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-v3-1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+neural-chat-7b-v3-1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+neural-chat-7b-v3-1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+neural-chat-7b-v3-1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+neural-chat-7b-v3-1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+neural-chat-7b-v3-1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+neural-chat-7b-v3-1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+neural-chat-7b-v3-1-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+neural-chat-7b-v3-1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+neural-chat-7b-v3-1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+neural-chat-7b-v3-1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+neural-chat-7b-v3-1-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,120 @@
+---
+license: apache-2.0
+tags:
+- LLMs
+- mistral
+- Intel
+- TensorBlock
+- GGUF
+pipeline_tag: text-generation
+base_model: Intel/neural-chat-7b-v3-1
+datasets:
+- Open-Orca/SlimOrca
+language:
+- en
+model-index:
+- name: neural-chat-7b-v3-1
+  results:
+  - task:
+      type: Large Language Model
+      name: Large Language Model
+    dataset:
+      name: Open-Orca/SlimOrca
+      type: Open-Orca/SlimOrca
+    metrics:
+    - type: ARC (25-shot)
+      value: 66.21
+      name: ARC (25-shot)
+      verified: true
+    - type: HellaSwag (10-shot)
+      value: 83.64
+      name: HellaSwag (10-shot)
+      verified: true
+    - type: MMLU (5-shot)
+      value: 62.37
+      name: MMLU (5-shot)
+      verified: true
+    - type: TruthfulQA (0-shot)
+      value: 59.65
+      name: TruthfulQA (0-shot)
+      verified: true
+    - type: Winogrande (5-shot)
+      value: 78.14
+      name: Winogrande (5-shot)
+      verified: true
+    - type: GSM8K (5-shot)
+      value: 19.56
+      name: GSM8K (5-shot)
+      verified: true
+    - type: DROP (3-shot)
+      value: 43.84
+      name: DROP (3-shot)
+      verified: true
+---
+
+<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-v3-1 - GGUF
+
+This repo contains GGUF format model files for [Intel/neural-chat-7b-v3-1](https://huggingface.co/Intel/neural-chat-7b-v3-1).
+
+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-v3-1-Q2_K.gguf](https://huggingface.co/tensorblock/neural-chat-7b-v3-1-GGUF/tree/main/neural-chat-7b-v3-1-Q2_K.gguf) | Q2_K | 2.532 GB | smallest, significant quality loss - not recommended for most purposes |
+| [neural-chat-7b-v3-1-Q3_K_S.gguf](https://huggingface.co/tensorblock/neural-chat-7b-v3-1-GGUF/tree/main/neural-chat-7b-v3-1-Q3_K_S.gguf) | Q3_K_S | 2.947 GB | very small, high quality loss |
+| [neural-chat-7b-v3-1-Q3_K_M.gguf](https://huggingface.co/tensorblock/neural-chat-7b-v3-1-GGUF/tree/main/neural-chat-7b-v3-1-Q3_K_M.gguf) | Q3_K_M | 3.277 GB | very small, high quality loss |
+| [neural-chat-7b-v3-1-Q3_K_L.gguf](https://huggingface.co/tensorblock/neural-chat-7b-v3-1-GGUF/tree/main/neural-chat-7b-v3-1-Q3_K_L.gguf) | Q3_K_L | 3.560 GB | small, substantial quality loss |
+| [neural-chat-7b-v3-1-Q4_0.gguf](https://huggingface.co/tensorblock/neural-chat-7b-v3-1-GGUF/tree/main/neural-chat-7b-v3-1-Q4_0.gguf) | Q4_0 | 3.827 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
+| [neural-chat-7b-v3-1-Q4_K_S.gguf](https://huggingface.co/tensorblock/neural-chat-7b-v3-1-GGUF/tree/main/neural-chat-7b-v3-1-Q4_K_S.gguf) | Q4_K_S | 3.856 GB | small, greater quality loss |
+| [neural-chat-7b-v3-1-Q4_K_M.gguf](https://huggingface.co/tensorblock/neural-chat-7b-v3-1-GGUF/tree/main/neural-chat-7b-v3-1-Q4_K_M.gguf) | Q4_K_M | 4.068 GB | medium, balanced quality - recommended |
+| [neural-chat-7b-v3-1-Q5_0.gguf](https://huggingface.co/tensorblock/neural-chat-7b-v3-1-GGUF/tree/main/neural-chat-7b-v3-1-Q5_0.gguf) | Q5_0 | 4.654 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
+| [neural-chat-7b-v3-1-Q5_K_S.gguf](https://huggingface.co/tensorblock/neural-chat-7b-v3-1-GGUF/tree/main/neural-chat-7b-v3-1-Q5_K_S.gguf) | Q5_K_S | 4.654 GB | large, low quality loss - recommended |
+| [neural-chat-7b-v3-1-Q5_K_M.gguf](https://huggingface.co/tensorblock/neural-chat-7b-v3-1-GGUF/tree/main/neural-chat-7b-v3-1-Q5_K_M.gguf) | Q5_K_M | 4.779 GB | large, very low quality loss - recommended |
+| [neural-chat-7b-v3-1-Q6_K.gguf](https://huggingface.co/tensorblock/neural-chat-7b-v3-1-GGUF/tree/main/neural-chat-7b-v3-1-Q6_K.gguf) | Q6_K | 5.534 GB | very large, extremely low quality loss |
+| [neural-chat-7b-v3-1-Q8_0.gguf](https://huggingface.co/tensorblock/neural-chat-7b-v3-1-GGUF/tree/main/neural-chat-7b-v3-1-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-v3-1-GGUF --include "neural-chat-7b-v3-1-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-v3-1-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
+```

neural-chat-7b-v3-1-Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:069c39a8ac22a7164bbb5838d7d02fb371dc43fbfdf6243e00f73c7da122f6c7
+size 2719243840

neural-chat-7b-v3-1-Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0c79ef14f93f5e5b3e076f935888c1baf97e8a98e0688387286a1d301cf99f3
+size 3822026304

neural-chat-7b-v3-1-Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:442f7f1e19404f1ed4943e971027baed086131888e928b46a58ba586c9b6fa91
+size 3518987840

neural-chat-7b-v3-1-Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b47152e52431156c7fa2f14a9e33916bcf348145616db0d0f452ee00089efef7
+size 3164569152

neural-chat-7b-v3-1-Q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a23b0918bb5a16ba34e00e128fd137e1d120527760ddca5e865fdf0a7baf8b49
+size 4108918336

neural-chat-7b-v3-1-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba1c328b39809e5bd9568e64ee181541373023bb1c38c5d292028a8f2fdd4265
+size 4368440896

neural-chat-7b-v3-1-Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16db303c609e7c0d947bf2df1f10922c72859a90b291084c02f15fb940905bc3
+size 4140375616

neural-chat-7b-v3-1-Q5_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7493949f7463f3bb9e1be0d9fdfa2f978b1df54f91bbdff4d368e6456ad9a7df
+size 4997717568

neural-chat-7b-v3-1-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d886f14f054748292e3c5749cd9a77697152b7f21d1cbe0570492692d06e0014
+size 5131411008

neural-chat-7b-v3-1-Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:590d56d9d9ae0b5401b36b77d9be83f0efda3f7538d13f830a981c8afa6c26cc
+size 4997717568

neural-chat-7b-v3-1-Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c804a960ec38c8cbc2bb50f6688e81ca1420bf51589cc9004a13af5ad7d1a4d
+size 5942066752

neural-chat-7b-v3-1-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6322ba3623f5966ad78222a69f84ef1d71ad3349433e4fe0fe5cf31933c105aa
+size 7695859264