Instructions to use basavyr/TriLM_3.9B_Unpacked_quantized with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use basavyr/TriLM_3.9B_Unpacked_quantized with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="basavyr/TriLM_3.9B_Unpacked_quantized",
	filename="TriLM_3.9B_Unpacked_quant_IQ2_TN.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 basavyr/TriLM_3.9B_Unpacked_quantized with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf basavyr/TriLM_3.9B_Unpacked_quantized:TQ1_0
# Run inference directly in the terminal:
llama-cli -hf basavyr/TriLM_3.9B_Unpacked_quantized:TQ1_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf basavyr/TriLM_3.9B_Unpacked_quantized:TQ1_0
# Run inference directly in the terminal:
llama-cli -hf basavyr/TriLM_3.9B_Unpacked_quantized:TQ1_0

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 basavyr/TriLM_3.9B_Unpacked_quantized:TQ1_0
# Run inference directly in the terminal:
./llama-cli -hf basavyr/TriLM_3.9B_Unpacked_quantized:TQ1_0

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 basavyr/TriLM_3.9B_Unpacked_quantized:TQ1_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf basavyr/TriLM_3.9B_Unpacked_quantized:TQ1_0

Use Docker

docker model run hf.co/basavyr/TriLM_3.9B_Unpacked_quantized:TQ1_0

LM Studio
Jan
Ollama
How to use basavyr/TriLM_3.9B_Unpacked_quantized with Ollama:
```
ollama run hf.co/basavyr/TriLM_3.9B_Unpacked_quantized:TQ1_0
```

Unsloth Studio new

How to use basavyr/TriLM_3.9B_Unpacked_quantized 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 basavyr/TriLM_3.9B_Unpacked_quantized 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 basavyr/TriLM_3.9B_Unpacked_quantized to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for basavyr/TriLM_3.9B_Unpacked_quantized to start chatting

Docker Model Runner
How to use basavyr/TriLM_3.9B_Unpacked_quantized with Docker Model Runner:
```
docker model run hf.co/basavyr/TriLM_3.9B_Unpacked_quantized:TQ1_0
```

Lemonade

How to use basavyr/TriLM_3.9B_Unpacked_quantized with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull basavyr/TriLM_3.9B_Unpacked_quantized:TQ1_0

Run and chat with the model

lemonade run user.TriLM_3.9B_Unpacked_quantized-TQ1_0

List all available models

lemonade list

basavyr commited on Aug 22, 2024

Commit

eaaa9e1

verified ·

1 Parent(s): e730fe0

Upload TriLM_3.9B_Unpacked_quant_IQ2_TN.gguf

Browse files

Adds the `IQ2_TN`quantized version of the ~4B TriLM model. This quantization has been done on Metal (i.e., the GPU on the M3 Pro silicon) via [`ik_llama.cpp`](https://github.com/ikawrakow/ik_llama.cpp).

[This PR](https://github.com/ikawrakow/ik_llama.cpp/pull/13) adds the `IQ2_TN` format with support for CUDA, AVX, and even Metal (thanks [ikawrakow](https://github.com/ikawrakow) 🙏). Thus, I decided to test quantization and inference for the 3.9B TriLM variant. It seems to work quite nice on the GPU.

Files changed (2) hide show

.gitattributes +1 -0
TriLM_3.9B_Unpacked_quant_IQ2_TN.gguf +3 -0

.gitattributes CHANGED Viewed

@@ -35,3 +35,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 TriLM_3.9B_Unpacked_quant_TQ1_0.gguf filter=lfs diff=lfs merge=lfs -text
 TriLM_3.9B_Unpacked_quant_TQ2_0.gguf filter=lfs diff=lfs merge=lfs -text

 *tfevents* filter=lfs diff=lfs merge=lfs -text
 TriLM_3.9B_Unpacked_quant_TQ1_0.gguf filter=lfs diff=lfs merge=lfs -text
 TriLM_3.9B_Unpacked_quant_TQ2_0.gguf filter=lfs diff=lfs merge=lfs -text
+TriLM_3.9B_Unpacked_quant_IQ2_TN.gguf filter=lfs diff=lfs merge=lfs -text

TriLM_3.9B_Unpacked_quant_IQ2_TN.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:ab9b72b7d05352679efe430929b6d4e3d04ff8c4574d6851eed3496e4fab94c6
+size 1166745280