Text Generation
GGUF
English
Chinese
glm
Mixture of Experts
quantized
glm_moe_dsa
Conversational
uncensored
conversational
Instructions to use softwareweaver/GLM-5.3-Uncensored-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use softwareweaver/GLM-5.3-Uncensored-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 softwareweaver/GLM-5.3-Uncensored-GGUF:BF16 # Run inference directly in the terminal: llama cli -hf softwareweaver/GLM-5.3-Uncensored-GGUF:BF16
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf softwareweaver/GLM-5.3-Uncensored-GGUF:BF16 # Run inference directly in the terminal: llama cli -hf softwareweaver/GLM-5.3-Uncensored-GGUF:BF16
Build from source code
git clone https://github.com/ggml-org/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-app # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama serve -hf softwareweaver/GLM-5.3-Uncensored-GGUF:BF16 # Run inference directly in the terminal: ./build/bin/llama cli -hf softwareweaver/GLM-5.3-Uncensored-GGUF:BF16
Use Docker
docker model run hf.co/softwareweaver/GLM-5.3-Uncensored-GGUF:BF16
- Llama new
- LM Studio
- Jan
- vLLM
How to use softwareweaver/GLM-5.3-Uncensored-GGUF with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "softwareweaver/GLM-5.3-Uncensored-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": "softwareweaver/GLM-5.3-Uncensored-GGUF", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/softwareweaver/GLM-5.3-Uncensored-GGUF:BF16
- Ollama
How to use softwareweaver/GLM-5.3-Uncensored-GGUF with Ollama:
ollama run hf.co/softwareweaver/GLM-5.3-Uncensored-GGUF:BF16
- Unsloth Desktop
- Pi
How to use softwareweaver/GLM-5.3-Uncensored-GGUF with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf softwareweaver/GLM-5.3-Uncensored-GGUF:BF16
Configure the model in Pi
# Install Pi: npm install -g @earendil-works/pi-coding-agent # Add to ~/.pi/agent/models.json: { "providers": { "llama-cpp": { "baseUrl": "http://localhost:9931/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "softwareweaver/GLM-5.3-Uncensored-GGUF:BF16" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Docker Model Runner
How to use softwareweaver/GLM-5.3-Uncensored-GGUF with Docker Model Runner:
docker model run hf.co/softwareweaver/GLM-5.3-Uncensored-GGUF:BF16
- Lemonade
How to use softwareweaver/GLM-5.3-Uncensored-GGUF with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull softwareweaver/GLM-5.3-Uncensored-GGUF:BF16
Run and chat with the model
lemonade run user.GLM-5.3-Uncensored-GGUF-BF16
List all available models
lemonade list
- Hermes Agent
How to use softwareweaver/GLM-5.3-Uncensored-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 softwareweaver/GLM-5.3-Uncensored-GGUF:BF16
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://127.0.0.1:9931/v1 hermes config set model.default softwareweaver/GLM-5.3-Uncensored-GGUF:BF16
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use softwareweaver/GLM-5.3-Uncensored-GGUF with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf softwareweaver/GLM-5.3-Uncensored-GGUF:BF16
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://127.0.0.1:9931/v1 \ --custom-model-id "softwareweaver/GLM-5.3-Uncensored-GGUF:BF16" \ --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"
Add files using upload-large-folder tool
Browse files- .gitattributes +27 -0
- Q4_K_M/GLM-5.3-UNCENSORED-Q4_K_M-00001-of-00027.gguf +3 -0
- Q4_K_M/GLM-5.3-UNCENSORED-Q4_K_M-00002-of-00027.gguf +3 -0
- Q4_K_M/GLM-5.3-UNCENSORED-Q4_K_M-00003-of-00027.gguf +3 -0
- Q4_K_M/GLM-5.3-UNCENSORED-Q4_K_M-00004-of-00027.gguf +3 -0
- Q4_K_M/GLM-5.3-UNCENSORED-Q4_K_M-00005-of-00027.gguf +3 -0
- Q4_K_M/GLM-5.3-UNCENSORED-Q4_K_M-00006-of-00027.gguf +3 -0
- Q4_K_M/GLM-5.3-UNCENSORED-Q4_K_M-00007-of-00027.gguf +3 -0
- Q4_K_M/GLM-5.3-UNCENSORED-Q4_K_M-00008-of-00027.gguf +3 -0
- Q4_K_M/GLM-5.3-UNCENSORED-Q4_K_M-00009-of-00027.gguf +3 -0
- Q4_K_M/GLM-5.3-UNCENSORED-Q4_K_M-00010-of-00027.gguf +3 -0
- Q4_K_M/GLM-5.3-UNCENSORED-Q4_K_M-00011-of-00027.gguf +3 -0
- Q4_K_M/GLM-5.3-UNCENSORED-Q4_K_M-00012-of-00027.gguf +3 -0
- Q4_K_M/GLM-5.3-UNCENSORED-Q4_K_M-00013-of-00027.gguf +3 -0
- Q4_K_M/GLM-5.3-UNCENSORED-Q4_K_M-00014-of-00027.gguf +3 -0
- Q4_K_M/GLM-5.3-UNCENSORED-Q4_K_M-00015-of-00027.gguf +3 -0
- Q4_K_M/GLM-5.3-UNCENSORED-Q4_K_M-00016-of-00027.gguf +3 -0
- Q4_K_M/GLM-5.3-UNCENSORED-Q4_K_M-00017-of-00027.gguf +3 -0
- Q4_K_M/GLM-5.3-UNCENSORED-Q4_K_M-00018-of-00027.gguf +3 -0
- Q4_K_M/GLM-5.3-UNCENSORED-Q4_K_M-00019-of-00027.gguf +3 -0
- Q4_K_M/GLM-5.3-UNCENSORED-Q4_K_M-00020-of-00027.gguf +3 -0
- Q4_K_M/GLM-5.3-UNCENSORED-Q4_K_M-00021-of-00027.gguf +3 -0
- Q4_K_M/GLM-5.3-UNCENSORED-Q4_K_M-00022-of-00027.gguf +3 -0
- Q4_K_M/GLM-5.3-UNCENSORED-Q4_K_M-00023-of-00027.gguf +3 -0
- Q4_K_M/GLM-5.3-UNCENSORED-Q4_K_M-00024-of-00027.gguf +3 -0
- Q4_K_M/GLM-5.3-UNCENSORED-Q4_K_M-00025-of-00027.gguf +3 -0
- Q4_K_M/GLM-5.3-UNCENSORED-Q4_K_M-00026-of-00027.gguf +3 -0
- Q4_K_M/GLM-5.3-UNCENSORED-Q4_K_M-00027-of-00027.gguf +3 -0
- README.md +28 -7
.gitattributes
CHANGED
|
@@ -33,3 +33,30 @@ 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 |
+
Q4_K_M/GLM-5.3-UNCENSORED-Q4_K_M-00027-of-00027.gguf filter=lfs diff=lfs merge=lfs -text
|
| 37 |
+
Q4_K_M/GLM-5.3-UNCENSORED-Q4_K_M-00026-of-00027.gguf filter=lfs diff=lfs merge=lfs -text
|
| 38 |
+
Q4_K_M/GLM-5.3-UNCENSORED-Q4_K_M-00025-of-00027.gguf filter=lfs diff=lfs merge=lfs -text
|
| 39 |
+
Q4_K_M/GLM-5.3-UNCENSORED-Q4_K_M-00017-of-00027.gguf filter=lfs diff=lfs merge=lfs -text
|
| 40 |
+
Q4_K_M/GLM-5.3-UNCENSORED-Q4_K_M-00014-of-00027.gguf filter=lfs diff=lfs merge=lfs -text
|
| 41 |
+
Q4_K_M/GLM-5.3-UNCENSORED-Q4_K_M-00023-of-00027.gguf filter=lfs diff=lfs merge=lfs -text
|
| 42 |
+
Q4_K_M/GLM-5.3-UNCENSORED-Q4_K_M-00024-of-00027.gguf filter=lfs diff=lfs merge=lfs -text
|
| 43 |
+
Q4_K_M/GLM-5.3-UNCENSORED-Q4_K_M-00008-of-00027.gguf filter=lfs diff=lfs merge=lfs -text
|
| 44 |
+
Q4_K_M/GLM-5.3-UNCENSORED-Q4_K_M-00022-of-00027.gguf filter=lfs diff=lfs merge=lfs -text
