
| blk.11.attn_v.weight q5_K | |
| blk.12.attn_v.weight q5_K | |
| blk.13.attn_v.weight q5_K | |
| blk.14.attn_v.weight q5_K | |
| blk.15.attn_v.weight q5_K | |
| blk.16.attn_v.weight q5_K | |
| blk.17.attn_v.weight q5_K | |
| blk.18.attn_v.weight q5_K | |
| blk.19.attn_v.weight q5_K | |
| blk.20.attn_v.weight q5_K | |
| blk.21.attn_v.weight q5_K | |
| blk.22.attn_v.weight q5_K | |
| blk.23.attn_v.weight q5_K | |
| blk.24.attn_v.weight q5_K | |
| blk.25.attn_v.weight q5_K | |
| blk.26.attn_v.weight q5_K | |
| blk.27.attn_v.weight q5_K | |
| blk.28.attn_v.weight q5_K | |
| blk.29.attn_v.weight q5_K | |
| blk.30.attn_v.weight q5_K | |
| blk.31.attn_v.weight q5_K | |
| blk.32.attn_v.weight q5_K | |
| blk.33.attn_v.weight q5_K | |
| blk.34.attn_v.weight q5_K | |
| blk.35.attn_v.weight q5_K | |
| blk.36.attn_v.weight q5_K | |
| blk.37.attn_v.weight q5_K | |
| blk.38.attn_v.weight q5_K | |
| blk.39.attn_v.weight q5_K | |
| blk.40.attn_v.weight q5_K | |
| blk.41.attn_v.weight q5_K | |
| blk.42.attn_v.weight q5_K | |
| blk.43.attn_v.weight q5_K | |
| blk.44.attn_v.weight q5_K | |
| [IQ1_M] iq1_m | |
| output.weight q5_K | |
| token_embd.weight q2_K | |
| blk.0.attn_output.weight iq2_xxs | |
| blk.0.attn_v.weight q4_K | |
| blk.0.ffn_down.weight q2_K | |
| blk.1.attn_output.weight iq2_xxs | |
| blk.1.attn_v.weight q4_K | |
| blk.1.ffn_down.weight q2_K | |
| blk.2.attn_output.weight iq2_xxs | |
| blk.2.attn_v.weight q4_K | |
| blk.2.ffn_down.weight q2_K | |
| blk.3.attn_output.weight iq2_xxs | |
| blk.3.attn_v.weight q4_K | |
| blk.3.ffn_down_exps.weight q2_K | |
| blk.3.ffn_down_shexp.weight q2_K | |
| blk.4.attn_output.weight iq2_xxs | |
| blk.4.attn_v.weight q4_K | |
| blk.5.attn_output.weight iq2_xxs | |
| blk.5.attn_v.weight q4_K | |
| blk.6.attn_output.weight iq2_xxs | |
| blk.6.attn_v.weight q4_K | |
| blk.7.attn_output.weight iq2_xxs | |
| blk.7.attn_v.weight q4_K | |
| blk.8.attn_output.weight iq2_xxs | |
| blk.8.attn_v.weight q4_K | |
| blk.9.attn_output.weight iq2_xxs | |
| blk.9.attn_v.weight q4_K | |
| blk.10.attn_output.weight iq2_xxs | |
| blk.10.attn_v.weight q4_K | |
| blk.11.attn_output.weight iq2_xxs | |
| blk.11.attn_v.weight q4_K | |
| blk.12.attn_output.weight iq2_xxs | |
| blk.12.attn_v.weight q4_K | |
| blk.13.attn_output.weight iq2_xxs | |
| blk.13.attn_v.weight q4_K | |
| blk.14.attn_output.weight iq2_xxs | |
| blk.14.attn_v.weight q4_K | |
| blk.15.attn_output.weight iq2_xxs | |
| blk.15.attn_v.weight q4_K | |
| blk.16.attn_output.weight iq2_xxs | |
