Instructions to use hrangel/MistralFineTuningSQL2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use hrangel/MistralFineTuningSQL2 with Transformers:

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

pipe = pipeline("text-generation", model="hrangel/MistralFineTuningSQL2")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("hrangel/MistralFineTuningSQL2")
model = AutoModelForCausalLM.from_pretrained("hrangel/MistralFineTuningSQL2")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use hrangel/MistralFineTuningSQL2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "hrangel/MistralFineTuningSQL2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "hrangel/MistralFineTuningSQL2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/hrangel/MistralFineTuningSQL2

SGLang

How to use hrangel/MistralFineTuningSQL2 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 "hrangel/MistralFineTuningSQL2" \
    --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": "hrangel/MistralFineTuningSQL2",
		"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 "hrangel/MistralFineTuningSQL2" \
        --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": "hrangel/MistralFineTuningSQL2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use hrangel/MistralFineTuningSQL2 with Docker Model Runner:
```
docker model run hf.co/hrangel/MistralFineTuningSQL2
```

hrangel commited on Apr 6, 2024

Commit

a2acb54

verified ·

1 Parent(s): 7ebff3f

Upload MistralForCausalLM

Browse files

Files changed (3) hide show

config.json +1 -1
generation_config.json +1 -1
model.safetensors +1 -1

config.json CHANGED Viewed

@@ -35,7 +35,7 @@
   "sliding_window": 4096,
   "tie_word_embeddings": false,
   "torch_dtype": "float32",
-  "transformers_version": "4.39.3",
   "use_cache": false,
   "vocab_size": 32001
 }

   "sliding_window": 4096,
   "tie_word_embeddings": false,
   "torch_dtype": "float32",
+  "transformers_version": "4.40.0.dev0",
   "use_cache": false,
   "vocab_size": 32001
 }

generation_config.json CHANGED Viewed

@@ -2,5 +2,5 @@
   "_from_model_config": true,
   "bos_token_id": 1,
   "eos_token_id": 2,
-  "transformers_version": "4.39.3"
 }

   "_from_model_config": true,
   "bos_token_id": 1,
   "eos_token_id": 2,
+  "transformers_version": "4.40.0.dev0"
 }

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cffb8384e98fade6c4779f001abbc84832978e806131c5c7549d5ae589242f73
 size 4990783162

 version https://git-lfs.github.com/spec/v1
+oid sha256:1ad9af25ae8b908af4eda6c79adb2101f8b591501f119f3772b480aa4076c539
 size 4990783162