Text Generation
GGUF
Safetensors
English
mark_slm_v2
llama.cpp
deepseek2
mixture-of-experts
multi-head-latent-attention
iq4_nl
mark-ai
systems-engineering
custom_code
conversational
Instructions to use miceworks/Mark-SLM-V2-302M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use miceworks/Mark-SLM-V2-302M 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 miceworks/Mark-SLM-V2-302M:IQ4_NL # Run inference directly in the terminal: llama cli -hf miceworks/Mark-SLM-V2-302M:IQ4_NL
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf miceworks/Mark-SLM-V2-302M:IQ4_NL # Run inference directly in the terminal: llama cli -hf miceworks/Mark-SLM-V2-302M:IQ4_NL
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 miceworks/Mark-SLM-V2-302M:IQ4_NL # Run inference directly in the terminal: ./build/bin/llama cli -hf miceworks/Mark-SLM-V2-302M:IQ4_NL
Use Docker
docker model run hf.co/miceworks/Mark-SLM-V2-302M:IQ4_NL
- Llama new
- LM Studio
- Jan
- vLLM
How to use miceworks/Mark-SLM-V2-302M with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "miceworks/Mark-SLM-V2-302M" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "miceworks/Mark-SLM-V2-302M", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/miceworks/Mark-SLM-V2-302M:IQ4_NL
- Ollama
How to use miceworks/Mark-SLM-V2-302M with Ollama:
ollama run hf.co/miceworks/Mark-SLM-V2-302M:IQ4_NL
- Unsloth Desktop
- Docker Model Runner
How to use miceworks/Mark-SLM-V2-302M with Docker Model Runner:
docker model run hf.co/miceworks/Mark-SLM-V2-302M:IQ4_NL
- Lemonade
How to use miceworks/Mark-SLM-V2-302M with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull miceworks/Mark-SLM-V2-302M:IQ4_NL
Run and chat with the model
lemonade run user.Mark-SLM-V2-302M-IQ4_NL
List all available models
lemonade list
- Atomic Chat
|
Download README.md from miceworks/Mark-SLM-V2-302M: direct link, hf CLI and curl.
- Browser
- Download file 8.13 kB
-
https://huggingface.co/miceworks/Mark-SLM-V2-302M/resolve/main/README.md
- Command line
-
hf download hf://miceworks/Mark-SLM-V2-302M/README.md
-
curl -L -o README.md https://huggingface.co/miceworks/Mark-SLM-V2-302M/resolve/main/README.md
8.13 kB
| license: apache-2.0 | |
| library_name: gguf | |
| pipeline_tag: text-generation | |
| language: | |
| - en | |
| datasets: | |
| - miceworks/Mark-Ultra-Curriculum | |
| tags: | |
| - gguf | |
| - llama.cpp | |
| - deepseek2 | |
| - mixture-of-experts | |
| - multi-head-latent-attention | |
| - iq4_nl | |
| - mark-ai | |
| - systems-engineering | |
| # Mark-SLM-V2-302M | |
| ## Overview | |
| Mark-SLM-V2-302M is an experimental narrow checkpoint in the 302M family naming convention. It contains 329,132,000 total physical parameters and activates 155.72M parameters per token across 16 layers. It features 16 routed experts and 1 shared expert (2 active routed experts per token). | |
| Quantized in IQ4_NL, the binary occupies 178.33 MiB (186.99 MB / 186,993,472 bytes) and runs on 8 GB consumer GPUs with minimal VRAM consumption. | |
| ## Specifications | |
| | Field | Value | | |
| | :--- | :--- | | |
| | Architecture | `deepseek2` | | |
| | Training Status | `EXPERIMENTAL_NARROW_CHECKPOINT` | | |
| | Weight State Label | `Experimental Narrow Checkpoint` | | |
| | Binary Size | `178.33 MiB (186.99 MB / 186,993,472 bytes)` | | |
| | Total Parameters | `329,132,000` (329132000 physical across 281 tensors) | | |
| | Active Parameters | `155,723,744` (155723744 active) | | |
| | Vocabulary Size | `49152` | | |
| | Layers | `16` | | |
| | Hidden Dimension | `768` | | |
| | Attention Heads | `12` | | |
| | MLA Ranks | `q_lora_rank=384`, `kv_lora_rank=192`, `qk_rope_head_dim=32` | | |
