Instructions to use kon171verma/intent-classifier with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use kon171verma/intent-classifier with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-classification", model="kon171verma/intent-classifier")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("kon171verma/intent-classifier", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use kon171verma/intent-classifier 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 kon171verma/intent-classifier:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf kon171verma/intent-classifier:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf kon171verma/intent-classifier:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf kon171verma/intent-classifier:Q4_K_M

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 kon171verma/intent-classifier:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama cli -hf kon171verma/intent-classifier:Q4_K_M

Use Docker

docker model run hf.co/kon171verma/intent-classifier:Q4_K_M

Llama new
LM Studio
Jan
Ollama
How to use kon171verma/intent-classifier with Ollama:
```
ollama run hf.co/kon171verma/intent-classifier:Q4_K_M
```
Unsloth Desktop

How to use kon171verma/intent-classifier with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf kon171verma/intent-classifier:Q4_K_M

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:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "kon171verma/intent-classifier:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use kon171verma/intent-classifier with Docker Model Runner:
```
docker model run hf.co/kon171verma/intent-classifier:Q4_K_M
```

Lemonade

How to use kon171verma/intent-classifier with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull kon171verma/intent-classifier:Q4_K_M

Run and chat with the model

lemonade run user.intent-classifier-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use kon171verma/intent-classifier with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf kon171verma/intent-classifier: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 kon171verma/intent-classifier:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use kon171verma/intent-classifier with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf kon171verma/intent-classifier: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 "kon171verma/intent-classifier: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"

kon171verma commited on Aug 2

Commit

a0bbb7a

1 Parent(s): 41cc92c

docs: add HF repo card metadata and refresh README

Browse files

Files changed (1) hide show

README.md +29 -25

README.md CHANGED Viewed

@@ -1,34 +1,38 @@
 # intent-classifier (release)
-This Hugging Face repo holds only the **final, released** models for the
-[kon172verma/intent-classifier](https://github.com/kon172verma/intent-classifier)
-project: merged (adapter-unloaded) full-weight models, plus their GGUF and
-ONNX exports. It intentionally does **not** contain adapters or in-progress
-experiments — see the experiments repo for those.
-## Related Repositories
-- **Training** — [kon172verma/intent-classifier](https://github.com/kon172verma/intent-classifier) (GitHub): fine-tuning code, release pipeline, `RELEASES.md`.
-- **Experiments** — [kon172verma/intent-classifier-experiments](https://huggingface.co/kon172verma/intent-classifier-experiments) (Hugging Face): every adapter produced during experimentation, by version.
-- **Inference** — [kon172verma/intent-classifier-inference](https://github.com/kon172verma/intent-classifier-inference) (GitHub): benchmarks the models published here on edge hardware.
-## Layout
-```
-{technique}_merged/{model_key}_{lora_config}_{dataset_size}/   # merged Transformers checkpoint
-GGUF/{model_key}/                                              # llama.cpp GGUF quantizations
-ONNX/{model_key}/                                               # ONNX Runtime exports (fp16, int8, ...)
-```
-Only the 2 best models chosen per version are published here. Each release
-is stamped as a matching tag (e.g. `v1.0`) on the
-[training repo](https://github.com/kon172verma/intent-classifier) — see that
-repo's `RELEASES.md` for exactly which experiments were selected.
-## Migration note
-This repo previously also held per-experiment LoRA/DoRA/LoRA+ adapters. Those
-are being migrated to
-[kon172verma/intent-classifier-experiments](https://huggingface.co/kon172verma/intent-classifier-experiments)
-(see `scripts/migrate_adapters_to_experiments.py` in the training repo) and
-will be removed from here once migration is verified.

+---
+license: apache-2.0
+tags:
+	- text-classification
+	- intent-classification
+	- llama
+	- qwen
+library_name: transformers
+---
 # intent-classifier (release)
+This Hugging Face repo contains only the final released models for the
+intent-classifier project.
+It is intentionally limited to release artifacts:
+- merged full-weight model checkpoints,
+- GGUF exports for llama.cpp,
+- ONNX exports for runtime backends.
+Adapters and intermediate experiment artifacts are stored in:
+https://huggingface.co/kon172verma/intent-classifier-experiments
+## Current model folders
+- qwen3-0.6b
+- llama3.2-1b
+## Related repositories
+- Training code: https://github.com/kon172verma/intent-classifier
+- Inference/benchmarking: https://github.com/kon172verma/intent-classifier-inference
+- Experiments (all adapters): https://huggingface.co/kon172verma/intent-classifier-experiments
+## Notes
+- Release selection and version mapping are tracked in the training repo.
+- This repo is kept minimal to make downstream inference and deployment workflows straightforward.