Instructions to use SkylinkLabs/CLIP with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use SkylinkLabs/CLIP with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="SkylinkLabs/CLIP",
	filename="t5-v1_1-xxl-encoder-Q3_K_S.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use SkylinkLabs/CLIP with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf SkylinkLabs/CLIP:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf SkylinkLabs/CLIP:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf SkylinkLabs/CLIP:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf SkylinkLabs/CLIP:Q4_K_M

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 SkylinkLabs/CLIP:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf SkylinkLabs/CLIP:Q4_K_M

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 SkylinkLabs/CLIP:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf SkylinkLabs/CLIP:Q4_K_M

Use Docker

docker model run hf.co/SkylinkLabs/CLIP:Q4_K_M

LM Studio
Jan
Ollama
How to use SkylinkLabs/CLIP with Ollama:
```
ollama run hf.co/SkylinkLabs/CLIP:Q4_K_M
```

Unsloth Studio new

How to use SkylinkLabs/CLIP 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 SkylinkLabs/CLIP 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 SkylinkLabs/CLIP to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for SkylinkLabs/CLIP to start chatting

Docker Model Runner
How to use SkylinkLabs/CLIP with Docker Model Runner:
```
docker model run hf.co/SkylinkLabs/CLIP:Q4_K_M
```

Lemonade

How to use SkylinkLabs/CLIP with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull SkylinkLabs/CLIP:Q4_K_M

Run and chat with the model

lemonade run user.CLIP-Q4_K_M

List all available models

lemonade list

dangquocdung commited on Jul 7, 2025

Commit

ff6c888

verified ·

1 Parent(s): 2b4e178

Upload 9 files

Browse files

Files changed (10) hide show

.gitattributes +4 -0
EVA02_CLIP_L_336_psz14_s6B.pt +3 -0
clip_l.safetensors +3 -0
clip_l_new.safetensors +3 -0
t5-v1_1-xxl-encoder-Q3_K_S.gguf +3 -0
t5-v1_1-xxl-encoder-Q4_K_M.gguf +3 -0
t5-v1_1-xxl-encoder-Q5_K_M.gguf +3 -0
t5-v1_1-xxl-encoder-Q8_0.gguf +3 -0
t5xxl_fp8_e4m3fn.safetensors +3 -0
t5xxl_fp8_e4m3fn_scaled.safetensors +3 -0

@@ -33,3 +33,7 @@ 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
+t5-v1_1-xxl-encoder-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+t5-v1_1-xxl-encoder-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+t5-v1_1-xxl-encoder-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+t5-v1_1-xxl-encoder-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text

+version https://git-lfs.github.com/spec/v1
+oid sha256:84c3a17a228c567a155259b2245b0b59072bf7da510260a0a02ec54de6d50b05
+size 856461210

+version https://git-lfs.github.com/spec/v1
+oid sha256:660c6f5b1abae9dc498ac2d21e1347d2abdb0cf6c0c0c8576cd796491d9a6cdd
+size 246144152

+version https://git-lfs.github.com/spec/v1
+oid sha256:eddcf5e2e2a88550aab21e04895e8ce4b2977e6c11dbbc7675b07927a3cda0dd
+size 323409740

+version https://git-lfs.github.com/spec/v1
+oid sha256:31ebe18e901bfb6e5709a20ec1c95fce29bce2b9545073231e0f909a53239f5c
+size 2099467456

+version https://git-lfs.github.com/spec/v1
+oid sha256:6be2b0b7e2de7cf2919340c88cb802a103a997ce46c53131cec91958c1db1af4
+size 2896123072

+version https://git-lfs.github.com/spec/v1
+oid sha256:b51cbb10b1a7aac6dd1c3b62f0ed908bfd06e0b42d2f3577d43e061361f51dae
+size 3386856640

+version https://git-lfs.github.com/spec/v1
+oid sha256:9ec60f6028534b7fe5af439fcb535d75a68592a9ca3fcdeb175ef89e3ee99825
+size 5061584064

+version https://git-lfs.github.com/spec/v1
+oid sha256:7d330da4816157540d6bb7838bf63a0f02f573fc48ca4d8de34bb0cbfd514f09
+size 4893934904

+version https://git-lfs.github.com/spec/v1
+oid sha256:a498f0485dc9536735258018417c3fd7758dc3bccc0a645feaa472b34955557a
+size 5157348688

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

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

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

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