Instructions to use baa-ai/GLM-5.2-RAM-307GB-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- llama-cpp-python
How to use baa-ai/GLM-5.2-RAM-307GB-GGUF with llama-cpp-python:
# !pip install llama-cpp-python from llama_cpp import Llama llm = Llama.from_pretrained( repo_id="baa-ai/GLM-5.2-RAM-307GB-GGUF", filename="GLM-5.2-RAM-local-knee-00001-of-00007.gguf", )
llm.create_chat_completion( messages = [ { "role": "user", "content": "What is the capital of France?" } ] ) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use baa-ai/GLM-5.2-RAM-307GB-GGUF 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 baa-ai/GLM-5.2-RAM-307GB-GGUF # Run inference directly in the terminal: llama cli -hf baa-ai/GLM-5.2-RAM-307GB-GGUF
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf baa-ai/GLM-5.2-RAM-307GB-GGUF # Run inference directly in the terminal: llama cli -hf baa-ai/GLM-5.2-RAM-307GB-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 baa-ai/GLM-5.2-RAM-307GB-GGUF # Run inference directly in the terminal: ./llama-cli -hf baa-ai/GLM-5.2-RAM-307GB-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 baa-ai/GLM-5.2-RAM-307GB-GGUF # Run inference directly in the terminal: ./build/bin/llama-cli -hf baa-ai/GLM-5.2-RAM-307GB-GGUF
Use Docker
docker model run hf.co/baa-ai/GLM-5.2-RAM-307GB-GGUF
- LM Studio
- Jan
- vLLM
How to use baa-ai/GLM-5.2-RAM-307GB-GGUF with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "baa-ai/GLM-5.2-RAM-307GB-GGUF" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "baa-ai/GLM-5.2-RAM-307GB-GGUF", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/baa-ai/GLM-5.2-RAM-307GB-GGUF
- Ollama
How to use baa-ai/GLM-5.2-RAM-307GB-GGUF with Ollama:
ollama run hf.co/baa-ai/GLM-5.2-RAM-307GB-GGUF
- Unsloth Studio
How to use baa-ai/GLM-5.2-RAM-307GB-GGUF 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 baa-ai/GLM-5.2-RAM-307GB-GGUF 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 baa-ai/GLM-5.2-RAM-307GB-GGUF to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for baa-ai/GLM-5.2-RAM-307GB-GGUF to start chatting
- Pi
How to use baa-ai/GLM-5.2-RAM-307GB-GGUF with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf baa-ai/GLM-5.2-RAM-307GB-GGUF
Configure the model in Pi
# Install Pi: npm install -g @mariozechner/pi-coding-agent # Add to ~/.pi/agent/models.json: { "providers": { "llama-cpp": { "baseUrl": "http://localhost:8080/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "baa-ai/GLM-5.2-RAM-307GB-GGUF" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Hermes Agent new
How to use baa-ai/GLM-5.2-RAM-307GB-GGUF with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf baa-ai/GLM-5.2-RAM-307GB-GGUF
Configure Hermes
# Install Hermes: curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash hermes setup # Point Hermes at the local server: hermes config set model.provider custom hermes config set model.base_url http://127.0.0.1:8080/v1 hermes config set model.default baa-ai/GLM-5.2-RAM-307GB-GGUF
Run Hermes
hermes
- Atomic Chat new
- OpenClaw new
How to use baa-ai/GLM-5.2-RAM-307GB-GGUF with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf baa-ai/GLM-5.2-RAM-307GB-GGUF
Configure OpenClaw
# Install OpenClaw: npm install -g openclaw@latest # Register the local server and set it as the default model: openclaw onboard --non-interactive --mode local \ --auth-choice custom-api-key \ --custom-base-url http://127.0.0.1:8080/v1 \ --custom-model-id "baa-ai/GLM-5.2-RAM-307GB-GGUF" \ --custom-provider-id llama-cpp \ --custom-compatibility openai \ --custom-text-input \ --accept-risk \ --skip-health
Run OpenClaw
openclaw agent --local --agent main --message "Hello from Hugging Face"
- Docker Model Runner
How to use baa-ai/GLM-5.2-RAM-307GB-GGUF with Docker Model Runner:
docker model run hf.co/baa-ai/GLM-5.2-RAM-307GB-GGUF
- Lemonade
How to use baa-ai/GLM-5.2-RAM-307GB-GGUF with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull baa-ai/GLM-5.2-RAM-307GB-GGUF
Run and chat with the model
lemonade run user.GLM-5.2-RAM-307GB-GGUF-{{QUANT_TAG}}List all available models
lemonade list
Add files using upload-large-folder tool
Browse files- .gitattributes +7 -0
- GLM-5.2-RAM-local-knee-00001-of-00007.gguf +3 -0
- GLM-5.2-RAM-local-knee-00002-of-00007.gguf +3 -0
- GLM-5.2-RAM-local-knee-00003-of-00007.gguf +3 -0
- GLM-5.2-RAM-local-knee-00004-of-00007.gguf +3 -0
- GLM-5.2-RAM-local-knee-00005-of-00007.gguf +3 -0
- GLM-5.2-RAM-local-knee-00006-of-00007.gguf +3 -0
- GLM-5.2-RAM-local-knee-00007-of-00007.gguf +3 -0
- spec_glm_knee.txt +1005 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,10 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
GLM-5.2-RAM-local-knee-00001-of-00007.gguf filter=lfs diff=lfs merge=lfs -text
|
| 37 |
+
GLM-5.2-RAM-local-knee-00005-of-00007.gguf filter=lfs diff=lfs merge=lfs -text
|
| 38 |
+
GLM-5.2-RAM-local-knee-00006-of-00007.gguf filter=lfs diff=lfs merge=lfs -text
|
| 39 |
+
GLM-5.2-RAM-local-knee-00002-of-00007.gguf filter=lfs diff=lfs merge=lfs -text
|
| 40 |
+
GLM-5.2-RAM-local-knee-00004-of-00007.gguf filter=lfs diff=lfs merge=lfs -text
|
| 41 |
+
GLM-5.2-RAM-local-knee-00003-of-00007.gguf filter=lfs diff=lfs merge=lfs -text
|
| 42 |
+
GLM-5.2-RAM-local-knee-00007-of-00007.gguf filter=lfs diff=lfs merge=lfs -text
|
GLM-5.2-RAM-local-knee-00001-of-00007.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:68c95394fd692b8c66f7a006fba0fda0f4425b9a4dde5d35b5451b0e971a4703
|
| 3 |
+
size 46928861184
|
GLM-5.2-RAM-local-knee-00002-of-00007.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a3939d9dcb7a7a111027c63add3560536dd3f7c8a7c7890ede7db81bb135d50b
|
| 3 |
+
size 47400683136
|
GLM-5.2-RAM-local-knee-00003-of-00007.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3f8b95fc9f58f15c1467e5ae637338ce8e37f3ac4e80f13d1872b146ca8a0676
|
| 3 |
+
size 47388493440
|
GLM-5.2-RAM-local-knee-00004-of-00007.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:556666310c1e85bfb3ccbd0369b7661722c0404527029d752eef6037d440a696
|
| 3 |
+
size 47371518272
|
GLM-5.2-RAM-local-knee-00005-of-00007.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:34b07961b5c1fa56d13d8c0a7072a8d4f85f442526aa809c190d024f24c4354e
|
| 3 |
+
size 47382398592
|
