Image-Text-to-Text
Transformers
GGUF
PyTorch
English
multimodal
action
agent
computer use
gui agents
Mixture of Experts
conversational
Instructions to use Hcompany/Holo-3.1-35B-A3B-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Hcompany/Holo-3.1-35B-A3B-GGUF with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="Hcompany/Holo-3.1-35B-A3B-GGUF") messages = [ { "role": "user", "content": [ {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"}, {"type": "text", "text": "What animal is on the candy?"} ] }, ] pipe(text=messages)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Hcompany/Holo-3.1-35B-A3B-GGUF", dtype="auto") - llama-cpp-python
How to use Hcompany/Holo-3.1-35B-A3B-GGUF with llama-cpp-python:
# !pip install llama-cpp-python from llama_cpp import Llama llm = Llama.from_pretrained( repo_id="Hcompany/Holo-3.1-35B-A3B-GGUF", filename="imatrix.gguf", )
llm.create_chat_completion( messages = [ { "role": "user", "content": [ { "type": "text", "text": "Describe this image in one sentence." }, { "type": "image_url", "image_url": { "url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg" } } ] } ] ) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use Hcompany/Holo-3.1-35B-A3B-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 Hcompany/Holo-3.1-35B-A3B-GGUF:Q4_K_M # Run inference directly in the terminal: llama cli -hf Hcompany/Holo-3.1-35B-A3B-GGUF:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf Hcompany/Holo-3.1-35B-A3B-GGUF:Q4_K_M # Run inference directly in the terminal: llama cli -hf Hcompany/Holo-3.1-35B-A3B-GGUF:Q4_K_M
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 Hcompany/Holo-3.1-35B-A3B-GGUF:Q4_K_M # Run inference directly in the terminal: ./llama-cli -hf Hcompany/Holo-3.1-35B-A3B-GGUF:Q4_K_M
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 Hcompany/Holo-3.1-35B-A3B-GGUF:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama-cli -hf Hcompany/Holo-3.1-35B-A3B-GGUF:Q4_K_M
Use Docker
docker model run hf.co/Hcompany/Holo-3.1-35B-A3B-GGUF:Q4_K_M
- LM Studio
- Jan
- vLLM
How to use Hcompany/Holo-3.1-35B-A3B-GGUF with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Hcompany/Holo-3.1-35B-A3B-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": "Hcompany/Holo-3.1-35B-A3B-GGUF", "messages": [ { "role": "user", "content": [ { "type": "text", "text": "Describe this image in one sentence." }, { "type": "image_url", "image_url": { "url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg" } } ] } ] }'Use Docker
docker model run hf.co/Hcompany/Holo-3.1-35B-A3B-GGUF:Q4_K_M
- SGLang
How to use Hcompany/Holo-3.1-35B-A3B-GGUF with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "Hcompany/Holo-3.1-35B-A3B-GGUF" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Hcompany/Holo-3.1-35B-A3B-GGUF", "messages": [ { "role": "user", "content": [ { "type": "text", "text": "Describe this image in one sentence." }, { "type": "image_url", "image_url": { "url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg" } } ] } ] }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "Hcompany/Holo-3.1-35B-A3B-GGUF" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Hcompany/Holo-3.1-35B-A3B-GGUF", "messages": [ { "role": "user", "content": [ { "type": "text", "text": "Describe this image in one sentence." }, { "type": "image_url", "image_url": { "url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg" } } ] } ] }' - Ollama
How to use Hcompany/Holo-3.1-35B-A3B-GGUF with Ollama:
ollama run hf.co/Hcompany/Holo-3.1-35B-A3B-GGUF:Q4_K_M
- Unsloth Studio
How to use Hcompany/Holo-3.1-35B-A3B-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 Hcompany/Holo-3.1-35B-A3B-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 Hcompany/Holo-3.1-35B-A3B-GGUF to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for Hcompany/Holo-3.1-35B-A3B-GGUF to start chatting
- Pi
How to use Hcompany/Holo-3.1-35B-A3B-GGUF with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf Hcompany/Holo-3.1-35B-A3B-GGUF:Q4_K_M
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": "Hcompany/Holo-3.1-35B-A3B-GGUF:Q4_K_M" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Hermes Agent new
How to use Hcompany/Holo-3.1-35B-A3B-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 Hcompany/Holo-3.1-35B-A3B-GGUF:Q4_K_M
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 Hcompany/Holo-3.1-35B-A3B-GGUF:Q4_K_M
Run Hermes
hermes
- Atomic Chat new
- OpenClaw new
How to use Hcompany/Holo-3.1-35B-A3B-GGUF with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf Hcompany/Holo-3.1-35B-A3B-GGUF:Q4_K_M
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 "Hcompany/Holo-3.1-35B-A3B-GGUF:Q4_K_M" \ --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 Hcompany/Holo-3.1-35B-A3B-GGUF with Docker Model Runner:
docker model run hf.co/Hcompany/Holo-3.1-35B-A3B-GGUF:Q4_K_M
- Lemonade
How to use Hcompany/Holo-3.1-35B-A3B-GGUF with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull Hcompany/Holo-3.1-35B-A3B-GGUF:Q4_K_M
Run and chat with the model
lemonade run user.Holo-3.1-35B-A3B-GGUF-Q4_K_M
List all available models
lemonade list
Delete convert_mmproj.log
Browse files- convert_mmproj.log +0 -372
convert_mmproj.log
DELETED
|
@@ -1,372 +0,0 @@
|
|
| 1 |
-
INFO:hf-to-gguf:Loading model: source_model
|
| 2 |
-
INFO:hf-to-gguf:Model architecture: Qwen3_5MoeForConditionalGeneration
|
| 3 |
-
INFO:hf-to-gguf:gguf: loading model weight map from 'model.safetensors.index.json'
|
| 4 |
-
INFO:hf-to-gguf:gguf: indexing model part 'model-00001-of-00026.safetensors'
|
| 5 |
-
INFO:hf-to-gguf:gguf: indexing model part 'model-00002-of-00026.safetensors'
|
| 6 |
-
INFO:hf-to-gguf:gguf: indexing model part 'model-00003-of-00026.safetensors'
|
| 7 |
-
INFO:hf-to-gguf:gguf: indexing model part 'model-00004-of-00026.safetensors'
|
| 8 |
-
INFO:hf-to-gguf:gguf: indexing model part 'model-00005-of-00026.safetensors'
|
| 9 |
-
INFO:hf-to-gguf:gguf: indexing model part 'model-00006-of-00026.safetensors'
|
| 10 |
-
INFO:hf-to-gguf:gguf: indexing model part 'model-00007-of-00026.safetensors'
|
| 11 |
-
INFO:hf-to-gguf:gguf: indexing model part 'model-00008-of-00026.safetensors'
|
| 12 |
-
INFO:hf-to-gguf:gguf: indexing model part 'model-00009-of-00026.safetensors'
|
| 13 |
-
INFO:hf-to-gguf:gguf: indexing model part 'model-00010-of-00026.safetensors'
|
| 14 |
-
INFO:hf-to-gguf:gguf: indexing model part 'model-00011-of-00026.safetensors'
|
| 15 |
-
INFO:hf-to-gguf:gguf: indexing model part 'model-00012-of-00026.safetensors'
|
| 16 |
-
INFO:hf-to-gguf:gguf: indexing model part 'model-00013-of-00026.safetensors'
|
| 17 |
-
INFO:hf-to-gguf:gguf: indexing model part 'model-00014-of-00026.safetensors'
|
| 18 |
-
INFO:hf-to-gguf:gguf: indexing model part 'model-00015-of-00026.safetensors'
|
| 19 |
-
INFO:hf-to-gguf:gguf: indexing model part 'model-00016-of-00026.safetensors'
|
| 20 |
-
INFO:hf-to-gguf:gguf: indexing model part 'model-00017-of-00026.safetensors'
|
| 21 |
-
INFO:hf-to-gguf:gguf: indexing model part 'model-00018-of-00026.safetensors'
|
| 22 |
-
INFO:hf-to-gguf:gguf: indexing model part 'model-00019-of-00026.safetensors'
|
| 23 |
-
INFO:hf-to-gguf:gguf: indexing model part 'model-00020-of-00026.safetensors'
|
| 24 |
-
INFO:hf-to-gguf:gguf: indexing model part 'model-00021-of-00026.safetensors'
|
| 25 |
-
INFO:hf-to-gguf:gguf: indexing model part 'model-00022-of-00026.safetensors'
|
| 26 |
-
INFO:hf-to-gguf:gguf: indexing model part 'model-00023-of-00026.safetensors'
|
| 27 |
-
INFO:hf-to-gguf:gguf: indexing model part 'model-00024-of-00026.safetensors'
|
| 28 |
-
INFO:hf-to-gguf:gguf: indexing model part 'model-00025-of-00026.safetensors'
|
| 29 |
-
INFO:hf-to-gguf:gguf: indexing model part 'model-00026-of-00026.safetensors'
|
| 30 |
-
INFO:gguf.gguf_writer:gguf: This GGUF file is for Little Endian only
|
| 31 |
-
INFO:hf-to-gguf:Exporting model...
