Instructions to use LetheanNetwork/lemer-bk with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use LetheanNetwork/lemer-bk with Transformers:

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("LetheanNetwork/lemer-bk")
model = AutoModelForMultimodalLM.from_pretrained("LetheanNetwork/lemer-bk", device_map="auto")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use LetheanNetwork/lemer-bk 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 LetheanNetwork/lemer-bk:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf LetheanNetwork/lemer-bk:Q4_K_M

Install from WinGet (Windows)

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

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 LetheanNetwork/lemer-bk:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf LetheanNetwork/lemer-bk:Q4_K_M

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 LetheanNetwork/lemer-bk:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf LetheanNetwork/lemer-bk:Q4_K_M

Use Docker

docker model run hf.co/LetheanNetwork/lemer-bk:Q4_K_M

LM Studio
Jan
Ollama
How to use LetheanNetwork/lemer-bk with Ollama:
```
ollama run hf.co/LetheanNetwork/lemer-bk:Q4_K_M
```
Unsloth Desktop

How to use LetheanNetwork/lemer-bk with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf LetheanNetwork/lemer-bk: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": "LetheanNetwork/lemer-bk:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use LetheanNetwork/lemer-bk with Docker Model Runner:
```
docker model run hf.co/LetheanNetwork/lemer-bk:Q4_K_M
```

Lemonade

How to use LetheanNetwork/lemer-bk with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull LetheanNetwork/lemer-bk:Q4_K_M

Run and chat with the model

lemonade run user.lemer-bk-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use LetheanNetwork/lemer-bk with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf LetheanNetwork/lemer-bk: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 LetheanNetwork/lemer-bk:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use LetheanNetwork/lemer-bk with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf LetheanNetwork/lemer-bk: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 "LetheanNetwork/lemer-bk: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"

lthn commited on Apr 6

Commit

fb0fd7a

verified ·

1 Parent(s): 191c1a1

docs: add benchmarks grid + rapid-mlx usage

Browse files

Files changed (1) hide show

README.md +76 -16

README.md CHANGED Viewed

@@ -9,6 +9,8 @@ tags:
 - transformers
 - 8-bit
 - gguf
 base_model:
 - google/gemma-4-E2B-it
 base_model_relation: quantized
@@ -18,13 +20,60 @@ library_name: mlx
 # Lemer
-A Gemma 4 E2B fine-tune by [Lethean Network](https://lthn.ai/lemer).
-EUPL-1.2 · Apache 2.0 base · [lthn.ai/lemer](https://lthn.ai/lemer)
 ## Use
-### MLX
 ```bash
 pip install mlx-lm
@@ -37,10 +86,21 @@ model, tokenizer = load("lthn/lemer", revision="4bit")
 response = generate(model, tokenizer, prompt="Hello", max_tokens=200)
 ```
-### Ollama
 ```bash
-# Coming soon
 ```
 ### HF Transformers
@@ -71,17 +131,18 @@ tokenizer = AutoTokenizer.from_pretrained("lthn/lemer", revision="bf16-hf")
 | Branch | Size |
 |--------|------|
-| `bf16-gguf` | Coming soon |
-| `8bit-gguf` | Coming soon |
-| `6bit-gguf` | Coming soon |
-| `5bit-gguf` | Coming soon |
-| `4bit-gguf` | Coming soon |
 ### HF Transformers
 | Branch | Size |
 |--------|------|
-| `bf16-hf` | Coming soon |
 ## Base
@@ -89,11 +150,10 @@ tokenizer = AutoTokenizer.from_pretrained("lthn/lemer", revision="bf16-hf")
 ## More
-- [lthn.ai/lemer](https://lthn.ai/lemer)
-- [Lethean Network](https://lthn.ai)
-- [GitHub](https://github.com/dappcore)
 ## Licence
 Training data and adapter: [EUPL-1.2](https://joinup.ec.europa.eu/collection/eupl/eupl-text-eupl-12)
-Base model: [Apache 2.0](https://www.apache.org/licenses/LICENSE-2.0)

