Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,15 @@ saved_model/**/* 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-3B-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+DeepSeek-R1-Distill-Llama-3B-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+DeepSeek-R1-Distill-Llama-3B-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+DeepSeek-R1-Distill-Llama-3B-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+DeepSeek-R1-Distill-Llama-3B-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+DeepSeek-R1-Distill-Llama-3B-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+DeepSeek-R1-Distill-Llama-3B-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+DeepSeek-R1-Distill-Llama-3B-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+DeepSeek-R1-Distill-Llama-3B-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+DeepSeek-R1-Distill-Llama-3B-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+DeepSeek-R1-Distill-Llama-3B-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+DeepSeek-R1-Distill-Llama-3B-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text

DeepSeek-R1-Distill-Llama-3B-Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:213c0478997e4574d1946d85d95e54656cef02c129a03dc74eb101e7c8109020
+size 1363932736

DeepSeek-R1-Distill-Llama-3B-Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0bc9232f5f78949d1a22b47783028a14080b1b8ec29b29fbaff3d689b5b1ca2b
+size 1815344704

DeepSeek-R1-Distill-Llama-3B-Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3dcc904ef956274aba1cd1d2e28607dfd93d7b265b09ce7bac9abc09fb1fc03
+size 1687156288

DeepSeek-R1-Distill-Llama-3B-Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54b2b54669afb134b453348faf7597aff89ba010ebd87ddf858d634094e5ab13
+size 1542846016

DeepSeek-R1-Distill-Llama-3B-Q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32fd77c178731ccee89f7fa240ba626a96f6f6721a0bedae323cc25065d500c3
+size 1917187648

DeepSeek-R1-Distill-Llama-3B-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:859a46d8995ed079432fb45bf9abc7d12c44ab0b56f891de5a5049aa552dc4cc
+size 2019374656

DeepSeek-R1-Distill-Llama-3B-Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59dc612de6e21bdc59d15c60d2cebfdcc537589f1d3ea710a52bd3197e69f86e
+size 1928197696

DeepSeek-R1-Distill-Llama-3B-Q5_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b44b98434aba6c71ead83b97e2c9b4ccd734fb18a2255ea408530fdbfe0be0b
+size 2269509184

DeepSeek-R1-Distill-Llama-3B-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ee1dbc06d28091a8d6735c2b5874f37184af17fa258b83444bee7811bd9bf67
+size 2322150976

DeepSeek-R1-Distill-Llama-3B-Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d58867e5957ffb3574a3f6c21e83b37ce8ed5806bbff8944784d1b8864cd1d3
+size 2269509184

DeepSeek-R1-Distill-Llama-3B-Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74fabf7dec352ae2a33d8d3331a00498c8f8830fcade8435b87a8720018d8ce6
+size 2643850816

DeepSeek-R1-Distill-Llama-3B-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c18570b116510cac780b9b9664480aeb6beee2124292f88fca6c4f66204e0ec6
+size 3421896256

README.md

@@ -0,0 +1,184 @@
+---
+language:
+- en
+license: mit
+library_name: transformers
+tags:
+- reasoning
+- axolotl
+- r1
+- TensorBlock
+- GGUF
+base_model: suayptalha/DeepSeek-R1-Distill-Llama-3B
+datasets:
+- ServiceNow-AI/R1-Distill-SFT
+pipeline_tag: text-generation
+model-index:
+- name: DeepSeek-R1-Distill-Llama-3B
+  results:
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: IFEval (0-Shot)
+      type: HuggingFaceH4/ifeval
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: inst_level_strict_acc and prompt_level_strict_acc
+      value: 70.93
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=suayptalha/DeepSeek-R1-Distill-Llama-3B
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: BBH (3-Shot)
+      type: BBH
+      args:
+        num_few_shot: 3
+    metrics:
+    - type: acc_norm
+      value: 21.45
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=suayptalha/DeepSeek-R1-Distill-Llama-3B
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MATH Lvl 5 (4-Shot)
+      type: hendrycks/competition_math
+      args:
+        num_few_shot: 4
+    metrics:
+    - type: exact_match
+      value: 20.92
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=suayptalha/DeepSeek-R1-Distill-Llama-3B
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: GPQA (0-shot)
+      type: Idavidrein/gpqa
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: acc_norm
+      value: 1.45
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=suayptalha/DeepSeek-R1-Distill-Llama-3B
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MuSR (0-shot)
+      type: TAUR-Lab/MuSR
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: acc_norm
+      value: 2.91
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=suayptalha/DeepSeek-R1-Distill-Llama-3B
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MMLU-PRO (5-shot)
+      type: TIGER-Lab/MMLU-Pro
+      config: main
+      split: test
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 21.98
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=suayptalha/DeepSeek-R1-Distill-Llama-3B
+      name: Open LLM Leaderboard
+---
+
+<div style="width: auto; margin-left: auto; margin-right: auto">
+<img src="https://i.imgur.com/jC7kdl8.jpeg" alt="TensorBlock" style="width: 100%; min-width: 400px; display: block; margin: auto;">
+</div>
+<div style="display: flex; justify-content: space-between; width: 100%;">
+    <div style="display: flex; flex-direction: column; align-items: flex-start;">
+        <p style="margin-top: 0.5em; margin-bottom: 0em;">
+            Feedback and support: TensorBlock's  <a href="https://x.com/tensorblock_aoi">Twitter/X</a>, <a href="https://t.me/TensorBlock">Telegram Group</a> and <a href="https://x.com/tensorblock_aoi">Discord server</a>
+        </p>
+    </div>
+</div>
+
+## suayptalha/DeepSeek-R1-Distill-Llama-3B - GGUF
+
+This repo contains GGUF format model files for [suayptalha/DeepSeek-R1-Distill-Llama-3B](https://huggingface.co/suayptalha/DeepSeek-R1-Distill-Llama-3B).
+
+The files were quantized using machines provided by [TensorBlock](https://tensorblock.co/), and they are compatible with llama.cpp as of [commit b4882](https://github.com/ggml-org/llama.cpp/commit/be7c3034108473beda214fd1d7c98fd6a7a3bdf5).
+
+<div style="text-align: left; margin: 20px 0;">
+    <a href="https://tensorblock.co/waitlist/client" style="display: inline-block; padding: 10px 20px; background-color: #007bff; color: white; text-decoration: none; border-radius: 5px; font-weight: bold;">
+        Run them on the TensorBlock client using your local machine ↗
+    </a>
+</div>
+
+## Prompt template
+
+```
+<|begin_of_text|><|start_header_id|>system<|end_header_id|>
+
+{system_prompt}<|eot_id|><|start_header_id|>user<|end_header_id|>
+
+{prompt}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
+```
+
+## Model file specification
+
+| Filename | Quant type | File Size | Description |
+| -------- | ---------- | --------- | ----------- |
+| [DeepSeek-R1-Distill-Llama-3B-Q2_K.gguf](https://huggingface.co/tensorblock/DeepSeek-R1-Distill-Llama-3B-GGUF/blob/main/DeepSeek-R1-Distill-Llama-3B-Q2_K.gguf) | Q2_K | 1.364 GB | smallest, significant quality loss - not recommended for most purposes |
+| [DeepSeek-R1-Distill-Llama-3B-Q3_K_S.gguf](https://huggingface.co/tensorblock/DeepSeek-R1-Distill-Llama-3B-GGUF/blob/main/DeepSeek-R1-Distill-Llama-3B-Q3_K_S.gguf) | Q3_K_S | 1.543 GB | very small, high quality loss |
+| [DeepSeek-R1-Distill-Llama-3B-Q3_K_M.gguf](https://huggingface.co/tensorblock/DeepSeek-R1-Distill-Llama-3B-GGUF/blob/main/DeepSeek-R1-Distill-Llama-3B-Q3_K_M.gguf) | Q3_K_M | 1.687 GB | very small, high quality loss |
+| [DeepSeek-R1-Distill-Llama-3B-Q3_K_L.gguf](https://huggingface.co/tensorblock/DeepSeek-R1-Distill-Llama-3B-GGUF/blob/main/DeepSeek-R1-Distill-Llama-3B-Q3_K_L.gguf) | Q3_K_L | 1.815 GB | small, substantial quality loss |
+| [DeepSeek-R1-Distill-Llama-3B-Q4_0.gguf](https://huggingface.co/tensorblock/DeepSeek-R1-Distill-Llama-3B-GGUF/blob/main/DeepSeek-R1-Distill-Llama-3B-Q4_0.gguf) | Q4_0 | 1.917 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
+| [DeepSeek-R1-Distill-Llama-3B-Q4_K_S.gguf](https://huggingface.co/tensorblock/DeepSeek-R1-Distill-Llama-3B-GGUF/blob/main/DeepSeek-R1-Distill-Llama-3B-Q4_K_S.gguf) | Q4_K_S | 1.928 GB | small, greater quality loss |
+| [DeepSeek-R1-Distill-Llama-3B-Q4_K_M.gguf](https://huggingface.co/tensorblock/DeepSeek-R1-Distill-Llama-3B-GGUF/blob/main/DeepSeek-R1-Distill-Llama-3B-Q4_K_M.gguf) | Q4_K_M | 2.019 GB | medium, balanced quality - recommended |
+| [DeepSeek-R1-Distill-Llama-3B-Q5_0.gguf](https://huggingface.co/tensorblock/DeepSeek-R1-Distill-Llama-3B-GGUF/blob/main/DeepSeek-R1-Distill-Llama-3B-Q5_0.gguf) | Q5_0 | 2.270 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
+| [DeepSeek-R1-Distill-Llama-3B-Q5_K_S.gguf](https://huggingface.co/tensorblock/DeepSeek-R1-Distill-Llama-3B-GGUF/blob/main/DeepSeek-R1-Distill-Llama-3B-Q5_K_S.gguf) | Q5_K_S | 2.270 GB | large, low quality loss - recommended |
+| [DeepSeek-R1-Distill-Llama-3B-Q5_K_M.gguf](https://huggingface.co/tensorblock/DeepSeek-R1-Distill-Llama-3B-GGUF/blob/main/DeepSeek-R1-Distill-Llama-3B-Q5_K_M.gguf) | Q5_K_M | 2.322 GB | large, very low quality loss - recommended |
+| [DeepSeek-R1-Distill-Llama-3B-Q6_K.gguf](https://huggingface.co/tensorblock/DeepSeek-R1-Distill-Llama-3B-GGUF/blob/main/DeepSeek-R1-Distill-Llama-3B-Q6_K.gguf) | Q6_K | 2.644 GB | very large, extremely low quality loss |
+| [DeepSeek-R1-Distill-Llama-3B-Q8_0.gguf](https://huggingface.co/tensorblock/DeepSeek-R1-Distill-Llama-3B-GGUF/blob/main/DeepSeek-R1-Distill-Llama-3B-Q8_0.gguf) | Q8_0 | 3.422 GB | very large, extremely low quality loss - not recommended |
+
+
+## Downloading instruction
+
+### Command line
+
+Firstly, install Huggingface Client
+
+```shell
+pip install -U "huggingface_hub[cli]"
+```
+
+Then, downoad the individual model file the a local directory
+
+```shell
+huggingface-cli download tensorblock/DeepSeek-R1-Distill-Llama-3B-GGUF --include "DeepSeek-R1-Distill-Llama-3B-Q2_K.gguf" --local-dir MY_LOCAL_DIR
+```
+
+If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try:
+
+```shell
+huggingface-cli download tensorblock/DeepSeek-R1-Distill-Llama-3B-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
+```