|
| 32 |
-
INFO:hf-to-gguf:v.blk.0.ffn_up.weight, torch.bfloat16 --> F16, shape = {1152, 4304}
|
| 33 |
-
INFO:hf-to-gguf:v.blk.0.ffn_down.weight, torch.bfloat16 --> F16, shape = {4304, 1152}
|
| 34 |
-
INFO:hf-to-gguf:v.blk.1.ffn_up.weight, torch.bfloat16 --> F16, shape = {1152, 4304}
|
| 35 |
-
INFO:hf-to-gguf:v.blk.1.ffn_down.weight, torch.bfloat16 --> F16, shape = {4304, 1152}
|
| 36 |
-
INFO:hf-to-gguf:v.blk.10.ffn_up.weight, torch.bfloat16 --> F16, shape = {1152, 4304}
|
| 37 |
-
INFO:hf-to-gguf:v.blk.10.ffn_down.weight, torch.bfloat16 --> F16, shape = {4304, 1152}
|
| 38 |
-
INFO:hf-to-gguf:v.blk.11.ffn_up.weight, torch.bfloat16 --> F16, shape = {1152, 4304}
|
| 39 |
-
INFO:hf-to-gguf:v.blk.11.ffn_down.weight, torch.bfloat16 --> F16, shape = {4304, 1152}
|
| 40 |
-
INFO:hf-to-gguf:v.blk.12.ffn_up.weight, torch.bfloat16 --> F16, shape = {1152, 4304}
|
| 41 |
-
INFO:hf-to-gguf:v.blk.12.ffn_down.weight, torch.bfloat16 --> F16, shape = {4304, 1152}
|
| 42 |
-
INFO:hf-to-gguf:mm.0.weight, torch.bfloat16 --> F16, shape = {4608, 4608}
|
| 43 |
-
INFO:hf-to-gguf:mm.2.weight, torch.bfloat16 --> F16, shape = {4608, 2048}
|
| 44 |
-
INFO:hf-to-gguf:v.blk.0.attn_out.bias, torch.bfloat16 --> F32, shape = {1152}
|
| 45 |
-
INFO:hf-to-gguf:v.blk.0.attn_out.weight, torch.bfloat16 --> F16, shape = {1152, 1152}
|
| 46 |
-
INFO:hf-to-gguf:v.blk.0.attn_qkv.bias, torch.bfloat16 --> F32, shape = {3456}
|
| 47 |
-
INFO:hf-to-gguf:v.blk.0.attn_qkv.weight, torch.bfloat16 --> F16, shape = {1152, 3456}
|
| 48 |
-
INFO:hf-to-gguf:v.blk.0.ffn_up.bias, torch.bfloat16 --> F32, shape = {4304}
|
| 49 |
-
INFO:hf-to-gguf:v.blk.0.ffn_down.bias, torch.bfloat16 --> F32, shape = {1152}
|
| 50 |
-
INFO:hf-to-gguf:v.blk.0.ln1.bias, torch.bfloat16 --> F32, shape = {1152}
|
| 51 |
-
INFO:hf-to-gguf:v.blk.0.ln1.weight, torch.bfloat16 --> F32, shape = {1152}
|
| 52 |
-
INFO:hf-to-gguf:v.blk.0.ln2.bias, torch.bfloat16 --> F32, shape = {1152}
|
| 53 |
-
INFO:hf-to-gguf:v.blk.0.ln2.weight, torch.bfloat16 --> F32, shape = {1152}
|
| 54 |
-
INFO:hf-to-gguf:v.blk.1.attn_out.bias, torch.bfloat16 --> F32, shape = {1152}
|
| 55 |
-
INFO:hf-to-gguf:v.blk.1.attn_out.weight, torch.bfloat16 --> F16, shape = {1152, 1152}
|
| 56 |
-
INFO:hf-to-gguf:v.blk.1.attn_qkv.bias, torch.bfloat16 --> F32, shape = {3456}
|
| 57 |
-
INFO:hf-to-gguf:v.blk.1.attn_qkv.weight, torch.bfloat16 --> F16, shape = {1152, 3456}
|
| 58 |
-
INFO:hf-to-gguf:v.blk.1.ffn_up.bias, torch.bfloat16 --> F32, shape = {4304}
|
| 59 |
-
INFO:hf-to-gguf:v.blk.1.ffn_down.bias, torch.bfloat16 --> F32, shape = {1152}
|
| 60 |
-
INFO:hf-to-gguf:v.blk.1.ln1.bias, torch.bfloat16 --> F32, shape = {1152}
|
| 61 |
-
INFO:hf-to-gguf:v.blk.1.ln1.weight, torch.bfloat16 --> F32, shape = {1152}
|
| 62 |
-
INFO:hf-to-gguf:v.blk.1.ln2.bias, torch.bfloat16 --> F32, shape = {1152}
|
| 63 |
-
INFO:hf-to-gguf:v.blk.1.ln2.weight, torch.bfloat16 --> F32, shape = {1152}
|
| 64 |
-
INFO:hf-to-gguf:v.blk.10.attn_out.bias, torch.bfloat16 --> F32, shape = {1152}
|
| 65 |
-
INFO:hf-to-gguf:v.blk.10.attn_out.weight, torch.bfloat16 --> F16, shape = {1152, 1152}
|
| 66 |
-
INFO:hf-to-gguf:v.blk.10.attn_qkv.bias, torch.bfloat16 --> F32, shape = {3456}
|
| 67 |
-
INFO:hf-to-gguf:v.blk.10.attn_qkv.weight, torch.bfloat16 --> F16, shape = {1152, 3456}
|
| 68 |
-
INFO:hf-to-gguf:v.blk.10.ffn_up.bias, torch.bfloat16 --> F32, shape = {4304}
|
| 69 |
-
INFO:hf-to-gguf:v.blk.10.ffn_down.bias, torch.bfloat16 --> F32, shape = {1152}
|
| 70 |
-
INFO:hf-to-gguf:v.blk.10.ln1.bias, torch.bfloat16 --> F32, shape = {1152}
|
| 71 |
-
INFO:hf-to-gguf:v.blk.10.ln1.weight, torch.bfloat16 --> F32, shape = {1152}
|
| 72 |
-
INFO:hf-to-gguf:v.blk.10.ln2.bias, torch.bfloat16 --> F32, shape = {1152}
|
| 73 |
-
INFO:hf-to-gguf:v.blk.10.ln2.weight, torch.bfloat16 --> F32, shape = {1152}
|
| 74 |
-
INFO:hf-to-gguf:v.blk.11.attn_out.bias, torch.bfloat16 --> F32, shape = {1152}
|
| 75 |
-
INFO:hf-to-gguf:v.blk.11.attn_out.weight, torch.bfloat16 --> F16, shape = {1152, 1152}
|
| 76 |
-
INFO:hf-to-gguf:v.blk.11.attn_qkv.bias, torch.bfloat16 --> F32, shape = {3456}
|
| 77 |
-
INFO:hf-to-gguf:v.blk.11.attn_qkv.weight, torch.bfloat16 --> F16, shape = {1152, 3456}
|
| 78 |
-
INFO:hf-to-gguf:v.blk.11.ffn_up.bias, torch.bfloat16 --> F32, shape = {4304}
|
| 79 |
-
INFO:hf-to-gguf:v.blk.11.ffn_down.bias, torch.bfloat16 --> F32, shape = {1152}
|
| 80 |
-
INFO:hf-to-gguf:v.blk.11.ln1.bias, torch.bfloat16 --> F32, shape = {1152}
