初始化项目，由ModelHub XC社区提供模型

Model: unsloth/DeepSeek-R1-Distill-Llama-8B-GGUF Source: Original Platform
2026-06-29 18:54:13 +08:00
commit 224ed5b6aa
32 changed files with 513 additions and 0 deletions
--- a/.gitattributes
+++ b/.gitattributes
@@ -0,0 +1,62 @@
 *.7z filter=lfs diff=lfs merge=lfs -text
 *.arrow filter=lfs diff=lfs merge=lfs -text
 *.bin filter=lfs diff=lfs merge=lfs -text
 *.bz2 filter=lfs diff=lfs merge=lfs -text
 *.ckpt filter=lfs diff=lfs merge=lfs -text
 *.ftz filter=lfs diff=lfs merge=lfs -text
 *.gz filter=lfs diff=lfs merge=lfs -text
 *.h5 filter=lfs diff=lfs merge=lfs -text
 *.joblib filter=lfs diff=lfs merge=lfs -text
 *.lfs.* filter=lfs diff=lfs merge=lfs -text
 *.mlmodel filter=lfs diff=lfs merge=lfs -text
 *.model filter=lfs diff=lfs merge=lfs -text
 *.msgpack filter=lfs diff=lfs merge=lfs -text
 *.npy filter=lfs diff=lfs merge=lfs -text
 *.npz filter=lfs diff=lfs merge=lfs -text
 *.onnx filter=lfs diff=lfs merge=lfs -text
 *.ot filter=lfs diff=lfs merge=lfs -text
 *.parquet filter=lfs diff=lfs merge=lfs -text
 *.pb filter=lfs diff=lfs merge=lfs -text
 *.pickle filter=lfs diff=lfs merge=lfs -text
 *.pkl filter=lfs diff=lfs merge=lfs -text
 *.pt filter=lfs diff=lfs merge=lfs -text
 *.pth filter=lfs diff=lfs merge=lfs -text
 *.rar filter=lfs diff=lfs merge=lfs -text
 *.safetensors filter=lfs diff=lfs merge=lfs -text
 saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.tar.* filter=lfs diff=lfs merge=lfs -text
 *.tar filter=lfs diff=lfs merge=lfs -text
 *.tflite filter=lfs diff=lfs merge=lfs -text
 *.tgz filter=lfs diff=lfs merge=lfs -text
 *.wasm filter=lfs diff=lfs merge=lfs -text
 *.xz filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 DeepSeek-R1-Distill-Llama-8B-Q2_K_L.gguf filter=lfs diff=lfs merge=lfs -text
 DeepSeek-R1-Distill-Llama-8B-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
 DeepSeek-R1-Distill-Llama-8B-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
 DeepSeek-R1-Distill-Llama-8B-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
 DeepSeek-R1-Distill-Llama-8B-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
 DeepSeek-R1-Distill-Llama-8B-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
 DeepSeek-R1-Distill-Llama-8B-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
 DeepSeek-R1-Distill-Llama-8B-F16.gguf filter=lfs diff=lfs merge=lfs -text
 DeepSeek-R1-Distill-Llama-8B-UD-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text
 DeepSeek-R1-Distill-Llama-8B-UD-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text
 DeepSeek-R1-Distill-Llama-8B-UD-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text
 DeepSeek-R1-Distill-Llama-8B-UD-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text
 DeepSeek-R1-Distill-Llama-8B-UD-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text
 DeepSeek-R1-Distill-Llama-8B-UD-Q4_K_XL.gguf filter=lfs diff=lfs merge=lfs -text
 DeepSeek-R1-Distill-Llama-8B-BF16.gguf filter=lfs diff=lfs merge=lfs -text
 DeepSeek-R1-Distill-Llama-8B-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text
 DeepSeek-R1-Distill-Llama-8B-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
 DeepSeek-R1-Distill-Llama-8B-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
 DeepSeek-R1-Distill-Llama-8B-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
 DeepSeek-R1-Distill-Llama-8B-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text
 DeepSeek-R1-Distill-Llama-8B-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
 DeepSeek-R1-Distill-Llama-8B-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
 DeepSeek-R1-Distill-Llama-8B-UD-Q2_K_XL.gguf filter=lfs diff=lfs merge=lfs -text
 DeepSeek-R1-Distill-Llama-8B-UD-Q3_K_XL.gguf filter=lfs diff=lfs merge=lfs -text
 DeepSeek-R1-Distill-Llama-8B-UD-Q5_K_XL.gguf filter=lfs diff=lfs merge=lfs -text
 DeepSeek-R1-Distill-Llama-8B-UD-Q6_K_XL.gguf filter=lfs diff=lfs merge=lfs -text
 DeepSeek-R1-Distill-Llama-8B-UD-Q8_K_XL.gguf filter=lfs diff=lfs merge=lfs -text
--- a/DeepSeek-R1-Distill-Llama-8B-BF16.gguf
+++ b/DeepSeek-R1-Distill-Llama-8B-BF16.gguf
@@ -0,0 +1,3 @@
 version https://git-lfs.github.com/spec/v1
 oid sha256:06298d7029a8d3b8fa65bab77d810836f0b69d9c2f1581c75d09792421721dc4
 size 16068893856
--- a/DeepSeek-R1-Distill-Llama-8B-F16.gguf
+++ b/DeepSeek-R1-Distill-Llama-8B-F16.gguf
@@ -0,0 +1,3 @@
 version https://git-lfs.github.com/spec/v1
 oid sha256:4e4e7cf0946ab9d63a41316c115c9bd9d68058c1e4b265fc51c387159738088c
 size 16068893408
--- a/DeepSeek-R1-Distill-Llama-8B-IQ4_NL.gguf
+++ b/DeepSeek-R1-Distill-Llama-8B-IQ4_NL.gguf
@@ -0,0 +1,3 @@
 version https://git-lfs.github.com/spec/v1
 oid sha256:e6849a4a8deacbc4ea215c7e70370536e30c82ce53cc209107d7ea06cbe2db29
 size 4677991872
--- a/DeepSeek-R1-Distill-Llama-8B-IQ4_XS.gguf
+++ b/DeepSeek-R1-Distill-Llama-8B-IQ4_XS.gguf
@@ -0,0 +1,3 @@
 version https://git-lfs.github.com/spec/v1
 oid sha256:df6473076371976320dc13339fed94e1532c84ef3b3f4b2eeaf0fe0f19ed7376
 size 4464082368
--- a/DeepSeek-R1-Distill-Llama-8B-Q2_K.gguf
+++ b/DeepSeek-R1-Distill-Llama-8B-Q2_K.gguf
@@ -0,0 +1,3 @@
 version https://git-lfs.github.com/spec/v1
 oid sha256:4fc8724925a93a74bd8b858ad47fa5e8c8d0a2740ec257c0a93267a12073d67b
 size 3179134400
--- a/DeepSeek-R1-Distill-Llama-8B-Q2_K_L.gguf
+++ b/DeepSeek-R1-Distill-Llama-8B-Q2_K_L.gguf
@@ -0,0 +1,3 @@
 version https://git-lfs.github.com/spec/v1
 oid sha256:dd619fc424ef209425bb55901c2bfb0f5ca07d0c8ab618d9fff522b2faf94f8e
 size 3302260160
--- a/DeepSeek-R1-Distill-Llama-8B-Q3_K_M.gguf
+++ b/DeepSeek-R1-Distill-Llama-8B-Q3_K_M.gguf
@@ -0,0 +1,3 @@
 version https://git-lfs.github.com/spec/v1
 oid sha256:b472323613ea8fd028c72ff2c85bde9ca6f162379d5651d3fe77393bb7dd1747
 size 4018920896
--- a/DeepSeek-R1-Distill-Llama-8B-Q3_K_S.gguf
+++ b/DeepSeek-R1-Distill-Llama-8B-Q3_K_S.gguf
@@ -0,0 +1,3 @@
 version https://git-lfs.github.com/spec/v1
 oid sha256:af9cc4e9443dabe2e50491f28349e235afb7eaf826348c503378b19e068dad5f
 size 3664502208
--- a/DeepSeek-R1-Distill-Llama-8B-Q4_0.gguf
+++ b/DeepSeek-R1-Distill-Llama-8B-Q4_0.gguf
@@ -0,0 +1,3 @@
 version https://git-lfs.github.com/spec/v1
 oid sha256:4b041b222221e8e37d6faffe7b8184392a239c18c2d9a22e89e485b9a5a321e0
 size 4675894720
--- a/DeepSeek-R1-Distill-Llama-8B-Q4_1.gguf
+++ b/DeepSeek-R1-Distill-Llama-8B-Q4_1.gguf
@@ -0,0 +1,3 @@
 version https://git-lfs.github.com/spec/v1
 oid sha256:7a99db150a33c0525b76281ac01123ade90a834a2f027ec9b3ad08ee139d01d9
 size 5130255808
--- a/DeepSeek-R1-Distill-Llama-8B-Q4_K_M.gguf
+++ b/DeepSeek-R1-Distill-Llama-8B-Q4_K_M.gguf
@@ -0,0 +1,3 @@
 version https://git-lfs.github.com/spec/v1
 oid sha256:0addb1339a82385bcd973186cd80d18dcc71885d45eabd899781a118d03827d9
 size 4920737216
--- a/DeepSeek-R1-Distill-Llama-8B-Q4_K_S.gguf
+++ b/DeepSeek-R1-Distill-Llama-8B-Q4_K_S.gguf
@@ -0,0 +1,3 @@
 version https://git-lfs.github.com/spec/v1
 oid sha256:0e5b2a6fa717186c287f20ae9779204759b04d520d1f9d4cb3421be9da9a6d3e
 size 4692671936
--- a/DeepSeek-R1-Distill-Llama-8B-Q5_K_M.gguf
+++ b/DeepSeek-R1-Distill-Llama-8B-Q5_K_M.gguf
@@ -0,0 +1,3 @@
 version https://git-lfs.github.com/spec/v1
 oid sha256:dcf118abe847f21160cb87a3d44ee500f370be7f9f6d347da7e8405a9294a214
 size 5732990400
--- a/DeepSeek-R1-Distill-Llama-8B-Q5_K_S.gguf
+++ b/DeepSeek-R1-Distill-Llama-8B-Q5_K_S.gguf
@@ -0,0 +1,3 @@
 version https://git-lfs.github.com/spec/v1
 oid sha256:06eb90905102e2d14c95259066bc3c40a928ee633c2d1e44aaae23846ab097f9
 size 5599296960
--- a/DeepSeek-R1-Distill-Llama-8B-Q6_K.gguf
+++ b/DeepSeek-R1-Distill-Llama-8B-Q6_K.gguf
@@ -0,0 +1,3 @@
 version https://git-lfs.github.com/spec/v1
 oid sha256:403a545b2dce6dfbc3022c9613c06ce1dd80a9288ba4259bfe495e42ec015ec7
 size 6596009408
--- a/DeepSeek-R1-Distill-Llama-8B-Q8_0.gguf
+++ b/DeepSeek-R1-Distill-Llama-8B-Q8_0.gguf
@@ -0,0 +1,3 @@
 version https://git-lfs.github.com/spec/v1
 oid sha256:8c6e3924d662d3f24a96b228a5c317510c27e91c587e71e78877ed18a875ec82
 size 8540773088
--- a/DeepSeek-R1-Distill-Llama-8B-UD-IQ1_M.gguf
+++ b/DeepSeek-R1-Distill-Llama-8B-UD-IQ1_M.gguf
@@ -0,0 +1,3 @@
 version https://git-lfs.github.com/spec/v1