|
| 45 |
+
Q4_K_M/GLM-5.3-UNCENSORED-Q4_K_M-00005-of-00027.gguf filter=lfs diff=lfs merge=lfs -text
|
| 46 |
+
Q4_K_M/GLM-5.3-UNCENSORED-Q4_K_M-00007-of-00027.gguf filter=lfs diff=lfs merge=lfs -text
|
| 47 |
+
Q4_K_M/GLM-5.3-UNCENSORED-Q4_K_M-00015-of-00027.gguf filter=lfs diff=lfs merge=lfs -text
|
| 48 |
+
Q4_K_M/GLM-5.3-UNCENSORED-Q4_K_M-00021-of-00027.gguf filter=lfs diff=lfs merge=lfs -text
|
| 49 |
+
Q4_K_M/GLM-5.3-UNCENSORED-Q4_K_M-00002-of-00027.gguf filter=lfs diff=lfs merge=lfs -text
|
| 50 |
+
Q4_K_M/GLM-5.3-UNCENSORED-Q4_K_M-00010-of-00027.gguf filter=lfs diff=lfs merge=lfs -text
|
| 51 |
+
Q4_K_M/GLM-5.3-UNCENSORED-Q4_K_M-00016-of-00027.gguf filter=lfs diff=lfs merge=lfs -text
|
| 52 |
+
Q4_K_M/GLM-5.3-UNCENSORED-Q4_K_M-00018-of-00027.gguf filter=lfs diff=lfs merge=lfs -text
|
| 53 |
+
Q4_K_M/GLM-5.3-UNCENSORED-Q4_K_M-00019-of-00027.gguf filter=lfs diff=lfs merge=lfs -text
|
| 54 |
+
Q4_K_M/GLM-5.3-UNCENSORED-Q4_K_M-00009-of-00027.gguf filter=lfs diff=lfs merge=lfs -text
|
| 55 |
+
Q4_K_M/GLM-5.3-UNCENSORED-Q4_K_M-00013-of-00027.gguf filter=lfs diff=lfs merge=lfs -text
|
| 56 |
+
Q4_K_M/GLM-5.3-UNCENSORED-Q4_K_M-00003-of-00027.gguf filter=lfs diff=lfs merge=lfs -text
|
| 57 |
+
Q4_K_M/GLM-5.3-UNCENSORED-Q4_K_M-00001-of-00027.gguf filter=lfs diff=lfs merge=lfs -text
|
| 58 |
+
Q4_K_M/GLM-5.3-UNCENSORED-Q4_K_M-00012-of-00027.gguf filter=lfs diff=lfs merge=lfs -text
|
| 59 |
+
Q4_K_M/GLM-5.3-UNCENSORED-Q4_K_M-00011-of-00027.gguf filter=lfs diff=lfs merge=lfs -text
|
| 60 |
+
Q4_K_M/GLM-5.3-UNCENSORED-Q4_K_M-00020-of-00027.gguf filter=lfs diff=lfs merge=lfs -text
|
| 61 |
+
Q4_K_M/GLM-5.3-UNCENSORED-Q4_K_M-00004-of-00027.gguf filter=lfs diff=lfs merge=lfs -text
|
| 62 |
+
Q4_K_M/GLM-5.3-UNCENSORED-Q4_K_M-00006-of-00027.gguf filter=lfs diff=lfs merge=lfs -text
|
Q4_K_M/GLM-5.3-UNCENSORED-Q4_K_M-00001-of-00027.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ffe96aa0be027792ad5a7262ba463271d31f9fa7a281c40d15168c15482c4498
|
| 3 |
+
size 17590583840
|
Q4_K_M/GLM-5.3-UNCENSORED-Q4_K_M-00002-of-00027.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3d44e03d7c9f4110d0345792613b867c9323542b5ac6bd51450d2f1b5037eee1
|
| 3 |
+
size 16524732064
|
Q4_K_M/GLM-5.3-UNCENSORED-Q4_K_M-00003-of-00027.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7036770bb832ff521523de064a36f795a09f27b78a97689184d59042de5363a2
|
| 3 |
+
size 17510033248
|
Q4_K_M/GLM-5.3-UNCENSORED-Q4_K_M-00004-of-00027.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:131f250f6dd36c0cb64103135bc07b9376499285ba5226e5cd3e8c0073d9550b
|
| 3 |
+
size 17504760352
|
Q4_K_M/GLM-5.3-UNCENSORED-Q4_K_M-00005-of-00027.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:476851f18cb822800ff5215fba42464edc8d93701f5c741123284546f0bf29d6
|
| 3 |
+
size 17510033280
|
Q4_K_M/GLM-5.3-UNCENSORED-Q4_K_M-00006-of-00027.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3889c1ce02796501b16b6ef917390c7a850c8922806f1b794fdd96fc0508c955
|
| 3 |
