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
+saiga-7b-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+saiga-7b-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+saiga-7b-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+saiga-7b-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+saiga-7b-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+saiga-7b-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+saiga-7b-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+saiga-7b-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+saiga-7b-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+saiga-7b-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+saiga-7b-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+saiga-7b-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,175 @@
+---
+language:
+- it
+license: apache-2.0
+base_model: FinancialSupport/saiga-7b
+tags:
+- TensorBlock
+- GGUF
+model-index:
+- name: saiga-7b
+  results:
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: AI2 Reasoning Challenge (25-Shot)
+      type: ai2_arc
+      config: ARC-Challenge
+      split: test
+      args:
+        num_few_shot: 25
+    metrics:
+    - type: acc_norm
+      value: 63.14
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=FinancialSupport/saiga-7b
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: HellaSwag (10-Shot)
+      type: hellaswag
+      split: validation
+      args:
+        num_few_shot: 10
+    metrics:
+    - type: acc_norm
+      value: 83.14
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=FinancialSupport/saiga-7b
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MMLU (5-Shot)
+      type: cais/mmlu
+      config: all
+      split: test
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 61.66
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=FinancialSupport/saiga-7b
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: TruthfulQA (0-shot)
+      type: truthful_qa
+      config: multiple_choice
+      split: validation
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: mc2
+      value: 54.99
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=FinancialSupport/saiga-7b
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: Winogrande (5-shot)
+      type: winogrande
+      config: winogrande_xl
+      split: validation
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 79.01
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=FinancialSupport/saiga-7b
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: GSM8k (5-shot)
+      type: gsm8k
+      config: main
+      split: test
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 45.11
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=FinancialSupport/saiga-7b
+      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>
+
+## FinancialSupport/saiga-7b - GGUF
+
+This repo contains GGUF format model files for [FinancialSupport/saiga-7b](https://huggingface.co/FinancialSupport/saiga-7b).
+
+The files were quantized using machines provided by [TensorBlock](https://tensorblock.co/), and they are compatible with llama.cpp as of [commit b4011](https://github.com/ggerganov/llama.cpp/commit/a6744e43e80f4be6398fc7733a01642c846dce1d).
+
+## Prompt template
+
+```
+<s>[INST] {prompt} [/INST]
+```
+
+## Model file specification
+
+| Filename | Quant type | File Size | Description |
+| -------- | ---------- | --------- | ----------- |
+| [saiga-7b-Q2_K.gguf](https://huggingface.co/tensorblock/saiga-7b-GGUF/tree/main/saiga-7b-Q2_K.gguf) | Q2_K | 2.532 GB | smallest, significant quality loss - not recommended for most purposes |
+| [saiga-7b-Q3_K_S.gguf](https://huggingface.co/tensorblock/saiga-7b-GGUF/tree/main/saiga-7b-Q3_K_S.gguf) | Q3_K_S | 2.947 GB | very small, high quality loss |
+| [saiga-7b-Q3_K_M.gguf](https://huggingface.co/tensorblock/saiga-7b-GGUF/tree/main/saiga-7b-Q3_K_M.gguf) | Q3_K_M | 3.277 GB | very small, high quality loss |
+| [saiga-7b-Q3_K_L.gguf](https://huggingface.co/tensorblock/saiga-7b-GGUF/tree/main/saiga-7b-Q3_K_L.gguf) | Q3_K_L | 3.560 GB | small, substantial quality loss |
+| [saiga-7b-Q4_0.gguf](https://huggingface.co/tensorblock/saiga-7b-GGUF/tree/main/saiga-7b-Q4_0.gguf) | Q4_0 | 3.827 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
+| [saiga-7b-Q4_K_S.gguf](https://huggingface.co/tensorblock/saiga-7b-GGUF/tree/main/saiga-7b-Q4_K_S.gguf) | Q4_K_S | 3.856 GB | small, greater quality loss |
+| [saiga-7b-Q4_K_M.gguf](https://huggingface.co/tensorblock/saiga-7b-GGUF/tree/main/saiga-7b-Q4_K_M.gguf) | Q4_K_M | 4.068 GB | medium, balanced quality - recommended |
+| [saiga-7b-Q5_0.gguf](https://huggingface.co/tensorblock/saiga-7b-GGUF/tree/main/saiga-7b-Q5_0.gguf) | Q5_0 | 4.654 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
+| [saiga-7b-Q5_K_S.gguf](https://huggingface.co/tensorblock/saiga-7b-GGUF/tree/main/saiga-7b-Q5_K_S.gguf) | Q5_K_S | 4.654 GB | large, low quality loss - recommended |
+| [saiga-7b-Q5_K_M.gguf](https://huggingface.co/tensorblock/saiga-7b-GGUF/tree/main/saiga-7b-Q5_K_M.gguf) | Q5_K_M | 4.779 GB | large, very low quality loss - recommended |
+| [saiga-7b-Q6_K.gguf](https://huggingface.co/tensorblock/saiga-7b-GGUF/tree/main/saiga-7b-Q6_K.gguf) | Q6_K | 5.534 GB | very large, extremely low quality loss |
+| [saiga-7b-Q8_0.gguf](https://huggingface.co/tensorblock/saiga-7b-GGUF/tree/main/saiga-7b-Q8_0.gguf) | Q8_0 | 7.167 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/saiga-7b-GGUF --include "saiga-7b-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/saiga-7b-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
+```

saiga-7b-Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02cede3a2dcc8193363d573be694f341c2fb6a878c4d8853f2437d3c14349e12
+size 2719242880

saiga-7b-Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb1f72eb934b78b31ffc5665ad4e6b53bb86d7fd4244e903d9763e5c69032c67
+size 3822025344

saiga-7b-Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:376aa3603e4c8ff5ade14505dfc5cf55c9e34de17f3571a413ff9f79876afdc7
+size 3518986880

saiga-7b-Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1441e4c2943bb3f8e43b93f5cef96306a3d55b5d733e65b8853a74942df02bfe
+size 3164568192

saiga-7b-Q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e44ae023b3d3232eab656c0d15011a52319c98be61190f5c8e138ea6e3f68c34
+size 4108917376

saiga-7b-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dfb9a948e0dabf047f362b9bb08464b7801758743bdbd7cd74f39d44f85db3e4
+size 4368439936

saiga-7b-Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca39f17754877ecddf72330e2b7edd3e1ddea06b86373405743e8f66f7d29656
+size 4140374656

saiga-7b-Q5_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4af8f0e83b0c9ae1c5ab3593c86769fc2e62b15efbddc72bdc533055e98a82a
+size 4997716608

saiga-7b-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c747bfe566676d00cb891feed9e1c2038c14d20383a8cd75f4e29b6325cde7b
+size 5131410048

saiga-7b-Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b989b280de9458c433e8800bad9d540d464d9a4d0ad44709ddf80be23ecfa6a5
+size 4997716608

saiga-7b-Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7794349dc70ca6c1b01d920315f281a95d6e3d63a51d46512c6cb13692b38aa4
+size 5942065792

saiga-7b-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1612a76e42c6fa8213fe5bb770a06be5e97991d58b217504bca2b1f1bd5eb836
+size 7695858304