 oid sha256:bb7cbaacbdf50833b1703b3fae1781d144bfd2bffea66f9a27ef01167797cfac
 size 2292202944
--- a/DeepSeek-R1-Distill-Llama-8B-UD-IQ1_S.gguf
+++ b/DeepSeek-R1-Distill-Llama-8B-UD-IQ1_S.gguf
@@ -0,0 +1,3 @@
 version https://git-lfs.github.com/spec/v1
 oid sha256:4195f0b2c4b5af77a878a8cd04d57a45ac3cc9cdc48724c2b536cd4c0ab71815
 size 2164669888
--- a/DeepSeek-R1-Distill-Llama-8B-UD-IQ2_M.gguf
+++ b/DeepSeek-R1-Distill-Llama-8B-UD-IQ2_M.gguf
@@ -0,0 +1,3 @@
 version https://git-lfs.github.com/spec/v1
 oid sha256:8d2070aa908b3913f9d94f5a903defa138214c549045fcc10cca34997df88f5d
 size 3003268544
--- a/DeepSeek-R1-Distill-Llama-8B-UD-IQ2_XXS.gguf
+++ b/DeepSeek-R1-Distill-Llama-8B-UD-IQ2_XXS.gguf
@@ -0,0 +1,3 @@
 version https://git-lfs.github.com/spec/v1
 oid sha256:165b51ea372b96f84c03c3cadea2cfb086d75c37329eabd18fbc89c7ee054670
 size 2504867264
--- a/DeepSeek-R1-Distill-Llama-8B-UD-IQ3_XXS.gguf
+++ b/DeepSeek-R1-Distill-Llama-8B-UD-IQ3_XXS.gguf
@@ -0,0 +1,3 @@
 version https://git-lfs.github.com/spec/v1
 oid sha256:e73763e4972172dfa1c9f41e38358f80cdfebc947bbcee25122f2cda0f09bf5c
 size 3321773504
--- a/DeepSeek-R1-Distill-Llama-8B-UD-Q2_K_XL.gguf
+++ b/DeepSeek-R1-Distill-Llama-8B-UD-Q2_K_XL.gguf
@@ -0,0 +1,3 @@
 version https://git-lfs.github.com/spec/v1
 oid sha256:f09aad0d970b8326920c784baa9be920aeab4f74a450fee8c7628b634d2544e8
 size 3388767680
--- a/DeepSeek-R1-Distill-Llama-8B-UD-Q3_K_XL.gguf
+++ b/DeepSeek-R1-Distill-Llama-8B-UD-Q3_K_XL.gguf
@@ -0,0 +1,3 @@
 version https://git-lfs.github.com/spec/v1
 oid sha256:466c7688c4b24021ecd492d01e2dfaf773d09d1a2d5b62c0d74d39c67ada0022
 size 4199611840
--- a/DeepSeek-R1-Distill-Llama-8B-UD-Q4_K_XL.gguf
+++ b/DeepSeek-R1-Distill-Llama-8B-UD-Q4_K_XL.gguf
@@ -0,0 +1,3 @@
 version https://git-lfs.github.com/spec/v1
 oid sha256:c068e09539243f226c9c68c9bbe6f0fe23ee1aa6b647af465769714f046ff9f1
 size 4994203072
--- a/DeepSeek-R1-Distill-Llama-8B-UD-Q5_K_XL.gguf
+++ b/DeepSeek-R1-Distill-Llama-8B-UD-Q5_K_XL.gguf
@@ -0,0 +1,3 @@
 version https://git-lfs.github.com/spec/v1
 oid sha256:9766fd00d00f11efcb0c82052ef0ad086eaa1b60c3d3dee7a7ee886b986c5dc7
 size 5738134976
--- a/DeepSeek-R1-Distill-Llama-8B-UD-Q6_K_XL.gguf
+++ b/DeepSeek-R1-Distill-Llama-8B-UD-Q6_K_XL.gguf
@@ -0,0 +1,3 @@
 version https://git-lfs.github.com/spec/v1
 oid sha256:7d60707ba8014a10a9ab390f0cde339198f8b2ca1d69df375c90ae26ed2b815d
 size 7329930688
--- a/DeepSeek-R1-Distill-Llama-8B-UD-Q8_K_XL.gguf
+++ b/DeepSeek-R1-Distill-Llama-8B-UD-Q8_K_XL.gguf
@@ -0,0 +1,3 @@
 version https://git-lfs.github.com/spec/v1
 oid sha256:8ac6fc63283e0d99497d5b08ec974aedfbdeed5faf9f7b364f29921552f0efc9
 size 10575666624
--- a/README.md
+++ b/README.md
@@ -0,0 +1,335 @@
 ---
 base_model: deepseek-ai/DeepSeek-R1-Distill-Llama-8B
 language:
 - en
 library_name: transformers
 license: llama3.1
 tags:
 - deepseek
 - unsloth
 - transformers
 - llama
 - llama-3
 - meta
 ---
 <div>
  <p style="margin-bottom: 0; margin-top: 0;">
    <strong>See <a href="https://huggingface.co/collections/unsloth/deepseek-r1-all-versions-678e1c48f5d2fce87892ace5">our collection</a> for versions of Deepseek-R1 including GGUF & 4-bit formats.</strong>
  </p>
  <p style="margin-bottom: 0;">
    <em>Unsloth's DeepSeek-R1 <a href="https://unsloth.ai/blog/deepseekr1-dynamic">1.58-bit + 2-bit Dynamic Quants</a> is selectively quantized, greatly improving accuracy over standard 1-bit/2-bit.</em>
  </p>
  <div style="display: flex; gap: 5px; align-items: center; ">
    <a href="https://github.com/unslothai/unsloth/">
      <img src="https://github.com/unslothai/unsloth/raw/main/images/unsloth%20new%20logo.png" width="133">
    </a>
    <a href="https://discord.gg/unsloth">
      <img src="https://github.com/unslothai/unsloth/raw/main/images/Discord%20button.png" width="173">
    </a>
    <a href="https://docs.unsloth.ai/basics/tutorial-how-to-run-deepseek-r1-on-your-own-local-device">
      <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>
 </div>
 You can view more detailed instructions in our blog: [unsloth.ai/blog/deepseek-r1](https://unsloth.ai/blog/deepseek-r1)
 1. Do not forget about `<｜User｜>` and `<｜Assistant｜>` tokens! - Or use a chat template formatter
 2. Obtain the latest `llama.cpp` at https://github.com/ggerganov/llama.cpp
 3. Example with Q8_0 K quantized cache **Notice -no-cnv disables auto conversation mode**
   ```bash
   ./llama.cpp/llama-cli \
       --model unsloth/DeepSeek-R1-Distill-Llama-8B-GGUF/DeepSeek-R1-Distill-Llama-8B-Q4_K_M.gguf \
       --cache-type-k q8_0 \
       --threads 16 \
       --prompt '<｜User｜>What is 1+1?<｜Assistant｜>' \
       -no-cnv
   ```
   Example output:
   ```txt
    <think>
    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...
   ```
 4. 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 unsloth/DeepSeek-R1-Distill-Llama-8B-GGUF/DeepSeek-R1-Distill-Llama-8B-Q4_K_M.gguf
   --cache-type-k q8_0 
   --threads 16 
   --prompt '<｜User｜>What is 1+1?<｜Assistant｜>'
   --n-gpu-layers 20 \
    -no-cnv
   ```
 # 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)
 [<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
 ## ✨ Finetune for Free
 All notebooks are **beginner friendly**! Add your dataset, click "Run All", and you'll get a 2x faster finetuned model which can be exported to GGUF, vLLM or uploaded to Hugging Face.
 | Unsloth supports          |    Free Notebooks                                                                                           | Performance | Memory use |
 |-----------------|--------------------------------------------------------------------------------------------------------------------------|-------------|----------|
 | **GRPO with Phi-4 (14B)**      | [▶️ Start on Colab](https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Phi_4_(14B)-GRPO.ipynb)               | 2x faster | 80% less |
 | **Llama-3.2 (3B)**      | [▶️ Start on Colab](https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Llama3.2_(1B_and_3B)-Conversational.ipynb)               | 2.4x faster | 58% less |
 | **Llama-3.2 (11B vision)**      | [▶️ Start on Colab](https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Llama3.2_(11B)-Vision.ipynb)               | 2x faster | 60% less |
 | **Qwen2 VL (7B)**      | [▶️ Start on Colab](https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Qwen2_VL_(7B)-Vision.ipynb)               | 1.8x faster | 60% less |
 | **Qwen2.5 (7B)**      | [▶️ Start on Colab](https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Qwen2.5_(7B)-Alpaca.ipynb)               | 2x faster | 60% less |
 | **Llama-3.1 (8B)**      | [▶️ Start on Colab](https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Llama3.1_(8B)-Alpaca.ipynb)               | 2.4x faster | 58% less |
 | **Phi-3.5 (mini)** | [▶️ Start on Colab](https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Phi_3.5_Mini-Conversational.ipynb)               | 2x faster | 50% less |
 | **Gemma 2 (9B)**      | [▶️ Start on Colab](https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Gemma2_(9B)-Alpaca.ipynb)               | 2.4x faster | 58% less |
 | **Mistral (7B)**    | [▶️ Start on Colab](https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Mistral_v0.3_(7B)-Conversational.ipynb)               | 2.2x faster | 62% less |
 [<img src="https://raw.githubusercontent.com/unslothai/unsloth/refs/heads/main/images/documentation%20green%20button.png" width="200"/>](https://docs.unsloth.ai)
 - This [Llama 3.2 conversational notebook](https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Llama3.2_(1B_and_3B)-Conversational.ipynb) is useful for ShareGPT ChatML / Vicuna templates.
 - This [text completion notebook](https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Mistral_(7B)-Text_Completion.ipynb) is for raw text. This [DPO notebook](https://colab.research.google.com/drive/15vttTpzzVXv_tJwEk-hIcQ0S9FcEWvwP?usp=sharing) replicates Zephyr.
 - \* Kaggle has 2x T4s, but we use 1. Due to overhead, 1x T4 is 5x faster.
 ## Special Thanks
 A huge thank you to the DeepSeek team for creating and releasing these models.
