Update README.md

README.md

@@ -28,84 +28,9 @@ tags:
       <img src="https://raw.githubusercontent.com/unslothai/unsloth/refs/heads/main/images/documentation%20green%20button.png" width="143">
     </a>
   </div>
-<h1 style="margin-top: 0rem;">Instructions to run this model in llama.cpp:</h2>
+<h1 style="margin-top: 0rem;">Finetune your own Reasoning model like R1 with Unsloth!</h2>
 </div>
 
-Or you can view more detailed instructions here: [unsloth.ai/blog/deepseekr1-dynamic](https://unsloth.ai/blog/deepseekr1-dynamic)
-1. Do not forget about `<｜User｜>` and `<｜Assistant｜>` tokens! - Or use a chat template formatter. Also 
-do not forget about `<think>\n`! 
-Prompt format: `"<｜User｜>Create a Flappy Bird game in Python.<｜Assistant｜><think>\n"`
-2. Obtain the latest `llama.cpp` at https://github.com/ggerganov/llama.cpp. You can follow the build instructions below as well:
-```bash
-apt-get update
-apt-get install build-essential cmake curl libcurl4-openssl-dev -y
-git clone https://github.com/ggerganov/llama.cpp
-cmake llama.cpp -B llama.cpp/build \
-	-DBUILD_SHARED_LIBS=OFF -DGGML_CUDA=ON -DLLAMA_CURL=ON
-cmake --build llama.cpp/build --config Release -j --clean-first --target llama-quantize llama-cli llama-gguf-split
-cp llama.cpp/build/bin/llama-* llama.cpp
-```
-3. It's best to use `--min-p 0.05` to counteract very rare token predictions - I found this to work well especially for the 1.58bit model.
-4. Download the model via:
-```python
-# pip install huggingface_hub hf_transfer
-# import os # Optional for faster downloading
-# os.environ["HF_HUB_ENABLE_HF_TRANSFER"] = "1"
-
-from huggingface_hub import snapshot_download
-snapshot_download(
-  repo_id = "unsloth/r1-1776-GGUF",
-  local_dir = "r1-1776-GGUF",
-  allow_patterns = ["*UD-Q2_K_XL*"], # Select quant type Q2_K_XL for dynamic 2bit
-)
-```
-5. Example with Q4_0 K quantized cache **Notice -no-cnv disables auto conversation mode**
-```bash
-   ./llama.cpp/llama-cli \
-	  --model r1-1776-GGUF/UD-Q2_K_XL/r1-1776-UD-Q2_K_XL-00001-of-00005.gguf \
-	  --cache-type-k q4_0 \
-	  --threads 12 -no-cnv --prio 2 \
-	  --temp 0.6 \
-	  --ctx-size 8192 \
-	  --seed 3407 \
-	  --prompt "<｜User｜>Create a Flappy Bird game in Python.<｜Assistant｜><think>\n"
-```
-   Example output:
-   
-   ```txt
-    Okay, so I need to figure out what 1 plus 1 is. Hmm, where do I even start? I remember from school that adding numbers is pretty basic, but I want to make sure I understand it properly.
-    Let me think, 1 plus 1. So, I have one item and I add another one. Maybe like a apple plus another apple. If I have one apple and someone gives me another, I now have two apples. So, 1 plus 1 should be 2. That makes sense.
-    Wait, but sometimes math can be tricky. Could it be something else? Like, in a different number system maybe? But I think the question is straightforward, using regular numbers, not like binary or hexadecimal or anything.
-    I also recall that in arithmetic, addition is combining quantities. So, if you have two quantities of 1, combining them gives you a total of 2. Yeah, that seems right.
-    Is there a scenario where 1 plus 1 wouldn't be 2? I can't think of any...
-   ```
-   
-6. If you have a GPU (RTX 4090 for example) with 24GB, you can offload multiple layers to the GPU for faster processing. If you have multiple GPUs, you can probably offload more layers.
-```bash
-  ./llama.cpp/llama-cli \
-    --model r1-1776-GGUF/UD-Q2_K_XL/r1-1776-UD-Q2_K_XL-00001-of-00005.gguf \
-    --cache-type-k q4_0 \
-    --threads 12 -no-cnv --prio 2 \
-    --n-gpu-layers 7 \
-    --temp 0.6 \
-    --ctx-size 8192 \
-    --seed 3407 \
-    --prompt "<｜User｜>Create a Flappy Bird game in Python.<｜Assistant｜><think>\n"
-```
-7. If you want to merge the weights together, use this script:
-```
-./llama.cpp/llama-gguf-split --merge \
-    r1-1776-GGUF/UD-Q2_K_XL/r1-1776-UD-Q2_K_XL-00001-of-00005.gguf \
-    merged_file.gguf
-```
-
-| Dynamic Bits     | Type   | Disk Size |  Accuracy | Link                      | Details   |
-| -------- | -------- | ------------ | ------------ | ---------------------|  ---------- |
-| 2bit | UD-Q2_K_XL |   **211GB**    | Better      | [Link](https://huggingface.co/unsloth/r1-1776-GGUF/tree/main/r1-1776-UD-Q2_K_XL) | MoE all 2.5bit. `down_proj` in MoE mixture of 3.5/2.5bit |
-| 3bit | UD-Q3_K_XL |   **298GB**    | Best        | [Link](https://huggingface.co/unsloth/r1-1776-GGUF/tree/main/r1-1776-UD-Q3_K_XL) | MoE Q3_K_M. Attention parts are upcasted |
-| 4bit | UD-Q4_K_XL |   **377GB**    | Best        | [Link](https://huggingface.co/unsloth/r1-1776-GGUF/tree/main/r1-1776-UD-Q4_K_XL) | MoE Q4_K_M. Attention parts are upcasted |
-
-# Finetune your own Reasoning model like R1 with Unsloth!
 We have a free Google Colab notebook for turning Llama 3.1 (8B) into a reasoning model: https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Llama3.1_(8B)-GRPO.ipynb
 
 [<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/Discord%20button.png" width="200"/>](https://discord.gg/unsloth)