GLM-5.2-RAM-local-knee-00006-of-00007.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dbb39766ae1b7711bd92d736c695c5cfbb0dd043c815c0b1d3436500d7b7fb6f
|
| 3 |
+
size 47382398592
|
GLM-5.2-RAM-local-knee-00007-of-00007.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4d7dbae0d18eeccf47485649e7d003337cc5ebfb43f1c7ec28f69651fbd2cd6f
|
| 3 |
+
size 45930854528
|
spec_glm_knee.txt
ADDED
|
@@ -0,0 +1,1005 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
blk.0.attn_k_b.weight=q6_K
|
| 2 |
+
blk.0.attn_kv_a_mqa.weight=q8_0
|
| 3 |
+
blk.0.attn_output.weight=q4_K
|
| 4 |
+
blk.0.attn_q_a.weight=q8_0
|
| 5 |
+
blk.0.attn_q_b.weight=q6_K
|
| 6 |
+
blk.0.attn_v_b.weight=q6_K
|
| 7 |
+
blk.0.ffn_down.weight=q4_K
|
| 8 |
+
blk.0.ffn_gate.weight=q4_K
|
| 9 |
+
blk.0.ffn_up.weight=q4_K
|
| 10 |
+
blk.0.indexer.attn_k.weight=f16
|
| 11 |
+
blk.0.indexer.attn_q_b.weight=q8_0
|
| 12 |
+
blk.0.indexer.proj.weight=f16
|
| 13 |
+
blk.1.attn_k_b.weight=q6_K
|
| 14 |
+
blk.1.attn_kv_a_mqa.weight=q8_0
|
| 15 |
+
blk.1.attn_output.weight=q4_K
|
| 16 |
+
blk.1.attn_q_a.weight=q8_0
|
| 17 |
+
blk.1.attn_q_b.weight=q6_K
|
| 18 |
+
blk.1.attn_v_b.weight=q6_K
|
| 19 |
+
blk.1.ffn_down.weight=q4_K
|
| 20 |
+
blk.1.ffn_gate.weight=q4_K
|
| 21 |
+
blk.1.ffn_up.weight=q4_K
|
| 22 |
+
blk.1.indexer.attn_k.weight=f16
|
| 23 |
+
blk.1.indexer.attn_q_b.weight=q8_0
|
| 24 |
+
blk.1.indexer.proj.weight=f16
|
| 25 |
+
blk.10.attn_k_b.weight=q6_K
|
| 26 |
+
blk.10.attn_kv_a_mqa.weight=q8_0
|
| 27 |
+
blk.10.attn_output.weight=q4_K
|
| 28 |
+
blk.10.attn_q_a.weight=q6_K
|
| 29 |
+
blk.10.attn_q_b.weight=q6_K
|
| 30 |
+
blk.10.attn_v_b.weight=q6_K
|
| 31 |
+
blk.10.ffn_down_exps.weight=q3_K
|
| 32 |
+
blk.10.ffn_down_shexp.weight=q6_K
|
| 33 |
+
blk.10.ffn_gate_exps.weight=q3_K
|
| 34 |
+
blk.10.ffn_gate_shexp.weight=q6_K
|
| 35 |
+
blk.10.ffn_up_exps.weight=q3_K
|
| 36 |
+
blk.10.ffn_up_shexp.weight=q6_K
|
| 37 |
+
blk.10.indexer.attn_k.weight=f16
|
| 38 |
+
blk.10.indexer.attn_q_b.weight=q8_0
|
| 39 |
+
blk.10.indexer.proj.weight=f16
|
| 40 |
+
blk.11.attn_k_b.weight=q6_K
|
| 41 |
+
blk.11.attn_kv_a_mqa.weight=q8_0
|
| 42 |
+
blk.11.attn_output.weight=q4_K
|
| 43 |
+
blk.11.attn_q_a.weight=q6_K
|
| 44 |
+
blk.11.attn_q_b.weight=q6_K
|
| 45 |
+
blk.11.attn_v_b.weight=q6_K
|
| 46 |
+
blk.11.ffn_down_exps.weight=q3_K
|
| 47 |
+
blk.11.ffn_down_shexp.weight=q6_K
|
| 48 |
+
blk.11.ffn_gate_exps.weight=q3_K
|
| 49 |
+
blk.11.ffn_gate_shexp.weight=q6_K
|
| 50 |
+
blk.11.ffn_up_exps.weight=q3_K
|
| 51 |
+
blk.11.ffn_up_shexp.weight=q6_K
|
| 52 |
+
blk.12.attn_k_b.weight=q6_K
|
| 53 |
+
blk.12.attn_kv_a_mqa.weight=q8_0
|
| 54 |
+
blk.12.attn_output.weight=q4_K
|
| 55 |
+
blk.12.attn_q_a.weight=q6_K
|
| 56 |
+
blk.12.attn_q_b.weight=q6_K
|
| 57 |
+
blk.12.attn_v_b.weight=q6_K
|
| 58 |
+
blk.12.ffn_down_exps.weight=q3_K
|
| 59 |
+
blk.12.ffn_down_shexp.weight=q8_0
|
| 60 |
+
blk.12.ffn_gate_exps.weight=q3_K
|
| 61 |
+
blk.12.ffn_gate_shexp.weight=q6_K
|
| 62 |
+
blk.12.ffn_up_exps.weight=q3_K
|
| 63 |
+
blk.12.ffn_up_shexp.weight=q6_K
|
| 64 |
+
blk.13.attn_k_b.weight=q6_K
|
| 65 |
+
blk.13.attn_kv_a_mqa.weight=q8_0
|
| 66 |
+
blk.13.attn_output.weight=q4_K
|
| 67 |
+
blk.13.attn_q_a.weight=q6_K
|
| 68 |
+
blk.13.attn_q_b.weight=q6_K
|
| 69 |
+
blk.13.attn_v_b.weight=q6_K
|
| 70 |
+
blk.13.ffn_down_exps.weight=q3_K
|
| 71 |
+
blk.13.ffn_down_shexp.weight=q8_0
|
| 72 |
+
blk.13.ffn_gate_exps.weight=q3_K
|
| 73 |
+
blk.13.ffn_gate_shexp.weight=q6_K
|
| 74 |
+
blk.13.ffn_up_exps.weight=q3_K
|
| 75 |
+
blk.13.ffn_up_shexp.weight=q6_K
|
| 76 |
+
blk.14.attn_k_b.weight=q6_K
|
| 77 |
+
blk.14.attn_kv_a_mqa.weight=q8_0
|
| 78 |
+
blk.14.attn_output.weight=q4_K
|
| 79 |
+
blk.14.attn_q_a.weight=q6_K
|
| 80 |
+
blk.14.attn_q_b.weight=q6_K
|
| 81 |
+
blk.14.attn_v_b.weight=q6_K
|
| 82 |
+
blk.14.ffn_down_exps.weight=q3_K
|
| 83 |
+
blk.14.ffn_down_shexp.weight=q8_0
|
| 84 |
+
blk.14.ffn_gate_exps.weight=q3_K
|
| 85 |
+
blk.14.ffn_gate_shexp.weight=q6_K
|
| 86 |
+
blk.14.ffn_up_exps.weight=q3_K
|
| 87 |
+
blk.14.ffn_up_shexp.weight=q6_K
|
| 88 |
+
blk.14.indexer.attn_k.weight=f16
|
| 89 |
+
blk.14.indexer.attn_q_b.weight=q8_0
|
| 90 |
+
blk.14.indexer.proj.weight=f16
|
| 91 |
+
blk.15.attn_k_b.weight=q6_K
|
| 92 |
+
blk.15.attn_kv_a_mqa.weight=q8_0
|
| 93 |
+
blk.15.attn_output.weight=q4_K
|
| 94 |
+
blk.15.attn_q_a.weight=q6_K
|
| 95 |
+
blk.15.attn_q_b.weight=q6_K
|
| 96 |
+
blk.15.attn_v_b.weight=q6_K
|
| 97 |
+
blk.15.ffn_down_exps.weight=q3_K
|
| 98 |
+
blk.15.ffn_down_shexp.weight=q8_0
|
| 99 |
+
blk.15.ffn_gate_exps.weight=q3_K
|
| 100 |
+
blk.15.ffn_gate_shexp.weight=q6_K
|
| 101 |
+
blk.15.ffn_up_exps.weight=q3_K
|
| 102 |
+
blk.15.ffn_up_shexp.weight=q6_K
|
| 103 |
+
blk.16.attn_k_b.weight=q6_K
|
| 104 |
+
blk.16.attn_kv_a_mqa.weight=q8_0
|
| 105 |
+
blk.16.attn_output.weight=q4_K
|
| 106 |
+
blk.16.attn_q_a.weight=q6_K
|
| 107 |
+
blk.16.attn_q_b.weight=q6_K
|
| 108 |
+
blk.16.attn_v_b.weight=q6_K
|
| 109 |
+
blk.16.ffn_down_exps.weight=q3_K
|
| 110 |
+
blk.16.ffn_down_shexp.weight=q8_0
|
| 111 |
+
blk.16.ffn_gate_exps.weight=q3_K
|
| 112 |
+
blk.16.ffn_gate_shexp.weight=q6_K
|
| 113 |
+
blk.16.ffn_up_exps.weight=q3_K
|
| 114 |
+
blk.16.ffn_up_shexp.weight=q6_K
|
| 115 |
+
blk.17.attn_k_b.weight=q6_K
|
| 116 |
+
blk.17.attn_kv_a_mqa.weight=q8_0
|
| 117 |
+
blk.17.attn_output.weight=q4_K
|
| 118 |
+
blk.17.attn_q_a.weight=q6_K
|
| 119 |
+
blk.17.attn_q_b.weight=q6_K
|
| 120 |
+
blk.17.attn_v_b.weight=q6_K
|
| 121 |
+
blk.17.ffn_down_exps.weight=q3_K
|
| 122 |
+
blk.17.ffn_down_shexp.weight=q8_0
|
| 123 |
+
blk.17.ffn_gate_exps.weight=q3_K
|
| 124 |
+
blk.17.ffn_gate_shexp.weight=q6_K
|
| 125 |
+
blk.17.ffn_up_exps.weight=q3_K
|
| 126 |
+
blk.17.ffn_up_shexp.weight=q6_K
|
| 127 |
+
blk.18.attn_k_b.weight=q6_K
|
| 128 |
+
blk.18.attn_kv_a_mqa.weight=q8_0
|
| 129 |
+
blk.18.attn_output.weight=q4_K
|
| 130 |
+
blk.18.attn_q_a.weight=q6_K
|
| 131 |
+
blk.18.attn_q_b.weight=q6_K
|
| 132 |
+
blk.18.attn_v_b.weight=q6_K
|
| 133 |
+
blk.18.ffn_down_exps.weight=q3_K
|
| 134 |
+
blk.18.ffn_down_shexp.weight=q8_0
|
| 135 |
+
blk.18.ffn_gate_exps.weight=q3_K
|
| 136 |
+
blk.18.ffn_gate_shexp.weight=q6_K
|
| 137 |
+
blk.18.ffn_up_exps.weight=q3_K
|
| 138 |
+
blk.18.ffn_up_shexp.weight=q6_K
