Instructions to use tensorblock/LosslessMegaCoder-Falcon-40b-mini-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tensorblock/LosslessMegaCoder-Falcon-40b-mini-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="tensorblock/LosslessMegaCoder-Falcon-40b-mini-GGUF",
	filename="LosslessMegaCoder-Falcon-40b-mini-Q2_K.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 tensorblock/LosslessMegaCoder-Falcon-40b-mini-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf tensorblock/LosslessMegaCoder-Falcon-40b-mini-GGUF:Q2_K
# Run inference directly in the terminal:
llama-cli -hf tensorblock/LosslessMegaCoder-Falcon-40b-mini-GGUF:Q2_K

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf tensorblock/LosslessMegaCoder-Falcon-40b-mini-GGUF:Q2_K
# Run inference directly in the terminal:
llama-cli -hf tensorblock/LosslessMegaCoder-Falcon-40b-mini-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/LosslessMegaCoder-Falcon-40b-mini-GGUF:Q2_K
# Run inference directly in the terminal:
./llama-cli -hf tensorblock/LosslessMegaCoder-Falcon-40b-mini-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/LosslessMegaCoder-Falcon-40b-mini-GGUF:Q2_K
# Run inference directly in the terminal:
./build/bin/llama-cli -hf tensorblock/LosslessMegaCoder-Falcon-40b-mini-GGUF:Q2_K

Use Docker

docker model run hf.co/tensorblock/LosslessMegaCoder-Falcon-40b-mini-GGUF:Q2_K

LM Studio
Jan
Ollama
How to use tensorblock/LosslessMegaCoder-Falcon-40b-mini-GGUF with Ollama:
```
ollama run hf.co/tensorblock/LosslessMegaCoder-Falcon-40b-mini-GGUF:Q2_K
```

Unsloth Studio new

How to use tensorblock/LosslessMegaCoder-Falcon-40b-mini-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/LosslessMegaCoder-Falcon-40b-mini-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/LosslessMegaCoder-Falcon-40b-mini-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/LosslessMegaCoder-Falcon-40b-mini-GGUF to start chatting

Docker Model Runner
How to use tensorblock/LosslessMegaCoder-Falcon-40b-mini-GGUF with Docker Model Runner:
```
docker model run hf.co/tensorblock/LosslessMegaCoder-Falcon-40b-mini-GGUF:Q2_K
```

Lemonade

How to use tensorblock/LosslessMegaCoder-Falcon-40b-mini-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull tensorblock/LosslessMegaCoder-Falcon-40b-mini-GGUF:Q2_K

Run and chat with the model

lemonade run user.LosslessMegaCoder-Falcon-40b-mini-GGUF-Q2_K

List all available models

lemonade list

morriszms commited on Jan 27

Commit

fcbe5a3

verified ·

1 Parent(s): 7f9ce73

Remove .gguf files (keep Q2_K.gguf)

Browse files

Files changed (11) hide show

LosslessMegaCoder-Falcon-40b-mini-Q3_K_L.gguf +0 -3
LosslessMegaCoder-Falcon-40b-mini-Q3_K_M.gguf +0 -3
LosslessMegaCoder-Falcon-40b-mini-Q3_K_S.gguf +0 -3
LosslessMegaCoder-Falcon-40b-mini-Q4_0.gguf +0 -3
LosslessMegaCoder-Falcon-40b-mini-Q4_K_M.gguf +0 -3
LosslessMegaCoder-Falcon-40b-mini-Q4_K_S.gguf +0 -3
LosslessMegaCoder-Falcon-40b-mini-Q5_0.gguf +0 -3
LosslessMegaCoder-Falcon-40b-mini-Q5_K_M.gguf +0 -3
LosslessMegaCoder-Falcon-40b-mini-Q5_K_S.gguf +0 -3
LosslessMegaCoder-Falcon-40b-mini-Q6_K.gguf +0 -3
LosslessMegaCoder-Falcon-40b-mini-Q8_0.gguf +0 -3

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:f2c303938e1eeb6f74b5b4a6d7561d053bc04a2a82872789d0aa4d31f02e058d
-size 21370594144

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:9194ab50b1cf3c2e372a77ad34b1293c210c9bf8e44bd2bc4f49e5238aa6d205
-size 19866936160

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:40decb99969da135f4fb6117908f2dc85b6a9b1ca24c4382d8b27944d4c87b91
-size 18095104864

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:b92d1864b041fdee35621f47ff059e9ae00dffc29807d92774b015fe2f9fcca2
-size 23509689184

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:5f61d31d2fd7e1855b19844a68edf12aaa25d3d5bc6bae42b0c4e10da4c3cf18
-size 25189507936