+
size 17510033280
|
Q4_K_M/GLM-5.3-UNCENSORED-Q4_K_M-00007-of-00027.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:32779b9d6a6f636840a9388c5dd62537f022e2432b55e45bb033bbd4220792f4
|
| 3 |
+
size 17510033280
|
Q4_K_M/GLM-5.3-UNCENSORED-Q4_K_M-00008-of-00027.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1c00642221061a927958c485f8db2686f6608ddfe7aab93d9495b42df253aa50
|
| 3 |
+
size 17504760352
|
Q4_K_M/GLM-5.3-UNCENSORED-Q4_K_M-00009-of-00027.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b28d508c83700810ec778fff92ded0b9d44db446b802f04578199a466ae0f842
|
| 3 |
+
size 17510033280
|
Q4_K_M/GLM-5.3-UNCENSORED-Q4_K_M-00010-of-00027.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fd5bb3dc27544a636a69a387405f9a6d0f0716ed637bdbb84a29cfd1473fc9d8
|
| 3 |
+
size 17510033280
|
Q4_K_M/GLM-5.3-UNCENSORED-Q4_K_M-00011-of-00027.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:46335192ec2463bf4959731ed33ed7d88a61458f981f2adedd69c6f7b2d3e45f
|
| 3 |
+
size 17510033280
|
Q4_K_M/GLM-5.3-UNCENSORED-Q4_K_M-00012-of-00027.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d0b187ce8a34559b634083338ff5e37ae5e50f7fcba32ebaa1ec3bfbb204a935
|
| 3 |
+
size 17504760352
|
Q4_K_M/GLM-5.3-UNCENSORED-Q4_K_M-00013-of-00027.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9ff7701a78648ed6004bb7aa62755efd76ab6e49529a479d8a20976075abab50
|
| 3 |
+
size 17510033280
|
Q4_K_M/GLM-5.3-UNCENSORED-Q4_K_M-00014-of-00027.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:36464e7a8d2420c70be35b93d950b341818c3df4bebed3a6c6eab54db82b003f
|
| 3 |
+
size 17510033280
|
Q4_K_M/GLM-5.3-UNCENSORED-Q4_K_M-00015-of-00027.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d177c3be887d3ee502d43c3a481cc5a7c7801a8aa16d66770a51dc7fe5506aac
|
| 3 |
+
size 17510033280
|
Q4_K_M/GLM-5.3-UNCENSORED-Q4_K_M-00016-of-00027.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a3bb5d6f40e0e7f6adc70ad2d5a7d9591c31b59ec07ef73e291d26a22a2d2f97
|
| 3 |
+
size 17504760352
|
Q4_K_M/GLM-5.3-UNCENSORED-Q4_K_M-00017-of-00027.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2763d4bbe598ef21218180a3b5c7535adcce12cd54210a20ce61586ec3f3b612
|
| 3 |
+
size 17510033280
|
Q4_K_M/GLM-5.3-UNCENSORED-Q4_K_M-00018-of-00027.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f8392b0c409d5e25474f1788ca926438dcac9ebe1722865cfc6fe5fb439405d5
|
| 3 |
+
size 17510033280
|
Q4_K_M/GLM-5.3-UNCENSORED-Q4_K_M-00019-of-00027.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5e804e43f5eec6afef4cddb4e1f904ac9f38c03b590f73f22dec033efc64e496
|
| 3 |
+
size 17510033280
|
Q4_K_M/GLM-5.3-UNCENSORED-Q4_K_M-00020-of-00027.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:11ca508fec87df6d7702a8730f549705b31f69caff65ec9ad2b6537851c0b878
|
| 3 |
+
size 17504760352
|
Q4_K_M/GLM-5.3-UNCENSORED-Q4_K_M-00021-of-00027.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:44990d4c8fb959234b9a243ce7f1009ed263b558107d2f9ab894c52fef9b5dc3
|
| 3 |
+
size 17510033280
|
