DeepseaOne commited on
Commit
6e25ece
·
verified ·
1 Parent(s): 41e8416

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +2 -0
README.md CHANGED
@@ -15,6 +15,8 @@ tags:
15
 
16
  NVFP4 (4-bit) quant of [CohereLabs/North-Mini-Code-1.0](https://huggingface.co/CohereLabs/North-Mini-Code-1.0), made with [llm-compressor](https://github.com/vllm-project/llm-compressor) (`nvfp4-pack-quantized`). ~17 GB. Experts quantized; router/gate/`lm_head` kept high-precision.
17
 
 
 
18
  Serve with vLLM (needs `Cohere2MoeForCausalLM` support + `cohere_melody`):
19
 
20
  ```bash
 
15
 
16
  NVFP4 (4-bit) quant of [CohereLabs/North-Mini-Code-1.0](https://huggingface.co/CohereLabs/North-Mini-Code-1.0), made with [llm-compressor](https://github.com/vllm-project/llm-compressor) (`nvfp4-pack-quantized`). ~17 GB. Experts quantized; router/gate/`lm_head` kept high-precision.
17
 
18
+ > Note: HF auto-reports ~17B parameters because it counts the FP4-packed `uint8` tensors (2 weights per byte). The actual model is **30B total / 3B active** (MoE), same as the base model.
19
+
20
  Serve with vLLM (needs `Cohere2MoeForCausalLM` support + `cohere_melody`):
21
 
22
  ```bash