| | MoE Experts | `16 routed, 1 shared (2 active/token)` | | |
| | Expert FFN Dim | `384` | | |
| | Context Length | `4096` tokens | | |
| | Quantization Type | `IQ4_NL` (4-bit non-linear) | | |
| | SHA-256 | `3c8c59547297bece64b49a08f39eac57cda23a47e47016283c5a63f3b31f174d` | | |
| ## Architecture | |
| ### Multi-Head Latent Attention (MLA) | |
| The model projects key and value states into a shared low-rank latent representation to decouple memory scaling from context length: | |
| ```text | |
| c_KV = h_t * W_DKV (dim: 192) | |
| c_Q = h_t * W_DQ (dim: 384) | |
| q_C = RMSNorm(c_Q * W_UQ) | |
| k_C = RMSNorm(c_KV * W_UK) | |
| ``` | |
| Decoupled rotary position embeddings are concatenated along a separate dimension: | |
| ```text | |
| k_R = RoPE(h_t * W_KR) (dim: 32) | |
| q_t = [q_C ; q_R] | |
| k_t = [k_C ; k_R] | |
| ``` | |
| ### KV Cache Memory Usage | |
| Physical memory consumption of the KV cache per token in FP16: | |
| `KV_bytes_per_token = 16 * (192 + 32) * 2 = 7,168 bytes/token` | |
| | Context Window | MLA KV Cache | Standard MHA KV Cache | Memory Savings | | |
| | :--- | :--- | :--- | :--- | | |
| | 4,096 tokens | 28.00 MiB | 192.00 MiB | 6.9x | | |
| | 8,192 tokens | 56.00 MiB | 384.00 MiB | 6.9x | | |
| | 32,768 tokens | 224.00 MiB | 1536.00 MiB | 6.9x | | |
| ### Mixture-of-Experts (Aux-Loss-Free Routing) | |
| - **Shared Experts (1S)**: Constantly active path for common representations: | |
| $$F_{\text{shared}}(x) = (\text{SiLU}(x W_{\text{gate}}) \odot (x W_{\text{up}})) W_{\text{down}}$$ | |
| - **Routed Experts (16R, Top-2)**: Routed using token-to-expert affinities $s_{i,t} = \sigma(u_t^T e_i)$ over biased scores $s_{i,t} + b_i$, where router bias vectors (`blk.{l}.exp_probs_b.bias`) are stored in FP32 precision. | |
| #### Aux-Loss-Free Routing Equation | |
| Router biases update per step to prevent expert collapse without penalizing primary task loss using the exact sign-based rule: | |
| $$b_i \leftarrow b_i + \gamma \cdot \operatorname{sign}(\bar{f} - f_i)$$ | |
| where $\gamma = 0.001$, $f_i$ is empirical expert frequency within the batch, and $\bar{f}$ is target uniform frequency. | |
| Router bias vectors are stored in FP32 precision or initialized to uniform values during pre-training to ensure stable routing dynamics. | |
| #### Domain Clan Partitioning | |
| The 16 routed experts are partitioned into 4 functional clans (4 experts per clan): | |
| - **Clan 0 (Experts 0-3)**: Systems code, kernel semantics, and concurrency. | |
| - **Clan 1 (Experts 4-7)**: Mathematics, formal logic, and STEM reasoning. | |
| - **Clan 2 (Experts 8-11)**: Security boundaries, protocols, and validation. | |
| - **Clan 3 (Experts 12-15)**: Structured Data, Tool Calling, and Symbolic Logic. | |
| ## Training Pipeline and Reproducibility | |
| - Training Code: Official pipelines and architecture implementations are maintained in the [Mark-AI scripts directory](https://github.com/thu12dta3/Mark-AI/tree/main/scripts). | |
| - Curricula and Datasets: Trained on open datasets hosted on the Hugging Face Hub, including [miceworks/Mark-Open-SLM-Curriculum](https://huggingface.co/datasets/miceworks/Mark-Open-SLM-Curriculum), [miceworks/Mark-Cyber-Curriculum](https://huggingface.co/datasets/miceworks/Mark-Cyber-Curriculum), and [miceworks/Mark-Ultra-Curriculum](https://huggingface.co/datasets/miceworks/Mark-Ultra-Curriculum). | |
| - Optimization Settings: AdamW optimizer ($\beta_1 = 0.9, \beta_2 = 0.95$, weight decay $0.1$, gradient clipping $1.0$). | |
