Instructions to use tensorblock/KoSOLAR-10.7B-merge-v3.2-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tensorblock/KoSOLAR-10.7B-merge-v3.2-GGUF with Transformers:

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("tensorblock/KoSOLAR-10.7B-merge-v3.2-GGUF", dtype="auto")

llama-cpp-python

How to use tensorblock/KoSOLAR-10.7B-merge-v3.2-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="tensorblock/KoSOLAR-10.7B-merge-v3.2-GGUF",
	filename="KoSOLAR-10.7B-merge-v3.2-Q2_K.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use tensorblock/KoSOLAR-10.7B-merge-v3.2-GGUF with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf tensorblock/KoSOLAR-10.7B-merge-v3.2-GGUF:Q2_K
# Run inference directly in the terminal:
llama cli -hf tensorblock/KoSOLAR-10.7B-merge-v3.2-GGUF:Q2_K

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf tensorblock/KoSOLAR-10.7B-merge-v3.2-GGUF:Q2_K
# Run inference directly in the terminal:
llama cli -hf tensorblock/KoSOLAR-10.7B-merge-v3.2-GGUF:Q2_K

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf tensorblock/KoSOLAR-10.7B-merge-v3.2-GGUF:Q2_K
# Run inference directly in the terminal:
./llama-cli -hf tensorblock/KoSOLAR-10.7B-merge-v3.2-GGUF:Q2_K

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf tensorblock/KoSOLAR-10.7B-merge-v3.2-GGUF:Q2_K
# Run inference directly in the terminal:
./build/bin/llama-cli -hf tensorblock/KoSOLAR-10.7B-merge-v3.2-GGUF:Q2_K

Use Docker

docker model run hf.co/tensorblock/KoSOLAR-10.7B-merge-v3.2-GGUF:Q2_K

LM Studio
Jan
Ollama
How to use tensorblock/KoSOLAR-10.7B-merge-v3.2-GGUF with Ollama:
```
ollama run hf.co/tensorblock/KoSOLAR-10.7B-merge-v3.2-GGUF:Q2_K
```

Unsloth Studio

How to use tensorblock/KoSOLAR-10.7B-merge-v3.2-GGUF with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for tensorblock/KoSOLAR-10.7B-merge-v3.2-GGUF to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for tensorblock/KoSOLAR-10.7B-merge-v3.2-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for tensorblock/KoSOLAR-10.7B-merge-v3.2-GGUF to start chatting

Atomic Chat new
Docker Model Runner
How to use tensorblock/KoSOLAR-10.7B-merge-v3.2-GGUF with Docker Model Runner:
```
docker model run hf.co/tensorblock/KoSOLAR-10.7B-merge-v3.2-GGUF:Q2_K
```

Lemonade

How to use tensorblock/KoSOLAR-10.7B-merge-v3.2-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull tensorblock/KoSOLAR-10.7B-merge-v3.2-GGUF:Q2_K

Run and chat with the model

lemonade run user.KoSOLAR-10.7B-merge-v3.2-GGUF-Q2_K

List all available models

lemonade list

morriszms commited on Nov 15, 2024

Commit

5decd8a

verified ·

1 Parent(s): 9b8fcf4

Upload folder using huggingface_hub

Browse files

Files changed (14) hide show

.gitattributes +12 -0
KoSOLAR-10.7B-merge-v3.2-Q2_K.gguf +3 -0
KoSOLAR-10.7B-merge-v3.2-Q3_K_L.gguf +3 -0
KoSOLAR-10.7B-merge-v3.2-Q3_K_M.gguf +3 -0
KoSOLAR-10.7B-merge-v3.2-Q3_K_S.gguf +3 -0
KoSOLAR-10.7B-merge-v3.2-Q4_0.gguf +3 -0
KoSOLAR-10.7B-merge-v3.2-Q4_K_M.gguf +3 -0
KoSOLAR-10.7B-merge-v3.2-Q4_K_S.gguf +3 -0
KoSOLAR-10.7B-merge-v3.2-Q5_0.gguf +3 -0
KoSOLAR-10.7B-merge-v3.2-Q5_K_M.gguf +3 -0
KoSOLAR-10.7B-merge-v3.2-Q5_K_S.gguf +3 -0
KoSOLAR-10.7B-merge-v3.2-Q6_K.gguf +3 -0
KoSOLAR-10.7B-merge-v3.2-Q8_0.gguf +3 -0
README.md +73 -0