| blk.16.attn_v.weight q4_K | |
| blk.17.attn_output.weight iq2_xxs | |
| blk.17.attn_v.weight q4_K | |
| blk.18.attn_output.weight iq2_xxs | |
| blk.18.attn_v.weight q4_K | |
| blk.19.attn_output.weight iq2_xxs | |
| blk.19.attn_v.weight q4_K | |
| blk.20.attn_output.weight iq2_xxs | |
| blk.20.attn_v.weight q4_K | |
| blk.21.attn_output.weight iq2_xxs | |
| blk.21.attn_v.weight q4_K | |
| blk.22.attn_output.weight iq2_xxs | |
| blk.22.attn_v.weight q4_K | |
| blk.23.attn_output.weight iq2_xxs | |
| blk.23.attn_v.weight q4_K | |
| blk.24.attn_output.weight iq2_xxs | |
| blk.24.attn_v.weight q4_K | |
| blk.25.attn_output.weight iq2_xxs | |
| blk.25.attn_v.weight q4_K | |
| blk.26.attn_output.weight iq2_xxs | |
| blk.26.attn_v.weight q4_K | |
| blk.27.attn_output.weight iq2_xxs | |
| blk.27.attn_v.weight q4_K | |
| blk.28.attn_output.weight iq2_xxs | |
| blk.28.attn_v.weight q4_K | |
| blk.29.attn_output.weight iq2_xxs | |
| blk.29.attn_v.weight q4_K | |
| blk.30.attn_output.weight iq2_xxs | |
| blk.30.attn_v.weight q4_K | |
| blk.31.attn_output.weight iq2_xxs | |
| blk.31.attn_v.weight q4_K | |
| blk.32.attn_output.weight iq2_xxs | |
| blk.32.attn_v.weight q4_K | |
| blk.33.attn_output.weight iq2_xxs | |
| blk.33.attn_v.weight q4_K | |
| blk.34.attn_output.weight iq2_xxs | |
| blk.34.attn_v.weight q4_K | |
| blk.35.attn_output.weight iq2_xxs | |
| blk.35.attn_v.weight q4_K | |
| blk.36.attn_output.weight iq2_xxs | |
| blk.36.attn_v.weight q4_K | |
| blk.37.attn_output.weight iq2_xxs | |
| blk.37.attn_v.weight q4_K | |
| blk.38.attn_output.weight iq2_xxs | |
| blk.38.attn_v.weight q4_K | |
| blk.39.attn_output.weight iq2_xxs | |
| blk.39.attn_v.weight q4_K | |
| blk.40.attn_output.weight iq2_xxs | |
| blk.40.attn_v.weight q4_K | |
| blk.41.attn_output.weight iq2_xxs | |
| blk.41.attn_v.weight q4_K | |
| blk.42.attn_output.weight iq2_xxs | |
| blk.42.attn_v.weight q4_K | |
| blk.43.attn_output.weight iq2_xxs | |
| blk.43.attn_v.weight q4_K | |
| blk.44.attn_output.weight iq2_xxs | |
| blk.44.attn_v.weight q4_K | |
| [BF16] bf16 | |
| [TQ1_0] tq1_0 | |
| output.weight q6_K | |
| token_embd.weight q4_K | |
| [TQ2_0] tq2_0 | |
| output.weight q6_K | |
| token_embd.weight q4_K | |
| [MXFP4_MOE] mxfp4 | |
| output.weight q8_0 | |
| token_embd.weight q8_0 | |
| blk.0.attn_gate.weight q8_0 | |
| blk.0.attn_k.weight q8_0 | |
| blk.0.attn_output.weight q8_0 | |
| blk.0.attn_q.weight q8_0 | |
| blk.0.attn_v.weight q8_0 | |
| blk.0.ffn_down.weight q8_0 | |
