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

Libraries

How to use Descant/SQL_Gen with Transformers:

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

llama-cpp-python

How to use Descant/SQL_Gen with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Descant/SQL_Gen",
	filename="gemma-3-full-finetune.BF16.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use Descant/SQL_Gen with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Descant/SQL_Gen:BF16
# Run inference directly in the terminal:
llama-cli -hf Descant/SQL_Gen:BF16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Descant/SQL_Gen:BF16
# Run inference directly in the terminal:
llama-cli -hf Descant/SQL_Gen:BF16

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 Descant/SQL_Gen:BF16
# Run inference directly in the terminal:
./llama-cli -hf Descant/SQL_Gen:BF16

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 Descant/SQL_Gen:BF16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Descant/SQL_Gen:BF16

Use Docker

docker model run hf.co/Descant/SQL_Gen:BF16

LM Studio
Jan
Ollama
How to use Descant/SQL_Gen with Ollama:
```
ollama run hf.co/Descant/SQL_Gen:BF16
```

Unsloth Studio

How to use Descant/SQL_Gen 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 Descant/SQL_Gen 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 Descant/SQL_Gen to start chatting

Using HuggingFace Spaces for Unsloth

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

Docker Model Runner
How to use Descant/SQL_Gen with Docker Model Runner:
```
docker model run hf.co/Descant/SQL_Gen:BF16
```

Lemonade

How to use Descant/SQL_Gen with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Descant/SQL_Gen:BF16

Run and chat with the model

lemonade run user.SQL_Gen-BF16

List all available models

lemonade list

Descant commited on Apr 4, 2025

Commit

82a1ad7

verified ·

1 Parent(s): fce83a7

Upload model trained with Unsloth

Browse files

Upload model trained with Unsloth 2x faster

Files changed (2) hide show

adapter_config.json +1 -9
adapter_model.safetensors +2 -2

adapter_config.json CHANGED Viewed

@@ -23,15 +23,7 @@
   "r": 32,
   "rank_pattern": {},
   "revision": null,
-  "target_modules": [
-    "gate_proj",
-    "o_proj",
-    "v_proj",
-    "k_proj",
-    "up_proj",
-    "down_proj",
-    "q_proj"
-  ],
   "task_type": "CAUSAL_LM",
   "trainable_token_indices": null,
   "use_dora": false,

   "r": 32,
   "rank_pattern": {},
   "revision": null,
+  "target_modules": "(?:.*?(?:language|text).*?(?:self_attn|attention|attn|mlp|feed_forward|ffn|dense).*?(?:k_proj|v_proj|q_proj|out_proj|fc1|fc2|o_proj|gate_proj|up_proj|down_proj).*?)|(?:\\bmodel\\.layers\\.[\\d]{1,}\\.(?:self_attn|attention|attn|mlp|feed_forward|ffn|dense)\\.(?:(?:k_proj|v_proj|q_proj|out_proj|fc1|fc2|o_proj|gate_proj|up_proj|down_proj)))",
   "task_type": "CAUSAL_LM",
   "trainable_token_indices": null,
   "use_dora": false,

adapter_model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:830758b090c160275e3fbec02f2db6856fa655001b1de7644b4c132f3edc74f0
-size 262405680

 version https://git-lfs.github.com/spec/v1
+oid sha256:3b89ec607e4c5ca758be7773c3f1b5956387340f55e825c08c4459db238799d2
+size 238491136