|
| 81 |
-
INFO:hf-to-gguf:v.blk.11.ln1.weight, torch.bfloat16 --> F32, shape = {1152}
|
| 82 |
-
INFO:hf-to-gguf:v.blk.11.ln2.bias, torch.bfloat16 --> F32, shape = {1152}
|
| 83 |
-
INFO:hf-to-gguf:v.blk.11.ln2.weight, torch.bfloat16 --> F32, shape = {1152}
|
| 84 |
-
INFO:hf-to-gguf:v.blk.12.attn_out.bias, torch.bfloat16 --> F32, shape = {1152}
|
| 85 |
-
INFO:hf-to-gguf:v.blk.12.attn_out.weight, torch.bfloat16 --> F16, shape = {1152, 1152}
|
| 86 |
-
INFO:hf-to-gguf:v.blk.12.attn_qkv.bias, torch.bfloat16 --> F32, shape = {3456}
|
| 87 |
-
INFO:hf-to-gguf:v.blk.12.attn_qkv.weight, torch.bfloat16 --> F16, shape = {1152, 3456}
|
| 88 |
-
INFO:hf-to-gguf:v.blk.12.ffn_up.bias, torch.bfloat16 --> F32, shape = {4304}
|
| 89 |
-
INFO:hf-to-gguf:v.blk.12.ffn_down.bias, torch.bfloat16 --> F32, shape = {1152}
|
| 90 |
-
INFO:hf-to-gguf:v.blk.12.ln1.bias, torch.bfloat16 --> F32, shape = {1152}
|
| 91 |
-
INFO:hf-to-gguf:v.blk.12.ln1.weight, torch.bfloat16 --> F32, shape = {1152}
|
| 92 |
-
INFO:hf-to-gguf:v.blk.12.ln2.bias, torch.bfloat16 --> F32, shape = {1152}
|
| 93 |
-
INFO:hf-to-gguf:v.blk.12.ln2.weight, torch.bfloat16 --> F32, shape = {1152}
|
| 94 |
-
INFO:hf-to-gguf:v.blk.13.attn_out.bias, torch.bfloat16 --> F32, shape = {1152}
|
| 95 |
-
INFO:hf-to-gguf:v.blk.13.attn_out.weight, torch.bfloat16 --> F16, shape = {1152, 1152}
|
| 96 |
-
INFO:hf-to-gguf:v.blk.13.attn_qkv.bias, torch.bfloat16 --> F32, shape = {3456}
|
| 97 |
-
INFO:hf-to-gguf:v.blk.13.attn_qkv.weight, torch.bfloat16 --> F16, shape = {1152, 3456}
|
| 98 |
-
INFO:hf-to-gguf:v.blk.13.ffn_up.bias, torch.bfloat16 --> F32, shape = {4304}
|
| 99 |
-
INFO:hf-to-gguf:v.blk.13.ffn_up.weight, torch.bfloat16 --> F16, shape = {1152, 4304}
|
| 100 |
-
INFO:hf-to-gguf:v.blk.13.ffn_down.bias, torch.bfloat16 --> F32, shape = {1152}
|
| 101 |
-
INFO:hf-to-gguf:v.blk.13.ffn_down.weight, torch.bfloat16 --> F16, shape = {4304, 1152}
|
| 102 |
-
INFO:hf-to-gguf:v.blk.13.ln1.bias, torch.bfloat16 --> F32, shape = {1152}
|
| 103 |
-
INFO:hf-to-gguf:v.blk.13.ln1.weight, torch.bfloat16 --> F32, shape = {1152}
|
| 104 |
-
INFO:hf-to-gguf:v.blk.13.ln2.bias, torch.bfloat16 --> F32, shape = {1152}
|
| 105 |
-
INFO:hf-to-gguf:v.blk.13.ln2.weight, torch.bfloat16 --> F32, shape = {1152}
|
| 106 |
-
INFO:hf-to-gguf:v.blk.14.attn_out.bias, torch.bfloat16 --> F32, shape = {1152}
|
| 107 |
-
INFO:hf-to-gguf:v.blk.14.attn_out.weight, torch.bfloat16 --> F16, shape = {1152, 1152}
|
| 108 |
-
INFO:hf-to-gguf:v.blk.14.attn_qkv.bias, torch.bfloat16 --> F32, shape = {3456}
|
| 109 |
-
INFO:hf-to-gguf:v.blk.14.attn_qkv.weight, torch.bfloat16 --> F16, shape = {1152, 3456}
|
| 110 |
-
INFO:hf-to-gguf:v.blk.14.ffn_up.bias, torch.bfloat16 --> F32, shape = {4304}
|
| 111 |
-
INFO:hf-to-gguf:v.blk.14.ffn_up.weight, torch.bfloat16 --> F16, shape = {1152, 4304}
|
| 112 |
-
INFO:hf-to-gguf:v.blk.14.ffn_down.bias, torch.bfloat16 --> F32, shape = {1152}
|
| 113 |
-
INFO:hf-to-gguf:v.blk.14.ffn_down.weight, torch.bfloat16 --> F16, shape = {4304, 1152}
|
| 114 |
-
INFO:hf-to-gguf:v.blk.14.ln1.bias, torch.bfloat16 --> F32, shape = {1152}
|
| 115 |
-
INFO:hf-to-gguf:v.blk.14.ln1.weight, torch.bfloat16 --> F32, shape = {1152}
|
| 116 |
-
INFO:hf-to-gguf:v.blk.14.ln2.bias, torch.bfloat16 --> F32, shape = {1152}
|
| 117 |
-
INFO:hf-to-gguf:v.blk.14.ln2.weight, torch.bfloat16 --> F32, shape = {1152}
|
| 118 |
-
INFO:hf-to-gguf:v.blk.15.attn_out.bias, torch.bfloat16 --> F32, shape = {1152}
|
| 119 |
-
INFO:hf-to-gguf:v.blk.15.attn_out.weight, torch.bfloat16 --> F16, shape = {1152, 1152}
|
| 120 |
-
INFO:hf-to-gguf:v.blk.15.attn_qkv.bias, torch.bfloat16 --> F32, shape = {3456}
|
| 121 |
-
INFO:hf-to-gguf:v.blk.15.attn_qkv.weight, torch.bfloat16 --> F16, shape = {1152, 3456}
|
| 122 |
-
INFO:hf-to-gguf:v.blk.15.ffn_up.bias, torch.bfloat16 --> F32, shape = {4304}
|
| 123 |
-
INFO:hf-to-gguf:v.blk.15.ffn_up.weight, torch.bfloat16 --> F16, shape = {1152, 4304}
|
| 124 |
-
INFO:hf-to-gguf:v.blk.15.ffn_down.bias, torch.bfloat16 --> F32, shape = {1152}
|
| 125 |
-
INFO:hf-to-gguf:v.blk.15.ffn_down.weight, torch.bfloat16 --> F16, shape = {4304, 1152}
|
| 126 |
-
INFO:hf-to-gguf:v.blk.15.ln1.bias, torch.bfloat16 --> F32, shape = {1152}
|
| 127 |
-
INFO:hf-to-gguf:v.blk.15.ln1.weight, torch.bfloat16 --> F32, shape = {1152}
|
| 128 |
-
INFO:hf-to-gguf:v.blk.15.ln2.bias, torch.bfloat16 --> F32, shape = {1152}
|
| 129 |
-
