Instructions to use hvbhanot/slim-7b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use hvbhanot/slim-7b with Transformers:

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

pipe = pipeline("text-generation", model="hvbhanot/slim-7b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("hvbhanot/slim-7b")
model = AutoModelForCausalLM.from_pretrained("hvbhanot/slim-7b", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use hvbhanot/slim-7b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "hvbhanot/slim-7b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "hvbhanot/slim-7b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/hvbhanot/slim-7b

SGLang

How to use hvbhanot/slim-7b 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 "hvbhanot/slim-7b" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "hvbhanot/slim-7b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "hvbhanot/slim-7b" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "hvbhanot/slim-7b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use hvbhanot/slim-7b with Docker Model Runner:
```
docker model run hf.co/hvbhanot/slim-7b
```

slim-7b / README.md

hvbhanot

Update README.md

0dfc2b3 verified 7 months ago

preview code

Raw

History Blame Contribute Delete

984 Bytes

	---
	library_name: transformers
	tags:
	- SLiM
	- qlora
	- eidos
	base_model:
	- Qwen/Qwen2.5-Coder-7B-Instruct
	---

	## Model Description:

	SLiM-7b is a fine-tuned version of the Qwen2.5-Coder-7B-Instruct model, specialized in generating and understanding SLiM/Eidos code for evolutionary simulations. Trained efficiently using QLoRA on a curated dataset of SLiM recipes, code examples, and synthetic scenarios, this model serves as an expert AI assistant for evolutionary biologists. It excels at generating functional SLiM code from natural language prompts, completing partial code, explaining complex simulation concepts, and assisting in modifying existing models. This enables users to quickly develop, debug, and understand simulations involving population genetics, selection, mutation, recombination, spatial structures, and tree-sequence recording. Like all large language models, it may occasionally generate imperfect code or explanations, so verification is always recommended.