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
+L-MChat-Small-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+L-MChat-Small-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+L-MChat-Small-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+L-MChat-Small-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+L-MChat-Small-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+L-MChat-Small-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+L-MChat-Small-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+L-MChat-Small-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+L-MChat-Small-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+L-MChat-Small-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+L-MChat-Small-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+L-MChat-Small-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text

L-MChat-Small-Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80743d46e27f69207bd58b3d4b3d7c79c30b48b3a950cf5ec3ee1dbcc2bfe497
+size 1109720768

L-MChat-Small-Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e090aafb934e052468c4af127dc510cf6b221d5b56c7f84f45fe341b843d147
+size 1575231168

L-MChat-Small-Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8926d5feee6e7edaf25f6b4a11f08387bb2c85790123963e6dc02a17edb045aa
+size 1426136768

L-MChat-Small-Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:caa311906919964983267bf6ebc3b93ffc873f46b03f7e27bed42c4a44a4f2c3
+size 1250827968

L-MChat-Small-Q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4c829cce09a469201a83ced21f23b7968596ad682c2f27a8cb5b4c6385e3d20
+size 1602469568

L-MChat-Small-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ca11b0473eba42fd394d106e6d2809f3139b09c792dff353dc9322ab4ae7f71
+size 1737637568

L-MChat-Small-Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9c04aa5c0b319fceb2eebe5efdfcffa4de51fb19d63eaff4b37e5c0a4fd9749
+size 1618853568

L-MChat-Small-Q5_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b447e36e17fd8cff2123ad1df79644b5e7a372acf3e2bbec900b353938d6a154
+size 1933426368

L-MChat-Small-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0a42e5315fd2a248c1561e9b79506d99b261c46369f55b5808a9e7595dc92f1
+size 2003058368

L-MChat-Small-Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a44372f1de5704dd4cf011154f7c9b4f530f4c0829c888b3f66a9330a4e1f939
+size 1933426368

L-MChat-Small-Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:990f0b585e27502fb9a715cf7118990d086dbb9b25fb94103f5beb7542948f82
+size 2285067968

L-MChat-Small-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a05565f48bffe23339d9541ea99a2f12c358fa217d84ab7d30ac2214d61f7a5
+size 2958040768

README.md

@@ -0,0 +1,180 @@
+---
+license: mit
+library_name: transformers
+tags:
+- mergekit
+- merge
+- TensorBlock
+- GGUF
+base_model: Artples/L-MChat-Small
+model-index:
+- name: L-MChat-Small
+  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: 61.6
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Artples/L-MChat-Small
+      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: 75.9
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Artples/L-MChat-Small
+      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: 57.41
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Artples/L-MChat-Small
+      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: 49.94
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Artples/L-MChat-Small
+      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: 74.98
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Artples/L-MChat-Small
+      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: 58.98
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Artples/L-MChat-Small
+      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>
+
+## Artples/L-MChat-Small - GGUF
+
+This repo contains GGUF format model files for [Artples/L-MChat-Small](https://huggingface.co/Artples/L-MChat-Small).
+
+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
+
+```
+<|im_start|>system
+{system_prompt}<|im_end|>
+<|im_start|>user
+{prompt}<|im_end|>
+<|im_start|>assistant
+```
+
+## Model file specification
+
+| Filename | Quant type | File Size | Description |
+| -------- | ---------- | --------- | ----------- |
+| [L-MChat-Small-Q2_K.gguf](https://huggingface.co/tensorblock/L-MChat-Small-GGUF/tree/main/L-MChat-Small-Q2_K.gguf) | Q2_K | 1.034 GB | smallest, significant quality loss - not recommended for most purposes |
+| [L-MChat-Small-Q3_K_S.gguf](https://huggingface.co/tensorblock/L-MChat-Small-GGUF/tree/main/L-MChat-Small-Q3_K_S.gguf) | Q3_K_S | 1.165 GB | very small, high quality loss |
+| [L-MChat-Small-Q3_K_M.gguf](https://huggingface.co/tensorblock/L-MChat-Small-GGUF/tree/main/L-MChat-Small-Q3_K_M.gguf) | Q3_K_M | 1.328 GB | very small, high quality loss |
+| [L-MChat-Small-Q3_K_L.gguf](https://huggingface.co/tensorblock/L-MChat-Small-GGUF/tree/main/L-MChat-Small-Q3_K_L.gguf) | Q3_K_L | 1.467 GB | small, substantial quality loss |
+| [L-MChat-Small-Q4_0.gguf](https://huggingface.co/tensorblock/L-MChat-Small-GGUF/tree/main/L-MChat-Small-Q4_0.gguf) | Q4_0 | 1.492 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
+| [L-MChat-Small-Q4_K_S.gguf](https://huggingface.co/tensorblock/L-MChat-Small-GGUF/tree/main/L-MChat-Small-Q4_K_S.gguf) | Q4_K_S | 1.508 GB | small, greater quality loss |
+| [L-MChat-Small-Q4_K_M.gguf](https://huggingface.co/tensorblock/L-MChat-Small-GGUF/tree/main/L-MChat-Small-Q4_K_M.gguf) | Q4_K_M | 1.618 GB | medium, balanced quality - recommended |
+| [L-MChat-Small-Q5_0.gguf](https://huggingface.co/tensorblock/L-MChat-Small-GGUF/tree/main/L-MChat-Small-Q5_0.gguf) | Q5_0 | 1.801 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
+| [L-MChat-Small-Q5_K_S.gguf](https://huggingface.co/tensorblock/L-MChat-Small-GGUF/tree/main/L-MChat-Small-Q5_K_S.gguf) | Q5_K_S | 1.801 GB | large, low quality loss - recommended |
+| [L-MChat-Small-Q5_K_M.gguf](https://huggingface.co/tensorblock/L-MChat-Small-GGUF/tree/main/L-MChat-Small-Q5_K_M.gguf) | Q5_K_M | 1.865 GB | large, very low quality loss - recommended |
+| [L-MChat-Small-Q6_K.gguf](https://huggingface.co/tensorblock/L-MChat-Small-GGUF/tree/main/L-MChat-Small-Q6_K.gguf) | Q6_K | 2.128 GB | very large, extremely low quality loss |
+| [L-MChat-Small-Q8_0.gguf](https://huggingface.co/tensorblock/L-MChat-Small-GGUF/tree/main/L-MChat-Small-Q8_0.gguf) | Q8_0 | 2.755 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/L-MChat-Small-GGUF --include "L-MChat-Small-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/L-MChat-Small-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
+```