| blk.0.ffn_gate.weight q8_0 | |
| blk.0.ffn_up.weight q8_0 | |
| blk.1.attn_gate.weight q8_0 | |
| blk.1.attn_k.weight q8_0 | |
| blk.1.attn_output.weight q8_0 | |
| blk.1.attn_q.weight q8_0 | |
| blk.1.attn_v.weight q8_0 | |
| blk.1.ffn_down.weight q8_0 | |
| blk.1.ffn_gate.weight q8_0 | |
| blk.1.ffn_up.weight q8_0 | |
| blk.2.attn_gate.weight q8_0 | |
| blk.2.attn_k.weight q8_0 | |
| blk.2.attn_output.weight q8_0 | |
| blk.2.attn_q.weight q8_0 | |
| blk.2.attn_v.weight q8_0 | |
| blk.2.ffn_down.weight q8_0 | |
| blk.2.ffn_gate.weight q8_0 | |
| blk.2.ffn_up.weight q8_0 | |
| blk.3.attn_gate.weight q8_0 | |
| blk.3.attn_k.weight q8_0 | |
| blk.3.attn_output.weight q8_0 | |
| blk.3.attn_q.weight q8_0 | |
| blk.3.attn_v.weight q8_0 | |
| blk.3.ffn_down_shexp.weight q8_0 | |
| blk.3.ffn_gate_shexp.weight q8_0 | |
| blk.3.ffn_up_shexp.weight q8_0 | |
| blk.4.attn_gate.weight q8_0 | |
| blk.4.attn_k.weight q8_0 | |
| blk.4.attn_output.weight q8_0 | |
| blk.4.attn_q.weight q8_0 | |
| blk.4.attn_v.weight q8_0 | |
| blk.4.ffn_down_shexp.weight q8_0 | |
| blk.4.ffn_gate_shexp.weight q8_0 | |
| blk.4.ffn_up_shexp.weight q8_0 | |
| blk.5.attn_gate.weight q8_0 | |
| blk.5.attn_k.weight q8_0 | |
| blk.5.attn_output.weight q8_0 | |
| blk.5.attn_q.weight q8_0 | |
| blk.5.attn_v.weight q8_0 | |
| blk.5.ffn_down_shexp.weight q8_0 | |
| blk.5.ffn_gate_shexp.weight q8_0 | |
| blk.5.ffn_up_shexp.weight q8_0 | |
| blk.6.attn_gate.weight q8_0 | |
| blk.6.attn_k.weight q8_0 | |
| blk.6.attn_output.weight q8_0 | |
| blk.6.attn_q.weight q8_0 | |
| blk.6.attn_v.weight q8_0 | |
| blk.6.ffn_down_shexp.weight q8_0 | |
| blk.6.ffn_gate_shexp.weight q8_0 | |
| blk.6.ffn_up_shexp.weight q8_0 | |
| blk.7.attn_gate.weight q8_0 | |
| blk.7.attn_k.weight q8_0 | |
| blk.7.attn_output.weight q8_0 | |
| blk.7.attn_q.weight q8_0 | |
| blk.7.attn_v.weight q8_0 | |
| blk.7.ffn_down_shexp.weight q8_0 | |
| blk.7.ffn_gate_shexp.weight q8_0 | |
| blk.7.ffn_up_shexp.weight q8_0 | |
| blk.8.attn_gate.weight q8_0 | |
| blk.8.attn_k.weight q8_0 | |
| blk.8.attn_output.weight q8_0 | |
| blk.8.attn_q.weight q8_0 | |
| blk.8.attn_v.weight q8_0 | |
| blk.8.ffn_down_shexp.weight q8_0 | |
| blk.8.ffn_gate_shexp.weight q8_0 | |
| blk.8.ffn_up_shexp.weight q8_0 | |
| blk.9.attn_gate.weight q8_0 | |
| blk.9.attn_k.weight q8_0 | |
| blk.9.attn_output.weight q8_0 | |
| blk.9.attn_q.weight q8_0 | |
| blk.9.attn_v.weight q8_0 | |
| blk.9.ffn_down_shexp.weight q8_0 | |
| blk.9.ffn_gate_shexp.weight q8_0 | |
| blk.9.ffn_up_shexp.weight q8_0 | |