|
| 139 |
+
blk.18.indexer.attn_k.weight=f16
|
| 140 |
+
blk.18.indexer.attn_q_b.weight=q8_0
|
| 141 |
+
blk.18.indexer.proj.weight=f16
|
| 142 |
+
blk.19.attn_k_b.weight=q6_K
|
| 143 |
+
blk.19.attn_kv_a_mqa.weight=q8_0
|
| 144 |
+
blk.19.attn_output.weight=q4_K
|
| 145 |
+
blk.19.attn_q_a.weight=q6_K
|
| 146 |
+
blk.19.attn_q_b.weight=q6_K
|
| 147 |
+
blk.19.attn_v_b.weight=q6_K
|
| 148 |
+
blk.19.ffn_down_exps.weight=q3_K
|
| 149 |
+
blk.19.ffn_down_shexp.weight=q8_0
|
| 150 |
+
blk.19.ffn_gate_exps.weight=q3_K
|
| 151 |
+
blk.19.ffn_gate_shexp.weight=q6_K
|
| 152 |
+
blk.19.ffn_up_exps.weight=q3_K
|
| 153 |
+
blk.19.ffn_up_shexp.weight=q6_K
|
| 154 |
+
blk.2.attn_k_b.weight=q8_0
|
| 155 |
+
blk.2.attn_kv_a_mqa.weight=q8_0
|
| 156 |
+
blk.2.attn_output.weight=q4_K
|
| 157 |
+
blk.2.attn_q_a.weight=q8_0
|
| 158 |
+
blk.2.attn_q_b.weight=q6_K
|
| 159 |
+
blk.2.attn_v_b.weight=q8_0
|
| 160 |
+
blk.2.ffn_down.weight=q4_K
|
| 161 |
+
blk.2.ffn_gate.weight=q4_K
|
| 162 |
+
blk.2.ffn_up.weight=q4_K
|
| 163 |
+
blk.2.indexer.attn_k.weight=f16
|
| 164 |
+
blk.2.indexer.attn_q_b.weight=q8_0
|
| 165 |
+
blk.2.indexer.proj.weight=f16
|
| 166 |
+
blk.20.attn_k_b.weight=q6_K
|
| 167 |
+
blk.20.attn_kv_a_mqa.weight=q8_0
|
| 168 |
+
blk.20.attn_output.weight=q4_K
|
| 169 |
+
blk.20.attn_q_a.weight=q6_K
|
| 170 |
+
blk.20.attn_q_b.weight=q6_K
|
| 171 |
+
blk.20.attn_v_b.weight=q6_K
|
| 172 |
+
blk.20.ffn_down_exps.weight=q3_K
|
| 173 |
+
blk.20.ffn_down_shexp.weight=q8_0
|
| 174 |
+
blk.20.ffn_gate_exps.weight=q3_K
|
| 175 |
+
blk.20.ffn_gate_shexp.weight=q8_0
|
| 176 |
+
blk.20.ffn_up_exps.weight=q3_K
|
| 177 |
+
blk.20.ffn_up_shexp.weight=q8_0
|
| 178 |
+
blk.21.attn_k_b.weight=q6_K
|
| 179 |
+
blk.21.attn_kv_a_mqa.weight=q8_0
|
| 180 |
+
blk.21.attn_output.weight=q4_K
|
| 181 |
+
blk.21.attn_q_a.weight=q6_K
|
| 182 |
+
blk.21.attn_q_b.weight=q6_K
|
| 183 |
+
blk.21.attn_v_b.weight=q6_K
|
| 184 |
+
blk.21.ffn_down_exps.weight=q3_K
|
| 185 |
+
blk.21.ffn_down_shexp.weight=q8_0
|
| 186 |
+
blk.21.ffn_gate_exps.weight=q3_K
|
| 187 |
+
blk.21.ffn_gate_shexp.weight=q8_0
|
| 188 |
+
blk.21.ffn_up_exps.weight=q3_K
|
| 189 |
+
blk.21.ffn_up_shexp.weight=q6_K
|
| 190 |
+
blk.22.attn_k_b.weight=q6_K
|
| 191 |
+
blk.22.attn_kv_a_mqa.weight=q8_0
|
| 192 |
+
blk.22.attn_output.weight=q4_K
|
| 193 |
+
blk.22.attn_q_a.weight=q6_K
|
| 194 |
+
blk.22.attn_q_b.weight=q6_K
|
| 195 |
+
blk.22.attn_v_b.weight=q6_K
|
| 196 |
+
blk.22.ffn_down_exps.weight=q3_K
|
| 197 |
+
blk.22.ffn_down_shexp.weight=q8_0
|
| 198 |
+
blk.22.ffn_gate_exps.weight=q3_K
|
| 199 |
+
blk.22.ffn_gate_shexp.weight=q8_0
|
| 200 |
+
blk.22.ffn_up_exps.weight=q3_K
|
| 201 |
+
blk.22.ffn_up_shexp.weight=q8_0
|
| 202 |
+
blk.22.indexer.attn_k.weight=f16
|
| 203 |
+
blk.22.indexer.attn_q_b.weight=q8_0
|
| 204 |
+
blk.22.indexer.proj.weight=f16
|
| 205 |
+
blk.23.attn_k_b.weight=q6_K
|
| 206 |
+
blk.23.attn_kv_a_mqa.weight=q8_0
|
| 207 |
+
blk.23.attn_output.weight=q4_K
|
| 208 |
+
blk.23.attn_q_a.weight=q6_K
|
| 209 |
+
blk.23.attn_q_b.weight=q6_K
|
| 210 |
+
blk.23.attn_v_b.weight=q6_K
|
| 211 |
+
blk.23.ffn_down_exps.weight=q3_K
|
| 212 |
+
blk.23.ffn_down_shexp.weight=q8_0
|
| 213 |
+
blk.23.ffn_gate_exps.weight=q3_K
|
| 214 |
+
blk.23.ffn_gate_shexp.weight=q8_0
|
| 215 |
+
blk.23.ffn_up_exps.weight=q3_K
|
| 216 |
+
blk.23.ffn_up_shexp.weight=q6_K
|
| 217 |
+
blk.24.attn_k_b.weight=q6_K
|
| 218 |
+
blk.24.attn_kv_a_mqa.weight=q8_0
|
| 219 |
+
blk.24.attn_output.weight=q4_K
|
| 220 |
+
blk.24.attn_q_a.weight=q6_K
|
| 221 |
+
blk.24.attn_q_b.weight=q6_K
|
| 222 |
+
blk.24.attn_v_b.weight=q6_K
|
| 223 |
+
blk.24.ffn_down_exps.weight=q3_K
|
| 224 |
+
blk.24.ffn_down_shexp.weight=q8_0
|
| 225 |
+
blk.24.ffn_gate_exps.weight=q3_K
|
| 226 |
+
blk.24.ffn_gate_shexp.weight=q6_K
|
| 227 |
+
blk.24.ffn_up_exps.weight=q3_K
|
| 228 |
+
blk.24.ffn_up_shexp.weight=q6_K
|
| 229 |
+
blk.25.attn_k_b.weight=q6_K
|
| 230 |
+
blk.25.attn_kv_a_mqa.weight=q8_0
|
| 231 |
+
blk.25.attn_output.weight=q4_K
|
| 232 |
+
blk.25.attn_q_a.weight=q6_K
|
| 233 |
+
blk.25.attn_q_b.weight=q6_K
|
| 234 |
+
blk.25.attn_v_b.weight=q6_K
|
| 235 |
+
blk.25.ffn_down_exps.weight=q3_K
|
| 236 |
+
blk.25.ffn_down_shexp.weight=q8_0
|
| 237 |
+
blk.25.ffn_gate_exps.weight=q3_K
|
| 238 |
+
blk.25.ffn_gate_shexp.weight=q6_K
|
| 239 |
+
blk.25.ffn_up_exps.weight=q3_K
|
| 240 |
+
blk.25.ffn_up_shexp.weight=q6_K
|
| 241 |
+
blk.26.attn_k_b.weight=q6_K
|
| 242 |
+
blk.26.attn_kv_a_mqa.weight=q8_0
|
| 243 |
+
blk.26.attn_output.weight=q4_K
|
| 244 |
+
blk.26.attn_q_a.weight=q6_K
|
| 245 |
+
blk.26.attn_q_b.weight=q6_K
|
| 246 |
+
blk.26.attn_v_b.weight=q6_K
|
| 247 |
+
blk.26.ffn_down_exps.weight=q3_K
|
| 248 |
+
blk.26.ffn_down_shexp.weight=q8_0
|
| 249 |
+
blk.26.ffn_gate_exps.weight=q3_K
|
| 250 |
+
blk.26.ffn_gate_shexp.weight=q6_K
|
| 251 |
+
blk.26.ffn_up_exps.weight=q3_K
|
| 252 |
+
blk.26.ffn_up_shexp.weight=q6_K
|
| 253 |
+
blk.26.indexer.attn_k.weight=f16
|
| 254 |
+
blk.26.indexer.attn_q_b.weight=q8_0
|
| 255 |
+
blk.26.indexer.proj.weight=f16
|
| 256 |
+
blk.27.attn_k_b.weight=q6_K
|
| 257 |
+
blk.27.attn_kv_a_mqa.weight=q8_0
|
| 258 |
+
blk.27.attn_output.weight=q4_K
|
| 259 |
+
blk.27.attn_q_a.weight=q6_K
|
| 260 |
+
blk.27.attn_q_b.weight=q6_K
|
| 261 |
+
blk.27.attn_v_b.weight=q6_K
|
| 262 |
+
blk.27.ffn_down_exps.weight=q3_K
|
| 263 |
+
blk.27.ffn_down_shexp.weight=q8_0
|
| 264 |
+
blk.27.ffn_gate_exps.weight=q3_K
|
| 265 |
+
blk.27.ffn_gate_shexp.weight=q6_K
|
| 266 |
+
blk.27.ffn_up_exps.weight=q3_K
|
| 267 |
+
blk.27.ffn_up_shexp.weight=q6_K
|
| 268 |
+
blk.28.attn_k_b.weight=q6_K
|
| 269 |
+
blk.28.attn_kv_a_mqa.weight=q8_0
|
| 270 |
+
blk.28.attn_output.weight=q4_K
|
| 271 |
+
blk.28.attn_q_a.weight=q6_K
|
| 272 |
+
blk.28.attn_q_b.weight=q6_K
|
| 273 |
+
blk.28.attn_v_b.weight=q6_K
|
| 274 |
+
blk.28.ffn_down_exps.weight=q3_K
|
| 275 |
+
blk.28.ffn_down_shexp.weight=q8_0
|
| 276 |
+
blk.28.ffn_gate_exps.weight=q3_K
|
| 277 |
+
blk.28.ffn_gate_shexp.weight=q6_K
|
| 278 |
+
blk.28.ffn_up_exps.weight=q3_K
|
| 279 |
+
blk.28.ffn_up_shexp.weight=q6_K
|
| 280 |
+
blk.29.attn_k_b.weight=q6_K
|
| 281 |
+
blk.29.attn_kv_a_mqa.weight=q8_0
|
| 282 |
+
blk.29.attn_output.weight=q4_K
|
| 283 |
+
blk.29.attn_q_a.weight=q6_K
|
| 284 |
+
blk.29.attn_q_b.weight=q6_K
|
| 285 |
+
blk.29.attn_v_b.weight=q6_K
|
| 286 |
+
blk.29.ffn_down_exps.weight=q3_K
|
| 287 |
+
blk.29.ffn_down_shexp.weight=q8_0
|
| 288 |
+
blk.29.ffn_gate_exps.weight=q3_K
|
| 289 |
+
blk.29.ffn_gate_shexp.weight=q6_K
|
| 290 |
+
blk.29.ffn_up_exps.weight=q3_K
|
| 291 |
+
blk.29.ffn_up_shexp.weight=q6_K
|
| 292 |
+
blk.3.attn_k_b.weight=q8_0
|
| 293 |
+
blk.3.attn_kv_a_mqa.weight=q8_0
|
| 294 |
+
blk.3.attn_output.weight=q4_K
|
| 295 |
+
blk.3.attn_q_a.weight=q8_0
|
| 296 |
+
blk.3.attn_q_b.weight=q6_K
|
| 297 |
+
blk.3.attn_v_b.weight=q8_0
|
| 298 |
+
blk.3.ffn_down_exps.weight=q3_K
|
| 299 |
+
blk.3.ffn_down_shexp.weight=q6_K
|
| 300 |
+
blk.3.ffn_gate_exps.weight=q3_K
|
| 301 |
+
blk.3.ffn_gate_shexp.weight=q8_0
|
| 302 |
+
blk.3.ffn_up_exps.weight=q3_K
|
| 303 |
+
blk.3.ffn_up_shexp.weight=q8_0
|
| 304 |
+
blk.30.attn_k_b.weight=q6_K
|
| 305 |
+
blk.30.attn_kv_a_mqa.weight=q8_0
|
| 306 |
+
blk.30.attn_output.weight=q4_K
|
| 307 |
+
blk.30.attn_q_a.weight=q6_K
|
| 308 |
+
blk.30.attn_q_b.weight=q6_K
|
| 309 |
+
blk.30.attn_v_b.weight=q6_K
|
| 310 |
+
blk.30.ffn_down_exps.weight=q3_K
|
| 311 |
+
blk.30.ffn_down_shexp.weight=q8_0
|
| 312 |
+
blk.30.ffn_gate_exps.weight=q3_K
|
| 313 |
+
blk.30.ffn_gate_shexp.weight=q6_K
|
| 314 |
+
blk.30.ffn_up_exps.weight=q3_K
|
| 315 |
+
blk.30.ffn_up_shexp.weight=q6_K
|
| 316 |
+
blk.30.indexer.attn_k.weight=f16
|
| 317 |
+
blk.30.indexer.attn_q_b.weight=q8_0
|
| 318 |
+
blk.30.indexer.proj.weight=f16
|
| 319 |
+
blk.31.attn_k_b.weight=q6_K
|
| 320 |
+
blk.31.attn_kv_a_mqa.weight=q8_0
|
| 321 |
+
blk.31.attn_output.weight=q4_K
|
| 322 |
+
blk.31.attn_q_a.weight=q6_K
|
| 323 |
+
blk.31.attn_q_b.weight=q6_K
|
| 324 |
+
blk.31.attn_v_b.weight=q6_K
|
| 325 |
+
blk.31.ffn_down_exps.weight=q3_K
|
| 326 |
+
blk.31.ffn_down_shexp.weight=q8_0
|
| 327 |
+
blk.31.ffn_gate_exps.weight=q3_K
|
| 328 |
+
blk.31.ffn_gate_shexp.weight=q8_0
|
| 329 |
+
blk.31.ffn_up_exps.weight=q3_K
|
| 330 |
+
blk.31.ffn_up_shexp.weight=q6_K
|
| 331 |
+
blk.32.attn_k_b.weight=q6_K
|
| 332 |
+
blk.32.attn_kv_a_mqa.weight=q8_0
|
| 333 |
+
blk.32.attn_output.weight=q4_K
|
| 334 |
+
blk.32.attn_q_a.weight=q6_K
|
| 335 |
+
blk.32.attn_q_b.weight=q6_K
|
| 336 |
+
blk.32.attn_v_b.weight=q6_K
|
| 337 |
+
blk.32.ffn_down_exps.weight=q3_K
|
| 338 |
+
blk.32.ffn_down_shexp.weight=q8_0
|
| 339 |
+
blk.32.ffn_gate_exps.weight=q3_K
|
| 340 |
+
blk.32.ffn_gate_shexp.weight=q6_K
|
| 341 |
+
blk.32.ffn_up_exps.weight=q3_K
|
| 342 |
+
blk.32.ffn_up_shexp.weight=q6_K
|
| 343 |
+
blk.33.attn_k_b.weight=q6_K
|
| 344 |
+
blk.33.attn_kv_a_mqa.weight=q8_0
|
| 345 |
+
blk.33.attn_output.weight=q4_K
|
| 346 |
+
blk.33.attn_q_a.weight=q6_K
|
| 347 |
+
blk.33.attn_q_b.weight=q6_K
|
| 348 |
+
blk.33.attn_v_b.weight=q6_K
|
| 349 |
+
blk.33.ffn_down_exps.weight=q3_K
|
| 350 |
+
blk.33.ffn_down_shexp.weight=q8_0
|
| 351 |
+
blk.33.ffn_gate_exps.weight=q3_K
|
| 352 |
+
blk.33.ffn_gate_shexp.weight=q8_0
|
| 353 |
+
blk.33.ffn_up_exps.weight=q3_K
|
| 354 |
+
blk.33.ffn_up_shexp.weight=q6_K
|
| 355 |
+
blk.34.attn_k_b.weight=q6_K
|
| 356 |
+
blk.34.attn_kv_a_mqa.weight=q8_0
|
| 357 |
+
blk.34.attn_output.weight=q4_K
|
| 358 |
+
blk.34.attn_q_a.weight=q6_K
|
| 359 |
+
blk.34.attn_q_b.weight=q6_K
|
| 360 |
+
blk.34.attn_v_b.weight=q6_K
|
| 361 |
+
blk.34.ffn_down_exps.weight=q3_K
|
| 362 |
+
blk.34.ffn_down_shexp.weight=q8_0
|
| 363 |
+
blk.34.ffn_gate_exps.weight=q3_K
|
| 364 |
+
blk.34.ffn_gate_shexp.weight=q6_K
|
| 365 |
+
blk.34.ffn_up_exps.weight=q3_K
|
| 366 |
+
blk.34.ffn_up_shexp.weight=q6_K
|
| 367 |
+
blk.34.indexer.attn_k.weight=f16
|
| 368 |
+
blk.34.indexer.attn_q_b.weight=q8_0
|
| 369 |
+
blk.34.indexer.proj.weight=f16
|
| 370 |
+
blk.35.attn_k_b.weight=q6_K
|
| 371 |
+
blk.35.attn_kv_a_mqa.weight=q8_0
|
| 372 |
+
blk.35.attn_output.weight=q4_K
|
| 373 |
+
blk.35.attn_q_a.weight=q6_K
|
| 374 |
+
blk.35.attn_q_b.weight=q6_K
|
| 375 |
+
blk.35.attn_v_b.weight=q6_K
|
| 376 |
+
blk.35.ffn_down_exps.weight=q3_K
|
| 377 |
+
blk.35.ffn_down_shexp.weight=q8_0
|
| 378 |
+
blk.35.ffn_gate_exps.weight=q3_K
|
| 379 |
+
blk.35.ffn_gate_shexp.weight=q6_K
|
| 380 |
+
blk.35.ffn_up_exps.weight=q3_K
|
| 381 |
+
blk.35.ffn_up_shexp.weight=q6_K
|
| 382 |
+
blk.36.attn_k_b.weight=q6_K
|
| 383 |
+
blk.36.attn_kv_a_mqa.weight=q8_0
|
| 384 |
+
blk.36.attn_output.weight=q4_K
|
| 385 |
+
blk.36.attn_q_a.weight=q6_K
|
| 386 |
+
blk.36.attn_q_b.weight=q6_K
|
| 387 |
+
blk.36.attn_v_b.weight=q6_K
|
| 388 |
+
blk.36.ffn_down_exps.weight=q3_K
|
| 389 |
+
blk.36.ffn_down_shexp.weight=q8_0
|
| 390 |
+
blk.36.ffn_gate_exps.weight=q3_K
|
| 391 |
+
blk.36.ffn_gate_shexp.weight=q6_K
|
| 392 |
+
blk.36.ffn_up_exps.weight=q3_K
|
| 393 |
+
blk.36.ffn_up_shexp.weight=q6_K
|
| 394 |
+
blk.37.attn_k_b.weight=q6_K
|
| 395 |
+
blk.37.attn_kv_a_mqa.weight=q8_0
|
| 396 |
+
blk.37.attn_output.weight=q4_K
|
| 397 |
+
blk.37.attn_q_a.weight=q6_K
|
| 398 |
+
blk.37.attn_q_b.weight=q6_K
|
| 399 |
+
blk.37.attn_v_b.weight=q6_K
|
| 400 |
+
blk.37.ffn_down_exps.weight=q3_K
|
| 401 |
+
blk.37.ffn_down_shexp.weight=q8_0
|
| 402 |
+
blk.37.ffn_gate_exps.weight=q3_K
|
| 403 |
+
blk.37.ffn_gate_shexp.weight=q6_K
|
| 404 |
+
blk.37.ffn_up_exps.weight=q3_K
|
| 405 |
+
blk.37.ffn_up_shexp.weight=q6_K
|
| 406 |
+
blk.38.attn_k_b.weight=q6_K
|
| 407 |
+
blk.38.attn_kv_a_mqa.weight=q8_0
|
| 408 |
+
blk.38.attn_output.weight=q4_K
|
| 409 |
+
blk.38.attn_q_a.weight=q6_K
|
| 410 |
+
blk.38.attn_q_b.weight=q6_K
|
| 411 |
+
blk.38.attn_v_b.weight=q6_K
|
| 412 |
+
blk.38.ffn_down_exps.weight=q3_K
|
| 413 |
+
blk.38.ffn_down_shexp.weight=q8_0
|
| 414 |
+
blk.38.ffn_gate_exps.weight=q3_K
|
| 415 |
+
blk.38.ffn_gate_shexp.weight=q6_K
|
| 416 |
+
blk.38.ffn_up_exps.weight=q3_K
|
| 417 |
+
blk.38.ffn_up_shexp.weight=q6_K
|
| 418 |
+
blk.38.indexer.attn_k.weight=f16
|
| 419 |
+
blk.38.indexer.attn_q_b.weight=q8_0
|
| 420 |
+
blk.38.indexer.proj.weight=f16
|
| 421 |
+
blk.39.attn_k_b.weight=q6_K
|
| 422 |
+
blk.39.attn_kv_a_mqa.weight=q8_0
|
| 423 |
+
blk.39.attn_output.weight=q4_K
|
| 424 |
+
blk.39.attn_q_a.weight=q6_K
|
| 425 |
+
blk.39.attn_q_b.weight=q6_K
|
| 426 |
+
blk.39.attn_v_b.weight=q6_K
|
| 427 |
+
blk.39.ffn_down_exps.weight=q3_K
|
| 428 |
