ky00040 commited on
Commit
6c363b4
·
verified ·
1 Parent(s): ef22c63

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +18 -0
README.md CHANGED
@@ -168,6 +168,24 @@ You are a Motoko expert for the Internet Computer. Write clean, compilable Motok
168
  3. **Mention state**: "Use Map for storage" guides the model toward correct patterns
169
  4. **Temperature 0.1** for reliable code, **0.7** for creative variations
170
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
171
  ## Known Limitations
172
 
173
  - Standalone function prompts without context may reference undefined types
 
168
  3. **Mention state**: "Use Map for storage" guides the model toward correct patterns
169
  4. **Temperature 0.1** for reliable code, **0.7** for creative variations
170
 
171
+ ## Hardware Requirements
172
+
173
+ This is a **MoE (Mixture of Experts) model** — 30B total parameters but only **3B active** per forward pass, making it much lighter than a dense 30B model.
174
+
175
+ | Setup | VRAM | Precision | Works? |
176
+ |-------|------|-----------|--------|
177
+ | 1x RTX 5090 / A100 40GB | 32-40GB | INT8 | ✅ Recommended |
178
+ | 2x RTX 5090 / 1x A100 80GB | 64-80GB | bf16 | ✅ Full precision |
179
+ | 1x RTX 5080 / 4090 / 4080 | 16-24GB | AWQ 4-bit | ✅ Quantized |
180
+ | Apple M4 Pro/Max | 36-128GB unified | MLX / llama.cpp | ✅ |
181
+
182
+ **Supported frameworks:**
183
+ - `transformers` + `peft` (recommended, tested)
184
+ - `vLLM` for serving
185
+ - `llama.cpp` / `Ollama` (with GGUF conversion)
186
+
187
+ > **Note:** This model is NOT compatible with Unsloth due to MoE architecture limitations.
188
+
189
  ## Known Limitations
190
 
191
  - Standalone function prompts without context may reference undefined types