| blk.10.attn_gate.weight q8_0 | |
| blk.10.attn_k.weight q8_0 | |
| blk.10.attn_output.weight q8_0 | |
| blk.10.attn_q.weight q8_0 | |
| blk.10.attn_v.weight q8_0 | |
| blk.10.ffn_down_shexp.weight q8_0 | |
| blk.10.ffn_gate_shexp.weight q8_0 | |
| blk.10.ffn_up_shexp.weight q8_0 | |
| blk.11.attn_gate.weight q8_0 | |
| blk.11.attn_k.weight q8_0 | |
| blk.11.attn_output.weight q8_0 | |
| blk.11.attn_q.weight q8_0 | |
| blk.11.attn_v.weight q8_0 | |
| blk.11.ffn_down_shexp.weight q8_0 | |
| blk.11.ffn_gate_shexp.weight q8_0 | |
| blk.11.ffn_up_shexp.weight q8_0 | |
| blk.12.attn_gate.weight q8_0 | |
| blk.12.attn_k.weight q8_0 | |
| blk.12.attn_output.weight q8_0 | |
| blk.12.attn_q.weight q8_0 | |
| blk.12.attn_v.weight q8_0 | |
| blk.12.ffn_down_shexp.weight q8_0 | |
| blk.12.ffn_gate_shexp.weight q8_0 | |
| blk.12.ffn_up_shexp.weight q8_0 | |
| blk.13.attn_gate.weight q8_0 | |
| blk.13.attn_k.weight q8_0 | |
| blk.13.attn_output.weight q8_0 | |
| blk.13.attn_q.weight q8_0 | |
| blk.13.attn_v.weight q8_0 | |
| blk.13.ffn_down_shexp.weight q8_0 | |
| blk.13.ffn_gate_shexp.weight q8_0 | |
| blk.13.ffn_up_shexp.weight q8_0 | |
| blk.14.attn_gate.weight q8_0 | |
| blk.14.attn_k.weight q8_0 | |
| blk.14.attn_output.weight q8_0 | |
| blk.14.attn_q.weight q8_0 | |
| blk.14.attn_v.weight q8_0 | |
| blk.14.ffn_down_shexp.weight q8_0 | |
| blk.14.ffn_gate_shexp.weight q8_0 | |
| blk.14.ffn_up_shexp.weight q8_0 | |
| blk.15.attn_gate.weight q8_0 | |
| blk.15.attn_k.weight q8_0 | |
| blk.15.attn_output.weight q8_0 | |
| blk.15.attn_q.weight q8_0 | |
| blk.15.attn_v.weight q8_0 | |
| blk.15.ffn_down_shexp.weight q8_0 | |
| blk.15.ffn_gate_shexp.weight q8_0 | |
| blk.15.ffn_up_shexp.weight q8_0 | |
| blk.16.attn_gate.weight q8_0 | |
| blk.16.attn_k.weight q8_0 | |
| blk.16.attn_output.weight q8_0 | |
| blk.16.attn_q.weight q8_0 | |
| blk.16.attn_v.weight q8_0 | |
| blk.16.ffn_down_shexp.weight q8_0 | |
| blk.16.ffn_gate_shexp.weight q8_0 | |
| blk.16.ffn_up_shexp.weight q8_0 | |
| blk.17.attn_gate.weight q8_0 | |
| blk.17.attn_k.weight q8_0 | |
| blk.17.attn_output.weight q8_0 | |
| blk.17.attn_q.weight q8_0 | |
| blk.17.attn_v.weight q8_0 | |
| blk.17.ffn_down_shexp.weight q8_0 | |
| blk.17.ffn_gate_shexp.weight q8_0 | |
| blk.17.ffn_up_shexp.weight q8_0 | |
| blk.18.attn_gate.weight q8_0 | |
| blk.18.attn_k.weight q8_0 | |
| blk.18.attn_output.weight q8_0 | |
| blk.18.attn_q.weight q8_0 | |
| blk.18.attn_v.weight q8_0 | |
| blk.18.ffn_down_shexp.weight q8_0 | |
