Instructions to use bbkdevops/tinymind-ggufx-purecode with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use bbkdevops/tinymind-ggufx-purecode with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="bbkdevops/tinymind-ggufx-purecode",
	filename="tinymind-purebase.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use bbkdevops/tinymind-ggufx-purecode 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 bbkdevops/tinymind-ggufx-purecode
# Run inference directly in the terminal:
llama cli -hf bbkdevops/tinymind-ggufx-purecode

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf bbkdevops/tinymind-ggufx-purecode
# Run inference directly in the terminal:
llama cli -hf bbkdevops/tinymind-ggufx-purecode

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 bbkdevops/tinymind-ggufx-purecode
# Run inference directly in the terminal:
./llama-cli -hf bbkdevops/tinymind-ggufx-purecode

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 bbkdevops/tinymind-ggufx-purecode
# Run inference directly in the terminal:
./build/bin/llama-cli -hf bbkdevops/tinymind-ggufx-purecode

Use Docker

docker model run hf.co/bbkdevops/tinymind-ggufx-purecode

LM Studio
Jan

vLLM

How to use bbkdevops/tinymind-ggufx-purecode with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "bbkdevops/tinymind-ggufx-purecode"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "bbkdevops/tinymind-ggufx-purecode",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/bbkdevops/tinymind-ggufx-purecode

Ollama
How to use bbkdevops/tinymind-ggufx-purecode with Ollama:
```
ollama run hf.co/bbkdevops/tinymind-ggufx-purecode
```

Unsloth Studio

How to use bbkdevops/tinymind-ggufx-purecode 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 bbkdevops/tinymind-ggufx-purecode 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 bbkdevops/tinymind-ggufx-purecode to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for bbkdevops/tinymind-ggufx-purecode to start chatting

How to use bbkdevops/tinymind-ggufx-purecode with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf bbkdevops/tinymind-ggufx-purecode

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": "bbkdevops/tinymind-ggufx-purecode"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use bbkdevops/tinymind-ggufx-purecode with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf bbkdevops/tinymind-ggufx-purecode

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 bbkdevops/tinymind-ggufx-purecode

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use bbkdevops/tinymind-ggufx-purecode with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf bbkdevops/tinymind-ggufx-purecode

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 "bbkdevops/tinymind-ggufx-purecode" \
  --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 bbkdevops/tinymind-ggufx-purecode with Docker Model Runner:
```
docker model run hf.co/bbkdevops/tinymind-ggufx-purecode
```

Lemonade

How to use bbkdevops/tinymind-ggufx-purecode with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull bbkdevops/tinymind-ggufx-purecode