INFO:hf-to-gguf:v.blk.15.ln2.weight, torch.bfloat16 --> F32, shape = {1152}
|
| 130 |
-
INFO:hf-to-gguf:v.blk.16.attn_out.bias, torch.bfloat16 --> F32, shape = {1152}
|
| 131 |
-
INFO:hf-to-gguf:v.blk.16.attn_out.weight, torch.bfloat16 --> F16, shape = {1152, 1152}
|
| 132 |
-
INFO:hf-to-gguf:v.blk.16.attn_qkv.bias, torch.bfloat16 --> F32, shape = {3456}
|
| 133 |
-
INFO:hf-to-gguf:v.blk.16.attn_qkv.weight, torch.bfloat16 --> F16, shape = {1152, 3456}
|
| 134 |
-
INFO:hf-to-gguf:v.blk.16.ffn_up.bias, torch.bfloat16 --> F32, shape = {4304}
|
| 135 |
-
INFO:hf-to-gguf:v.blk.16.ffn_up.weight, torch.bfloat16 --> F16, shape = {1152, 4304}
|
| 136 |
-
INFO:hf-to-gguf:v.blk.16.ffn_down.bias, torch.bfloat16 --> F32, shape = {1152}
|
| 137 |
-
INFO:hf-to-gguf:v.blk.16.ffn_down.weight, torch.bfloat16 --> F16, shape = {4304, 1152}
|
| 138 |
-
INFO:hf-to-gguf:v.blk.16.ln1.bias, torch.bfloat16 --> F32, shape = {1152}
|
| 139 |
-
INFO:hf-to-gguf:v.blk.16.ln1.weight, torch.bfloat16 --> F32, shape = {1152}
|
| 140 |
-
INFO:hf-to-gguf:v.blk.16.ln2.bias, torch.bfloat16 --> F32, shape = {1152}
|
| 141 |
-
INFO:hf-to-gguf:v.blk.16.ln2.weight, torch.bfloat16 --> F32, shape = {1152}
|
| 142 |
-
INFO:hf-to-gguf:v.blk.17.attn_out.bias, torch.bfloat16 --> F32, shape = {1152}
|
| 143 |
-
INFO:hf-to-gguf:v.blk.17.attn_out.weight, torch.bfloat16 --> F16, shape = {1152, 1152}
|
| 144 |
-
INFO:hf-to-gguf:v.blk.17.attn_qkv.bias, torch.bfloat16 --> F32, shape = {3456}
|
| 145 |
-
INFO:hf-to-gguf:v.blk.17.attn_qkv.weight, torch.bfloat16 --> F16, shape = {1152, 3456}
|
| 146 |
-
INFO:hf-to-gguf:v.blk.17.ffn_up.bias, torch.bfloat16 --> F32, shape = {4304}
|
| 147 |
-
INFO:hf-to-gguf:v.blk.17.ffn_up.weight, torch.bfloat16 --> F16, shape = {1152, 4304}
|
| 148 |
-
INFO:hf-to-gguf:v.blk.17.ffn_down.bias, torch.bfloat16 --> F32, shape = {1152}
|
| 149 |
-
INFO:hf-to-gguf:v.blk.17.ffn_down.weight, torch.bfloat16 --> F16, shape = {4304, 1152}
|
| 150 |
-
INFO:hf-to-gguf:v.blk.17.ln1.bias, torch.bfloat16 --> F32, shape = {1152}
|
| 151 |
-
INFO:hf-to-gguf:v.blk.17.ln1.weight, torch.bfloat16 --> F32, shape = {1152}
|
| 152 |
-
INFO:hf-to-gguf:v.blk.17.ln2.bias, torch.bfloat16 --> F32, shape = {1152}
|
| 153 |
-
INFO:hf-to-gguf:v.blk.17.ln2.weight, torch.bfloat16 --> F32, shape = {1152}
|
| 154 |
-
INFO:hf-to-gguf:v.blk.18.attn_out.bias, torch.bfloat16 --> F32, shape = {1152}
|
| 155 |
-
INFO:hf-to-gguf:v.blk.18.attn_out.weight, torch.bfloat16 --> F16, shape = {1152, 1152}
|
| 156 |
-
INFO:hf-to-gguf:v.blk.18.attn_qkv.bias, torch.bfloat16 --> F32, shape = {3456}
|
| 157 |
-
INFO:hf-to-gguf:v.blk.18.attn_qkv.weight, torch.bfloat16 --> F16, shape = {1152, 3456}
|
| 158 |
-
INFO:hf-to-gguf:v.blk.18.ffn_up.bias, torch.bfloat16 --> F32, shape = {4304}
|
| 159 |
-
INFO:hf-to-gguf:v.blk.18.ffn_up.weight, torch.bfloat16 --> F16, shape = {1152, 4304}
|
| 160 |
-
INFO:hf-to-gguf:v.blk.18.ffn_down.bias, torch.bfloat16 --> F32, shape = {1152}
|
| 161 |
-
INFO:hf-to-gguf:v.blk.18.ffn_down.weight, torch.bfloat16 --> F16, shape = {4304, 1152}
|
| 162 |
-
INFO:hf-to-gguf:v.blk.18.ln1.bias, torch.bfloat16 --> F32, shape = {1152}
|
| 163 |
-
INFO:hf-to-gguf:v.blk.18.ln1.weight, torch.bfloat16 --> F32, shape = {1152}
|
| 164 |
-
INFO:hf-to-gguf:v.blk.18.ln2.bias, torch.bfloat16 --> F32, shape = {1152}
|
| 165 |
-
INFO:hf-to-gguf:v.blk.18.ln2.weight, torch.bfloat16 --> F32, shape = {1152}
|
| 166 |
-
INFO:hf-to-gguf:v.blk.19.attn_out.bias, torch.bfloat16 --> F32, shape = {1152}
|
| 167 |
-
INFO:hf-to-gguf:v.blk.19.attn_out.weight, torch.bfloat16 --> F16, shape = {1152, 1152}
|
| 168 |
-
INFO:hf-to-gguf:v.blk.19.attn_qkv.bias, torch.bfloat16 --> F32, shape = {3456}
|
| 169 |
-
INFO:hf-to-gguf:v.blk.19.attn_qkv.weight, torch.bfloat16 --> F16, shape = {1152, 3456}
|
| 170 |
-
INFO:hf-to-gguf:v.blk.19.ffn_up.bias, torch.bfloat16 --> F32, shape = {4304}
|
| 171 |
-
INFO:hf-to-gguf:v.blk.19.ffn_up.weight, torch.bfloat16 --> F16, shape = {1152, 4304}
|
| 172 |
-
INFO:hf-to-gguf:v.blk.19.ffn_down.bias, torch.bfloat16 --> F32, shape = {1152}
|
| 173 |
-
INFO:hf-to-gguf:v.blk.19.ffn_down.weight, torch.bfloat16 --> F16, shape = {4304, 1152}
|
| 174 |
-
INFO:hf-to-gguf:v.blk.19.ln1.bias, torch.bfloat16 --> F32, shape = {1152}
|
| 175 |
-
INFO:hf-to-gguf:v.blk.19.ln1.weight, torch.bfloat16 --> F32, shape = {1152}
|
| 176 |
-
INFO:hf-to-gguf:v.blk.19.ln2.bias, torch.bfloat16 --> F32, shape = {1152}
|
| 177 |
-