| blk.18.ffn_gate_shexp.weight q8_0 | |
| blk.18.ffn_up_shexp.weight q8_0 | |
| blk.19.attn_gate.weight q8_0 | |
| blk.19.attn_k.weight q8_0 | |
| blk.19.attn_output.weight q8_0 | |
| blk.19.attn_q.weight q8_0 | |
| blk.19.attn_v.weight q8_0 | |
| blk.19.ffn_down_shexp.weight q8_0 | |
| blk.19.ffn_gate_shexp.weight q8_0 | |
| blk.19.ffn_up_shexp.weight q8_0 | |
| blk.20.attn_gate.weight q8_0 | |
| blk.20.attn_k.weight q8_0 | |
| blk.20.attn_output.weight q8_0 | |
| blk.20.attn_q.weight q8_0 | |
| blk.20.attn_v.weight q8_0 | |
| blk.20.ffn_down_shexp.weight q8_0 | |
| blk.20.ffn_gate_shexp.weight q8_0 | |
| blk.20.ffn_up_shexp.weight q8_0 | |
| blk.21.attn_gate.weight q8_0 | |
| blk.21.attn_k.weight q8_0 | |
| blk.21.attn_output.weight q8_0 | |
| blk.21.attn_q.weight q8_0 | |
| blk.21.attn_v.weight q8_0 | |
| blk.21.ffn_down_shexp.weight q8_0 | |
| blk.21.ffn_gate_shexp.weight q8_0 | |
| blk.21.ffn_up_shexp.weight q8_0 | |
| blk.22.attn_gate.weight q8_0 | |
| blk.22.attn_k.weight q8_0 | |
| blk.22.attn_output.weight q8_0 | |
| blk.22.attn_q.weight q8_0 | |
| blk.22.attn_v.weight q8_0 | |
| blk.22.ffn_down_shexp.weight q8_0 | |
| blk.22.ffn_gate_shexp.weight q8_0 | |
| blk.22.ffn_up_shexp.weight q8_0 | |
| blk.23.attn_gate.weight q8_0 | |
| blk.23.attn_k.weight q8_0 | |
| blk.23.attn_output.weight q8_0 | |
| blk.23.attn_q.weight q8_0 | |
| blk.23.attn_v.weight q8_0 | |
| blk.23.ffn_down_shexp.weight q8_0 | |
| blk.23.ffn_gate_shexp.weight q8_0 | |
| blk.23.ffn_up_shexp.weight q8_0 | |
| blk.24.attn_gate.weight q8_0 | |
| blk.24.attn_k.weight q8_0 | |
| blk.24.attn_output.weight q8_0 | |
| blk.24.attn_q.weight q8_0 | |
| blk.24.attn_v.weight q8_0 | |
| blk.24.ffn_down_shexp.weight q8_0 | |
| blk.24.ffn_gate_shexp.weight q8_0 | |
| blk.24.ffn_up_shexp.weight q8_0 | |
| blk.25.attn_gate.weight q8_0 | |
| blk.25.attn_k.weight q8_0 | |
| blk.25.attn_output.weight q8_0 | |
| blk.25.attn_q.weight q8_0 | |
| blk.25.attn_v.weight q8_0 | |
| blk.25.ffn_down_shexp.weight q8_0 | |
| blk.25.ffn_gate_shexp.weight q8_0 | |
| blk.25.ffn_up_shexp.weight q8_0 | |
| blk.26.attn_gate.weight q8_0 | |
| blk.26.attn_k.weight q8_0 | |
| blk.26.attn_output.weight q8_0 | |
| blk.26.attn_q.weight q8_0 | |
| blk.26.attn_v.weight q8_0 | |
| blk.26.ffn_down_shexp.weight q8_0 | |
| blk.26.ffn_gate_shexp.weight q8_0 | |
| blk.26.ffn_up_shexp.weight q8_0 | |
| blk.27.attn_gate.weight q8_0 | |
| blk.27.attn_k.weight q8_0 | |
| blk.27.attn_output.weight q8_0 | |
| blk.27.attn_q.weight q8_0 | |
