Instructions to use llmware/slim-nli-tool with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use llmware/slim-nli-tool with Transformers:

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("llmware/slim-nli-tool", dtype="auto")

llama-cpp-python

How to use llmware/slim-nli-tool with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="llmware/slim-nli-tool",
	filename="slim-nli.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use llmware/slim-nli-tool 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 llmware/slim-nli-tool
# Run inference directly in the terminal:
llama cli -hf llmware/slim-nli-tool

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf llmware/slim-nli-tool
# Run inference directly in the terminal:
llama cli -hf llmware/slim-nli-tool

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 llmware/slim-nli-tool
# Run inference directly in the terminal:
./llama-cli -hf llmware/slim-nli-tool

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 llmware/slim-nli-tool
# Run inference directly in the terminal:
./build/bin/llama-cli -hf llmware/slim-nli-tool

Use Docker

docker model run hf.co/llmware/slim-nli-tool

LM Studio
Jan
Ollama
How to use llmware/slim-nli-tool with Ollama:
```
ollama run hf.co/llmware/slim-nli-tool
```

Unsloth Studio

How to use llmware/slim-nli-tool 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 llmware/slim-nli-tool 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 llmware/slim-nli-tool to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for llmware/slim-nli-tool to start chatting

Atomic Chat new
Docker Model Runner
How to use llmware/slim-nli-tool with Docker Model Runner:
```
docker model run hf.co/llmware/slim-nli-tool
```

Lemonade

How to use llmware/slim-nli-tool with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull llmware/slim-nli-tool

Run and chat with the model

lemonade run user.slim-nli-tool-{{QUANT_TAG}}

List all available models

lemonade list

Empirical Audit: Logical Limitations and Schema Interference

by Manamama - opened 4 days ago

Discussion

Manamama

4 days ago

I have conducted a formal audit of the slim-nli-tool using a battery of 10 fundamental logical syllogisms. While the model is highly efficient for sentiment-style NLI tasks, my testing reveals significant logical failures when tested against strict formal requirements.

Summary of Findings

Transitivity Failure: When presented with A > B and B > C, the model fails to correctly deduce the transitive property A > C (labeling it contradicts).
Logical Impossibility: The model fails to flag contradictory premises (A AND Not A) as a logical failure, incorrectly labeling them as supports.
Schema Interference: The model demonstrates "Schema Gravity," where it defaults to neutral or contradicts for simple logical truths that conflict with its internalized riddle schemas.

Conclusion

This model functions effectively as a "Stochastic Pattern Matcher" for sentiment-thematic affinity, but it cannot be used as a reliable logical auditor for formal deduction. It is not an incorruptible auditor; it is a probabilistic tool that requires heavy logical framing to produce reliable results.

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment