Instructions to use Kevinkre/phi35tuned with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Kevinkre/phi35tuned with Transformers:

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("Kevinkre/phi35tuned", dtype="auto")

llama-cpp-python

How to use Kevinkre/phi35tuned with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Kevinkre/phi35tuned",
	filename="unsloth.BF16.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use Kevinkre/phi35tuned with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Kevinkre/phi35tuned:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf Kevinkre/phi35tuned:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Kevinkre/phi35tuned:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf Kevinkre/phi35tuned: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 Kevinkre/phi35tuned:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Kevinkre/phi35tuned: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 Kevinkre/phi35tuned:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Kevinkre/phi35tuned:Q4_K_M

Use Docker

docker model run hf.co/Kevinkre/phi35tuned:Q4_K_M

LM Studio
Jan
Ollama
How to use Kevinkre/phi35tuned with Ollama:
```
ollama run hf.co/Kevinkre/phi35tuned:Q4_K_M
```

Unsloth Studio new

How to use Kevinkre/phi35tuned 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 Kevinkre/phi35tuned 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 Kevinkre/phi35tuned to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Kevinkre/phi35tuned to start chatting

Docker Model Runner
How to use Kevinkre/phi35tuned with Docker Model Runner:
```
docker model run hf.co/Kevinkre/phi35tuned:Q4_K_M
```

Lemonade

How to use Kevinkre/phi35tuned with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Kevinkre/phi35tuned:Q4_K_M

Run and chat with the model

lemonade run user.phi35tuned-Q4_K_M

List all available models

lemonade list

Kevinkre commited on Sep 19, 2024

Commit

c32af78

verified ·

1 Parent(s): 1178de9

(Trained with Unsloth)

Browse files

Files changed (1) hide show

config.json +1 -19

config.json CHANGED Viewed

@@ -1,21 +1,3 @@
 {
-  "architectures": [
-    "PhiForCausalLM"
-  ],
-  "model_type": "phi",
-  "torch_dtype": "float16",
-  "transformers_version": "4.35.0",
-  "max_position_embeddings": 2048,
-  "quantization_config": {
-    "load_in_4bit": true,
-    "bnb_4bit_compute_dtype": "float16"
-  },
-  "peft_config": {
-    "peft_type": "LORA",
-    "task_type": "CAUSAL_LM",
-    "inference_mode": false,
-    "r": 16,
-    "lora_alpha": 16,
-    "lora_dropout": 0
-  }
 }

 {
+    "model_type": "llama"
 }