| - Training Scope: Experimental narrow checkpoint (EXPERIMENTAL_NARROW_CHECKPOINT). Trained for 10,000 steps on miceworks/Mark-Ultra-Curriculum. The final training loss reached 0.263975, reflecting multi-epoch memorization on the small curriculum testbed dataset rather than broad open-domain generalization. | |
| ## Evaluation and Benchmark Results | |
| Achieved a final validation loss of 0.263975 across 10,000 training steps on the narrow miceworks/Mark-Ultra-Curriculum distribution (memorization artifact). | |
| ## Tokenizer and Vocabulary Specification | |
| - Vocabulary Size: `49152` tensor rows (4,311 active BPE tokens + 27,721 reserved padding slots) | |
| - Active BPE Merges: 3,981 merges | |
| - Epistemic Control Tokens: Self-RAG reasoning tags (`<think>`, `</think>`), tool delimiters (`<tool_call>`, `</tool_call>`), epistemic reflection tags (`[RETRIEVE]`, `[/RETRIEVE]`, `[EVALUATE]`, `[ACCEPT]`, `[REJECT]`) | |
| - Measured Compression Fertility: | |
| - English technical prose: $\approx 2.53\text{ characters/token}$ | |
| - Portuguese technical prose: $\approx 2.57\text{ characters/token}$ | |
| - C, Rust, and systems source code: $\approx 2.02\text{ characters/token}$ | |
| - Whitespace Round-Trip Fidelity: Indentation whitespace requires byte-fallback tokenization; leading 4 spaces may be stripped by ByteLevel decoder when token 28 is raw space sequence. | |
| ## Limitations and Intended Use | |
| - Architectural Research Scope: This model is an experimental architectural testbed for Multi-Head Latent Attention (MLA) and fine-grained MoE on 8 GB GPUs such as NVIDIA GeForce RTX 2060 Super (8 GB GDDR6, 256-bit, 448 GB/s), NOT a general-purpose conversational or multilingual assistant. | |
| - In-Distribution Curriculum Learning: Benchmark scores on `Mark-SLM-V3-150M` measure in-distribution learning on `miceworks/Mark-Open-SLM-Curriculum` (which includes official benchmark training splits permitted under Open SLM Leaderboard rules) rather than open-ended out-of-distribution generalization. | |
| - Parameter Scale Constraints: Absolute world knowledge and zero-shot reasoning capacity are bounded by compact parameter counts. | |
| ### Running Benchmarks on TPN Workbench and lm-evaluation-harness | |
| When running automated benchmarks on TPN Workbench, lm-evaluation-harness, LM Studio, or Hugging Face evaluation runners: | |
| - Select **Format: gguf** (or **Backend: llama.cpp**). | |
| - Do not evaluate via raw Python `transformers` with `safetensors` or `trust_remote_code=True`, because the native `deepseek2` MLA and fine-grained 3D MoE graph executes directly inside the C++/CUDA kernels of `llama.cpp`. | |
| ## Usage: Narrow Domain and Systems Engineering Verification | |
| This checkpoint is an experimental narrow checkpoint trained on specific low-level or systems engineering distributions. Outside its narrow domain, greedy inference produces fragmented outputs. | |
| ### Cryptographic Verification | |
| ```bash | |
| echo "3c8c59547297bece64b49a08f39eac57cda23a47e47016283c5a63f3b31f174d mark_slm_v2_302m_iq4_nl.gguf" | sha256sum -c - | |
| ``` | |
| ### Execution with llama.cpp | |
| ```bash | |
| llama-cli -m mark_slm_v2_302m_iq4_nl.gguf \ | |
| -p "Systems engineering stub: Implement a POSIX mutex initialization routine.\nCode:" \ | |
| -n 128 --temp 0.2 | |
| ``` | |
| ### Python Inspection | |
| ```python | |
| import gguf | |
| reader = gguf.GGUFReader("mark_slm_v2_302m_iq4_nl.gguf") | |
| print("Architecture:", reader.get_field("general.architecture")) | |
| print("Total Tensors:", len(reader.tensors)) | |
| total_params = sum(int(t.shape.prod()) for t in reader.tensors) | |
| print(f"Total Parameters: {total_params:,}") | |
| ``` | |