 # DeepSeek-R1
 <!-- markdownlint-disable first-line-h1 -->
 <!-- markdownlint-disable html -->
 <!-- markdownlint-disable no-duplicate-header -->
 <div align="center">
  <img src="https://github.com/deepseek-ai/DeepSeek-V2/blob/main/figures/logo.svg?raw=true" width="60%" alt="DeepSeek-V3" />
 </div>
 <hr>
 <div align="center" style="line-height: 1;">
  <a href="https://www.deepseek.com/" target="_blank" style="margin: 2px;">
    <img alt="Homepage" src="https://github.com/deepseek-ai/DeepSeek-V2/blob/main/figures/badge.svg?raw=true" style="display: inline-block; vertical-align: middle;"/>
  </a>
  <a href="https://chat.deepseek.com/" target="_blank" style="margin: 2px;">
    <img alt="Chat" src="https://img.shields.io/badge/🤖%20Chat-DeepSeek%20R1-536af5?color=536af5&logoColor=white" style="display: inline-block; vertical-align: middle;"/>
  </a>
  <a href="https://huggingface.co/deepseek-ai" target="_blank" style="margin: 2px;">
    <img alt="Hugging Face" src="https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-DeepSeek%20AI-ffc107?color=ffc107&logoColor=white" style="display: inline-block; vertical-align: middle;"/>
  </a>
 </div>
 <div align="center" style="line-height: 1;">
  <a href="https://discord.gg/Tc7c45Zzu5" target="_blank" style="margin: 2px;">
    <img alt="Discord" src="https://img.shields.io/badge/Discord-DeepSeek%20AI-7289da?logo=discord&logoColor=white&color=7289da" style="display: inline-block; vertical-align: middle;"/>
  </a>
  <a href="https://github.com/deepseek-ai/DeepSeek-V2/blob/main/figures/qr.jpeg?raw=true" target="_blank" style="margin: 2px;">
    <img alt="Wechat" src="https://img.shields.io/badge/WeChat-DeepSeek%20AI-brightgreen?logo=wechat&logoColor=white" style="display: inline-block; vertical-align: middle;"/>
  </a>
  <a href="https://twitter.com/deepseek_ai" target="_blank" style="margin: 2px;">
    <img alt="Twitter Follow" src="https://img.shields.io/badge/Twitter-deepseek_ai-white?logo=x&logoColor=white" style="display: inline-block; vertical-align: middle;"/>
  </a>
 </div>
 <div align="center" style="line-height: 1;">
  <a href="https://github.com/deepseek-ai/DeepSeek-R1/blob/main/LICENSE-CODE" style="margin: 2px;">
    <img alt="Code License" src="https://img.shields.io/badge/Code_License-MIT-f5de53?&color=f5de53" style="display: inline-block; vertical-align: middle;"/>
  </a>
  <a href="https://github.com/deepseek-ai/DeepSeek-R1/blob/main/LICENSE-MODEL" style="margin: 2px;">
    <img alt="Model License" src="https://img.shields.io/badge/Model_License-Model_Agreement-f5de53?&color=f5de53" style="display: inline-block; vertical-align: middle;"/>
  </a>
 </div>
 <p align="center">
  <a href="https://github.com/deepseek-ai/DeepSeek-R1/blob/main/DeepSeek_R1.pdf"><b>Paper Link</b>👁️</a>
 </p>
 ## 1. Introduction
 We introduce our first-generation reasoning models, DeepSeek-R1-Zero and DeepSeek-R1. 
 DeepSeek-R1-Zero, a model trained via large-scale reinforcement learning (RL) without supervised fine-tuning (SFT) as a preliminary step, demonstrated remarkable performance on reasoning.
 With RL, DeepSeek-R1-Zero naturally emerged with numerous powerful and interesting reasoning behaviors.
 However, DeepSeek-R1-Zero encounters challenges such as endless repetition, poor readability, and language mixing. To address these issues and further enhance reasoning performance,
 we introduce DeepSeek-R1, which incorporates cold-start data before RL.
 DeepSeek-R1 achieves performance comparable to OpenAI-o1 across math, code, and reasoning tasks. 
 To support the research community, we have open-sourced DeepSeek-R1-Zero, DeepSeek-R1, and six dense models distilled from DeepSeek-R1 based on Llama and Qwen. DeepSeek-R1-Distill-Qwen-32B outperforms OpenAI-o1-mini across various benchmarks, achieving new state-of-the-art results for dense models.
 **NOTE: Before running DeepSeek-R1 series models locally, we kindly recommend reviewing the [Usage Recommendation](#usage-recommendations) section.**
 <p align="center">
  <img width="80%" src="figures/benchmark.jpg">
 </p>
 ## 2. Model Summary
 ---
 **Post-Training: Large-Scale Reinforcement Learning on the Base Model**
 -  We directly apply reinforcement learning (RL) to the base model without relying on supervised fine-tuning (SFT) as a preliminary step. This approach allows the model to explore chain-of-thought (CoT) for solving complex problems, resulting in the development of DeepSeek-R1-Zero. DeepSeek-R1-Zero demonstrates capabilities such as self-verification, reflection, and generating long CoTs, marking a significant milestone for the research community. Notably, it is the first open research to validate that reasoning capabilities of LLMs can be incentivized purely through RL, without the need for SFT. This breakthrough paves the way for future advancements in this area.
 -   We introduce our pipeline to develop DeepSeek-R1. The pipeline incorporates two RL stages aimed at discovering improved reasoning patterns and aligning with human preferences, as well as two SFT stages that serve as the seed for the model's reasoning and non-reasoning capabilities.
    We believe the pipeline will benefit the industry by creating better models. 
 ---
 **Distillation: Smaller Models Can Be Powerful Too**
 -  We demonstrate that the reasoning patterns of larger models can be distilled into smaller models, resulting in better performance compared to the reasoning patterns discovered through RL on small models. The open source DeepSeek-R1, as well as its API, will benefit the research community to distill better smaller models in the future. 
 - Using the reasoning data generated by DeepSeek-R1, we fine-tuned several dense models that are widely used in the research community. The evaluation results demonstrate that the distilled smaller dense models perform exceptionally well on benchmarks. We open-source distilled 1.5B, 7B, 8B, 14B, 32B, and 70B checkpoints based on Qwen2.5 and Llama3 series to the community.
