Instructions to use rpatel622/Mellum2-12B-A2.5B-Thinking-Dflash-GGUF-FIXED with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use rpatel622/Mellum2-12B-A2.5B-Thinking-Dflash-GGUF-FIXED 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 rpatel622/Mellum2-12B-A2.5B-Thinking-Dflash-GGUF-FIXED:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf rpatel622/Mellum2-12B-A2.5B-Thinking-Dflash-GGUF-FIXED:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf rpatel622/Mellum2-12B-A2.5B-Thinking-Dflash-GGUF-FIXED:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf rpatel622/Mellum2-12B-A2.5B-Thinking-Dflash-GGUF-FIXED: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 rpatel622/Mellum2-12B-A2.5B-Thinking-Dflash-GGUF-FIXED:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf rpatel622/Mellum2-12B-A2.5B-Thinking-Dflash-GGUF-FIXED: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 rpatel622/Mellum2-12B-A2.5B-Thinking-Dflash-GGUF-FIXED:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf rpatel622/Mellum2-12B-A2.5B-Thinking-Dflash-GGUF-FIXED:Q4_K_M

Use Docker

docker model run hf.co/rpatel622/Mellum2-12B-A2.5B-Thinking-Dflash-GGUF-FIXED:Q4_K_M

LM Studio
Jan
Ollama
How to use rpatel622/Mellum2-12B-A2.5B-Thinking-Dflash-GGUF-FIXED with Ollama:
```
ollama run hf.co/rpatel622/Mellum2-12B-A2.5B-Thinking-Dflash-GGUF-FIXED:Q4_K_M
```

Unsloth Studio

How to use rpatel622/Mellum2-12B-A2.5B-Thinking-Dflash-GGUF-FIXED 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 rpatel622/Mellum2-12B-A2.5B-Thinking-Dflash-GGUF-FIXED 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 rpatel622/Mellum2-12B-A2.5B-Thinking-Dflash-GGUF-FIXED to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for rpatel622/Mellum2-12B-A2.5B-Thinking-Dflash-GGUF-FIXED to start chatting

Docker Model Runner
How to use rpatel622/Mellum2-12B-A2.5B-Thinking-Dflash-GGUF-FIXED with Docker Model Runner:
```
docker model run hf.co/rpatel622/Mellum2-12B-A2.5B-Thinking-Dflash-GGUF-FIXED:Q4_K_M
```

Lemonade

How to use rpatel622/Mellum2-12B-A2.5B-Thinking-Dflash-GGUF-FIXED with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull rpatel622/Mellum2-12B-A2.5B-Thinking-Dflash-GGUF-FIXED:Q4_K_M

Run and chat with the model

lemonade run user.Mellum2-12B-A2.5B-Thinking-Dflash-GGUF-FIXED-Q4_K_M

List all available models

lemonade list

Atomic Chat

rpatel622 commited on Jul 2

Commit

664f2a3

verified ·

1 Parent(s): 42fbc3c

Initial GGUF upload

Browse files

Files changed (4) hide show

.gitattributes +2 -0
README.md +0 -20
mellum2-dflash.Q8_0.gguf +3 -0
mellum2-dflash.bf16.gguf +3 -0

.gitattributes CHANGED Viewed

@@ -35,3 +35,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 mellum2-dflash.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
 mellum2-dflash.f16.gguf filter=lfs diff=lfs merge=lfs -text

 *tfevents* filter=lfs diff=lfs merge=lfs -text
 mellum2-dflash.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
 mellum2-dflash.f16.gguf filter=lfs diff=lfs merge=lfs -text
+mellum2-dflash.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+mellum2-dflash.bf16.gguf filter=lfs diff=lfs merge=lfs -text

README.md CHANGED Viewed

@@ -2,15 +2,6 @@
 license: apache-2.0
 base_model:
 - JetBrains/Mellum2-12B-A2.5B-Thinking
-language:
-- en
-tags:
-- dflash
-- mellum
-- jetbrains
-- gguf
-- quantize
-- code
 ---
 # Mellum2-12B-A2.5B-Thinking-Dflash GGUF
@@ -25,14 +16,3 @@ Converted using:
 https://github.com/Anbeeld/beellama.cpp
 This repository only contains GGUF conversions.
-# usage notes
-I'm using with beellama server on a 780m igpu with 32gb shared ddr5 memory. Really impressed so far.
-Context size : 131072
-Temp : 0.6
-Top-P : 0.95
-Top-K : 20
-Play around with repeat-penalty-n and repeat-penalty for best results. I'm using 8192 and 1.05.

 license: apache-2.0
 base_model:
 - JetBrains/Mellum2-12B-A2.5B-Thinking
 ---
 # Mellum2-12B-A2.5B-Thinking-Dflash GGUF
 https://github.com/Anbeeld/beellama.cpp
 This repository only contains GGUF conversions.

mellum2-dflash.Q8_0.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:81fa171b80bc6f76769b71aa2ea5d586d706499fb0157a77f0473606fe236b52
+size 889192384

mellum2-dflash.bf16.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:55919f948953585fff7d8a325a8b3b9197ee3b554022bf3c5ebea16d05382a10
+size 1670524864