+
blk.39.ffn_down_shexp.weight=q8_0
|
| 429 |
+
blk.39.ffn_gate_exps.weight=q3_K
|
| 430 |
+
blk.39.ffn_gate_shexp.weight=q6_K
|
| 431 |
+
blk.39.ffn_up_exps.weight=q3_K
|
| 432 |
+
blk.39.ffn_up_shexp.weight=q6_K
|
| 433 |
+
blk.4.attn_k_b.weight=q6_K
|
| 434 |
+
blk.4.attn_kv_a_mqa.weight=q8_0
|
| 435 |
+
blk.4.attn_output.weight=q4_K
|
| 436 |
+
blk.4.attn_q_a.weight=q8_0
|
| 437 |
+
blk.4.attn_q_b.weight=q6_K
|
| 438 |
+
blk.4.attn_v_b.weight=q6_K
|
| 439 |
+
blk.4.ffn_down_exps.weight=q3_K
|
| 440 |
+
blk.4.ffn_down_shexp.weight=q6_K
|
| 441 |
+
blk.4.ffn_gate_exps.weight=q3_K
|
| 442 |
+
blk.4.ffn_gate_shexp.weight=q8_0
|
| 443 |
+
blk.4.ffn_up_exps.weight=q3_K
|
| 444 |
+
blk.4.ffn_up_shexp.weight=q8_0
|
| 445 |
+
blk.40.attn_k_b.weight=q6_K
|
| 446 |
+
blk.40.attn_kv_a_mqa.weight=q8_0
|
| 447 |
+
blk.40.attn_output.weight=q4_K
|
| 448 |
+
blk.40.attn_q_a.weight=q6_K
|
| 449 |
+
blk.40.attn_q_b.weight=q6_K
|
| 450 |
+
blk.40.attn_v_b.weight=q6_K
|
| 451 |
+
blk.40.ffn_down_exps.weight=q3_K
|
| 452 |
+
blk.40.ffn_down_shexp.weight=q8_0
|
| 453 |
+
blk.40.ffn_gate_exps.weight=q3_K
|
| 454 |
+
blk.40.ffn_gate_shexp.weight=q6_K
|
| 455 |
+
blk.40.ffn_up_exps.weight=q3_K
|
| 456 |
+
blk.40.ffn_up_shexp.weight=q6_K
|
| 457 |
+
blk.41.attn_k_b.weight=q6_K
|
| 458 |
+
blk.41.attn_kv_a_mqa.weight=q8_0
|
| 459 |
+
blk.41.attn_output.weight=q4_K
|
| 460 |
+
blk.41.attn_q_a.weight=q6_K
|
| 461 |
+
blk.41.attn_q_b.weight=q6_K
|
| 462 |
+
blk.41.attn_v_b.weight=q6_K
|
| 463 |
+
blk.41.ffn_down_exps.weight=q3_K
|
| 464 |
+
blk.41.ffn_down_shexp.weight=q8_0
|
| 465 |
+
blk.41.ffn_gate_exps.weight=q3_K
|
| 466 |
+
blk.41.ffn_gate_shexp.weight=q6_K
|
| 467 |
+
blk.41.ffn_up_exps.weight=q3_K
|
| 468 |
+
blk.41.ffn_up_shexp.weight=q6_K
|
| 469 |
+
blk.42.attn_k_b.weight=q6_K
|
| 470 |
+
blk.42.attn_kv_a_mqa.weight=q8_0
|
| 471 |
+
blk.42.attn_output.weight=q4_K
|
| 472 |
+
blk.42.attn_q_a.weight=q6_K
|
| 473 |
+
blk.42.attn_q_b.weight=q6_K
|
| 474 |
+
blk.42.attn_v_b.weight=q6_K
|
| 475 |
+
blk.42.ffn_down_exps.weight=q3_K
|
| 476 |
+
blk.42.ffn_down_shexp.weight=q8_0
|
| 477 |
+
blk.42.ffn_gate_exps.weight=q3_K
|
| 478 |
+
blk.42.ffn_gate_shexp.weight=q6_K
|
| 479 |
+
blk.42.ffn_up_exps.weight=q3_K
|
| 480 |
+
blk.42.ffn_up_shexp.weight=q6_K
|
| 481 |
+
blk.42.indexer.attn_k.weight=f16
|
| 482 |
+
blk.42.indexer.attn_q_b.weight=q8_0
|
| 483 |
+
blk.42.indexer.proj.weight=f16
|
| 484 |
+
blk.43.attn_k_b.weight=q6_K
|
| 485 |
+
blk.43.attn_kv_a_mqa.weight=q8_0
|
| 486 |
+
blk.43.attn_output.weight=q4_K
|
| 487 |
+
blk.43.attn_q_a.weight=q6_K
|
| 488 |
+
blk.43.attn_q_b.weight=q6_K
|
| 489 |
+
blk.43.attn_v_b.weight=q6_K
|
| 490 |
+
blk.43.ffn_down_exps.weight=q3_K
|
| 491 |
+
blk.43.ffn_down_shexp.weight=q8_0
|
| 492 |
+
blk.43.ffn_gate_exps.weight=q3_K
|
| 493 |
+
blk.43.ffn_gate_shexp.weight=q6_K
|
| 494 |
+
blk.43.ffn_up_exps.weight=q3_K
|
| 495 |
+
blk.43.ffn_up_shexp.weight=q6_K
|
| 496 |
+
blk.44.attn_k_b.weight=q6_K
|
| 497 |
+
blk.44.attn_kv_a_mqa.weight=q8_0
|
| 498 |
+
blk.44.attn_output.weight=q4_K
|
| 499 |
+
blk.44.attn_q_a.weight=q6_K
|
| 500 |
+
blk.44.attn_q_b.weight=q6_K
|
| 501 |
+
blk.44.attn_v_b.weight=q6_K
|
| 502 |
+
blk.44.ffn_down_exps.weight=q3_K
|
| 503 |
+
blk.44.ffn_down_shexp.weight=q8_0
|
| 504 |
+
blk.44.ffn_gate_exps.weight=q3_K
|
| 505 |
+
blk.44.ffn_gate_shexp.weight=q6_K
|
| 506 |
+
blk.44.ffn_up_exps.weight=q3_K
|
| 507 |
+
blk.44.ffn_up_shexp.weight=q6_K
|
| 508 |
+
blk.45.attn_k_b.weight=q6_K
|
| 509 |
+
blk.45.attn_kv_a_mqa.weight=q8_0
|
| 510 |
+
blk.45.attn_output.weight=q4_K
|
| 511 |
+
blk.45.attn_q_a.weight=q6_K
|
| 512 |
+
blk.45.attn_q_b.weight=q6_K
|
| 513 |
+
blk.45.attn_v_b.weight=q6_K
|
| 514 |
+
blk.45.ffn_down_exps.weight=q3_K
|
| 515 |
+
blk.45.ffn_down_shexp.weight=q8_0
|
| 516 |
+
blk.45.ffn_gate_exps.weight=q3_K
|
| 517 |
+
blk.45.ffn_gate_shexp.weight=q6_K
|
| 518 |
+
blk.45.ffn_up_exps.weight=q3_K
|
| 519 |
+
blk.45.ffn_up_shexp.weight=q6_K
|
| 520 |
+
blk.46.attn_k_b.weight=q6_K
|
| 521 |
+
blk.46.attn_kv_a_mqa.weight=q8_0
|
| 522 |
+
blk.46.attn_output.weight=q4_K
|
| 523 |
+
blk.46.attn_q_a.weight=q6_K
|
| 524 |
+
blk.46.attn_q_b.weight=q6_K
|
| 525 |
+
blk.46.attn_v_b.weight=q6_K
|
| 526 |
+
blk.46.ffn_down_exps.weight=q3_K
|
| 527 |
+
blk.46.ffn_down_shexp.weight=q8_0
|
| 528 |
+
blk.46.ffn_gate_exps.weight=q3_K
|
| 529 |
+
blk.46.ffn_gate_shexp.weight=q6_K
|
| 530 |
+
blk.46.ffn_up_exps.weight=q3_K
|
| 531 |
+
blk.46.ffn_up_shexp.weight=q6_K
|
| 532 |
+
blk.46.indexer.attn_k.weight=f16
|
| 533 |
+
blk.46.indexer.attn_q_b.weight=q8_0
|
| 534 |
+
blk.46.indexer.proj.weight=f16
|
| 535 |
+
blk.47.attn_k_b.weight=q6_K
|
| 536 |
+
blk.47.attn_kv_a_mqa.weight=q8_0
|
| 537 |
+
blk.47.attn_output.weight=q4_K
|
| 538 |
+
blk.47.attn_q_a.weight=q6_K
|
| 539 |
+
blk.47.attn_q_b.weight=q6_K
|
| 540 |
+
blk.47.attn_v_b.weight=q6_K
|
| 541 |
+
blk.47.ffn_down_exps.weight=q3_K
|
| 542 |
+
blk.47.ffn_down_shexp.weight=q8_0
|
| 543 |
+
blk.47.ffn_gate_exps.weight=q3_K
|
| 544 |
+
blk.47.ffn_gate_shexp.weight=q6_K
|
| 545 |
+
blk.47.ffn_up_exps.weight=q3_K
|
| 546 |
+
blk.47.ffn_up_shexp.weight=q6_K
|
| 547 |
+
blk.48.attn_k_b.weight=q6_K
|
| 548 |
+
blk.48.attn_kv_a_mqa.weight=q8_0
|
| 549 |
+
blk.48.attn_output.weight=q4_K
|
| 550 |
+
blk.48.attn_q_a.weight=q6_K
|
| 551 |
+
blk.48.attn_q_b.weight=q6_K
|
| 552 |
+
blk.48.attn_v_b.weight=q6_K
|
| 553 |
+
blk.48.ffn_down_exps.weight=q3_K
|
| 554 |
+
blk.48.ffn_down_shexp.weight=q8_0
|
| 555 |
+
blk.48.ffn_gate_exps.weight=q3_K
|
| 556 |
+
blk.48.ffn_gate_shexp.weight=q6_K
|
| 557 |
+
blk.48.ffn_up_exps.weight=q3_K
|
| 558 |
+
blk.48.ffn_up_shexp.weight=q6_K
|
| 559 |
+
blk.49.attn_k_b.weight=q6_K
|
| 560 |
+
blk.49.attn_kv_a_mqa.weight=q8_0
|
| 561 |
+
blk.49.attn_output.weight=q4_K
|
| 562 |
+
blk.49.attn_q_a.weight=q6_K
|
| 563 |
+
blk.49.attn_q_b.weight=q6_K
|
| 564 |
+
blk.49.attn_v_b.weight=q6_K
|
| 565 |
+
blk.49.ffn_down_exps.weight=q3_K
|
| 566 |
+
blk.49.ffn_down_shexp.weight=q8_0
|
| 567 |
+
blk.49.ffn_gate_exps.weight=q3_K
|
| 568 |
+
blk.49.ffn_gate_shexp.weight=q6_K
|
| 569 |
+
blk.49.ffn_up_exps.weight=q3_K
|
| 570 |
+
blk.49.ffn_up_shexp.weight=q6_K
|
| 571 |
+
blk.5.attn_k_b.weight=q6_K
|
| 572 |
+