 ## 3. Model Downloads
 ### DeepSeek-R1 Models
 <div align="center">
 | **Model** | **#Total Params** | **#Activated Params** | **Context Length** | **Download** |
 | :------------: | :------------: | :------------: | :------------: | :------------: |
 | DeepSeek-R1-Zero | 671B | 37B | 128K   | [🤗 HuggingFace](https://huggingface.co/deepseek-ai/DeepSeek-R1-Zero)   |
 | DeepSeek-R1   | 671B | 37B |  128K   | [🤗 HuggingFace](https://huggingface.co/deepseek-ai/DeepSeek-R1)   |
 </div>
 DeepSeek-R1-Zero & DeepSeek-R1 are trained based on DeepSeek-V3-Base. 
 For more details regarding the model architecture, please refer to [DeepSeek-V3](https://github.com/deepseek-ai/DeepSeek-V3) repository.
 ### DeepSeek-R1-Distill Models
 <div align="center">
 | **Model** | **Base Model** | **Download** |
 | :------------: | :------------: | :------------: |
 | DeepSeek-R1-Distill-Qwen-1.5B  | [Qwen2.5-Math-1.5B](https://huggingface.co/Qwen/Qwen2.5-Math-1.5B) | [🤗 HuggingFace](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B)   |
 | DeepSeek-R1-Distill-Qwen-7B  | [Qwen2.5-Math-7B](https://huggingface.co/Qwen/Qwen2.5-Math-7B) | [🤗 HuggingFace](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-7B)   |
 | DeepSeek-R1-Distill-Llama-8B  | [Llama-3.1-8B](https://huggingface.co/meta-llama/Llama-3.1-8B) | [🤗 HuggingFace](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Llama-8B)   |
 | DeepSeek-R1-Distill-Qwen-14B   | [Qwen2.5-14B](https://huggingface.co/Qwen/Qwen2.5-14B) | [🤗 HuggingFace](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-14B)   |
 |DeepSeek-R1-Distill-Qwen-32B  | [Qwen2.5-32B](https://huggingface.co/Qwen/Qwen2.5-32B) | [🤗 HuggingFace](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B)   |
 | DeepSeek-R1-Distill-Llama-70B  | [Llama-3.3-70B-Instruct](https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct) | [🤗 HuggingFace](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Llama-70B)   |
 </div>
 DeepSeek-R1-Distill models are fine-tuned based on open-source models, using samples generated by DeepSeek-R1.
 We slightly change their configs and tokenizers. Please use our setting to run these models.
 ## 4. Evaluation Results
 ### DeepSeek-R1-Evaluation
 For all our models, the maximum generation length is set to 32,768 tokens. For benchmarks requiring sampling, we use a temperature of $0.6$, a top-p value of $0.95$, and generate 64 responses per query to estimate pass@1.
 <div align="center">
 | Category | Benchmark (Metric) | Claude-3.5-Sonnet-1022 | GPT-4o 0513 | DeepSeek V3 | OpenAI o1-mini | OpenAI o1-1217 | DeepSeek R1 |
 |----------|-------------------|----------------------|------------|--------------|----------------|------------|--------------|
 | | Architecture | - | - | MoE | - | - | MoE |
 | | # Activated Params | - | - | 37B | - | - | 37B |
 | | # Total Params | - | - | 671B | - | - | 671B |
 | English | MMLU (Pass@1) | 88.3 | 87.2 | 88.5 | 85.2 | **91.8** | 90.8 |
 | | MMLU-Redux (EM) | 88.9 | 88.0 | 89.1 | 86.7 | - | **92.9** |
 | | MMLU-Pro (EM) | 78.0 | 72.6 | 75.9 | 80.3 | - | **84.0** |
 | | DROP (3-shot F1) | 88.3 | 83.7 | 91.6 | 83.9 | 90.2 | **92.2** |
 | | IF-Eval (Prompt Strict) | **86.5** | 84.3 | 86.1 | 84.8 | - | 83.3 |
 | | GPQA-Diamond (Pass@1) | 65.0 | 49.9 | 59.1 | 60.0 | **75.7** | 71.5 |
 | | SimpleQA (Correct) | 28.4 | 38.2 | 24.9 | 7.0 | **47.0** | 30.1 |
 | | FRAMES (Acc.) | 72.5 | 80.5 | 73.3 | 76.9 | - | **82.5** |
 | | AlpacaEval2.0 (LC-winrate) | 52.0 | 51.1 | 70.0 | 57.8 | - | **87.6** |
 | | ArenaHard (GPT-4-1106) | 85.2 | 80.4 | 85.5 | 92.0 | - | **92.3** |
 | Code | LiveCodeBench (Pass@1-COT) | 33.8 | 34.2 | - | 53.8 | 63.4 | **65.9** |
 | | Codeforces (Percentile) | 20.3 | 23.6 | 58.7 | 93.4 | **96.6** | 96.3 |
 | | Codeforces (Rating) | 717 | 759 | 1134 | 1820 | **2061** | 2029 |
 | | SWE Verified (Resolved) | **50.8** | 38.8 | 42.0 | 41.6 | 48.9 | 49.2 |
 | | Aider-Polyglot (Acc.) | 45.3 | 16.0 | 49.6 | 32.9 | **61.7** | 53.3 |
 | Math | AIME 2024 (Pass@1) | 16.0 | 9.3 | 39.2 | 63.6 | 79.2 | **79.8** |
 | | MATH-500 (Pass@1) | 78.3 | 74.6 | 90.2 | 90.0 | 96.4 | **97.3** |
 | | CNMO 2024 (Pass@1) | 13.1 | 10.8 | 43.2 | 67.6 | - | **78.8** |
 | Chinese | CLUEWSC (EM) | 85.4 | 87.9 | 90.9 | 89.9 | - | **92.8** |
 | | C-Eval (EM) | 76.7 | 76.0 | 86.5 | 68.9 | - | **91.8** |
 | | C-SimpleQA (Correct) | 55.4 | 58.7 | **68.0** | 40.3 | - | 63.7 |
 </div>
 ### Distilled Model Evaluation
 <div align="center">
 | Model                                    | AIME 2024 pass@1 | AIME 2024 cons@64 | MATH-500 pass@1 | GPQA Diamond pass@1 | LiveCodeBench pass@1 | CodeForces rating |