 - transformers
 - 8-bit
 - gguf
+- lek
+- lethean
 base_model:
 - google/gemma-4-E2B-it
 base_model_relation: quantized
 # Lemer
+A Gemma 4 E2B with LEK activation by [Lethean Network](https://lthn.ai).
+EUPL-1.2 · Apache 2.0 base · [lthn.ai](https://lthn.ai)
+## Benchmarks
+MMLU-Pro (TIGER-Lab/MMLU-Pro, test split), deterministic (temperature=0), thinking enabled.
+Evaluated using [rapid-mlx](https://github.com/LetheanNetwork/Rapid-MLX) + OpenAI SDK + Google `parse_response()`.
+### Lemer vs Stock Gemma 4 E2B (bf16, 20 samples per category)
+|  | Stock E2B bf16 | Lemer bf16 | Delta |
+| :---- | :----: | :----: | :----: |
+| Biology | 40.0% | **60.0%** | +20.0% |
+| Math | 10.0% | **55.0%** | +45.0% |
+| Business | TBC | TBC | TBC |
+| Chemistry | TBC | TBC | TBC |
+| Computer Science | TBC | TBC | TBC |
+| Economics | TBC | TBC | TBC |
+| Engineering | TBC | TBC | TBC |
+| Health | TBC | TBC | TBC |
+| History | TBC | TBC | TBC |
+| Law | TBC | TBC | TBC |
+| Other | TBC | TBC | TBC |
+| Philosophy | TBC | TBC | TBC |
+| Physics | TBC | TBC | TBC |
+| Psychology | TBC | TBC | TBC |
+| **Average** | **25.0%** | **57.5%** | **+32.5%** |
+> Stock Gemma 4 E2B shows a strong bias toward answer option "I" (50-80% of responses), suggesting RLHF calibration issues when served via MLX. Lemer does not exhibit this bias.
+### Lemer Quantisation Benchmarks (MMLU-Pro, all categories, avg of 4 runs)
+|  | bf16 | 8bit | 6bit | 5bit | 4bit | mxfp8 | mxfp4 | nvfp4 |
+| :---- | :----: | :----: | :----: | :----: | :----: | :----: | :----: | :----: |
+| Biology | 60.0% | TBC | TBC | TBC | TBC | TBC | TBC | TBC |
+| Math | 55.0% | TBC | TBC | TBC | TBC | TBC | TBC | TBC |
+| Business | TBC | TBC | TBC | TBC | TBC | TBC | TBC | TBC |
+| Chemistry | TBC | TBC | TBC | TBC | TBC | TBC | TBC | TBC |
+| Computer Science | TBC | TBC | TBC | TBC | TBC | TBC | TBC | TBC |
+| Economics | TBC | TBC | TBC | TBC | TBC | TBC | TBC | TBC |
+| Engineering | TBC | TBC | TBC | TBC | TBC | TBC | TBC | TBC |
+| Health | TBC | TBC | TBC | TBC | TBC | TBC | TBC | TBC |
+| History | TBC | TBC | TBC | TBC | TBC | TBC | TBC | TBC |
+| Law | TBC | TBC | TBC | TBC | TBC | TBC | TBC | TBC |
+| Other | TBC | TBC | TBC | TBC | TBC | TBC | TBC | TBC |
+| Philosophy | TBC | TBC | TBC | TBC | TBC | TBC | TBC | TBC |
+| Physics | TBC | TBC | TBC | TBC | TBC | TBC | TBC | TBC |
+| Psychology | TBC | TBC | TBC | TBC | TBC | TBC | TBC | TBC |
+| **Average** | TBC | TBC | TBC | TBC | TBC | TBC | TBC | TBC |
 ## Use
+### MLX (recommended for Apple Silicon)
 ```bash
 pip install mlx-lm
 response = generate(model, tokenizer, prompt="Hello", max_tokens=200)
 ```
+### Rapid-MLX (OpenAI-compatible server)
 ```bash
+pip install rapid-mlx
+rapid-mlx serve lthn/lemer --port 8100
+```
+```python
+from openai import OpenAI
+client = OpenAI(base_url="http://localhost:8100/v1", api_key="not-needed")
+response = client.chat.completions.create(
+    model="default",
+    messages=[{"role": "user", "content": "Hello"}],
+)
+print(response.choices[0].message.content)
 ```
 ### HF Transformers
 | Branch | Size |
 |--------|------|
+| `bf16-gguf` | 8.7G |
+| `8bit-gguf` | 4.6G |
+| `6bit-gguf` | 3.6G |
+| `5bit-gguf` | 3.0G |
+| `4bit-gguf` | 2.5G |
+| `3bit-gguf` | 2.0G |
 ### HF Transformers
 | Branch | Size |
 |--------|------|
+| `bf16-hf` | 8.7G |
 ## Base
 ## More
+- [lthn.ai](https://lthn.ai)
+- [Lethean Network](https://github.com/LetheanNetwork)
 ## Licence
 Training data and adapter: [EUPL-1.2](https://joinup.ec.europa.eu/collection/eupl/eupl-text-eupl-12)
+Base model: [Apache 2.0](https://www.apache.org/licenses/LICENSE-2.0)