Instructions to use techhermit/qwen35-slice14b-release with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use techhermit/qwen35-slice14b-release with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("/workspace/distill_student_init10")
model = PeftModel.from_pretrained(base_model, "techhermit/qwen35-slice14b-release")

llama-cpp-python

How to use techhermit/qwen35-slice14b-release with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="techhermit/qwen35-slice14b-release",
	filename="release_repo-q6_k.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use techhermit/qwen35-slice14b-release 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 techhermit/qwen35-slice14b-release:Q6_K
# Run inference directly in the terminal:
llama cli -hf techhermit/qwen35-slice14b-release:Q6_K

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf techhermit/qwen35-slice14b-release:Q6_K
# Run inference directly in the terminal:
llama cli -hf techhermit/qwen35-slice14b-release:Q6_K

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 techhermit/qwen35-slice14b-release:Q6_K
# Run inference directly in the terminal:
./llama-cli -hf techhermit/qwen35-slice14b-release:Q6_K

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 techhermit/qwen35-slice14b-release:Q6_K
# Run inference directly in the terminal:
./build/bin/llama-cli -hf techhermit/qwen35-slice14b-release:Q6_K

Use Docker

docker model run hf.co/techhermit/qwen35-slice14b-release:Q6_K

LM Studio
Jan
Ollama
How to use techhermit/qwen35-slice14b-release with Ollama:
```
ollama run hf.co/techhermit/qwen35-slice14b-release:Q6_K
```

Unsloth Studio

How to use techhermit/qwen35-slice14b-release 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 techhermit/qwen35-slice14b-release 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 techhermit/qwen35-slice14b-release to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for techhermit/qwen35-slice14b-release to start chatting

How to use techhermit/qwen35-slice14b-release with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf techhermit/qwen35-slice14b-release:Q6_K

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": "techhermit/qwen35-slice14b-release:Q6_K"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use techhermit/qwen35-slice14b-release with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf techhermit/qwen35-slice14b-release:Q6_K

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 techhermit/qwen35-slice14b-release:Q6_K

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use techhermit/qwen35-slice14b-release with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf techhermit/qwen35-slice14b-release:Q6_K

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 "techhermit/qwen35-slice14b-release:Q6_K" \
  --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 techhermit/qwen35-slice14b-release with Docker Model Runner:
```
docker model run hf.co/techhermit/qwen35-slice14b-release:Q6_K
```

Lemonade

How to use techhermit/qwen35-slice14b-release with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull techhermit/qwen35-slice14b-release:Q6_K

Run and chat with the model

lemonade run user.qwen35-slice14b-release-Q6_K

List all available models

lemonade list

qwen35-slice14b-release / training_summary.json

techhermit

Upload distilled distill branch artifact

9218a44 verified 3 months ago

Raw

History Blame Contribute Delete

1.02 kB

	{
	"model": "/workspace/distill_student_init10",
	"data_dir": "/workspace/distill_cache/mixed_external_behavior_expanded_plus.jsonl.gz",
	"output_dir": "/workspace/distill_runs/external-behavior-expanded-plus-run6",
	"seq_len": 2048,
	"epochs": 1,
	"lr": 2.5e-05,
	"batch_size": 1,
	"grad_accum_steps": 8,
	"lora_r": 16,
	"lora_alpha": 32,
	"target_modules": [
	"q_proj",
	"k_proj",
	"v_proj",
	"o_proj",
	"gate_proj",
	"up_proj",
	"down_proj"
	],
	"total_params": 8651684096,
	"trainable_params": 19922944,
	"train_samples": 1557,
	"eval_samples": 81,
	"load_in_4bit": true,
	"teacher_temperature": 1.0,
	"resume_adapter": "/workspace/distill_runs/external-behavior-expanded-plus-run5/adapter",
	"eval_only": false,
	"eval_loss": 0.8480964277030696,
	"eval_ppl": 2.3351974012631542,
	"final_adapter_dir": "/workspace/distill_runs/external-behavior-expanded-plus-run6/adapter",
	"metrics_path": "/workspace/distill_runs/external-behavior-expanded-plus-run6/metrics.jsonl"
	}