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

FuseChat-7B-VaRM-Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c644a944c6abb3caa6c1c1beeb9686735d83045cff026be688f83ceeb83e919d
+size 2719252640

FuseChat-7B-VaRM-Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d2150a8a53c6b36023da38ef8ff60ebc1fe389f781fd6a0fead45aead9ac75c
+size 3822035936

FuseChat-7B-VaRM-Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e5504afbc17c1ff09e737987c1edcbbe2d360782e80d4096db84d1151b9e734
+size 3518997472

FuseChat-7B-VaRM-Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3cb52ff7efe7d1c451c561d0885b4fd0372ffc65a89c691636776f6677f5cce6
+size 3164578784

FuseChat-7B-VaRM-Q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc651dbddb1900141844ed190cebfe14819dea997731133a74b0c02c4ff29987
+size 4108929056

FuseChat-7B-VaRM-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec1169256482339bb6cb828adde51085653ba303f6d63527f7a8e2446423d3d7
+size 4368451616

FuseChat-7B-VaRM-Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13e9816e634d4f1e52497c182559787c389fec5a99e74f7ec061979b44140416
+size 4140386336

FuseChat-7B-VaRM-Q5_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2a6c4a5b0f3f0a06f4bf25bc311d23b87809fe0a059e91ac4574383a923532b
+size 4997729312

FuseChat-7B-VaRM-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e197899b2232f4573df88ee60ae66c7f6dd4151d6d491986f60ff2611a328f3
+size 5131422752

FuseChat-7B-VaRM-Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0772bda961e4ff61f60e9c667a623b29ae27bac69bca51be951aedb93c75c909
+size 4997729312

FuseChat-7B-VaRM-Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c303b7ba3da7e58fb98e735bfd854e797b33b74178a00e6aa3a6b68df3df84e5
+size 5942079584

FuseChat-7B-VaRM-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1069a3f2ec4732a6caf8331b763b03c2002c23c5c1774d3c73a26dcd61661a2
+size 7695876064

README.md

@@ -0,0 +1,202 @@
+---
+license: apache-2.0
+language:
+- en
+base_model: FuseAI/FuseChat-7B-VaRM
+datasets:
+- FuseAI/FuseChat-Mixture
+pipeline_tag: text-generation
+tags:
+- mistral
+- mixtral
+- solar
+- model-fusion
+- fusechat
+- TensorBlock
+- GGUF
+library_name: transformers
+model-index:
+- name: FuseChat-7B-VaRM
+  results:
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MT-Bench
+      type: unknown
+    metrics:
+    - type: unknown
+      value: 8.22
+      name: score
+    source:
+      url: https://huggingface.co/spaces/lmsys/mt-bench
+  - 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: 62.88
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=FuseAI/FuseChat-7B-VaRM
+      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: 84.25
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=FuseAI/FuseChat-7B-VaRM
+      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: 63.71
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=FuseAI/FuseChat-7B-VaRM
+      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: 45.67
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=FuseAI/FuseChat-7B-VaRM
+      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: 79.16
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=FuseAI/FuseChat-7B-VaRM
+      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: 63.46
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=FuseAI/FuseChat-7B-VaRM
+      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>
+
+## FuseAI/FuseChat-7B-VaRM - GGUF
+
+This repo contains GGUF format model files for [FuseAI/FuseChat-7B-VaRM](https://huggingface.co/FuseAI/FuseChat-7B-VaRM).
+
+The files were quantized using machines provided by [TensorBlock](https://tensorblock.co/), and they are compatible with llama.cpp as of [commit b4242](https://github.com/ggerganov/llama.cpp/commit/a6744e43e80f4be6398fc7733a01642c846dce1d).
+
+<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
+
+```
+<s>GPT4 Correct System: {system_prompt}<|end_of_turn|>GPT4 Correct User: {prompt}<|end_of_turn|>GPT4 Correct Assistant:
+```
+
+## Model file specification
+
+| Filename | Quant type | File Size | Description |
+| -------- | ---------- | --------- | ----------- |
+| [FuseChat-7B-VaRM-Q2_K.gguf](https://huggingface.co/tensorblock/FuseChat-7B-VaRM-GGUF/blob/main/FuseChat-7B-VaRM-Q2_K.gguf) | Q2_K | 2.719 GB | smallest, significant quality loss - not recommended for most purposes |
+| [FuseChat-7B-VaRM-Q3_K_S.gguf](https://huggingface.co/tensorblock/FuseChat-7B-VaRM-GGUF/blob/main/FuseChat-7B-VaRM-Q3_K_S.gguf) | Q3_K_S | 3.165 GB | very small, high quality loss |
+| [FuseChat-7B-VaRM-Q3_K_M.gguf](https://huggingface.co/tensorblock/FuseChat-7B-VaRM-GGUF/blob/main/FuseChat-7B-VaRM-Q3_K_M.gguf) | Q3_K_M | 3.519 GB | very small, high quality loss |
+| [FuseChat-7B-VaRM-Q3_K_L.gguf](https://huggingface.co/tensorblock/FuseChat-7B-VaRM-GGUF/blob/main/FuseChat-7B-VaRM-Q3_K_L.gguf) | Q3_K_L | 3.822 GB | small, substantial quality loss |
+| [FuseChat-7B-VaRM-Q4_0.gguf](https://huggingface.co/tensorblock/FuseChat-7B-VaRM-GGUF/blob/main/FuseChat-7B-VaRM-Q4_0.gguf) | Q4_0 | 4.109 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
+| [FuseChat-7B-VaRM-Q4_K_S.gguf](https://huggingface.co/tensorblock/FuseChat-7B-VaRM-GGUF/blob/main/FuseChat-7B-VaRM-Q4_K_S.gguf) | Q4_K_S | 4.140 GB | small, greater quality loss |
+| [FuseChat-7B-VaRM-Q4_K_M.gguf](https://huggingface.co/tensorblock/FuseChat-7B-VaRM-GGUF/blob/main/FuseChat-7B-VaRM-Q4_K_M.gguf) | Q4_K_M | 4.368 GB | medium, balanced quality - recommended |
+| [FuseChat-7B-VaRM-Q5_0.gguf](https://huggingface.co/tensorblock/FuseChat-7B-VaRM-GGUF/blob/main/FuseChat-7B-VaRM-Q5_0.gguf) | Q5_0 | 4.998 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
+| [FuseChat-7B-VaRM-Q5_K_S.gguf](https://huggingface.co/tensorblock/FuseChat-7B-VaRM-GGUF/blob/main/FuseChat-7B-VaRM-Q5_K_S.gguf) | Q5_K_S | 4.998 GB | large, low quality loss - recommended |
+| [FuseChat-7B-VaRM-Q5_K_M.gguf](https://huggingface.co/tensorblock/FuseChat-7B-VaRM-GGUF/blob/main/FuseChat-7B-VaRM-Q5_K_M.gguf) | Q5_K_M | 5.131 GB | large, very low quality loss - recommended |
+| [FuseChat-7B-VaRM-Q6_K.gguf](https://huggingface.co/tensorblock/FuseChat-7B-VaRM-GGUF/blob/main/FuseChat-7B-VaRM-Q6_K.gguf) | Q6_K | 5.942 GB | very large, extremely low quality loss |
+| [FuseChat-7B-VaRM-Q8_0.gguf](https://huggingface.co/tensorblock/FuseChat-7B-VaRM-GGUF/blob/main/FuseChat-7B-VaRM-Q8_0.gguf) | Q8_0 | 7.696 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/FuseChat-7B-VaRM-GGUF --include "FuseChat-7B-VaRM-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/FuseChat-7B-VaRM-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
+```