 |------------------------------------------|------------------|-------------------|-----------------|----------------------|----------------------|-------------------|
 | GPT-4o-0513                          | 9.3              | 13.4              | 74.6            | 49.9                 | 32.9                 | 759               |
 | Claude-3.5-Sonnet-1022             | 16.0             | 26.7                 | 78.3            | 65.0                 | 38.9                 | 717               |
 | o1-mini                              | 63.6             | 80.0              | 90.0            | 60.0                 | 53.8                 | **1820**          |
 | QwQ-32B-Preview                              | 44.0             | 60.0                 | 90.6            | 54.5               | 41.9                 | 1316              |
 | DeepSeek-R1-Distill-Qwen-1.5B       | 28.9             | 52.7              | 83.9            | 33.8                 | 16.9                 | 954               |
 | DeepSeek-R1-Distill-Qwen-7B          | 55.5             | 83.3              | 92.8            | 49.1                 | 37.6                 | 1189              |
 | DeepSeek-R1-Distill-Qwen-14B         | 69.7             | 80.0              | 93.9            | 59.1                 | 53.1                 | 1481              |
 | DeepSeek-R1-Distill-Qwen-32B        | **72.6**         | 83.3              | 94.3            | 62.1                 | 57.2                 | 1691              |
 | DeepSeek-R1-Distill-Llama-8B         | 50.4             | 80.0              | 89.1            | 49.0                 | 39.6                 | 1205              |
 | DeepSeek-R1-Distill-Llama-70B        | 70.0             | **86.7**          | **94.5**        | **65.2**             | **57.5**             | 1633              |
 </div>
 ## 5. Chat Website & API Platform
 You can chat with DeepSeek-R1 on DeepSeek's official website: [chat.deepseek.com](https://chat.deepseek.com), and switch on the button "DeepThink"
 We also provide OpenAI-Compatible API at DeepSeek Platform: [platform.deepseek.com](https://platform.deepseek.com/)
 ## 6. How to Run Locally
 ### DeepSeek-R1 Models
 Please visit [DeepSeek-V3](https://github.com/deepseek-ai/DeepSeek-V3) repo for more information about running DeepSeek-R1 locally.
 ### DeepSeek-R1-Distill Models
 DeepSeek-R1-Distill models can be utilized in the same manner as Qwen or Llama models.
 For instance, you can easily start a service using [vLLM](https://github.com/vllm-project/vllm):
 ```shell
 vllm serve deepseek-ai/DeepSeek-R1-Distill-Qwen-32B --tensor-parallel-size 2 --max-model-len 32768 --enforce-eager
 ```
 You can also easily start a service using [SGLang](https://github.com/sgl-project/sglang)
 ```bash
 python3 -m sglang.launch_server --model deepseek-ai/DeepSeek-R1-Distill-Qwen-32B --trust-remote-code --tp 2
 ```
 ### Usage Recommendations
 **We recommend adhering to the following configurations when utilizing the DeepSeek-R1 series models, including benchmarking, to achieve the expected performance:**
 1. Set the temperature within the range of 0.5-0.7 (0.6 is recommended) to prevent endless repetitions or incoherent outputs.
 2. **Avoid adding a system prompt; all instructions should be contained within the user prompt.**
 3. For mathematical problems, it is advisable to include a directive in your prompt such as: "Please reason step by step, and put your final answer within \boxed{}."
 4. When evaluating model performance, it is recommended to conduct multiple tests and average the results.
 ## 7. License
 This code repository and the model weights are licensed under the [MIT License](https://github.com/deepseek-ai/DeepSeek-R1/blob/main/LICENSE).
 DeepSeek-R1 series support commercial use, allow for any modifications and derivative works, including, but not limited to, distillation for training other LLMs. Please note that:
 - DeepSeek-R1-Distill-Qwen-1.5B, DeepSeek-R1-Distill-Qwen-7B, DeepSeek-R1-Distill-Qwen-14B and DeepSeek-R1-Distill-Qwen-32B are derived from [Qwen-2.5 series](https://github.com/QwenLM/Qwen2.5), which are originally licensed under [Apache 2.0 License](https://huggingface.co/Qwen/Qwen2.5-1.5B/blob/main/LICENSE), and now finetuned with 800k samples curated with DeepSeek-R1.
 - DeepSeek-R1-Distill-Llama-8B is derived from Llama3.1-8B-Base and is originally licensed under [llama3.1 license](https://huggingface.co/meta-llama/Llama-3.1-8B/blob/main/LICENSE).
 - DeepSeek-R1-Distill-Llama-70B is derived from Llama3.3-70B-Instruct and is originally licensed under [llama3.3 license](https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct/blob/main/LICENSE).
