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
+neural-chat-7b-v3-3-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+neural-chat-7b-v3-3-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+neural-chat-7b-v3-3-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+neural-chat-7b-v3-3-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+neural-chat-7b-v3-3-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+neural-chat-7b-v3-3-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+neural-chat-7b-v3-3-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+neural-chat-7b-v3-3-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+neural-chat-7b-v3-3-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+neural-chat-7b-v3-3-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+neural-chat-7b-v3-3-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+neural-chat-7b-v3-3-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,212 @@
+---
+license: apache-2.0
+tags:
+- LLMs
+- mistral
+- math
+- Intel
+- TensorBlock
+- GGUF
+base_model: Intel/neural-chat-7b-v3-3
+model-index:
+- name: neural-chat-7b-v3-3
+  results:
+  - task:
+      type: Large Language Model
+      name: Large Language Model
+    dataset:
+      name: meta-math/MetaMathQA
+      type: meta-math/MetaMathQA
+    metrics:
+    - type: ARC (25-shot)
+      value: 66.89
+      name: ARC (25-shot)
+      verified: true
+    - type: HellaSwag (10-shot)
+      value: 85.26
+      name: HellaSwag (10-shot)
+      verified: true
+    - type: MMLU (5-shot)
+      value: 63.07
+      name: MMLU (5-shot)
+      verified: true
+    - type: TruthfulQA (0-shot)
+      value: 63.01
+      name: TruthfulQA (0-shot)
+      verified: true
+    - type: Winogrande (5-shot)
+      value: 79.64
+      name: Winogrande (5-shot)
+      verified: true
+    - type: GSM8K (5-shot)
+      value: 61.11
+      name: GSM8K (5-shot)
+      verified: true
+  - 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: 66.89
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Intel/neural-chat-7b-v3-3
+      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: 85.26
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Intel/neural-chat-7b-v3-3
+      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: 63.07
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Intel/neural-chat-7b-v3-3
+      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: 63.01
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Intel/neural-chat-7b-v3-3
+      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: 79.64
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Intel/neural-chat-7b-v3-3
+      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: 61.11
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Intel/neural-chat-7b-v3-3
+      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>
+
+## Intel/neural-chat-7b-v3-3 - GGUF
+
+This repo contains GGUF format model files for [Intel/neural-chat-7b-v3-3](https://huggingface.co/Intel/neural-chat-7b-v3-3).
+
+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
+
+```
+### System:
+{system_prompt}
+### User:
+{prompt} 
+### Assistant:
+```
+
+## Model file specification
+
+| Filename | Quant type | File Size | Description |
+| -------- | ---------- | --------- | ----------- |
+| [neural-chat-7b-v3-3-Q2_K.gguf](https://huggingface.co/tensorblock/neural-chat-7b-v3-3-GGUF/tree/main/neural-chat-7b-v3-3-Q2_K.gguf) | Q2_K | 2.532 GB | smallest, significant quality loss - not recommended for most purposes |
+| [neural-chat-7b-v3-3-Q3_K_S.gguf](https://huggingface.co/tensorblock/neural-chat-7b-v3-3-GGUF/tree/main/neural-chat-7b-v3-3-Q3_K_S.gguf) | Q3_K_S | 2.947 GB | very small, high quality loss |
+| [neural-chat-7b-v3-3-Q3_K_M.gguf](https://huggingface.co/tensorblock/neural-chat-7b-v3-3-GGUF/tree/main/neural-chat-7b-v3-3-Q3_K_M.gguf) | Q3_K_M | 3.277 GB | very small, high quality loss |
+| [neural-chat-7b-v3-3-Q3_K_L.gguf](https://huggingface.co/tensorblock/neural-chat-7b-v3-3-GGUF/tree/main/neural-chat-7b-v3-3-Q3_K_L.gguf) | Q3_K_L | 3.560 GB | small, substantial quality loss |
+| [neural-chat-7b-v3-3-Q4_0.gguf](https://huggingface.co/tensorblock/neural-chat-7b-v3-3-GGUF/tree/main/neural-chat-7b-v3-3-Q4_0.gguf) | Q4_0 | 3.827 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
+| [neural-chat-7b-v3-3-Q4_K_S.gguf](https://huggingface.co/tensorblock/neural-chat-7b-v3-3-GGUF/tree/main/neural-chat-7b-v3-3-Q4_K_S.gguf) | Q4_K_S | 3.856 GB | small, greater quality loss |
+| [neural-chat-7b-v3-3-Q4_K_M.gguf](https://huggingface.co/tensorblock/neural-chat-7b-v3-3-GGUF/tree/main/neural-chat-7b-v3-3-Q4_K_M.gguf) | Q4_K_M | 4.068 GB | medium, balanced quality - recommended |
+| [neural-chat-7b-v3-3-Q5_0.gguf](https://huggingface.co/tensorblock/neural-chat-7b-v3-3-GGUF/tree/main/neural-chat-7b-v3-3-Q5_0.gguf) | Q5_0 | 4.654 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
+| [neural-chat-7b-v3-3-Q5_K_S.gguf](https://huggingface.co/tensorblock/neural-chat-7b-v3-3-GGUF/tree/main/neural-chat-7b-v3-3-Q5_K_S.gguf) | Q5_K_S | 4.654 GB | large, low quality loss - recommended |
+| [neural-chat-7b-v3-3-Q5_K_M.gguf](https://huggingface.co/tensorblock/neural-chat-7b-v3-3-GGUF/tree/main/neural-chat-7b-v3-3-Q5_K_M.gguf) | Q5_K_M | 4.779 GB | large, very low quality loss - recommended |
+| [neural-chat-7b-v3-3-Q6_K.gguf](https://huggingface.co/tensorblock/neural-chat-7b-v3-3-GGUF/tree/main/neural-chat-7b-v3-3-Q6_K.gguf) | Q6_K | 5.534 GB | very large, extremely low quality loss |
+| [neural-chat-7b-v3-3-Q8_0.gguf](https://huggingface.co/tensorblock/neural-chat-7b-v3-3-GGUF/tree/main/neural-chat-7b-v3-3-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/neural-chat-7b-v3-3-GGUF --include "neural-chat-7b-v3-3-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/neural-chat-7b-v3-3-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
+```