INFO:hf-to-gguf:v.blk.19.ln2.weight, torch.bfloat16 --> F32, shape = {1152}
|
| 178 |
-
INFO:hf-to-gguf:v.blk.2.attn_out.bias, torch.bfloat16 --> F32, shape = {1152}
|
| 179 |
-
INFO:hf-to-gguf:v.blk.2.attn_out.weight, torch.bfloat16 --> F16, shape = {1152, 1152}
|
| 180 |
-
INFO:hf-to-gguf:v.blk.2.attn_qkv.bias, torch.bfloat16 --> F32, shape = {3456}
|
| 181 |
-
INFO:hf-to-gguf:v.blk.2.attn_qkv.weight, torch.bfloat16 --> F16, shape = {1152, 3456}
|
| 182 |
-
INFO:hf-to-gguf:v.blk.2.ffn_up.bias, torch.bfloat16 --> F32, shape = {4304}
|
| 183 |
-
INFO:hf-to-gguf:v.blk.2.ffn_up.weight, torch.bfloat16 --> F16, shape = {1152, 4304}
|
| 184 |
-
INFO:hf-to-gguf:v.blk.2.ffn_down.bias, torch.bfloat16 --> F32, shape = {1152}
|
| 185 |
-
INFO:hf-to-gguf:v.blk.2.ffn_down.weight, torch.bfloat16 --> F16, shape = {4304, 1152}
|
| 186 |
-
INFO:hf-to-gguf:v.blk.2.ln1.bias, torch.bfloat16 --> F32, shape = {1152}
|
| 187 |
-
INFO:hf-to-gguf:v.blk.2.ln1.weight, torch.bfloat16 --> F32, shape = {1152}
|
| 188 |
-
INFO:hf-to-gguf:v.blk.2.ln2.bias, torch.bfloat16 --> F32, shape = {1152}
|
| 189 |
-
INFO:hf-to-gguf:v.blk.2.ln2.weight, torch.bfloat16 --> F32, shape = {1152}
|
| 190 |
-
INFO:hf-to-gguf:v.blk.20.attn_out.bias, torch.bfloat16 --> F32, shape = {1152}
|
| 191 |
-
INFO:hf-to-gguf:v.blk.20.attn_out.weight, torch.bfloat16 --> F16, shape = {1152, 1152}
|
| 192 |
-
INFO:hf-to-gguf:v.blk.20.attn_qkv.bias, torch.bfloat16 --> F32, shape = {3456}
|
| 193 |
-
INFO:hf-to-gguf:v.blk.20.attn_qkv.weight, torch.bfloat16 --> F16, shape = {1152, 3456}
|
| 194 |
-
INFO:hf-to-gguf:v.blk.20.ffn_up.bias, torch.bfloat16 --> F32, shape = {4304}
|
| 195 |
-
INFO:hf-to-gguf:v.blk.20.ffn_up.weight, torch.bfloat16 --> F16, shape = {1152, 4304}
|
| 196 |
-
INFO:hf-to-gguf:v.blk.20.ffn_down.bias, torch.bfloat16 --> F32, shape = {1152}
|
| 197 |
-
INFO:hf-to-gguf:v.blk.20.ffn_down.weight, torch.bfloat16 --> F16, shape = {4304, 1152}
|
| 198 |
-
INFO:hf-to-gguf:v.blk.20.ln1.bias, torch.bfloat16 --> F32, shape = {1152}
|
| 199 |
-
INFO:hf-to-gguf:v.blk.20.ln1.weight, torch.bfloat16 --> F32, shape = {1152}
|
| 200 |
-
INFO:hf-to-gguf:v.blk.20.ln2.bias, torch.bfloat16 --> F32, shape = {1152}
|
| 201 |
-
INFO:hf-to-gguf:v.blk.20.ln2.weight, torch.bfloat16 --> F32, shape = {1152}
|
| 202 |
-
INFO:hf-to-gguf:v.blk.21.attn_out.bias, torch.bfloat16 --> F32, shape = {1152}
|
| 203 |
-
INFO:hf-to-gguf:v.blk.21.attn_out.weight, torch.bfloat16 --> F16, shape = {1152, 1152}
|
| 204 |
-
INFO:hf-to-gguf:v.blk.21.attn_qkv.bias, torch.bfloat16 --> F32, shape = {3456}
|
| 205 |
-
INFO:hf-to-gguf:v.blk.21.attn_qkv.weight, torch.bfloat16 --> F16, shape = {1152, 3456}
|
| 206 |
-
INFO:hf-to-gguf:v.blk.21.ffn_up.bias, torch.bfloat16 --> F32, shape = {4304}
|
| 207 |
-
INFO:hf-to-gguf:v.blk.21.ffn_up.weight, torch.bfloat16 --> F16, shape = {1152, 4304}
|
| 208 |
-
INFO:hf-to-gguf:v.blk.21.ffn_down.bias, torch.bfloat16 --> F32, shape = {1152}
|
| 209 |
-
INFO:hf-to-gguf:v.blk.21.ffn_down.weight, torch.bfloat16 --> F16, shape = {4304, 1152}
|
| 210 |
-
INFO:hf-to-gguf:v.blk.21.ln1.bias, torch.bfloat16 --> F32, shape = {1152}
|
| 211 |
-
INFO:hf-to-gguf:v.blk.21.ln1.weight, torch.bfloat16 --> F32, shape = {1152}
|
| 212 |
-
INFO:hf-to-gguf:v.blk.21.ln2.bias, torch.bfloat16 --> F32, shape = {1152}
|
| 213 |
-
INFO:hf-to-gguf:v.blk.21.ln2.weight, torch.bfloat16 --> F32, shape = {1152}
|
| 214 |
-
INFO:hf-to-gguf:v.blk.22.attn_out.bias, torch.bfloat16 --> F32, shape = {1152}
|
| 215 |
-
INFO:hf-to-gguf:v.blk.22.attn_out.weight, torch.bfloat16 --> F16, shape = {1152, 1152}
|
| 216 |
-
INFO:hf-to-gguf:v.blk.22.attn_qkv.bias, torch.bfloat16 --> F32, shape = {3456}
|
| 217 |
-
INFO:hf-to-gguf:v.blk.22.attn_qkv.weight, torch.bfloat16 --> F16, shape = {1152, 3456}
|
| 218 |
-
INFO:hf-to-gguf:v.blk.22.ffn_up.bias, torch.bfloat16 --> F32, shape = {4304}
|
| 219 |
-
INFO:hf-to-gguf:v.blk.22.ffn_up.weight, torch.bfloat16 --> F16, shape = {1152, 4304}
|
| 220 |
-
INFO:hf-to-gguf:v.blk.22.ffn_down.bias, torch.bfloat16 --> F32, shape = {1152}
|
| 221 |
-
INFO:hf-to-gguf:v.blk.22.ffn_down.weight, torch.bfloat16 --> F16, shape = {4304, 1152}
|
| 222 |
-
INFO:hf-to-gguf:v.blk.22.ln1.bias, torch.bfloat16 --> F32, shape = {1152}
|
| 223 |
-
INFO:hf-to-gguf:v.blk.22.ln1.weight, torch.bfloat16 --> F32, shape = {1152}
|
| 224 |
-
INFO:hf-to-gguf:v.blk.22.ln2.bias, torch.bfloat16 --> F32, shape = {1152}
|
| 225 |
-
INFO:hf-to-gguf:v.blk.22.ln2.weight, torch.bfloat16 --> F32, shape = {1152}
