Instructions to use philipjohnbasile/GLM-5.2-Demolition-q4a4-soul-MLX with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use philipjohnbasile/GLM-5.2-Demolition-q4a4-soul-MLX with MLX:

# Make sure mlx-lm is installed
# pip install --upgrade mlx-lm

# Generate text with mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("philipjohnbasile/GLM-5.2-Demolition-q4a4-soul-MLX")

prompt = "Write a story about Einstein"
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
    messages, add_generation_prompt=True
)

text = generate(model, tokenizer, prompt=prompt, verbose=True)

Notebooks
Google Colab
Kaggle
Local Apps Settings
LM Studio

How to use philipjohnbasile/GLM-5.2-Demolition-q4a4-soul-MLX with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "philipjohnbasile/GLM-5.2-Demolition-q4a4-soul-MLX"

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "mlx-lm": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "philipjohnbasile/GLM-5.2-Demolition-q4a4-soul-MLX"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use philipjohnbasile/GLM-5.2-Demolition-q4a4-soul-MLX with Hermes Agent:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "philipjohnbasile/GLM-5.2-Demolition-q4a4-soul-MLX"

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 philipjohnbasile/GLM-5.2-Demolition-q4a4-soul-MLX

Run Hermes

hermes

OpenClaw new

How to use philipjohnbasile/GLM-5.2-Demolition-q4a4-soul-MLX with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "philipjohnbasile/GLM-5.2-Demolition-q4a4-soul-MLX"

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 "philipjohnbasile/GLM-5.2-Demolition-q4a4-soul-MLX" \
  --custom-provider-id mlx-lm \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

MLX LM

How to use philipjohnbasile/GLM-5.2-Demolition-q4a4-soul-MLX with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "philipjohnbasile/GLM-5.2-Demolition-q4a4-soul-MLX"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "philipjohnbasile/GLM-5.2-Demolition-q4a4-soul-MLX"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "philipjohnbasile/GLM-5.2-Demolition-q4a4-soul-MLX",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

GLM-5.2-Demolition-q4a4-soul-MLX / TRAINING_DATA.md

philipjohnbasile

Upload TRAINING_DATA.md with huggingface_hub

2149cc8 verified 15 days ago

preview code

Raw

History Blame

2.79 kB

	# Training Data — provenance · licenses · contamination (ledger)

	Honest record of what the model was healed on, where it came from, and proof the reported numbers aren't
	memorized. (The model is released; the heal data itself is not published.)

	## Heal / SFT sources
	External open datasets (via `scripts/27_build_heal_data.py`, `scripts/06_heal_lora.py`) + self-generated/verified
	data + hand-authored gold seeds.

	\| Dataset \| Use \| License (verify before redistributing the data) \|
	\|---\|---\|---\|
	\| `open-r1/Mixture-of-Thoughts` \| reasoning + code \| Apache-2.0 \|
	\| `open-r1/OpenR1-Math-220k` \| math reasoning \| Apache-2.0 \|
	\| `open-thoughts/OpenThoughts-114k` \| reasoning \| Apache-2.0 \|
	\| `HuggingFaceH4/ultrachat_200k` \| general chat \| MIT \|
	\| `theblackcat102/evol-codealpaca-v1` \| instruction→code \| Apache-2.0 ⚠ Evol/GPT-distilled — check model-output terms \|
	\| `Salesforce/xlam-function-calling-60k` \| tool-calling \| CC-BY-4.0 \|
	\| `glaiveai/glaive-function-calling-v2` \| tool-calling \| Apache-2.0 (verify) \|
	\| `glaiveai/reasoning-v1-20m` \| reasoning \| (verify) \|
	\| `SWE-bench/SWE-smith-trajectories` \| agentic / tool \| MIT (verify) \|
	\| `internlm/Lean-Workbook` \| Lean proofs \| Apache-2.0 (verify) \|

	Self-generated / hand-authored (ours → MIT): the Lean expert-iteration flywheel output, the design-soul +
	7-facet gold seeds (`heal/facets/seeds/`, `heal/design/seeds/`), CallSieve retrieval data, verifier-mesh RFT.

	## Eval benchmarks — TESTING only, never trained on
	`openai/openai_humaneval` (MIT) · `openai/gsm8k` (MIT) · `mbpp` (CC-BY) · miniF2F (MIT). Loaded by
	`58_bench` / `59_stem_diag` / `73_minif2f` for evaluation, not heal.