blk.5.attn_kv_a_mqa.weight=q8_0
|
| 573 |
+
blk.5.attn_output.weight=q4_K
|
| 574 |
+
blk.5.attn_q_a.weight=q8_0
|
| 575 |
+
blk.5.attn_q_b.weight=q6_K
|
| 576 |
+
blk.5.attn_v_b.weight=q6_K
|
| 577 |
+
blk.5.ffn_down_exps.weight=q3_K
|
| 578 |
+
blk.5.ffn_down_shexp.weight=q6_K
|
| 579 |
+
blk.5.ffn_gate_exps.weight=q3_K
|
| 580 |
+
blk.5.ffn_gate_shexp.weight=q8_0
|
| 581 |
+
blk.5.ffn_up_exps.weight=q3_K
|
| 582 |
+
blk.5.ffn_up_shexp.weight=q6_K
|
| 583 |
+
blk.50.attn_k_b.weight=q6_K
|
| 584 |
+
blk.50.attn_kv_a_mqa.weight=q8_0
|
| 585 |
+
blk.50.attn_output.weight=q4_K
|
| 586 |
+
blk.50.attn_q_a.weight=q6_K
|
| 587 |
+
blk.50.attn_q_b.weight=q6_K
|
| 588 |
+
blk.50.attn_v_b.weight=q6_K
|
| 589 |
+
blk.50.ffn_down_exps.weight=q3_K
|
| 590 |
+
blk.50.ffn_down_shexp.weight=q8_0
|
| 591 |
+
blk.50.ffn_gate_exps.weight=q3_K
|
| 592 |
+
blk.50.ffn_gate_shexp.weight=q6_K
|
| 593 |
+
blk.50.ffn_up_exps.weight=q3_K
|
| 594 |
+
blk.50.ffn_up_shexp.weight=q6_K
|
| 595 |
+
blk.50.indexer.attn_k.weight=f16
|
| 596 |
+
blk.50.indexer.attn_q_b.weight=q8_0
|
| 597 |
+
blk.50.indexer.proj.weight=f16
|
| 598 |
+
blk.51.attn_k_b.weight=q6_K
|
| 599 |
+
blk.51.attn_kv_a_mqa.weight=q8_0
|
| 600 |
+
blk.51.attn_output.weight=q4_K
|
| 601 |
+
blk.51.attn_q_a.weight=q6_K
|
| 602 |
+
blk.51.attn_q_b.weight=q6_K
|
| 603 |
+
blk.51.attn_v_b.weight=q6_K
|
| 604 |
+
blk.51.ffn_down_exps.weight=q3_K
|
| 605 |
+
blk.51.ffn_down_shexp.weight=q8_0
|
| 606 |
+
blk.51.ffn_gate_exps.weight=q3_K
|
| 607 |
+
blk.51.ffn_gate_shexp.weight=q6_K
|
| 608 |
+
blk.51.ffn_up_exps.weight=q3_K
|
| 609 |
+
blk.51.ffn_up_shexp.weight=q6_K
|
| 610 |
+
blk.52.attn_k_b.weight=q6_K
|
| 611 |
+
blk.52.attn_kv_a_mqa.weight=q8_0
|
| 612 |
+
blk.52.attn_output.weight=q4_K
|
| 613 |
+
blk.52.attn_q_a.weight=q6_K
|
| 614 |
+
blk.52.attn_q_b.weight=q6_K
|
| 615 |
+
blk.52.attn_v_b.weight=q6_K
|
| 616 |
+
blk.52.ffn_down_exps.weight=q3_K
|
| 617 |
+
blk.52.ffn_down_shexp.weight=q8_0
|
| 618 |
+
blk.52.ffn_gate_exps.weight=q3_K
|
| 619 |
+
blk.52.ffn_gate_shexp.weight=q6_K
|
| 620 |
+
blk.52.ffn_up_exps.weight=q3_K
|
| 621 |
+
blk.52.ffn_up_shexp.weight=q6_K
|
| 622 |
+
blk.53.attn_k_b.weight=q6_K
|
| 623 |
+
blk.53.attn_kv_a_mqa.weight=q8_0
|
| 624 |
+
blk.53.attn_output.weight=q4_K
|
| 625 |
+
blk.53.attn_q_a.weight=q6_K
|
| 626 |
+
blk.53.attn_q_b.weight=q6_K
|
| 627 |
+
blk.53.attn_v_b.weight=q6_K
|
| 628 |
+
blk.53.ffn_down_exps.weight=q3_K
|
| 629 |
+
blk.53.ffn_down_shexp.weight=q8_0
|
| 630 |
+
blk.53.ffn_gate_exps.weight=q3_K
|
| 631 |
+
blk.53.ffn_gate_shexp.weight=q6_K
|
| 632 |
+
blk.53.ffn_up_exps.weight=q3_K
|
| 633 |
+
blk.53.ffn_up_shexp.weight=q6_K
|
| 634 |
+
blk.54.attn_k_b.weight=q6_K
|
| 635 |
+
blk.54.attn_kv_a_mqa.weight=q8_0
|
| 636 |
+
blk.54.attn_output.weight=q4_K
|
| 637 |
+
blk.54.attn_q_a.weight=q6_K
|
| 638 |
+
blk.54.attn_q_b.weight=q6_K
|
| 639 |
+
blk.54.attn_v_b.weight=q6_K
|
| 640 |
+
blk.54.ffn_down_exps.weight=q3_K
|
| 641 |
+
blk.54.ffn_down_shexp.weight=q8_0
|
| 642 |
+
blk.54.ffn_gate_exps.weight=q3_K
|
| 643 |
+
blk.54.ffn_gate_shexp.weight=q6_K
|
| 644 |
+
blk.54.ffn_up_exps.weight=q3_K
|
| 645 |
+
blk.54.ffn_up_shexp.weight=q6_K
|
| 646 |
+
blk.54.indexer.attn_k.weight=f16
|
| 647 |
+
blk.54.indexer.attn_q_b.weight=q8_0
|
| 648 |
+
blk.54.indexer.proj.weight=f16
|
| 649 |
+
blk.55.attn_k_b.weight=q6_K
|
| 650 |
+
blk.55.attn_kv_a_mqa.weight=q8_0
|
| 651 |
+
blk.55.attn_output.weight=q4_K
|
| 652 |
+
blk.55.attn_q_a.weight=q6_K
|
| 653 |
+
blk.55.attn_q_b.weight=q6_K
|
| 654 |
+
blk.55.attn_v_b.weight=q6_K
|
| 655 |
+
blk.55.ffn_down_exps.weight=q3_K
|
| 656 |
+
blk.55.ffn_down_shexp.weight=q8_0
|
| 657 |
+
blk.55.ffn_gate_exps.weight=q3_K
|
| 658 |
+
blk.55.ffn_gate_shexp.weight=q6_K
|
| 659 |
+
blk.55.ffn_up_exps.weight=q3_K
|
| 660 |
+
blk.55.ffn_up_shexp.weight=q6_K
|
| 661 |
+
blk.56.attn_k_b.weight=q6_K
|
| 662 |
+
blk.56.attn_kv_a_mqa.weight=q8_0
|
| 663 |
+
blk.56.attn_output.weight=q4_K
|
| 664 |
+
blk.56.attn_q_a.weight=q6_K
|
| 665 |
+
blk.56.attn_q_b.weight=q6_K
|
| 666 |
+
blk.56.attn_v_b.weight=q6_K
|
| 667 |
+
blk.56.ffn_down_exps.weight=q3_K
|
| 668 |
+
blk.56.ffn_down_shexp.weight=q8_0
|
| 669 |
+
blk.56.ffn_gate_exps.weight=q3_K
|
| 670 |
+
blk.56.ffn_gate_shexp.weight=q6_K
|
| 671 |
+
blk.56.ffn_up_exps.weight=q3_K
|
| 672 |
+
blk.56.ffn_up_shexp.weight=q6_K
|
| 673 |
+
blk.57.attn_k_b.weight=q6_K
|
| 674 |
+
blk.57.attn_kv_a_mqa.weight=q8_0
|
| 675 |
+
blk.57.attn_output.weight=q4_K
|
| 676 |
+
blk.57.attn_q_a.weight=q6_K
|
| 677 |
+
blk.57.attn_q_b.weight=q6_K
|
| 678 |
+
blk.57.attn_v_b.weight=q6_K
|
| 679 |
+
blk.57.ffn_down_exps.weight=q3_K
|
| 680 |
+
blk.57.ffn_down_shexp.weight=q8_0
|
| 681 |
+
blk.57.ffn_gate_exps.weight=q3_K
|
| 682 |
+
blk.57.ffn_gate_shexp.weight=q6_K
|
| 683 |
+
blk.57.ffn_up_exps.weight=q3_K
|
| 684 |
+
blk.57.ffn_up_shexp.weight=q6_K
|
| 685 |
+
blk.58.attn_k_b.weight=q6_K
|
| 686 |
+
blk.58.attn_kv_a_mqa.weight=q8_0
|
| 687 |
+
blk.58.attn_output.weight=q4_K
|
| 688 |
+
blk.58.attn_q_a.weight=q6_K
|
| 689 |
+
blk.58.attn_q_b.weight=q6_K
|
| 690 |
+
blk.58.attn_v_b.weight=q6_K
|
| 691 |
+
blk.58.ffn_down_exps.weight=q3_K
|
| 692 |
+
blk.58.ffn_down_shexp.weight=q8_0
|
| 693 |
+
blk.58.ffn_gate_exps.weight=q3_K
|
| 694 |
+
blk.58.ffn_gate_shexp.weight=q6_K
|
| 695 |
+
blk.58.ffn_up_exps.weight=q3_K
|
| 696 |
+
blk.58.ffn_up_shexp.weight=q6_K
|
| 697 |
+
blk.58.indexer.attn_k.weight=f16
|
| 698 |
+
blk.58.indexer.attn_q_b.weight=q8_0
|
| 699 |
+
blk.58.indexer.proj.weight=f16
|
| 700 |
+
blk.59.attn_k_b.weight=q6_K
|
| 701 |
+
blk.59.attn_kv_a_mqa.weight=q8_0
|
| 702 |
+
blk.59.attn_output.weight=q4_K
|
| 703 |
+
blk.59.attn_q_a.weight=q6_K
|
| 704 |
+
blk.59.attn_q_b.weight=q6_K
|
| 705 |
+
blk.59.attn_v_b.weight=q6_K
|
| 706 |
+
blk.59.ffn_down_exps.weight=q3_K
|
| 707 |
+
blk.59.ffn_down_shexp.weight=q8_0
|
| 708 |
+
blk.59.ffn_gate_exps.weight=q3_K
|
| 709 |
+
blk.59.ffn_gate_shexp.weight=q6_K
|
| 710 |
+
blk.59.ffn_up_exps.weight=q3_K
|
| 711 |
+
blk.59.ffn_up_shexp.weight=q6_K
|
| 712 |
+
blk.6.attn_k_b.weight=q6_K
|
| 713 |
+
blk.6.attn_kv_a_mqa.weight=q8_0
|
| 714 |
+
blk.6.attn_output.weight=q4_K
|
| 715 |
+
blk.6.attn_q_a.weight=q8_0
|
| 716 |
+
blk.6.attn_q_b.weight=q6_K
|