| blk.27.attn_v.weight q8_0 | |
| blk.27.ffn_down_shexp.weight q8_0 | |
| blk.27.ffn_gate_shexp.weight q8_0 | |
| blk.27.ffn_up_shexp.weight q8_0 | |
| blk.28.attn_gate.weight q8_0 | |
| blk.28.attn_k.weight q8_0 | |
| blk.28.attn_output.weight q8_0 | |
| blk.28.attn_q.weight q8_0 | |
| blk.28.attn_v.weight q8_0 | |
| blk.28.ffn_down_shexp.weight q8_0 | |
| blk.28.ffn_gate_shexp.weight q8_0 | |
| blk.28.ffn_up_shexp.weight q8_0 | |
| blk.29.attn_gate.weight q8_0 | |
| blk.29.attn_k.weight q8_0 | |
| blk.29.attn_output.weight q8_0 | |
| blk.29.attn_q.weight q8_0 | |
| blk.29.attn_v.weight q8_0 | |
| blk.29.ffn_down_shexp.weight q8_0 | |
| blk.29.ffn_gate_shexp.weight q8_0 | |
| blk.29.ffn_up_shexp.weight q8_0 | |
| blk.30.attn_gate.weight q8_0 | |
| blk.30.attn_k.weight q8_0 | |
| blk.30.attn_output.weight q8_0 | |
| blk.30.attn_q.weight q8_0 | |
| blk.30.attn_v.weight q8_0 | |
| blk.30.ffn_down_shexp.weight q8_0 | |
| blk.30.ffn_gate_shexp.weight q8_0 | |
| blk.30.ffn_up_shexp.weight q8_0 | |
| blk.31.attn_gate.weight q8_0 | |
| blk.31.attn_k.weight q8_0 | |
| blk.31.attn_output.weight q8_0 | |
| blk.31.attn_q.weight q8_0 | |
| blk.31.attn_v.weight q8_0 | |
| blk.31.ffn_down_shexp.weight q8_0 | |
| blk.31.ffn_gate_shexp.weight q8_0 | |
| blk.31.ffn_up_shexp.weight q8_0 | |
| blk.32.attn_gate.weight q8_0 | |
| blk.32.attn_k.weight q8_0 | |
| blk.32.attn_output.weight q8_0 | |
| blk.32.attn_q.weight q8_0 | |
| blk.32.attn_v.weight q8_0 | |
| blk.32.ffn_down_shexp.weight q8_0 | |
| blk.32.ffn_gate_shexp.weight q8_0 | |
| blk.32.ffn_up_shexp.weight q8_0 | |
| blk.33.attn_gate.weight q8_0 | |
| blk.33.attn_k.weight q8_0 | |
| blk.33.attn_output.weight q8_0 | |
| blk.33.attn_q.weight q8_0 | |
| blk.33.attn_v.weight q8_0 | |
| blk.33.ffn_down_shexp.weight q8_0 | |
| blk.33.ffn_gate_shexp.weight q8_0 | |
| blk.33.ffn_up_shexp.weight q8_0 | |
| blk.34.attn_gate.weight q8_0 | |
| blk.34.attn_k.weight q8_0 | |
| blk.34.attn_output.weight q8_0 | |
| blk.34.attn_q.weight q8_0 | |
| blk.34.attn_v.weight q8_0 | |
| blk.34.ffn_down_shexp.weight q8_0 | |
| blk.34.ffn_gate_shexp.weight q8_0 | |
| blk.34.ffn_up_shexp.weight q8_0 | |
| blk.35.attn_gate.weight q8_0 | |
| blk.35.attn_k.weight q8_0 | |
| blk.35.attn_output.weight q8_0 | |
| blk.35.attn_q.weight q8_0 | |
| blk.35.attn_v.weight q8_0 | |
| blk.35.ffn_down_shexp.weight q8_0 | |
| blk.35.ffn_gate_shexp.weight q8_0 | |
| blk.35.ffn_up_shexp.weight q8_0 | |
| blk.36.attn_gate.weight q8_0 | |
| blk.36.attn_k.weight q8_0 | |
