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

Libraries

How to use Kaballas/lora_model with Transformers:

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

llama-cpp-python

How to use Kaballas/lora_model with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Kaballas/lora_model",
	filename="unsloth.Q8_0.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 Kaballas/lora_model with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Kaballas/lora_model:Q8_0
# Run inference directly in the terminal:
llama-cli -hf Kaballas/lora_model:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Kaballas/lora_model:Q8_0
# Run inference directly in the terminal:
llama-cli -hf Kaballas/lora_model: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 Kaballas/lora_model:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf Kaballas/lora_model: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 Kaballas/lora_model:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Kaballas/lora_model:Q8_0

Use Docker

docker model run hf.co/Kaballas/lora_model:Q8_0

LM Studio
Jan
Ollama
How to use Kaballas/lora_model with Ollama:
```
ollama run hf.co/Kaballas/lora_model:Q8_0
```

Unsloth Studio new

How to use Kaballas/lora_model 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 Kaballas/lora_model 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 Kaballas/lora_model to start chatting

Using HuggingFace Spaces for Unsloth

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

Docker Model Runner
How to use Kaballas/lora_model with Docker Model Runner:
```
docker model run hf.co/Kaballas/lora_model:Q8_0
```

Lemonade

How to use Kaballas/lora_model with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Kaballas/lora_model:Q8_0

Run and chat with the model

lemonade run user.lora_model-Q8_0

List all available models

lemonade list

Kaballas commited on Jul 18, 2024

Commit

cb90190

verified ·

1 Parent(s): 39a69c5

Upload model trained with Unsloth

Browse files

Upload model trained with Unsloth 2x faster

Files changed (2) hide show

adapter_config.json +7 -10
adapter_model.safetensors +2 -2

adapter_config.json CHANGED Viewed

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "unsloth/mistral-7b-bnb-4bit",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
@@ -14,22 +14,19 @@
   "lora_dropout": 0,
   "megatron_config": null,
   "megatron_core": "megatron.core",
-  "modules_to_save": [
-    "lm_head",
-    "embed_tokens"
-  ],
   "peft_type": "LORA",
   "r": 16,
   "rank_pattern": {},
   "revision": "unsloth",
   "target_modules": [
-    "down_proj",
-    "up_proj",
     "gate_proj",
-    "k_proj",
     "q_proj",
-    "v_proj",
-    "o_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

 {
   "alpha_pattern": {},
   "auto_mapping": null,
+  "base_model_name_or_path": "unsloth/gemma-2-9b-bnb-4bit",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
   "lora_dropout": 0,
   "megatron_config": null,
   "megatron_core": "megatron.core",
+  "modules_to_save": null,
   "peft_type": "LORA",
   "r": 16,
   "rank_pattern": {},
   "revision": "unsloth",
   "target_modules": [
+    "v_proj",
     "gate_proj",
     "q_proj",
+    "o_proj",
+    "up_proj",
+    "k_proj",
+    "down_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:484fdb37fd28dc2d4d943f6d663d0556a431407229fb9c57ada61dd7e8ef786f
-size 1216409944

 version https://git-lfs.github.com/spec/v1
+oid sha256:a91b82402fa23b3d9d5a9d0f7e5d3a7e3f384881d81bfc8e536ef9e4c527704a
+size 216151256