.gitattributes CHANGED Viewed

@@ -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

 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+KoSOLAR-10.7B-merge-v3.2-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+KoSOLAR-10.7B-merge-v3.2-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+KoSOLAR-10.7B-merge-v3.2-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+KoSOLAR-10.7B-merge-v3.2-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+KoSOLAR-10.7B-merge-v3.2-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+KoSOLAR-10.7B-merge-v3.2-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+KoSOLAR-10.7B-merge-v3.2-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+KoSOLAR-10.7B-merge-v3.2-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+KoSOLAR-10.7B-merge-v3.2-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+KoSOLAR-10.7B-merge-v3.2-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+KoSOLAR-10.7B-merge-v3.2-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+KoSOLAR-10.7B-merge-v3.2-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text

KoSOLAR-10.7B-merge-v3.2-Q2_K.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:1f0dcfa700d376f5316b74359e00043c15cefb61ad15d7efcfd3cdbb04af9610
+size 4045613760

KoSOLAR-10.7B-merge-v3.2-Q3_K_L.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:735b1832fa3ca1e7849f1883251654324aa742b7e149cf66570b3b8dfa37c212
+size 5696858816

KoSOLAR-10.7B-merge-v3.2-Q3_K_M.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:42d84ed900c8ce1e66873648b62c995252fcb1bf6018b82e503704ce59561a89
+size 5241776832

KoSOLAR-10.7B-merge-v3.2-Q3_K_S.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:d751b6f29b96f30670ded4d80212a5281cfa4572bd6e1a1bc28e772bddb5c004
+size 4710673088

KoSOLAR-10.7B-merge-v3.2-Q4_0.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:5fcc8ab7d0f610cb30e30f9130dc9add407bf77709419caa7f120cf1c52275e4
+size 6123367104

KoSOLAR-10.7B-merge-v3.2-Q4_K_M.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:d4132e9c9bac4a5e54a7a7098d2e542f473d21770f68bc3c3c34f5507d07550a
+size 6512650944

KoSOLAR-10.7B-merge-v3.2-Q4_K_S.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:f34cef2344c405ce16dfb3f20827fc23f30f2e33fb40c264fd0489a77748da9d
+size 6169504448

KoSOLAR-10.7B-merge-v3.2-Q5_0.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:4b4179eafc9978aa38f69573a8fa402b57ee4723554257af7c61163d4fe47c00
+size 7452961472

KoSOLAR-10.7B-merge-v3.2-Q5_K_M.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:67969c40c013b49af10b13ee066886fe9c9cf1d9c512f98f3184799f776f9528
+size 7653501632

KoSOLAR-10.7B-merge-v3.2-Q5_K_S.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:b09736ffedfca225c67c24a96f52c7e4426974b9dc432047ec62c93d52754741
+size 7452961472

KoSOLAR-10.7B-merge-v3.2-Q6_K.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:63d9f4516fee6620ada05dc79aa6204128977166011f1adcc4e88307064a3b91
+size 8865655488

KoSOLAR-10.7B-merge-v3.2-Q8_0.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:9b568539d3282b0a4806b88c125db28ec3becdf588b156c0c55837d5cab0cd70
+size 11482376896