Run and chat with the model

lemonade run user.tinymind-ggufx-purecode-{{QUANT_TAG}}

List all available models

lemonade list

tinymind-ggufx-purecode / gguf_evo_upgrade_manifest.json

bbkdevops

Add TinyMind GGUF-X PureCode sidecar evidence pack

4a188dd verified about 2 months ago

Raw

History Blame Contribute Delete

4.85 kB

	{
	"base_modelfile": "model\\astraweave-fusion\\artifacts\\Modelfile.rawzero",
	"compare_script": "reports\\ggufx_purecode_latest\\compare_rawzero_vs_evo.ps1",
	"create_script": "reports\\ggufx_purecode_latest\\create_ollama_evo.ps1",
	"created_at": "2026-05-27T16:22:59.715373+00:00",
	"eval_prompts": "reports\\ggufx_purecode_latest\\gguf_evo_eval_prompts.jsonl",
	"evo_modelfile": "reports\\ggufx_purecode_latest\\Modelfile.evo",
	"ggufx_format": {
	"binary_compatibility": {
	"base_container": "GGUF",
	"base_container_version": 3,
	"runtime_target": "Ollama / llama.cpp compatible GGUF loader",
	"sidecar_required_for_tinymind_features": true
	},
	"claim_rules": {
	"may_claim_better_than_gguf_v3": false,
	"may_claim_binary_gguf_v3_compatibility": true,
	"may_claim_custom_tinymind_format_pack": true,
	"may_claim_weights_retrained_inside_gguf": false,
	"required_to_unlock_better_than_v3_claim": [
	"real adapter-to-GGUF merge/export log",
	"baseline GGUF v3 eval",
	"GGUF-X eval on same prompts",
	"latency/memory report",
	"hashes for every artifact"
	]
	},
	"format_kind": "GGUF-v3-compatible-binary-plus-TinyMind-sidecar",
	"schema_version": "tinymind-gguf-x-v1",
	"tinymind_extensions": {
	"adapter_lineage_gate": {
	"adapter_manifest": "model\\tinymind-12b\\adapters\\tinymind-12b-ggufx-purecode-lr3e7-s4-25690527_232007\\tinymind_12b_manifest.json",
	"enabled": true,
	"purpose": "separate trained LoRA evidence from GGUF packaging evidence",
	"training_manifest": "model\\tinymind-12b\\adapters\\tinymind-12b-ggufx-purecode-lr3e7-s4-25690527_232007\\tinymind_12b_manifest.json"
	},
	"evidence_first_decode_law": {
	"enabled": true,
	"purpose": "reduce hallucination/repetition without pretending the GGUF weights changed",
	"repeat_penalty": 1.19,
	"temperature": 0.14,
	"top_p": 0.78
	},
	"purity_lineage_gate": {
	"enabled": true,
	"manifest": "reports\\purity_concentrator_code_puremax_latest\\purity_concentrator_manifest.json",
	"purpose": "tie runtime claims to the exact purity-concentrated dataset used for adapter training"
	},
	"regen_ledger_ready_metadata": {
	"enabled": true,
	"kv_growth_claim": "bounded only when paired with Evidence Ledger/ReGenesis retrieval runtime"
	}
	}
	},
	"ggufx_readme": "reports\\ggufx_purecode_latest\\README_GGUF_X.md",
	"ggufx_spec": "reports\\ggufx_purecode_latest\\tinymind_ggufx_spec.json",
	"lineage": {
	"adapter_eval_loss": 2.808002471923828,
	"adapter_manifest": "model\\tinymind-12b\\adapters\\tinymind-12b-ggufx-purecode-lr3e7-s4-25690527_232007\\tinymind_12b_manifest.json",
	"adapter_perplexity": 16.576772556518506,
	"data_manifest": "reports\\purity_concentrator_code_puremax_latest\\purity_concentrator_manifest.json",
	"dominant_domain_share": 0.17511939959062997,
	"purity_density": 0.7211701159881736,
	"training_eval_loss": 2.808002471923828,
	"training_manifest": "model\\tinymind-12b\\adapters\\tinymind-12b-ggufx-purecode-lr3e7-s4-25690527_232007\\tinymind_12b_manifest.json",
	"training_perplexity": 16.576772556518506
	},
	"model_name": "tinymind-ggufx-purecode",
	"promotion_gate": {
	"adapter_training_evidence_present": true,
	"can_claim_better_than_v3": false,
	"can_claim_runtime_quality_upgrade": true,
	"can_claim_weights_better_than_source": false,
	"custom_ggufx_sidecar_created": true,
	"evo_eval_required": true,
	"gguf_binary_tensor_merge_performed": false,
	"must_beat_baseline_on_prompt_suite": true,
	"rawzero_baseline_required": true,
	"reason": "This pack upgrades GGUF runtime behavior and evaluation path. Weight-level improvement requires real conversion/export from trained adapters plus benchmark evidence.",
	"weight_training_performed": true
	},
	"runtime_upgrade": {
	"context_window_requested": 65536,
	"decode_profile": {
	"mirostat": 2,
	"repeat_penalty": 1.19,
	"temperature": 0.14,
	"top_k": 32,
	"top_p": 0.78
	},
	"quality_controls": [
	"evidence-first system law",
	"Thai-English technical preservation",
	"long-context anchor discipline",
	"claim-boundary enforcement",
	"lower-temperature repetition-resistant decoding"
	]
	},
	"schema_version": "tinymind-gguf-evo-upgrade-v1",
	"source_gguf": "model\\astraweave-fusion\\artifacts\\tinymind-purebase.gguf",
	"source_gguf_sha256": "b8707e57f676d8dd1b80f623b45200cc92e6966b0e95275e606f412095a49fde",
	"source_gguf_size_bytes": 16868240704,
	"source_gguf_size_gb": 15.709773361682892
	}