Instructions to use jtatman/tinymistral-magicoder-instruct-248m with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use jtatman/tinymistral-magicoder-instruct-248m with Transformers:

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

pipe = pipeline("text-generation", model="jtatman/tinymistral-magicoder-instruct-248m")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("jtatman/tinymistral-magicoder-instruct-248m")
model = AutoModelForCausalLM.from_pretrained("jtatman/tinymistral-magicoder-instruct-248m")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use jtatman/tinymistral-magicoder-instruct-248m with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "jtatman/tinymistral-magicoder-instruct-248m"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "jtatman/tinymistral-magicoder-instruct-248m",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/jtatman/tinymistral-magicoder-instruct-248m

SGLang

How to use jtatman/tinymistral-magicoder-instruct-248m 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 "jtatman/tinymistral-magicoder-instruct-248m" \
    --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": "jtatman/tinymistral-magicoder-instruct-248m",
		"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 "jtatman/tinymistral-magicoder-instruct-248m" \
        --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": "jtatman/tinymistral-magicoder-instruct-248m",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use jtatman/tinymistral-magicoder-instruct-248m with Docker Model Runner:
```
docker model run hf.co/jtatman/tinymistral-magicoder-instruct-248m
```

jtatman commited on Dec 17, 2023

Commit

9ef8f0a

1 Parent(s): e717d30

Upload MistralForCausalLM

Browse files

Files changed (2) hide show

config.json +1 -1
model.safetensors +2 -2

config.json CHANGED Viewed

@@ -22,5 +22,5 @@
   "torch_dtype": "float16",
   "transformers_version": "4.37.0.dev0",
   "use_cache": true,
-  "vocab_size": 32005
 }

   "torch_dtype": "float16",
   "transformers_version": "4.37.0.dev0",
   "use_cache": true,
+  "vocab_size": 32064
 }

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed5258bdcde7f85a5bf0c1f1d131b17ef8445efb58e751e30e81aa2d37134a8a
-size 496060584

 version https://git-lfs.github.com/spec/v1
+oid sha256:cf4e8365454a9e19f57353a65599793d88d95789b92ce4b4b713029d0d76b0c2
+size 496302248