| blk.36.attn_output.weight q8_0 | |
| blk.36.attn_q.weight q8_0 | |
| blk.36.attn_v.weight q8_0 | |
| blk.36.ffn_down_shexp.weight q8_0 | |
| blk.36.ffn_gate_shexp.weight q8_0 | |
| blk.36.ffn_up_shexp.weight q8_0 | |
| blk.37.attn_gate.weight q8_0 | |
| blk.37.attn_k.weight q8_0 | |
| blk.37.attn_output.weight q8_0 | |
| blk.37.attn_q.weight q8_0 | |
| blk.37.attn_v.weight q8_0 | |
| blk.37.ffn_down_shexp.weight q8_0 | |
| blk.37.ffn_gate_shexp.weight q8_0 | |
| blk.37.ffn_up_shexp.weight q8_0 | |
| blk.38.attn_gate.weight q8_0 | |
| blk.38.attn_k.weight q8_0 | |
| blk.38.attn_output.weight q8_0 | |
| blk.38.attn_q.weight q8_0 | |
| blk.38.attn_v.weight q8_0 | |
| blk.38.ffn_down_shexp.weight q8_0 | |
| blk.38.ffn_gate_shexp.weight q8_0 | |
| blk.38.ffn_up_shexp.weight q8_0 | |
| blk.39.attn_gate.weight q8_0 | |
| blk.39.attn_k.weight q8_0 | |
| blk.39.attn_output.weight q8_0 | |
| blk.39.attn_q.weight q8_0 | |
| blk.39.attn_v.weight q8_0 | |
| blk.39.ffn_down_shexp.weight q8_0 | |
| blk.39.ffn_gate_shexp.weight q8_0 | |
| blk.39.ffn_up_shexp.weight q8_0 | |
| blk.40.attn_gate.weight q8_0 | |
| blk.40.attn_k.weight q8_0 | |
| blk.40.attn_output.weight q8_0 | |
| blk.40.attn_q.weight q8_0 | |
| blk.40.attn_v.weight q8_0 | |
| blk.40.ffn_down_shexp.weight q8_0 | |
| blk.40.ffn_gate_shexp.weight q8_0 | |
| blk.40.ffn_up_shexp.weight q8_0 | |
| blk.41.attn_gate.weight q8_0 | |
| blk.41.attn_k.weight q8_0 | |
| blk.41.attn_output.weight q8_0 | |
| blk.41.attn_q.weight q8_0 | |
| blk.41.attn_v.weight q8_0 | |
| blk.41.ffn_down_shexp.weight q8_0 | |
| blk.41.ffn_gate_shexp.weight q8_0 | |
| blk.41.ffn_up_shexp.weight q8_0 | |
| blk.42.attn_gate.weight q8_0 | |
| blk.42.attn_k.weight q8_0 | |
| blk.42.attn_output.weight q8_0 | |
| blk.42.attn_q.weight q8_0 | |
| blk.42.attn_v.weight q8_0 | |
| blk.42.ffn_down_shexp.weight q8_0 | |
| blk.42.ffn_gate_shexp.weight q8_0 | |
| blk.42.ffn_up_shexp.weight q8_0 | |
| blk.43.attn_gate.weight q8_0 | |
| blk.43.attn_k.weight q8_0 | |
| blk.43.attn_output.weight q8_0 | |
| blk.43.attn_q.weight q8_0 | |
| blk.43.attn_v.weight q8_0 | |
| blk.43.ffn_down_shexp.weight q8_0 | |
| blk.43.ffn_gate_shexp.weight q8_0 | |
| blk.43.ffn_up_shexp.weight q8_0 | |
| blk.44.attn_gate.weight q8_0 | |
| blk.44.attn_k.weight q8_0 | |
| blk.44.attn_output.weight q8_0 | |
| blk.44.attn_q.weight q8_0 | |
| blk.44.attn_v.weight q8_0 | |
| blk.44.ffn_down_shexp.weight q8_0 | |
| blk.44.ffn_gate_shexp.weight q8_0 | |
| blk.44.ffn_up_shexp.weight q8_0 | |