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
+Medichat-Llama3-8B-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+Medichat-Llama3-8B-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+Medichat-Llama3-8B-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Medichat-Llama3-8B-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Medichat-Llama3-8B-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+Medichat-Llama3-8B-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Medichat-Llama3-8B-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Medichat-Llama3-8B-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+Medichat-Llama3-8B-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Medichat-Llama3-8B-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Medichat-Llama3-8B-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+Medichat-Llama3-8B-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text

Medichat-Llama3-8B-Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:392c64acf7e824f7135473e3cb97d833b02647efc76045bc5a18ea5006c51234
+size 3179132960

Medichat-Llama3-8B-Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5217a378106e9573a306ba6371bd6c4fb663aba25164ccbfc194c61286e0e37
+size 4321957920

Medichat-Llama3-8B-Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4cec3be834df911412a1b1810a3053f108720378e0951b157440352865aa3b23
+size 4018919456

Medichat-Llama3-8B-Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6791c9dad7ee2d0142268dd3ee738058edc239f37dc7d5e8d6669a48fea7cc32
+size 3664500768

Medichat-Llama3-8B-Q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a38a7d3518d25ed14220e57977041a5c3380fd0559332f236aa03c4beaf0959
+size 4661213216

Medichat-Llama3-8B-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90fbdeea43dce2d2796952a834ebc270578b5745abe2974f5ee29d9e58f7296e
+size 4920735776

Medichat-Llama3-8B-Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b325bcc5feda3bff24ed3dd1dae99cfc70496b70b7d01e9ea7020b4f01a8c4dd
+size 4692670496

Medichat-Llama3-8B-Q5_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c486d65b6426bf91f8198fd8668c537291704ab56908bc1ba485ed39715a2d4f
+size 5599295520

Medichat-Llama3-8B-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0aad069826404201438106c8761e50eb7cbd437456c93044ef54bc4f08282f6
+size 5732988960

Medichat-Llama3-8B-Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bdc7d3417d577cf8a0f2a6cd2c76dcea13c5de36baca5eb35a031516f1ab91e8
+size 5599295520

Medichat-Llama3-8B-Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b25acaae76a7d91e66d2c6985b637880129bf206ca6cee2cb54aa3ad8b44d1e
+size 6596007968

Medichat-Llama3-8B-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20874cc3fd33d44a7d76db95e96e2537ee63250b0300b2f32d4a53e07f6f23bf
+size 8540772384

README.md

@@ -0,0 +1,191 @@
+---
+base_model: sethuiyer/Medichat-Llama3-8B
+library_name: transformers
+tags:
+- mergekit
+- merge
+- medical
+- TensorBlock
+- GGUF
+license: other
+datasets:
+- mlabonne/orpo-dpo-mix-40k
+- Open-Orca/SlimOrca-Dedup
+- jondurbin/airoboros-3.2
+- microsoft/orca-math-word-problems-200k
+- m-a-p/Code-Feedback
+- MaziyarPanahi/WizardLM_evol_instruct_V2_196k
+- ruslanmv/ai-medical-chatbot
+language:
+- en
+model-index:
+- name: Medichat-Llama3-8B
+  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: 59.13
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sethuiyer/Medichat-Llama3-8B
+      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: 82.9
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sethuiyer/Medichat-Llama3-8B
+      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: 60.35
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sethuiyer/Medichat-Llama3-8B
+      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: 49.65
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sethuiyer/Medichat-Llama3-8B
+      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: 78.93
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sethuiyer/Medichat-Llama3-8B
+      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: 60.35
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sethuiyer/Medichat-Llama3-8B
+      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>
+
+## sethuiyer/Medichat-Llama3-8B - GGUF
+
+This repo contains GGUF format model files for [sethuiyer/Medichat-Llama3-8B](https://huggingface.co/sethuiyer/Medichat-Llama3-8B).
+
+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 |
+| -------- | ---------- | --------- | ----------- |
+| [Medichat-Llama3-8B-Q2_K.gguf](https://huggingface.co/tensorblock/Medichat-Llama3-8B-GGUF/tree/main/Medichat-Llama3-8B-Q2_K.gguf) | Q2_K | 2.961 GB | smallest, significant quality loss - not recommended for most purposes |
+| [Medichat-Llama3-8B-Q3_K_S.gguf](https://huggingface.co/tensorblock/Medichat-Llama3-8B-GGUF/tree/main/Medichat-Llama3-8B-Q3_K_S.gguf) | Q3_K_S | 3.413 GB | very small, high quality loss |
+| [Medichat-Llama3-8B-Q3_K_M.gguf](https://huggingface.co/tensorblock/Medichat-Llama3-8B-GGUF/tree/main/Medichat-Llama3-8B-Q3_K_M.gguf) | Q3_K_M | 3.743 GB | very small, high quality loss |
+| [Medichat-Llama3-8B-Q3_K_L.gguf](https://huggingface.co/tensorblock/Medichat-Llama3-8B-GGUF/tree/main/Medichat-Llama3-8B-Q3_K_L.gguf) | Q3_K_L | 4.025 GB | small, substantial quality loss |
+| [Medichat-Llama3-8B-Q4_0.gguf](https://huggingface.co/tensorblock/Medichat-Llama3-8B-GGUF/tree/main/Medichat-Llama3-8B-Q4_0.gguf) | Q4_0 | 4.341 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
+| [Medichat-Llama3-8B-Q4_K_S.gguf](https://huggingface.co/tensorblock/Medichat-Llama3-8B-GGUF/tree/main/Medichat-Llama3-8B-Q4_K_S.gguf) | Q4_K_S | 4.370 GB | small, greater quality loss |
+| [Medichat-Llama3-8B-Q4_K_M.gguf](https://huggingface.co/tensorblock/Medichat-Llama3-8B-GGUF/tree/main/Medichat-Llama3-8B-Q4_K_M.gguf) | Q4_K_M | 4.583 GB | medium, balanced quality - recommended |
+| [Medichat-Llama3-8B-Q5_0.gguf](https://huggingface.co/tensorblock/Medichat-Llama3-8B-GGUF/tree/main/Medichat-Llama3-8B-Q5_0.gguf) | Q5_0 | 5.215 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
+| [Medichat-Llama3-8B-Q5_K_S.gguf](https://huggingface.co/tensorblock/Medichat-Llama3-8B-GGUF/tree/main/Medichat-Llama3-8B-Q5_K_S.gguf) | Q5_K_S | 5.215 GB | large, low quality loss - recommended |
+| [Medichat-Llama3-8B-Q5_K_M.gguf](https://huggingface.co/tensorblock/Medichat-Llama3-8B-GGUF/tree/main/Medichat-Llama3-8B-Q5_K_M.gguf) | Q5_K_M | 5.339 GB | large, very low quality loss - recommended |
+| [Medichat-Llama3-8B-Q6_K.gguf](https://huggingface.co/tensorblock/Medichat-Llama3-8B-GGUF/tree/main/Medichat-Llama3-8B-Q6_K.gguf) | Q6_K | 6.143 GB | very large, extremely low quality loss |
+| [Medichat-Llama3-8B-Q8_0.gguf](https://huggingface.co/tensorblock/Medichat-Llama3-8B-GGUF/tree/main/Medichat-Llama3-8B-Q8_0.gguf) | Q8_0 | 7.954 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/Medichat-Llama3-8B-GGUF --include "Medichat-Llama3-8B-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/Medichat-Llama3-8B-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
+```