| 717 |
+
blk.6.attn_v_b.weight=q6_K
|
| 718 |
+
blk.6.ffn_down_exps.weight=q3_K
|
| 719 |
+
blk.6.ffn_down_shexp.weight=q8_0
|
| 720 |
+
blk.6.ffn_gate_exps.weight=q3_K
|
| 721 |
+
blk.6.ffn_gate_shexp.weight=q6_K
|
| 722 |
+
blk.6.ffn_up_exps.weight=q3_K
|
| 723 |
+
blk.6.ffn_up_shexp.weight=q6_K
|
| 724 |
+
blk.6.indexer.attn_k.weight=f16
|
| 725 |
+
blk.6.indexer.attn_q_b.weight=q8_0
|
| 726 |
+
blk.6.indexer.proj.weight=f16
|
| 727 |
+
blk.60.attn_k_b.weight=q6_K
|
| 728 |
+
blk.60.attn_kv_a_mqa.weight=q8_0
|
| 729 |
+
blk.60.attn_output.weight=q4_K
|
| 730 |
+
blk.60.attn_q_a.weight=q6_K
|
| 731 |
+
blk.60.attn_q_b.weight=q6_K
|
| 732 |
+
blk.60.attn_v_b.weight=q6_K
|
| 733 |
+
blk.60.ffn_down_exps.weight=q3_K
|
| 734 |
+
blk.60.ffn_down_shexp.weight=q8_0
|
| 735 |
+
blk.60.ffn_gate_exps.weight=q3_K
|
| 736 |
+
blk.60.ffn_gate_shexp.weight=q6_K
|
| 737 |
+
blk.60.ffn_up_exps.weight=q3_K
|
| 738 |
+
blk.60.ffn_up_shexp.weight=q6_K
|
| 739 |
+
blk.61.attn_k_b.weight=q6_K
|
| 740 |
+
blk.61.attn_kv_a_mqa.weight=q8_0
|
| 741 |
+
blk.61.attn_output.weight=q4_K
|
| 742 |
+
blk.61.attn_q_a.weight=q6_K
|
| 743 |
+
blk.61.attn_q_b.weight=q6_K
|
| 744 |
+
blk.61.attn_v_b.weight=q6_K
|
| 745 |
+
blk.61.ffn_down_exps.weight=q3_K
|
| 746 |
+
blk.61.ffn_down_shexp.weight=q8_0
|
| 747 |
+
blk.61.ffn_gate_exps.weight=q3_K
|
| 748 |
+
blk.61.ffn_gate_shexp.weight=q6_K
|
| 749 |
+
blk.61.ffn_up_exps.weight=q3_K
|
| 750 |
+
blk.61.ffn_up_shexp.weight=q6_K
|
| 751 |
+
blk.62.attn_k_b.weight=q6_K
|
| 752 |
+
blk.62.attn_kv_a_mqa.weight=q8_0
|
| 753 |
+
blk.62.attn_output.weight=q4_K
|
| 754 |
+
blk.62.attn_q_a.weight=q6_K
|
| 755 |
+
blk.62.attn_q_b.weight=q6_K
|
| 756 |
+
blk.62.attn_v_b.weight=q6_K
|
| 757 |
+
blk.62.ffn_down_exps.weight=q3_K
|
| 758 |
+
blk.62.ffn_down_shexp.weight=q8_0
|
| 759 |
+
blk.62.ffn_gate_exps.weight=q3_K
|
| 760 |
+
blk.62.ffn_gate_shexp.weight=q6_K
|
| 761 |
+
blk.62.ffn_up_exps.weight=q3_K
|
| 762 |
+
blk.62.ffn_up_shexp.weight=q6_K
|
| 763 |
+
blk.62.indexer.attn_k.weight=f16
|
| 764 |
+
blk.62.indexer.attn_q_b.weight=q8_0
|
| 765 |
+
blk.62.indexer.proj.weight=f16
|
| 766 |
+
blk.63.attn_k_b.weight=q6_K
|
| 767 |
+
blk.63.attn_kv_a_mqa.weight=q8_0
|
| 768 |
+
blk.63.attn_output.weight=q4_K
|
| 769 |
+
blk.63.attn_q_a.weight=q6_K
|
| 770 |
+
blk.63.attn_q_b.weight=q6_K
|
| 771 |
+
blk.63.attn_v_b.weight=q6_K
|
| 772 |
+
blk.63.ffn_down_exps.weight=q3_K
|
| 773 |
+
blk.63.ffn_down_shexp.weight=q8_0
|
| 774 |
+
blk.63.ffn_gate_exps.weight=q3_K
|
| 775 |
+
blk.63.ffn_gate_shexp.weight=q6_K
|
| 776 |
+
blk.63.ffn_up_exps.weight=q3_K
|
| 777 |
+
blk.63.ffn_up_shexp.weight=q6_K
|
| 778 |
+
blk.64.attn_k_b.weight=q6_K
|
| 779 |
+
blk.64.attn_kv_a_mqa.weight=q8_0
|
| 780 |
+
blk.64.attn_output.weight=q4_K
|
| 781 |
+
blk.64.attn_q_a.weight=q6_K
|
| 782 |
+
blk.64.attn_q_b.weight=q6_K
|
| 783 |
+
blk.64.attn_v_b.weight=q6_K
|
| 784 |
+
blk.64.ffn_down_exps.weight=q3_K
|
| 785 |
+
blk.64.ffn_down_shexp.weight=q8_0
|
| 786 |
+
blk.64.ffn_gate_exps.weight=q3_K
|
| 787 |
+
blk.64.ffn_gate_shexp.weight=q6_K
|
| 788 |
+
blk.64.ffn_up_exps.weight=q3_K
|
| 789 |
+
blk.64.ffn_up_shexp.weight=q6_K
|
| 790 |
+
blk.65.attn_k_b.weight=q6_K
|
| 791 |
+
blk.65.attn_kv_a_mqa.weight=q8_0
|
| 792 |
+
blk.65.attn_output.weight=q4_K
|
| 793 |
+
blk.65.attn_q_a.weight=q6_K
|
| 794 |
+
blk.65.attn_q_b.weight=q6_K
|
| 795 |
+
blk.65.attn_v_b.weight=q6_K
|
| 796 |
+
blk.65.ffn_down_exps.weight=q3_K
|
| 797 |
+
blk.65.ffn_down_shexp.weight=q8_0
|
| 798 |
+
blk.65.ffn_gate_exps.weight=q3_K
|
| 799 |
+
blk.65.ffn_gate_shexp.weight=q6_K
|
| 800 |
+
blk.65.ffn_up_exps.weight=q3_K
|
| 801 |
+
blk.65.ffn_up_shexp.weight=q6_K
|
| 802 |
+
blk.66.attn_k_b.weight=q6_K
|
| 803 |
+
blk.66.attn_kv_a_mqa.weight=q8_0
|
| 804 |
+
blk.66.attn_output.weight=q4_K
|
| 805 |
+
blk.66.attn_q_a.weight=q6_K
|
| 806 |
+
blk.66.attn_q_b.weight=q6_K
|
| 807 |
+
blk.66.attn_v_b.weight=q6_K
|
| 808 |
+
blk.66.ffn_down_exps.weight=q3_K
|
| 809 |
+
blk.66.ffn_down_shexp.weight=q8_0
|
| 810 |
+
blk.66.ffn_gate_exps.weight=q3_K
|
| 811 |
+
blk.66.ffn_gate_shexp.weight=q6_K
|
| 812 |
+
blk.66.ffn_up_exps.weight=q3_K
|
| 813 |
+
blk.66.ffn_up_shexp.weight=q6_K
|
| 814 |
+
blk.66.indexer.attn_k.weight=f16
|
| 815 |
+
blk.66.indexer.attn_q_b.weight=q8_0
|
| 816 |
+
blk.66.indexer.proj.weight=f16
|
| 817 |
+
blk.67.attn_k_b.weight=q6_K
|
| 818 |
+
blk.67.attn_kv_a_mqa.weight=q8_0
|
| 819 |
+
blk.67.attn_output.weight=q4_K
|
| 820 |
+
blk.67.attn_q_a.weight=q6_K
|
| 821 |
+
blk.67.attn_q_b.weight=q6_K
|
| 822 |
+
blk.67.attn_v_b.weight=q6_K
|
| 823 |
+
blk.67.ffn_down_exps.weight=q3_K
|
| 824 |
+
blk.67.ffn_down_shexp.weight=q8_0
|
| 825 |
+
blk.67.ffn_gate_exps.weight=q3_K
|
| 826 |
+
blk.67.ffn_gate_shexp.weight=q6_K
|
| 827 |
+
blk.67.ffn_up_exps.weight=q3_K
|
| 828 |
+
blk.67.ffn_up_shexp.weight=q6_K
|
| 829 |
+
blk.68.attn_k_b.weight=q6_K
|
| 830 |
+
blk.68.attn_kv_a_mqa.weight=q8_0
|
| 831 |
+
blk.68.attn_output.weight=q4_K
|
| 832 |
+
blk.68.attn_q_a.weight=q6_K
|
| 833 |
+
blk.68.attn_q_b.weight=q6_K
|
| 834 |
+
blk.68.attn_v_b.weight=q6_K
|
| 835 |
+
blk.68.ffn_down_exps.weight=q3_K
|
| 836 |
+
blk.68.ffn_down_shexp.weight=q8_0
|
| 837 |
+
blk.68.ffn_gate_exps.weight=q3_K
|
| 838 |
+
blk.68.ffn_gate_shexp.weight=q6_K
|
| 839 |
+
blk.68.ffn_up_exps.weight=q3_K
|
| 840 |
+
blk.68.ffn_up_shexp.weight=q6_K
|
| 841 |
+
blk.69.attn_k_b.weight=q6_K
|
| 842 |
+
blk.69.attn_kv_a_mqa.weight=q8_0
|
| 843 |
+
blk.69.attn_output.weight=q4_K
|
| 844 |
+
blk.69.attn_q_a.weight=q6_K
|
| 845 |
+
blk.69.attn_q_b.weight=q6_K
|
| 846 |
+
blk.69.attn_v_b.weight=q6_K
|
| 847 |
+
blk.69.ffn_down_exps.weight=q3_K
|
| 848 |
+
blk.69.ffn_down_shexp.weight=q8_0
|
| 849 |
+
blk.69.ffn_gate_exps.weight=q3_K
|
| 850 |
+
blk.69.ffn_gate_shexp.weight=q6_K
|
| 851 |
+
blk.69.ffn_up_exps.weight=q3_K
|
| 852 |
+
blk.69.ffn_up_shexp.weight=q6_K
|
| 853 |
+
blk.7.attn_k_b.weight=q6_K
|
| 854 |
+
blk.7.attn_kv_a_mqa.weight=q8_0
|
| 855 |
+
blk.7.attn_output.weight=q4_K
|
| 856 |
+
blk.7.attn_q_a.weight=q8_0
|
| 857 |
+
blk.7.attn_q_b.weight=q6_K
|
| 858 |
+
blk.7.attn_v_b.weight=q6_K
|
| 859 |
+
blk.7.ffn_down_exps.weight=q3_K
|
| 860 |
+
blk.7.ffn_down_shexp.weight=q8_0
|
| 861 |
+
blk.7.ffn_gate_exps.weight=q3_K
|
| 862 |
+
blk.7.ffn_gate_shexp.weight=q6_K
|
| 863 |
+
blk.7.ffn_up_exps.weight=q3_K
|
| 864 |
+
blk.7.ffn_up_shexp.weight=q6_K
|
| 865 |
+
blk.70.attn_k_b.weight=q6_K
|
| 866 |
+
blk.70.attn_kv_a_mqa.weight=q8_0
|
| 867 |
+
blk.70.attn_output.weight=q4_K
|
| 868 |
+
blk.70.attn_q_a.weight=q6_K
|
| 869 |
+
blk.70.attn_q_b.weight=q6_K
|
| 870 |
+
blk.70.attn_v_b.weight=q6_K
|
| 871 |
+
blk.70.ffn_down_exps.weight=q3_K
|
| 872 |
+
blk.70.ffn_down_shexp.weight=q8_0
|
| 873 |
+
blk.70.ffn_gate_exps.weight=q3_K
|
| 874 |
+
blk.70.ffn_gate_shexp.weight=q6_K
|
| 875 |
+
blk.70.ffn_up_exps.weight=q3_K
|
| 876 |
+
blk.70.ffn_up_shexp.weight=q6_K
|
| 877 |
+
blk.70.indexer.attn_k.weight=f16
|
| 878 |
+
blk.70.indexer.attn_q_b.weight=q8_0
|
| 879 |
+
blk.70.indexer.proj.weight=f16
|
| 880 |
+
blk.71.attn_k_b.weight=q6_K
|
| 881 |
+
blk.71.attn_kv_a_mqa.weight=q8_0
|
| 882 |
+
blk.71.attn_output.weight=q4_K
|
| 883 |
+
blk.71.attn_q_a.weight=q6_K
|
| 884 |
+
blk.71.attn_q_b.weight=q6_K
|
| 885 |
+
blk.71.attn_v_b.weight=q6_K
|
| 886 |
+
blk.71.ffn_down_exps.weight=q3_K
|
| 887 |
+
blk.71.ffn_down_shexp.weight=q8_0
|
| 888 |
+
blk.71.ffn_gate_exps.weight=q3_K
|
| 889 |
+
blk.71.ffn_gate_shexp.weight=q6_K
|
| 890 |
+
blk.71.ffn_up_exps.weight=q3_K
|
| 891 |
+
blk.71.ffn_up_shexp.weight=q8_0
|
| 892 |
+
blk.72.attn_k_b.weight=q6_K
|
| 893 |
+
blk.72.attn_kv_a_mqa.weight=q8_0
|
| 894 |
+
blk.72.attn_output.weight=q4_K
|
| 895 |
+
blk.72.attn_q_a.weight=q6_K
|
| 896 |
+
blk.72.attn_q_b.weight=q6_K
|
| 897 |
+
blk.72.attn_v_b.weight=q6_K
|
| 898 |
+
blk.72.ffn_down_exps.weight=q3_K
|
| 899 |
+
blk.72.ffn_down_shexp.weight=q8_0
|
| 900 |
+
blk.72.ffn_gate_exps.weight=q3_K
|
| 901 |
+
blk.72.ffn_gate_shexp.weight=q6_K
|
| 902 |
+
blk.72.ffn_up_exps.weight=q3_K
|
| 903 |
+
blk.72.ffn_up_shexp.weight=q6_K
|
| 904 |
+
blk.73.attn_k_b.weight=q6_K
|
| 905 |
+
blk.73.attn_kv_a_mqa.weight=q8_0
|
| 906 |
+
blk.73.attn_output.weight=q4_K
|
| 907 |
+
blk.73.attn_q_a.weight=q6_K
|
| 908 |
+
blk.73.attn_q_b.weight=q6_K
|
| 909 |
+
blk.73.attn_v_b.weight=q6_K
|
| 910 |
+
blk.73.ffn_down_exps.weight=q3_K
|
| 911 |
+
blk.73.ffn_down_shexp.weight=q8_0
|
| 912 |
+
blk.73.ffn_gate_exps.weight=q3_K
|
| 913 |
+
blk.73.ffn_gate_shexp.weight=q6_K
|
| 914 |
+
blk.73.ffn_up_exps.weight=q3_K
|
| 915 |
+
blk.73.ffn_up_shexp.weight=q8_0
|
| 916 |
+
blk.74.attn_k_b.weight=q6_K
|
| 917 |
+
blk.74.attn_kv_a_mqa.weight=q8_0
|
| 918 |
+
blk.74.attn_output.weight=q4_K
|
| 919 |
+
blk.74.attn_q_a.weight=q6_K
|
| 920 |
+
blk.74.attn_q_b.weight=q6_K
|
| 921 |
+
blk.74.attn_v_b.weight=q6_K
|
| 922 |
+
blk.74.ffn_down_exps.weight=q3_K
|
| 923 |
+
blk.74.ffn_down_shexp.weight=q8_0
|
| 924 |
+
blk.74.ffn_gate_exps.weight=q3_K
|
| 925 |
+
blk.74.ffn_gate_shexp.weight=q6_K
|
| 926 |
+
blk.74.ffn_up_exps.weight=q3_K
|
| 927 |
+
blk.74.ffn_up_shexp.weight=q6_K
|
| 928 |
+
blk.74.indexer.attn_k.weight=f16
|
| 929 |
+
blk.74.indexer.attn_q_b.weight=q8_0
|
| 930 |
+
blk.74.indexer.proj.weight=f16
|
| 931 |
+
blk.75.attn_k_b.weight=q6_K
|
| 932 |
+
blk.75.attn_kv_a_mqa.weight=q8_0
|
| 933 |
+
blk.75.attn_output.weight=q4_K
|
| 934 |
+
blk.75.attn_q_a.weight=q6_K
|
| 935 |
+
blk.75.attn_q_b.weight=q6_K
|
| 936 |
+
blk.75.attn_v_b.weight=q6_K
|
| 937 |
+
blk.75.ffn_down_exps.weight=q3_K
|
| 938 |
+
blk.75.ffn_down_shexp.weight=q8_0
|
| 939 |
+
blk.75.ffn_gate_exps.weight=q3_K
|
| 940 |
+
blk.75.ffn_gate_shexp.weight=q6_K
|
| 941 |
+
blk.75.ffn_up_exps.weight=q3_K
|
| 942 |
+
blk.75.ffn_up_shexp.weight=q6_K
|
| 943 |
+
blk.76.attn_k_b.weight=q6_K
|
| 944 |
+
blk.76.attn_kv_a_mqa.weight=q8_0
|
| 945 |
+
blk.76.attn_output.weight=q4_K
|
| 946 |
+
blk.76.attn_q_a.weight=q6_K
|
| 947 |
+
blk.76.attn_q_b.weight=q6_K
|
| 948 |
+
blk.76.attn_v_b.weight=q6_K
|
| 949 |
+
blk.76.ffn_down_exps.weight=q3_K
|
| 950 |
+
blk.76.ffn_down_shexp.weight=q8_0
|
| 951 |
+
blk.76.ffn_gate_exps.weight=q3_K
|
| 952 |
+
blk.76.ffn_gate_shexp.weight=q6_K
|
| 953 |
+
blk.76.ffn_up_exps.weight=q3_K
|
| 954 |
+
blk.76.ffn_up_shexp.weight=q6_K
|
| 955 |
+
blk.77.attn_k_b.weight=q6_K
|
| 956 |
+
blk.77.attn_kv_a_mqa.weight=q8_0
|
| 957 |
+
blk.77.attn_output.weight=q4_K
|
| 958 |
+
blk.77.attn_q_a.weight=q6_K
|
| 959 |
+
blk.77.attn_q_b.weight=q6_K
|
| 960 |
+
blk.77.attn_v_b.weight=q6_K
|
| 961 |
+
blk.77.ffn_down_exps.weight=q3_K
|
| 962 |
+
blk.77.ffn_down_shexp.weight=q8_0
|
| 963 |
+
blk.77.ffn_gate_exps.weight=q3_K
|
| 964 |
+
blk.77.ffn_gate_shexp.weight=q8_0
|
| 965 |
+
blk.77.ffn_up_exps.weight=q3_K
|
| 966 |
+
blk.77.ffn_up_shexp.weight=q8_0
|
| 967 |
+
blk.78.attn_k_b.weight=q6_K
|
| 968 |
+
blk.78.attn_kv_a_mqa.weight=q8_0
|
| 969 |
+
blk.78.attn_output.weight=q4_K
|
| 970 |
+
blk.78.attn_q_a.weight=q6_K
|
| 971 |
+
blk.78.attn_q_b.weight=q6_K
|
| 972 |
+
blk.78.attn_v_b.weight=q6_K
|
| 973 |
+
blk.78.ffn_down_exps.weight=q3_K
|
| 974 |
+
blk.78.ffn_down_shexp.weight=q8_0
|
| 975 |
+
blk.78.ffn_gate_exps.weight=q3_K
|
| 976 |
+
blk.78.ffn_gate_shexp.weight=q6_K
|
| 977 |
+
blk.78.ffn_up_exps.weight=q3_K
|
| 978 |
+
blk.78.ffn_up_shexp.weight=q8_0
|
| 979 |
+
blk.78.indexer.attn_k.weight=f16
|
| 980 |
+
blk.78.indexer.attn_q_b.weight=q8_0
|
| 981 |
+
blk.78.indexer.proj.weight=f16
|
| 982 |
+
blk.8.attn_k_b.weight=q6_K
|
| 983 |
+
blk.8.attn_kv_a_mqa.weight=q8_0
|
| 984 |
+
blk.8.attn_output.weight=q4_K
|
| 985 |
+
blk.8.attn_q_a.weight=q6_K
|
| 986 |
+
blk.8.attn_q_b.weight=q6_K
|
| 987 |
+
blk.8.attn_v_b.weight=q6_K
|
| 988 |
+
blk.8.ffn_down_exps.weight=q3_K
|
| 989 |
+
blk.8.ffn_down_shexp.weight=q8_0
|
| 990 |
+
blk.8.ffn_gate_exps.weight=q3_K
|
| 991 |
+
blk.8.ffn_gate_shexp.weight=q6_K
|
| 992 |
+
blk.8.ffn_up_exps.weight=q3_K
|
| 993 |
+
blk.8.ffn_up_shexp.weight=q6_K
|
| 994 |
+
blk.9.attn_k_b.weight=q6_K
|
| 995 |
+
blk.9.attn_kv_a_mqa.weight=q8_0
|
| 996 |
+
blk.9.attn_output.weight=q4_K
|
| 997 |
+
blk.9.attn_q_a.weight=q8_0
|
| 998 |
+
blk.9.attn_q_b.weight=q6_K
|
| 999 |
+
blk.9.attn_v_b.weight=q6_K
|
| 1000 |
+
blk.9.ffn_down_exps.weight=q3_K
|
| 1001 |
+
blk.9.ffn_down_shexp.weight=q8_0
|
| 1002 |
+
blk.9.ffn_gate_exps.weight=q3_K
|
| 1003 |
+
blk.9.ffn_gate_shexp.weight=q6_K
|
| 1004 |
+
blk.9.ffn_up_exps.weight=q3_K
|
| 1005 |
+
blk.9.ffn_up_shexp.weight=q6_K
|