Q4_K_M/GLM-5.3-UNCENSORED-Q4_K_M-00022-of-00027.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b7dd12dc36fafa1dc7538ded8070e4231a055628ba946bb9e33169cf89ddbd1f
|
| 3 |
+
size 17510033280
|
Q4_K_M/GLM-5.3-UNCENSORED-Q4_K_M-00023-of-00027.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:66e2ea64c704825c1f808fab2821a521f15168b867ca8224f3035b9e5dee1fe2
|
| 3 |
+
size 17259529024
|
Q4_K_M/GLM-5.3-UNCENSORED-Q4_K_M-00024-of-00027.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d5f3682a2ecb530bfae40140ffcf3f5efd33883deaf1f9786c8b272787251a74
|
| 3 |
+
size 17352132192
|
Q4_K_M/GLM-5.3-UNCENSORED-Q4_K_M-00025-of-00027.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:094f06e2bc8c7f2b0092a89835d11cb68aebc2860eb993c28f67975efa1c04a6
|
| 3 |
+
size 16524732128
|
Q4_K_M/GLM-5.3-UNCENSORED-Q4_K_M-00026-of-00027.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f460b236a30e5ad4f007e98756cb7f5f74d3fe4aed78f24a8e1a200d614b5916
|
| 3 |
+
size 17259529024
|
Q4_K_M/GLM-5.3-UNCENSORED-Q4_K_M-00027-of-00027.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8b0c6c36c971ec6a15cfcb31b2643c5d94295dda4abb7c76ecc9b62da78f42da
|
| 3 |
+
size 1866831680
|
README.md
CHANGED
|
@@ -1,8 +1,29 @@
|
|
| 1 |
---
|
| 2 |
-
|
| 3 |
-
|
| 4 |
-
|
| 5 |
-
|
| 6 |
-
|
| 7 |
-
-
|
| 8 |
-
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
+
license: mit
|
| 3 |
+
base_model: dealignai/GLM-5.3-UNCENSORED-FP8
|
| 4 |
+
pipeline_tag: text-generation
|
| 5 |
+
library_name: gguf
|
| 6 |
+
tags:
|
| 7 |
+
- gguf
|
| 8 |
+
- glm
|
| 9 |
+
- moe
|
| 10 |
+
- quantized
|
| 11 |
+
---
|
| 12 |
+
|
| 13 |
+
# GLM-5.3 Uncensored GGUF
|
| 14 |
+
|
| 15 |
+
Q4_K_M GGUF converted from [dealignai/GLM-5.3-UNCENSORED-FP8](https://huggingface.co/dealignai/GLM-5.3-UNCENSORED-FP8).
|
| 16 |
+
|
| 17 |
+
The source is a 753B-parameter mixture-of-experts model. The source revision used is `12170112d07e50d7dbe8e5ca1691f4fd8c1179e1`.
|
| 18 |
+
|
| 19 |
+
## Files
|
| 20 |
+
|
| 21 |
+
The `Q4_K_M/` folder contains 27 GGUF shards totaling approximately 454.55 GB. Every shard is below 20 GB. Download every shard into the same directory and point a compatible llama.cpp runtime at `GLM-5.3-UNCENSORED-Q4_K_M-00001-of-00027.gguf`.
|
| 22 |
+
|
| 23 |
+
## Conversion
|
| 24 |
+
|
| 25 |
+
The FP8 weights were dequantized using their saved scales to a BF16 GGUF, then quantized with llama.cpp to Q4_K_M without an importance matrix. The multi-token prediction (MTP/NextN) layer is retained. Splitting does not add another quantization step.
|
| 26 |
+
|
| 27 |
+
This conversion cannot restore precision already lost in the FP8 source. GGUF structure and MTP tensor presence are checked by the conversion pipeline; inference quality and speculative decoding performance have not been benchmarked for this release.
|
| 28 |
+
|
| 29 |
+
See the source model card for provenance, behavior, and usage notes. Credit for the modified source weights belongs to dealignai; this repository provides the GGUF conversion.
|