Instructions to use simmo/llama3.2-pyfim-3b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use simmo/llama3.2-pyfim-3b 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 simmo/llama3.2-pyfim-3b:Q8_0
# Run inference directly in the terminal:
llama cli -hf simmo/llama3.2-pyfim-3b:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf simmo/llama3.2-pyfim-3b:Q8_0
# Run inference directly in the terminal:
llama cli -hf simmo/llama3.2-pyfim-3b:Q8_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 simmo/llama3.2-pyfim-3b:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf simmo/llama3.2-pyfim-3b:Q8_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 simmo/llama3.2-pyfim-3b:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf simmo/llama3.2-pyfim-3b:Q8_0

Use Docker

docker model run hf.co/simmo/llama3.2-pyfim-3b:Q8_0

LM Studio
Jan
Ollama
How to use simmo/llama3.2-pyfim-3b with Ollama:
```
ollama run hf.co/simmo/llama3.2-pyfim-3b:Q8_0
```

Unsloth Studio

How to use simmo/llama3.2-pyfim-3b 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 simmo/llama3.2-pyfim-3b 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 simmo/llama3.2-pyfim-3b to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for simmo/llama3.2-pyfim-3b to start chatting

Docker Model Runner
How to use simmo/llama3.2-pyfim-3b with Docker Model Runner:
```
docker model run hf.co/simmo/llama3.2-pyfim-3b:Q8_0
```

Lemonade

How to use simmo/llama3.2-pyfim-3b with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull simmo/llama3.2-pyfim-3b:Q8_0

Run and chat with the model

lemonade run user.llama3.2-pyfim-3b-Q8_0

List all available models

lemonade list

Atomic Chat

simmo commited on Sep 27, 2024

Commit

e6d67ce

verified ·

1 Parent(s): 0d9cb88

Model at step: 500 on file data_1.csv (Trained with Unsloth)

Browse files

Files changed (3) hide show

config.json +1 -1
model-00001-of-00002.safetensors +1 -1
model-00002-of-00002.safetensors +1 -1

config.json CHANGED Viewed

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "unsloth/llama-3.2-3b-instruct-bnb-4bit",
   "architectures": [
     "LlamaForCausalLM"
   ],

 {
+  "_name_or_path": "simmo/llama3.2-pyfim-3b",
   "architectures": [
     "LlamaForCausalLM"
   ],

model-00001-of-00002.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4580fcaee24e6679d7a9fc14cfb0fd242c74a61f35e4a8e8944a5f4568dc0043
 size 4965799096

 version https://git-lfs.github.com/spec/v1
+oid sha256:cc39b65e8809fe7d9416068b6ff5bd3d7df954780cad76d88684266076e53e1d
 size 4965799096

model-00002-of-00002.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4bc3ffecc936a127cb6263141bed4402c0d512e68c6c026029354c7762a20c95
 size 2247734992

 version https://git-lfs.github.com/spec/v1
+oid sha256:82224272dd85ea601b976675492211ad5be013e606e7d0397f80420a20d1d4b6
 size 2247734992