Instructions to use TroyDoesAI/Codestral-RAG-19B-Pruned with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TroyDoesAI/Codestral-RAG-19B-Pruned with Transformers:

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

pipe = pipeline("text-generation", model="TroyDoesAI/Codestral-RAG-19B-Pruned")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("TroyDoesAI/Codestral-RAG-19B-Pruned")
model = AutoModelForCausalLM.from_pretrained("TroyDoesAI/Codestral-RAG-19B-Pruned")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use TroyDoesAI/Codestral-RAG-19B-Pruned with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "TroyDoesAI/Codestral-RAG-19B-Pruned"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "TroyDoesAI/Codestral-RAG-19B-Pruned",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/TroyDoesAI/Codestral-RAG-19B-Pruned

SGLang

How to use TroyDoesAI/Codestral-RAG-19B-Pruned 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 "TroyDoesAI/Codestral-RAG-19B-Pruned" \
    --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": "TroyDoesAI/Codestral-RAG-19B-Pruned",
		"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 "TroyDoesAI/Codestral-RAG-19B-Pruned" \
        --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": "TroyDoesAI/Codestral-RAG-19B-Pruned",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use TroyDoesAI/Codestral-RAG-19B-Pruned with Docker Model Runner:
```
docker model run hf.co/TroyDoesAI/Codestral-RAG-19B-Pruned
```

TroyDoesAI commited on May 31, 2024

Commit

bffaaa5

verified ·

1 Parent(s): 1170da3

Update README.md

Browse files

Files changed (1) hide show

README.md +0 -4

README.md CHANGED Viewed

@@ -1,7 +1,3 @@
----
-license: cc-by-nd-4.0
----
 For those trying to shoe horn this large model on your machine every GB of saved memory counts when offloading to System RAM!
 Here is a pruned down the 22.2 Billion parameter model by 4 junk layers to make a 19B that doesnt appear to lose any sense of quality.






1	For those trying to shoe horn this large model on your machine every GB of saved memory counts when offloading to System RAM!
2
3	Here is a pruned down the 22.2 Billion parameter model by 4 junk layers to make a 19B that doesnt appear to lose any sense of quality.