neural-chat-7b-v3-3-Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11e61d31a419ff6dd4d035bc08fd72b1704d0b3a0e5814dd1df4a5df083b93cb
+size 2719243680

neural-chat-7b-v3-3-Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5892c6d580c624720c428cfd5704667da786183631a8de0fce89e7ab8d8f4760
+size 3822026144

neural-chat-7b-v3-3-Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b938f550c0265d2147fb4a871e0ff457268e58ceef63951aea536d5cb82ec677
+size 3518987680

neural-chat-7b-v3-3-Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f137edf06bebe4d5fffbf3984c75eb17145f6d63f5699f97b6048f5716d4b96a
+size 3164568992

neural-chat-7b-v3-3-Q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35c20212ddf185796a2f677fd06234417f790d99108762dd43f0ed5a5d9ef504
+size 4108918176

neural-chat-7b-v3-3-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:372a10cabc30b7a5cb85c2ab8fb1a08741fe8d7f3784d508591f1eeb078b9c20
+size 4368440736

neural-chat-7b-v3-3-Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:447d009894f3ba4e42dc92ae185f35d6eab8ea4701a10cf0ad0d0bab655591bd
+size 4140375456

neural-chat-7b-v3-3-Q5_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a35349bdebf24c5d93caa9b19ea460f45825871c2caf284cc36f5d89133934a1
+size 4997717408

neural-chat-7b-v3-3-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e291ee602066d127f066f78cc813c410839957181fb6377884084e22d3264fc8
+size 5131410848

neural-chat-7b-v3-3-Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:320b0e0672422d751c56d3cd756c3cd1dc8d3056ba46b78525f36674bee437aa
+size 4997717408

neural-chat-7b-v3-3-Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c71322a3a4e26c1605d82c363531cad17fc10cd4dbf42c7a1e41b65b60125657
+size 5942066592

neural-chat-7b-v3-3-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:752c83ae008629dad42d48b5e968b9d0e9c3a7accc1de04474f7e5e344f1375b
+size 7695859104