Instructions to use tensorblock/cot_5k-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tensorblock/cot_5k-GGUF with Transformers:

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("tensorblock/cot_5k-GGUF", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use tensorblock/cot_5k-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/cot_5k-GGUF:Q2_K
# Run inference directly in the terminal:
llama cli -hf tensorblock/cot_5k-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/cot_5k-GGUF:Q2_K
# Run inference directly in the terminal:
llama cli -hf tensorblock/cot_5k-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/cot_5k-GGUF:Q2_K
# Run inference directly in the terminal:
./llama-cli -hf tensorblock/cot_5k-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/cot_5k-GGUF:Q2_K
# Run inference directly in the terminal:
./build/bin/llama-cli -hf tensorblock/cot_5k-GGUF:Q2_K

Use Docker

docker model run hf.co/tensorblock/cot_5k-GGUF:Q2_K

LM Studio
Jan
Ollama
How to use tensorblock/cot_5k-GGUF with Ollama:
```
ollama run hf.co/tensorblock/cot_5k-GGUF:Q2_K
```

Unsloth Studio

How to use tensorblock/cot_5k-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/cot_5k-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/cot_5k-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/cot_5k-GGUF to start chatting

Docker Model Runner
How to use tensorblock/cot_5k-GGUF with Docker Model Runner:
```
docker model run hf.co/tensorblock/cot_5k-GGUF:Q2_K
```

Lemonade

How to use tensorblock/cot_5k-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull tensorblock/cot_5k-GGUF:Q2_K

Run and chat with the model

lemonade run user.cot_5k-GGUF-Q2_K

List all available models

lemonade list

Atomic Chat

morriszms commited on Jan 27

Commit

5d8768e

verified ·

1 Parent(s): b88dd3f

Remove .gguf files (keep Q2_K.gguf)

Browse files

Files changed (11) hide show

cot_5k-Q3_K_L.gguf +0 -3
cot_5k-Q3_K_M.gguf +0 -3
cot_5k-Q3_K_S.gguf +0 -3
cot_5k-Q4_0.gguf +0 -3
cot_5k-Q4_K_M.gguf +0 -3
cot_5k-Q4_K_S.gguf +0 -3
cot_5k-Q5_0.gguf +0 -3
cot_5k-Q5_K_M.gguf +0 -3
cot_5k-Q5_K_S.gguf +0 -3
cot_5k-Q6_K.gguf +0 -3
cot_5k-Q8_0.gguf +0 -3

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:bb81104667b514a7047016472da8788021f71e6a9661a9b31acade396b3a9fa5
-size 914985280

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:065476efd6c0aa3a3ea0a4c384e75573af07ab4e47327dda1a73502886f9a9e0
-size 857706816

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:4d8bcf887a3ebe25b5c3a0d785afdae75f9cca4e65e7b41a29a8c766bfd74948
-size 791712064

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:968e1bb41b920cc1f02972796eb479bc916704e0f55c098293494a7751412ad9
-size 982782272

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:05b264fbb75a03498e615dab8100dd5bb7d91ffe29ad9a33582ec6b51ebf2f9b
-size 1031442752