Instructions to use bowang0911/pplx-embed-v1-0.6b-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use bowang0911/pplx-embed-v1-0.6b-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 bowang0911/pplx-embed-v1-0.6b-gguf:F16
# Run inference directly in the terminal:
llama cli -hf bowang0911/pplx-embed-v1-0.6b-gguf:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf bowang0911/pplx-embed-v1-0.6b-gguf:F16
# Run inference directly in the terminal:
llama cli -hf bowang0911/pplx-embed-v1-0.6b-gguf:F16

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 bowang0911/pplx-embed-v1-0.6b-gguf:F16
# Run inference directly in the terminal:
./llama-cli -hf bowang0911/pplx-embed-v1-0.6b-gguf:F16

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 bowang0911/pplx-embed-v1-0.6b-gguf:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf bowang0911/pplx-embed-v1-0.6b-gguf:F16

Use Docker

docker model run hf.co/bowang0911/pplx-embed-v1-0.6b-gguf:F16

LM Studio
Jan
Ollama
How to use bowang0911/pplx-embed-v1-0.6b-gguf with Ollama:
```
ollama run hf.co/bowang0911/pplx-embed-v1-0.6b-gguf:F16
```

Unsloth Studio

How to use bowang0911/pplx-embed-v1-0.6b-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 bowang0911/pplx-embed-v1-0.6b-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 bowang0911/pplx-embed-v1-0.6b-gguf to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for bowang0911/pplx-embed-v1-0.6b-gguf to start chatting

Docker Model Runner
How to use bowang0911/pplx-embed-v1-0.6b-gguf with Docker Model Runner:
```
docker model run hf.co/bowang0911/pplx-embed-v1-0.6b-gguf:F16
```

Lemonade

How to use bowang0911/pplx-embed-v1-0.6b-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull bowang0911/pplx-embed-v1-0.6b-gguf:F16

Run and chat with the model

lemonade run user.pplx-embed-v1-0.6b-gguf-F16

List all available models

lemonade list

Atomic Chat

bowang0911 commited on Mar 6

Commit

ab95a3d

verified ·

1 Parent(s): 8f1c274

Update README.md

Browse files

Files changed (1) hide show

README.md +14 -2

README.md CHANGED Viewed

@@ -6,7 +6,7 @@ tags:
   - gguf
   - qwen3
   - bidirectional
-license: mit
 ---
 # pplx-embed-v1-0.6b GGUF (F16)
@@ -27,7 +27,19 @@ from llama_cpp import Llama, llama_cpp
 llm = Llama(model_path="pplx-embed-v1-0.6b-f16.gguf", embedding=True, pooling_type=1)
 llama_cpp.llama_set_causal_attn(llm._ctx.ctx, False)
-embedding = llm.embed("your text here")
 ```
 CLI:

   - gguf
   - qwen3
   - bidirectional
+license: apache-2.0
 ---
 # pplx-embed-v1-0.6b GGUF (F16)
 llm = Llama(model_path="pplx-embed-v1-0.6b-f16.gguf", embedding=True, pooling_type=1)
 llama_cpp.llama_set_causal_attn(llm._ctx.ctx, False)
+raw = llm.embed("your text here")
+```
+> **Note:** The GGUF outputs raw float embeddings only. The original model natively produces int8/binary quantized embeddings via a post-processing step (`st_quantize.FlexibleQuantizer`). To match that behavior, apply the quantization manually:
+```python
+import numpy as np
+# Int8: tanh → scale → round → clamp (matches Int8TanhQuantizer)
+int8_emb = np.clip(np.round(np.tanh(raw) * 127), -128, 127).astype(np.int8)
+# Binary: sign (matches BinaryTanhQuantizer)
+binary_emb = np.where(np.array(raw) >= 0, 1, -1).astype(np.int8)
 ```
 CLI: