Update README.md

README.md

@@ -29,7 +29,7 @@ Created through innovative layer surgery combining multi-swap, interpolation, an
 
 | Quantization | Bits/Weight | Description | Download |
 |:---:|:---:|:---|:---:|
-| **Q8_0** | 8.00 | Highest quality, virtually lossless | [Qwen3-g023-tiny-v2-Q8_0.gguf](./Qwen3-g023-tiny-v2-Q8_0.gguf) |
+| **Q8_0** | 8.00 | Highest quality, virtually lossless (USE THIS ONE) | [Qwen3-g023-tiny-v2-Q8_0.gguf](./Qwen3-g023-tiny-v2-Q8_0.gguf) |
 | **Q6_K** | 6.57 | Excellent quality, good compression | [Qwen3-g023-tiny-v2-Q6_K.gguf](./Qwen3-g023-tiny-v2-Q6_K.gguf) |
 | **Q4_K_M** | 4.85 | Good balance of quality and size | [Qwen3-g023-tiny-v2-Q4_K_M.gguf](./Qwen3-g023-tiny-v2-Q4_K_M.gguf) |
 | **Q3_K_M** | 3.91 | High compression, moderate quality loss | [Qwen3-g023-tiny-v2-Q3_K_M.gguf](./Qwen3-g023-tiny-v2-Q3_K_M.gguf) |
@@ -93,12 +93,20 @@ Evaluated using a comprehensive test suite with 17 factual questions, 2 completi
 ```bash
 # Download the GGUF and create from Modelfile
 cat > Modelfile << 'EOF'
-FROM ./Qwen3-g023-tiny-v2-Q4_K_M.gguf
+FROM ./Qwen3-g023-tiny-v2-Q8_0.gguf
 
-PARAMETER temperature 0.6
+PARAMETER temperature 1.0
 PARAMETER top_p 0.95
-PARAMETER top_k 20
-PARAMETER min_p 0.0
+PARAMETER top_k 45
+PARAMETER min_p 0.1
+PARAMETER num_ctx 40000
+PARAMETER mirostat 2
+PARAMETER mirostat_tau 5.0
+PARAMETER mirostat_eta 0.1
+PARAMETER repeat_last_n 16384
+PARAMETER repeat_penalty 1.1
+PARAMETER presence_penalty 0.5
+PARAMETER frequency_penalty 1.0
 
 TEMPLATE """{{- if .System }}
 <|im_start|>system
@@ -126,16 +134,16 @@ ollama run qwen3-tiny-v2
 
 ```bash
 # Interactive chat
-llama-cli -m Qwen3-g023-tiny-v2-Q4_K_M.gguf \
+llama-cli -m Qwen3-g023-tiny-v2-Q8_0.gguf \
   --chat-template chatml -cnv
 
 # Thinking mode
-llama-cli -m Qwen3-g023-tiny-v2-Q4_K_M.gguf \
+llama-cli -m Qwen3-g023-tiny-v2-Q8_0.gguf \
   -p "<|im_start|>user\nExplain quantum computing<|im_end|>\n<|im_start|>assistant\n<think>\n" \
   -n 512
 
 # Non-thinking mode
-llama-cli -m Qwen3-g023-tiny-v2-Q4_K_M.gguf \
+llama-cli -m Qwen3-g023-tiny-v2-Q8_0.gguf \
   -p "<|im_start|>user\n/no_think What is 2+2?<|im_end|>\n<|im_start|>assistant\n" \
   -n 128
 ```
@@ -145,7 +153,7 @@ llama-cli -m Qwen3-g023-tiny-v2-Q4_K_M.gguf \
 ```python
 from llama_cpp import Llama
 
-model = Llama("Qwen3-g023-tiny-v2-Q4_K_M.gguf", n_ctx=4096)
+model = Llama("Qwen3-g023-tiny-v2-Q8_0.gguf", n_ctx=4096)
 response = model.create_chat_completion(
     messages=[
         {"role": "system", "content": "You are a helpful assistant."},