docs: clean card, cross-link models

README.md

@@ -1,89 +1,31 @@
 ---
 language:
-  - en
+- en
 license: eupl-1.2
-library_name: mlx
 tags:
-  - mlx
-  - safetensors
-  - gemma4
-  - lethean
-  - lem
-  - text-generation
-  - conversational
-  - 4-bit
+- safetensors
+- 4-bit
+- transformers
+- 8-bit
+- gguf
+- gemma4
 base_model:
-  - google/gemma-4-31B-it
+- google/gemma-4-31B-it
 base_model_relation: quantized
-pipeline_tag: text-generation
+pipeline_tag: any-to-any
+datasets:
+- lthn/LEM-research
 ---
 
 # Lemrd
 
-A Gemma 4 31B dense fine-tune by [Lethean Network](https://lthn.ai/lemrd).
-
-EUPL-1.2 · Apache 2.0 base · [lthn.ai/lemrd](https://lthn.ai/lemrd)
+A [Gemma 4 31B](https://huggingface.co/google/gemma-4-31B-it) finetune by [lthn.ai](https://lthn.ai) — EUPL-1.2
 
 ## Use
 
-### MLX
-
-```bash
-pip install mlx-lm
-```
-
-```python
-from mlx_lm import load, generate
-
-model, tokenizer = load("lthn/lemrd", revision="4bit")
-response = generate(model, tokenizer, prompt="Hello", max_tokens=200)
-```
-
-### Ollama
-
-```bash
-# Coming soon
-```
-
-### HF Transformers
-
-```python
-from transformers import AutoModelForCausalLM, AutoTokenizer
-
-model = AutoModelForCausalLM.from_pretrained("lthn/lemrd", revision="bf16-hf")
-tokenizer = AutoTokenizer.from_pretrained("lthn/lemrd", revision="bf16-hf")
-```
-
-## Branches
-
-### MLX
-
-| Branch | Size |
-|--------|------|
-| `bf16` | 57G |
-| `8bit` | 30G |
-| `6bit` | 23G |
-| `5bit` | 20G |
-| `4bit` | 16G |
-| `mxfp8` | 30G |
-| `mxfp4` | 15G |
-| `nvfp4` | 16G |
-
-### GGUF
-
-| Branch | Size |
-|--------|------|
-| `bf16-gguf` | Coming soon |
-| `8bit-gguf` | Coming soon |
-| `6bit-gguf` | Coming soon |
-| `5bit-gguf` | Coming soon |
-| `4bit-gguf` | Coming soon |
-
-### HF Transformers
+**MLX**: [4bit](https://huggingface.co/lthn/lemrd/tree/4bit), [5bit](https://huggingface.co/lthn/lemrd/tree/5bit), [6bit](https://huggingface.co/lthn/lemrd/tree/6bit), [8bit](https://huggingface.co/lthn/lemrd/tree/8bit), [bf16](https://huggingface.co/lthn/lemrd/tree/bf16), [mxfp4](https://huggingface.co/lthn/lemrd/tree/mxfp4), [mxfp8](https://huggingface.co/lthn/lemrd/tree/mxfp8), [nvfp4](https://huggingface.co/lthn/lemrd/tree/nvfp4)
 
-| Branch | Size |
-|--------|------|
-| `bf16-hf` | Coming soon |
+[Lemer (E2B)](https://huggingface.co/lthn/lemer) · [Lemma (E4B)](https://huggingface.co/lthn/lemma) · [Lemmy (26B)](https://huggingface.co/lthn/lemmy) · [Lemrd (31B)](https://huggingface.co/lthn/lemrd)
 
 ## Base
 
@@ -91,9 +33,8 @@ tokenizer = AutoTokenizer.from_pretrained("lthn/lemrd", revision="bf16-hf")
 
 ## More
 
-- [lthn.ai/lemrd](https://lthn.ai/lemrd)
-- [Lethean Network](https://lthn.ai)
-- [GitHub](https://github.com/dappcore)
+- [lthn.ai](https://lthn.ai)
+- [Lethean Network](https://github.com/LetheanNetwork)
 
 ## Licence