 ## 8. Citation
 ```
@misc{deepseekai2025deepseekr1incentivizingreasoningcapability,
      title={DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning}, 
      author={DeepSeek-AI and Daya Guo and Dejian Yang and Haowei Zhang and Junxiao Song and Ruoyu Zhang and Runxin Xu and Qihao Zhu and Shirong Ma and Peiyi Wang and Xiao Bi and Xiaokang Zhang and Xingkai Yu and Yu Wu and Z. F. Wu and Zhibin Gou and Zhihong Shao and Zhuoshu Li and Ziyi Gao and Aixin Liu and Bing Xue and Bingxuan Wang and Bochao Wu and Bei Feng and Chengda Lu and Chenggang Zhao and Chengqi Deng and Chenyu Zhang and Chong Ruan and Damai Dai and Deli Chen and Dongjie Ji and Erhang Li and Fangyun Lin and Fucong Dai and Fuli Luo and Guangbo Hao and Guanting Chen and Guowei Li and H. Zhang and Han Bao and Hanwei Xu and Haocheng Wang and Honghui Ding and Huajian Xin and Huazuo Gao and Hui Qu and Hui Li and Jianzhong Guo and Jiashi Li and Jiawei Wang and Jingchang Chen and Jingyang Yuan and Junjie Qiu and Junlong Li and J. L. Cai and Jiaqi Ni and Jian Liang and Jin Chen and Kai Dong and Kai Hu and Kaige Gao and Kang Guan and Kexin Huang and Kuai Yu and Lean Wang and Lecong Zhang and Liang Zhao and Litong Wang and Liyue Zhang and Lei Xu and Leyi Xia and Mingchuan Zhang and Minghua Zhang and Minghui Tang and Meng Li and Miaojun Wang and Mingming Li and Ning Tian and Panpan Huang and Peng Zhang and Qiancheng Wang and Qinyu Chen and Qiushi Du and Ruiqi Ge and Ruisong Zhang and Ruizhe Pan and Runji Wang and R. J. Chen and R. L. Jin and Ruyi Chen and Shanghao Lu and Shangyan Zhou and Shanhuang Chen and Shengfeng Ye and Shiyu Wang and Shuiping Yu and Shunfeng Zhou and Shuting Pan and S. S. Li and Shuang Zhou and Shaoqing Wu and Shengfeng Ye and Tao Yun and Tian Pei and Tianyu Sun and T. Wang and Wangding Zeng and Wanjia Zhao and Wen Liu and Wenfeng Liang and Wenjun Gao and Wenqin Yu and Wentao Zhang and W. L. Xiao and Wei An and Xiaodong Liu and Xiaohan Wang and Xiaokang Chen and Xiaotao Nie and Xin Cheng and Xin Liu and Xin Xie and Xingchao Liu and Xinyu Yang and Xinyuan Li and Xuecheng Su and Xuheng Lin and X. Q. Li and Xiangyue Jin and Xiaojin Shen and Xiaosha Chen and Xiaowen Sun and Xiaoxiang Wang and Xinnan Song and Xinyi Zhou and Xianzu Wang and Xinxia Shan and Y. K. Li and Y. Q. Wang and Y. X. Wei and Yang Zhang and Yanhong Xu and Yao Li and Yao Zhao and Yaofeng Sun and Yaohui Wang and Yi Yu and Yichao Zhang and Yifan Shi and Yiliang Xiong and Ying He and Yishi Piao and Yisong Wang and Yixuan Tan and Yiyang Ma and Yiyuan Liu and Yongqiang Guo and Yuan Ou and Yuduan Wang and Yue Gong and Yuheng Zou and Yujia He and Yunfan Xiong and Yuxiang Luo and Yuxiang You and Yuxuan Liu and Yuyang Zhou and Y. X. Zhu and Yanhong Xu and Yanping Huang and Yaohui Li and Yi Zheng and Yuchen Zhu and Yunxian Ma and Ying Tang and Yukun Zha and Yuting Yan and Z. Z. Ren and Zehui Ren and Zhangli Sha and Zhe Fu and Zhean Xu and Zhenda Xie and Zhengyan Zhang and Zhewen Hao and Zhicheng Ma and Zhigang Yan and Zhiyu Wu and Zihui Gu and Zijia Zhu and Zijun Liu and Zilin Li and Ziwei Xie and Ziyang Song and Zizheng Pan and Zhen Huang and Zhipeng Xu and Zhongyu Zhang and Zhen Zhang},
      year={2025},
      eprint={2501.12948},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2501.12948}, 
 }
 ```
 ## 9. Contact
 If you have any questions, please raise an issue or contact us at [service@deepseek.com](service@deepseek.com).
--- a/config.json
+++ b/config.json
@@ -0,0 +1,34 @@
 {
  "architectures": [
    "LlamaForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "bos_token_id": 128000,
  "eos_token_id": 128001,
  "hidden_act": "silu",
  "hidden_size": 4096,
  "initializer_range": 0.02,
  "intermediate_size": 14336,
  "max_position_embeddings": 131072,
  "mlp_bias": false,
  "model_type": "llama",
  "num_attention_heads": 32,
  "num_hidden_layers": 32,
  "num_key_value_heads": 8,
  "pretraining_tp": 1,
  "rms_norm_eps": 1e-05,
  "rope_scaling": {
    "factor": 8.0,
    "low_freq_factor": 1.0,
    "high_freq_factor": 4.0,
    "original_max_position_embeddings": 8192,
    "rope_type": "llama3"
  },
  "rope_theta": 500000.0,
  "tie_word_embeddings": false,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.43.0.dev0",
  "use_cache": true,
  "vocab_size": 128256
 }
--- a/configuration.json
+++ b/configuration.json
@@ -0,0 +1 @@
 {"framework": "pytorch", "task": "others", "allow_remote": true}
--- a/imatrix_unsloth.dat
+++ b/imatrix_unsloth.dat
		`@@ -0,0 +1 @@`
							`{"framework": "pytorch", "task": "others", "allow_remote": true}`