Instructions to use mlx-community/defog-sqlcoder-7b-2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mlx-community/defog-sqlcoder-7b-2 with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="mlx-community/defog-sqlcoder-7b-2")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("mlx-community/defog-sqlcoder-7b-2")
model = AutoModelForCausalLM.from_pretrained("mlx-community/defog-sqlcoder-7b-2", device_map="auto")

MLX

How to use mlx-community/defog-sqlcoder-7b-2 with MLX:

# Make sure mlx-lm is installed
# pip install --upgrade mlx-lm
# if on a CUDA device, also pip install mlx[cuda]

# Generate text with mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("mlx-community/defog-sqlcoder-7b-2")

prompt = "Once upon a time in"
text = generate(model, tokenizer, prompt=prompt, verbose=True)

Notebooks
Google Colab
Kaggle
Local Apps Settings
LM Studio

vLLM

How to use mlx-community/defog-sqlcoder-7b-2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "mlx-community/defog-sqlcoder-7b-2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mlx-community/defog-sqlcoder-7b-2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/mlx-community/defog-sqlcoder-7b-2

SGLang

How to use mlx-community/defog-sqlcoder-7b-2 with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "mlx-community/defog-sqlcoder-7b-2" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mlx-community/defog-sqlcoder-7b-2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "mlx-community/defog-sqlcoder-7b-2" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mlx-community/defog-sqlcoder-7b-2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

MLX LM

How to use mlx-community/defog-sqlcoder-7b-2 with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Generate some text
mlx_lm.generate --model "mlx-community/defog-sqlcoder-7b-2" --prompt "Once upon a time"

Docker Model Runner
How to use mlx-community/defog-sqlcoder-7b-2 with Docker Model Runner:
```
docker model run hf.co/mlx-community/defog-sqlcoder-7b-2
```

abhishek-ch commited on Feb 7, 2024

Commit

6cf7b61

verified ·

1 Parent(s): 1618f6a

Upload folder using huggingface_hub

Browse files

Files changed (4) hide show

config.json +2 -2
model-00001-of-00003.safetensors +1 -1
model-00002-of-00003.safetensors +1 -1
model-00003-of-00003.safetensors +1 -1

config.json CHANGED Viewed

@@ -19,7 +19,7 @@
     "output_hidden_states": false,
     "output_attentions": false,
     "torchscript": false,
-    "torch_dtype": "bfloat16",
     "use_bfloat16": false,
     "tf_legacy_loss": false,
     "pruned_heads": {},
@@ -76,7 +76,7 @@
     "decoder_start_token_id": null,
     "task_specific_params": null,
     "problem_type": null,
-    "_name_or_path": "/Users/gmcjy/.cache/huggingface/hub/models--defog--sqlcoder-7b-2/snapshots/09f5dfc1d1338bd44824d6d0a7a69682f9b4c977",
     "transformers_version": "4.37.2",
     "model_type": "llama"
 }

     "output_hidden_states": false,
     "output_attentions": false,
     "torchscript": false,
+    "torch_dtype": "float16",
     "use_bfloat16": false,
     "tf_legacy_loss": false,
     "pruned_heads": {},
     "decoder_start_token_id": null,
     "task_specific_params": null,
     "problem_type": null,
+    "_name_or_path": "/Users/gmcjy/.cache/huggingface/hub/models--defog--sqlcoder-7b-2/snapshots/b645fe3146087c7aedea712a900e208b3a3f0152",
     "transformers_version": "4.37.2",
     "model_type": "llama"
 }

model-00001-of-00003.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb9f8bd342521ca9fe90f76770f27c9a6131cf0298f0883466d6a93337ac3389
 size 5343884067

 version https://git-lfs.github.com/spec/v1
+oid sha256:5d5d078854b0b42be409d3aabc6ac74e49ff0bc1162574b9f47858897c671418
 size 5343884067

model-00002-of-00003.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:829b3e26e0b3438c7134c1bc9f21ccedf434a74b3a1866af9b9818da8412dd6c
 size 5352158545

 version https://git-lfs.github.com/spec/v1
+oid sha256:b5affecc3ce18b9ed9a04cfb4bf2d9c25241b59ecc015d6210d00d42b8cad789
 size 5352158545

model-00003-of-00003.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de26c11198a59ab7babaa95d426e54e6ad9c920c50c2f4d24129ede4273884eb
 size 2781084263

 version https://git-lfs.github.com/spec/v1
+oid sha256:017e68dc701004cc4a95ed5cfdedf04e4b5e97e1103c34c6612e2419df78b640
 size 2781084263