|
| 226 |
-
INFO:hf-to-gguf:v.blk.23.attn_out.bias, torch.bfloat16 --> F32, shape = {1152}
|
| 227 |
-
INFO:hf-to-gguf:v.blk.23.attn_out.weight, torch.bfloat16 --> F16, shape = {1152, 1152}
|
| 228 |
-
INFO:hf-to-gguf:v.blk.23.attn_qkv.bias, torch.bfloat16 --> F32, shape = {3456}
|
| 229 |
-
INFO:hf-to-gguf:v.blk.23.attn_qkv.weight, torch.bfloat16 --> F16, shape = {1152, 3456}
|
| 230 |
-
INFO:hf-to-gguf:v.blk.23.ffn_up.bias, torch.bfloat16 --> F32, shape = {4304}
|
| 231 |
-
INFO:hf-to-gguf:v.blk.23.ffn_up.weight, torch.bfloat16 --> F16, shape = {1152, 4304}
|
| 232 |
-
INFO:hf-to-gguf:v.blk.23.ffn_down.bias, torch.bfloat16 --> F32, shape = {1152}
|
| 233 |
-
INFO:hf-to-gguf:v.blk.23.ffn_down.weight, torch.bfloat16 --> F16, shape = {4304, 1152}
|
| 234 |
-
INFO:hf-to-gguf:v.blk.23.ln1.bias, torch.bfloat16 --> F32, shape = {1152}
|
| 235 |
-
INFO:hf-to-gguf:v.blk.23.ln1.weight, torch.bfloat16 --> F32, shape = {1152}
|
| 236 |
-
INFO:hf-to-gguf:v.blk.23.ln2.bias, torch.bfloat16 --> F32, shape = {1152}
|
| 237 |
-
INFO:hf-to-gguf:v.blk.23.ln2.weight, torch.bfloat16 --> F32, shape = {1152}
|
| 238 |
-
INFO:hf-to-gguf:v.blk.24.attn_out.bias, torch.bfloat16 --> F32, shape = {1152}
|
| 239 |
-
INFO:hf-to-gguf:v.blk.24.attn_out.weight, torch.bfloat16 --> F16, shape = {1152, 1152}
|
| 240 |
-
INFO:hf-to-gguf:v.blk.24.attn_qkv.bias, torch.bfloat16 --> F32, shape = {3456}
|
| 241 |
-
INFO:hf-to-gguf:v.blk.24.attn_qkv.weight, torch.bfloat16 --> F16, shape = {1152, 3456}
|
| 242 |
-
INFO:hf-to-gguf:v.blk.24.ffn_up.bias, torch.bfloat16 --> F32, shape = {4304}
|
| 243 |
-
INFO:hf-to-gguf:v.blk.24.ffn_up.weight, torch.bfloat16 --> F16, shape = {1152, 4304}
|
| 244 |
-
INFO:hf-to-gguf:v.blk.24.ffn_down.bias, torch.bfloat16 --> F32, shape = {1152}
|
| 245 |
-
INFO:hf-to-gguf:v.blk.24.ffn_down.weight, torch.bfloat16 --> F16, shape = {4304, 1152}
|
| 246 |
-
INFO:hf-to-gguf:v.blk.24.ln1.bias, torch.bfloat16 --> F32, shape = {1152}
|
| 247 |
-
INFO:hf-to-gguf:v.blk.24.ln1.weight, torch.bfloat16 --> F32, shape = {1152}
|
| 248 |
-
INFO:hf-to-gguf:v.blk.24.ln2.bias, torch.bfloat16 --> F32, shape = {1152}
|
| 249 |
-
INFO:hf-to-gguf:v.blk.24.ln2.weight, torch.bfloat16 --> F32, shape = {1152}
|
| 250 |
-
INFO:hf-to-gguf:v.blk.25.attn_out.bias, torch.bfloat16 --> F32, shape = {1152}
|
| 251 |
-
INFO:hf-to-gguf:v.blk.25.attn_out.weight, torch.bfloat16 --> F16, shape = {1152, 1152}
|
| 252 |
-
INFO:hf-to-gguf:v.blk.25.attn_qkv.bias, torch.bfloat16 --> F32, shape = {3456}
|
| 253 |
-
INFO:hf-to-gguf:v.blk.25.attn_qkv.weight, torch.bfloat16 --> F16, shape = {1152, 3456}
|
| 254 |
-
INFO:hf-to-gguf:v.blk.25.ffn_up.bias, torch.bfloat16 --> F32, shape = {4304}
|
| 255 |
-
INFO:hf-to-gguf:v.blk.25.ffn_up.weight, torch.bfloat16 --> F16, shape = {1152, 4304}
|
| 256 |
-
INFO:hf-to-gguf:v.blk.25.ffn_down.bias, torch.bfloat16 --> F32, shape = {1152}
|
| 257 |
-
INFO:hf-to-gguf:v.blk.25.ffn_down.weight, torch.bfloat16 --> F16, shape = {4304, 1152}
|
| 258 |
-
INFO:hf-to-gguf:v.blk.25.ln1.bias, torch.bfloat16 --> F32, shape = {1152}
|
| 259 |
-
INFO:hf-to-gguf:v.blk.25.ln1.weight, torch.bfloat16 --> F32, shape = {1152}
|
| 260 |
-
INFO:hf-to-gguf:v.blk.25.ln2.bias, torch.bfloat16 --> F32, shape = {1152}
|
| 261 |
-
INFO:hf-to-gguf:v.blk.25.ln2.weight, torch.bfloat16 --> F32, shape = {1152}
|
| 262 |
-
INFO:hf-to-gguf:v.blk.26.attn_out.bias, torch.bfloat16 --> F32, shape = {1152}
|
| 263 |
-
INFO:hf-to-gguf:v.blk.26.attn_out.weight, torch.bfloat16 --> F16, shape = {1152, 1152}
|
| 264 |
-
INFO:hf-to-gguf:v.blk.26.attn_qkv.bias, torch.bfloat16 --> F32, shape = {3456}
|
| 265 |
-
INFO:hf-to-gguf:v.blk.26.attn_qkv.weight, torch.bfloat16 --> F16, shape = {1152, 3456}
|
| 266 |
-
INFO:hf-to-gguf:v.blk.26.ffn_up.bias, torch.bfloat16 --> F32, shape = {4304}
|
| 267 |
-
INFO:hf-to-gguf:v.blk.26.ffn_up.weight, torch.bfloat16 --> F16, shape = {1152, 4304}
|
| 268 |
-
INFO:hf-to-gguf:v.blk.26.ffn_down.bias, torch.bfloat16 --> F32, shape = {1152}
|
| 269 |
-
INFO:hf-to-gguf:v.blk.26.ffn_down.weight, torch.bfloat16 --> F16, shape = {4304, 1152}
|
| 270 |
-
INFO:hf-to-gguf:v.blk.26.ln1.bias, torch.bfloat16 --> F32, shape = {1152}
|
| 271 |
-
INFO:hf-to-gguf:v.blk.26.ln1.weight, torch.bfloat16 --> F32, shape = {1152}
|
| 272 |
-
INFO:hf-to-gguf:v.blk.26.ln2.bias, torch.bfloat16 --> F32, shape = {1152}
|
| 273 |
-
INFO:hf-to-gguf:v.blk.26.ln2.weight, torch.bfloat16 --> F32, shape = {1152}