README.md ADDED Viewed

	@@ -0,0 +1,73 @@

+---
+base_model: JY623/KoSOLAR-10.7B-merge-v3.2
+library_name: transformers
+tags:
+- mergekit
+- merge
+- TensorBlock
+- GGUF
+license: apache-2.0
+---
+<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>
+## JY623/KoSOLAR-10.7B-merge-v3.2 - GGUF
+This repo contains GGUF format model files for [JY623/KoSOLAR-10.7B-merge-v3.2](https://huggingface.co/JY623/KoSOLAR-10.7B-merge-v3.2).
+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
+```
+```
+## Model file specification
+| Filename | Quant type | File Size | Description |
+| -------- | ---------- | --------- | ----------- |
+| [KoSOLAR-10.7B-merge-v3.2-Q2_K.gguf](https://huggingface.co/tensorblock/KoSOLAR-10.7B-merge-v3.2-GGUF/tree/main/KoSOLAR-10.7B-merge-v3.2-Q2_K.gguf) | Q2_K | 3.768 GB | smallest, significant quality loss - not recommended for most purposes |
+| [KoSOLAR-10.7B-merge-v3.2-Q3_K_S.gguf](https://huggingface.co/tensorblock/KoSOLAR-10.7B-merge-v3.2-GGUF/tree/main/KoSOLAR-10.7B-merge-v3.2-Q3_K_S.gguf) | Q3_K_S | 4.387 GB | very small, high quality loss |
+| [KoSOLAR-10.7B-merge-v3.2-Q3_K_M.gguf](https://huggingface.co/tensorblock/KoSOLAR-10.7B-merge-v3.2-GGUF/tree/main/KoSOLAR-10.7B-merge-v3.2-Q3_K_M.gguf) | Q3_K_M | 4.882 GB | very small, high quality loss |
+| [KoSOLAR-10.7B-merge-v3.2-Q3_K_L.gguf](https://huggingface.co/tensorblock/KoSOLAR-10.7B-merge-v3.2-GGUF/tree/main/KoSOLAR-10.7B-merge-v3.2-Q3_K_L.gguf) | Q3_K_L | 5.306 GB | small, substantial quality loss |
+| [KoSOLAR-10.7B-merge-v3.2-Q4_0.gguf](https://huggingface.co/tensorblock/KoSOLAR-10.7B-merge-v3.2-GGUF/tree/main/KoSOLAR-10.7B-merge-v3.2-Q4_0.gguf) | Q4_0 | 5.703 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
+| [KoSOLAR-10.7B-merge-v3.2-Q4_K_S.gguf](https://huggingface.co/tensorblock/KoSOLAR-10.7B-merge-v3.2-GGUF/tree/main/KoSOLAR-10.7B-merge-v3.2-Q4_K_S.gguf) | Q4_K_S | 5.746 GB | small, greater quality loss |
+| [KoSOLAR-10.7B-merge-v3.2-Q4_K_M.gguf](https://huggingface.co/tensorblock/KoSOLAR-10.7B-merge-v3.2-GGUF/tree/main/KoSOLAR-10.7B-merge-v3.2-Q4_K_M.gguf) | Q4_K_M | 6.065 GB | medium, balanced quality - recommended |
+| [KoSOLAR-10.7B-merge-v3.2-Q5_0.gguf](https://huggingface.co/tensorblock/KoSOLAR-10.7B-merge-v3.2-GGUF/tree/main/KoSOLAR-10.7B-merge-v3.2-Q5_0.gguf) | Q5_0 | 6.941 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
+| [KoSOLAR-10.7B-merge-v3.2-Q5_K_S.gguf](https://huggingface.co/tensorblock/KoSOLAR-10.7B-merge-v3.2-GGUF/tree/main/KoSOLAR-10.7B-merge-v3.2-Q5_K_S.gguf) | Q5_K_S | 6.941 GB | large, low quality loss - recommended |
+| [KoSOLAR-10.7B-merge-v3.2-Q5_K_M.gguf](https://huggingface.co/tensorblock/KoSOLAR-10.7B-merge-v3.2-GGUF/tree/main/KoSOLAR-10.7B-merge-v3.2-Q5_K_M.gguf) | Q5_K_M | 7.128 GB | large, very low quality loss - recommended |
+| [KoSOLAR-10.7B-merge-v3.2-Q6_K.gguf](https://huggingface.co/tensorblock/KoSOLAR-10.7B-merge-v3.2-GGUF/tree/main/KoSOLAR-10.7B-merge-v3.2-Q6_K.gguf) | Q6_K | 8.257 GB | very large, extremely low quality loss |
+| [KoSOLAR-10.7B-merge-v3.2-Q8_0.gguf](https://huggingface.co/tensorblock/KoSOLAR-10.7B-merge-v3.2-GGUF/tree/main/KoSOLAR-10.7B-merge-v3.2-Q8_0.gguf) | Q8_0 | 10.694 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/KoSOLAR-10.7B-merge-v3.2-GGUF --include "KoSOLAR-10.7B-merge-v3.2-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/KoSOLAR-10.7B-merge-v3.2-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
+```