	## Contamination — verified CLEAN (CPU, 2026-06-18)
	The honest risk: the big reasoning/code datasets above can contain benchmark problems → memorized, not
	reasoned. Checked with `scripts/81_contamination_check.py` (miniF2F vs Lean training) and
	`scripts/82_heal_benchmark_contam.py` (benchmarks vs the 236 M-char heal corpus):

	\| Benchmark \| Present in training? \| Verdict \|
	\|---\|---\|---\|
	\| miniF2F-test (226) \| 0 exact · 1 near-dup (0.4 %) \| ✓ honest \|
	\| HumanEval (164) \| 0.0 % \| ✓ the 19/20 is honest \|
	\| GSM8K-test (sampled 300) \| 0.0 % \| ✓ honest \|

	Method: name-agnostic normalized exact-match + token-Jaccard near-dup (miniF2F) and normalized prompt-substring
	(HumanEval/GSM8K) — verbatim/near-verbatim inclusion would be caught. **Reported numbers are reasoned, not
	memorized.**

	## License stance
	Self-generated + hand-authored → MIT (matches the model + base `zai-org/GLM-5.2`, MIT). External-dataset portions
	retain their upstream licenses (table). The released model is a derivative; **verify each dataset's license before
	redistributing the heal data itself.**

	# Training Data — provenance · licenses · contamination (ledger)

	Honest record of what the model was healed on, where it came from, and proof the reported numbers aren't
	memorized. (The model is released; the heal data itself is not published.)

	## Heal / SFT sources
	External open datasets (via `scripts/27_build_heal_data.py`, `scripts/06_heal_lora.py`) + self-generated/verified
	data + hand-authored gold seeds.

	\| Dataset \| Use \| License (verify before redistributing the data) \|
	\|---\|---\|---\|
	\| `open-r1/Mixture-of-Thoughts` \| reasoning + code \| Apache-2.0 \|
	\| `open-r1/OpenR1-Math-220k` \| math reasoning \| Apache-2.0 \|
	\| `open-thoughts/OpenThoughts-114k` \| reasoning \| Apache-2.0 \|
	\| `HuggingFaceH4/ultrachat_200k` \| general chat \| MIT \|
	\| `theblackcat102/evol-codealpaca-v1` \| instruction→code \| Apache-2.0 ⚠ Evol/GPT-distilled — check model-output terms \|
	\| `Salesforce/xlam-function-calling-60k` \| tool-calling \| CC-BY-4.0 \|
	\| `glaiveai/glaive-function-calling-v2` \| tool-calling \| Apache-2.0 (verify) \|
	\| `glaiveai/reasoning-v1-20m` \| reasoning \| (verify) \|
	\| `SWE-bench/SWE-smith-trajectories` \| agentic / tool \| MIT (verify) \|
	\| `internlm/Lean-Workbook` \| Lean proofs \| Apache-2.0 (verify) \|

	Self-generated / hand-authored (ours → MIT): the Lean expert-iteration flywheel output, the design-soul +
	7-facet gold seeds (`heal/facets/seeds/`, `heal/design/seeds/`), CallSieve retrieval data, verifier-mesh RFT.

	## Eval benchmarks — TESTING only, never trained on
	`openai/openai_humaneval` (MIT) · `openai/gsm8k` (MIT) · `mbpp` (CC-BY) · miniF2F (MIT). Loaded by
	`58_bench` / `59_stem_diag` / `73_minif2f` for evaluation, not heal.

	## Contamination — verified CLEAN (CPU, 2026-06-18)
	The honest risk: the big reasoning/code datasets above can contain benchmark problems → memorized, not
	reasoned. Checked with `scripts/81_contamination_check.py` (miniF2F vs Lean training) and
	`scripts/82_heal_benchmark_contam.py` (benchmarks vs the 236 M-char heal corpus):

	\| Benchmark \| Present in training? \| Verdict \|
	\|---\|---\|---\|
	\| miniF2F-test (226) \| 0 exact · 1 near-dup (0.4 %) \| ✓ honest \|
	\| HumanEval (164) \| 0.0 % \| ✓ the 19/20 is honest \|
	\| GSM8K-test (sampled 300) \| 0.0 % \| ✓ honest \|

	Method: name-agnostic normalized exact-match + token-Jaccard near-dup (miniF2F) and normalized prompt-substring
	(HumanEval/GSM8K) — verbatim/near-verbatim inclusion would be caught. **Reported numbers are reasoned, not
	memorized.**

	## License stance
	Self-generated + hand-authored → MIT (matches the model + base `zai-org/GLM-5.2`, MIT). External-dataset portions
	retain their upstream licenses (table). The released model is a derivative; **verify each dataset's license before
	redistributing the heal data itself.**