|
| 274 |
-
INFO:hf-to-gguf:v.blk.3.attn_out.bias, torch.bfloat16 --> F32, shape = {1152}
|
| 275 |
-
INFO:hf-to-gguf:v.blk.3.attn_out.weight, torch.bfloat16 --> F16, shape = {1152, 1152}
|
| 276 |
-
INFO:hf-to-gguf:v.blk.3.attn_qkv.bias, torch.bfloat16 --> F32, shape = {3456}
|
| 277 |
-
INFO:hf-to-gguf:v.blk.3.attn_qkv.weight, torch.bfloat16 --> F16, shape = {1152, 3456}
|
| 278 |
-
INFO:hf-to-gguf:v.blk.3.ffn_up.bias, torch.bfloat16 --> F32, shape = {4304}
|
| 279 |
-
INFO:hf-to-gguf:v.blk.3.ffn_up.weight, torch.bfloat16 --> F16, shape = {1152, 4304}
|
| 280 |
-
INFO:hf-to-gguf:v.blk.3.ffn_down.bias, torch.bfloat16 --> F32, shape = {1152}
|
| 281 |
-
INFO:hf-to-gguf:v.blk.3.ffn_down.weight, torch.bfloat16 --> F16, shape = {4304, 1152}
|
| 282 |
-
INFO:hf-to-gguf:v.blk.3.ln1.bias, torch.bfloat16 --> F32, shape = {1152}
|
| 283 |
-
INFO:hf-to-gguf:v.blk.3.ln1.weight, torch.bfloat16 --> F32, shape = {1152}
|
| 284 |
-
INFO:hf-to-gguf:v.blk.3.ln2.bias, torch.bfloat16 --> F32, shape = {1152}
|
| 285 |
-
INFO:hf-to-gguf:v.blk.3.ln2.weight, torch.bfloat16 --> F32, shape = {1152}
|
| 286 |
-
INFO:hf-to-gguf:v.blk.4.attn_out.bias, torch.bfloat16 --> F32, shape = {1152}
|
| 287 |
-
INFO:hf-to-gguf:v.blk.4.attn_out.weight, torch.bfloat16 --> F16, shape = {1152, 1152}
|
| 288 |
-
INFO:hf-to-gguf:v.blk.4.attn_qkv.bias, torch.bfloat16 --> F32, shape = {3456}
|
| 289 |
-
INFO:hf-to-gguf:v.blk.4.attn_qkv.weight, torch.bfloat16 --> F16, shape = {1152, 3456}
|
| 290 |
-
INFO:hf-to-gguf:v.blk.4.ffn_up.bias, torch.bfloat16 --> F32, shape = {4304}
|
| 291 |
-
INFO:hf-to-gguf:v.blk.4.ffn_up.weight, torch.bfloat16 --> F16, shape = {1152, 4304}
|
| 292 |
-
INFO:hf-to-gguf:v.blk.4.ffn_down.bias, torch.bfloat16 --> F32, shape = {1152}
|
| 293 |
-
INFO:hf-to-gguf:v.blk.4.ffn_down.weight, torch.bfloat16 --> F16, shape = {4304, 1152}
|
| 294 |
-
INFO:hf-to-gguf:v.blk.4.ln1.bias, torch.bfloat16 --> F32, shape = {1152}
|
| 295 |
-
INFO:hf-to-gguf:v.blk.4.ln1.weight, torch.bfloat16 --> F32, shape = {1152}
|
| 296 |
-
INFO:hf-to-gguf:v.blk.4.ln2.bias, torch.bfloat16 --> F32, shape = {1152}
|
| 297 |
-
INFO:hf-to-gguf:v.blk.4.ln2.weight, torch.bfloat16 --> F32, shape = {1152}
|
| 298 |
-
INFO:hf-to-gguf:v.blk.5.attn_out.bias, torch.bfloat16 --> F32, shape = {1152}
|
| 299 |
-
INFO:hf-to-gguf:v.blk.5.attn_out.weight, torch.bfloat16 --> F16, shape = {1152, 1152}
|
| 300 |
-
INFO:hf-to-gguf:v.blk.5.attn_qkv.bias, torch.bfloat16 --> F32, shape = {3456}
|
| 301 |
-
INFO:hf-to-gguf:v.blk.5.attn_qkv.weight, torch.bfloat16 --> F16, shape = {1152, 3456}
|
| 302 |
-
INFO:hf-to-gguf:v.blk.5.ffn_up.bias, torch.bfloat16 --> F32, shape = {4304}
|
| 303 |
-
INFO:hf-to-gguf:v.blk.5.ffn_up.weight, torch.bfloat16 --> F16, shape = {1152, 4304}
|
| 304 |
-
INFO:hf-to-gguf:v.blk.5.ffn_down.bias, torch.bfloat16 --> F32, shape = {1152}
|
| 305 |
-
INFO:hf-to-gguf:v.blk.5.ffn_down.weight, torch.bfloat16 --> F16, shape = {4304, 1152}
|
| 306 |
-
INFO:hf-to-gguf:v.blk.5.ln1.bias, torch.bfloat16 --> F32, shape = {1152}
|
| 307 |
-
INFO:hf-to-gguf:v.blk.5.ln1.weight, torch.bfloat16 --> F32, shape = {1152}
|
| 308 |
-
INFO:hf-to-gguf:v.blk.5.ln2.bias, torch.bfloat16 --> F32, shape = {1152}
|
| 309 |
-
INFO:hf-to-gguf:v.blk.5.ln2.weight, torch.bfloat16 --> F32, shape = {1152}
|
| 310 |
-
INFO:hf-to-gguf:v.blk.6.attn_out.bias, torch.bfloat16 --> F32, shape = {1152}
|
| 311 |
-
INFO:hf-to-gguf:v.blk.6.attn_out.weight, torch.bfloat16 --> F16, shape = {1152, 1152}
|
| 312 |
-
INFO:hf-to-gguf:v.blk.6.attn_qkv.bias, torch.bfloat16 --> F32, shape = {3456}
|
| 313 |
-
INFO:hf-to-gguf:v.blk.6.attn_qkv.weight, torch.bfloat16 --> F16, shape = {1152, 3456}
|
| 314 |
-
INFO:hf-to-gguf:v.blk.6.ffn_up.bias, torch.bfloat16 --> F32, shape = {4304}
|
| 315 |
-
INFO:hf-to-gguf:v.blk.6.ffn_up.weight, torch.bfloat16 --> F16, shape = {1152, 4304}
|
| 316 |
-
INFO:hf-to-gguf:v.blk.6.ffn_down.bias, torch.bfloat16 --> F32, shape = {1152}
|
| 317 |
-
INFO:hf-to-gguf:v.blk.6.ffn_down.weight, torch.bfloat16 --> F16, shape = {4304, 1152}
|
| 318 |
-
INFO:hf-to-gguf:v.blk.6.ln1.bias, torch.bfloat16 --> F32, shape = {1152}
|
| 319 |
-
INFO:hf-to-gguf:v.blk.6.ln1.weight, torch.bfloat16 --> F32, shape = {1152}
|
| 320 |
-
INFO:hf-to-gguf:v.blk.6.ln2.bias, torch.bfloat16 --> F32, shape = {1152}
|
| 321 |
-
INFO:hf-to-gguf:v.blk.6.ln2.weight, torch.bfloat16 --> F32, shape = {1152}
|
| 322 |
-
INFO:hf-to-gguf:v.blk.7.attn_out.bias, torch.bfloat16 --> F32, shape = {1152}
|
| 323 |
-
INFO:hf-to-gguf:v.blk.7.attn_out.weight, torch.bfloat16 --> F16, shape = {1152, 1152}
|
| 324 |
-
INFO:hf-to-gguf:v.blk.7.attn_qkv.bias, torch.bfloat16 --> F32, shape = {3456}
|
| 325 |
-
INFO:hf-to-gguf:v.blk.7.attn_qkv.weight, torch.bfloat16 --> F16, shape = {1152, 3456}
|
| 326 |
-
INFO:hf-to-gguf:v.blk.7.ffn_up.bias, torch.bfloat16 --> F32, shape = {4304}
|
| 327 |
-
INFO:hf-to-gguf:v.blk.7.ffn_up.weight, torch.bfloat16 --> F16, shape = {1152, 4304}
|
| 328 |
-
INFO:hf-to-gguf:v.blk.7.ffn_down.bias, torch.bfloat16 --> F32, shape = {1152}
|
| 329 |
-
INFO:hf-to-gguf:v.blk.7.ffn_down.weight, torch.bfloat16 --> F16, shape = {4304, 1152}
|
| 330 |
-
INFO:hf-to-gguf:v.blk.7.ln1.bias, torch.bfloat16 --> F32, shape = {1152}
|
| 331 |
-
INFO:hf-to-gguf:v.blk.7.ln1.weight, torch.bfloat16 --> F32, shape = {1152}
|
| 332 |
-
INFO:hf-to-gguf:v.blk.7.ln2.bias, torch.bfloat16 --> F32, shape = {1152}
|
| 333 |
-
INFO:hf-to-gguf:v.blk.7.ln2.weight, torch.bfloat16 --> F32, shape = {1152}
|
| 334 |
-
INFO:hf-to-gguf:v.blk.8.attn_out.bias, torch.bfloat16 --> F32, shape = {1152}
|
| 335 |
-
INFO:hf-to-gguf:v.blk.8.attn_out.weight, torch.bfloat16 --> F16, shape = {1152, 1152}
|
| 336 |
-
INFO:hf-to-gguf:v.blk.8.attn_qkv.bias, torch.bfloat16 --> F32, shape = {3456}
|
| 337 |
-
INFO:hf-to-gguf:v.blk.8.attn_qkv.weight, torch.bfloat16 --> F16, shape = {1152, 3456}
|
| 338 |
-
INFO:hf-to-gguf:v.blk.8.ffn_up.bias, torch.bfloat16 --> F32, shape = {4304}
|
| 339 |
-
INFO:hf-to-gguf:v.blk.8.ffn_up.weight, torch.bfloat16 --> F16, shape = {1152, 4304}
|
| 340 |
-
INFO:hf-to-gguf:v.blk.8.ffn_down.bias, torch.bfloat16 --> F32, shape = {1152}
|
| 341 |
-
INFO:hf-to-gguf:v.blk.8.ffn_down.weight, torch.bfloat16 --> F16, shape = {4304, 1152}
|
| 342 |
-
INFO:hf-to-gguf:v.blk.8.ln1.bias, torch.bfloat16 --> F32, shape = {1152}
|
| 343 |
-
INFO:hf-to-gguf:v.blk.8.ln1.weight, torch.bfloat16 --> F32, shape = {1152}
|
| 344 |
-
INFO:hf-to-gguf:v.blk.8.ln2.bias, torch.bfloat16 --> F32, shape = {1152}
|
| 345 |
-
INFO:hf-to-gguf:v.blk.8.ln2.weight, torch.bfloat16 --> F32, shape = {1152}
|
| 346 |
-
INFO:hf-to-gguf:v.blk.9.attn_out.bias, torch.bfloat16 --> F32, shape = {1152}
|
| 347 |
-
INFO:hf-to-gguf:v.blk.9.attn_out.weight, torch.bfloat16 --> F16, shape = {1152, 1152}
|
| 348 |
-
INFO:hf-to-gguf:v.blk.9.attn_qkv.bias, torch.bfloat16 --> F32, shape = {3456}
|
| 349 |
-
INFO:hf-to-gguf:v.blk.9.attn_qkv.weight, torch.bfloat16 --> F16, shape = {1152, 3456}
|
| 350 |
-
INFO:hf-to-gguf:v.blk.9.ffn_up.bias, torch.bfloat16 --> F32, shape = {4304}
|
| 351 |
-
INFO:hf-to-gguf:v.blk.9.ffn_up.weight, torch.bfloat16 --> F16, shape = {1152, 4304}
|
| 352 |
-
INFO:hf-to-gguf:v.blk.9.ffn_down.bias, torch.bfloat16 --> F32, shape = {1152}
|
| 353 |
-
INFO:hf-to-gguf:v.blk.9.ffn_down.weight, torch.bfloat16 --> F16, shape = {4304, 1152}
|
| 354 |
-
INFO:hf-to-gguf:v.blk.9.ln1.bias, torch.bfloat16 --> F32, shape = {1152}
|
| 355 |
-
INFO:hf-to-gguf:v.blk.9.ln1.weight, torch.bfloat16 --> F32, shape = {1152}
|
| 356 |
-
INFO:hf-to-gguf:v.blk.9.ln2.bias, torch.bfloat16 --> F32, shape = {1152}
|
| 357 |
-
INFO:hf-to-gguf:v.blk.9.ln2.weight, torch.bfloat16 --> F32, shape = {1152}
|
| 358 |
-
INFO:hf-to-gguf:mm.0.bias, torch.bfloat16 --> F32, shape = {4608}
|
| 359 |
-
INFO:hf-to-gguf:mm.2.bias, torch.bfloat16 --> F32, shape = {2048}
|
| 360 |
-
INFO:hf-to-gguf:v.post_ln.bias, torch.bfloat16 --> F32, shape = {1152}
|
| 361 |
-
INFO:hf-to-gguf:v.post_ln.weight, torch.bfloat16 --> F32, shape = {1152}
|
| 362 |
-
INFO:hf-to-gguf:v.patch_embd.bias, torch.bfloat16 --> F32, shape = {1152}
|
| 363 |
-
INFO:hf-to-gguf:v.patch_embd.weight, torch.bfloat16 --> F16, shape = {16, 16, 3, 1152}
|
| 364 |
-
INFO:hf-to-gguf:v.patch_embd.weight.1, torch.bfloat16 --> F16, shape = {16, 16, 3, 1152}
|
| 365 |
-
INFO:hf-to-gguf:v.position_embd.weight, torch.bfloat16 --> F32, shape = {1152, 2304}
|
| 366 |
-
INFO:hf-to-gguf:Set meta model
|
| 367 |
-
INFO:hf-to-gguf:Set model parameters
|
| 368 |
-
INFO:hf-to-gguf:Set model quantization version
|
| 369 |
-
INFO:gguf.gguf_writer:Writing the following files:
|
| 370 |
-
INFO:gguf.gguf_writer:/tmp/q_quant_work/mmproj.f16.gguf: n_tensors = 334, total_size = 899.3M
|
| 371 |
-
|
| 372 |
-
INFO:hf-to-gguf:Model successfully exported to /tmp/q_quant_work/mmproj.f16.gguf
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|