Instructions to use amalsp/mistral-finetuned-chatbot with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use amalsp/mistral-finetuned-chatbot with Transformers:

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

pipe = pipeline("text-generation", model="amalsp/mistral-finetuned-chatbot")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("amalsp/mistral-finetuned-chatbot", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use amalsp/mistral-finetuned-chatbot with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/amalsp/mistral-finetuned-chatbot

SGLang

How to use amalsp/mistral-finetuned-chatbot 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 "amalsp/mistral-finetuned-chatbot" \
    --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": "amalsp/mistral-finetuned-chatbot",
		"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 "amalsp/mistral-finetuned-chatbot" \
        --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": "amalsp/mistral-finetuned-chatbot",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use amalsp/mistral-finetuned-chatbot with Docker Model Runner:
```
docker model run hf.co/amalsp/mistral-finetuned-chatbot
```

🔧 Mistral Fine-Tuned Chatbot for AI Tool Queries

This model is a fine-tuned version of TheBloke/OpenHermes-2.5-Mistral-7B-GGUF on a custom dataset of AI tool instructions. It's designed to behave as a conversational assistant that can answer technical queries related to popular AI tools.

🧠 Model Details

Base model: OpenHermes-2.5-Mistral-7B-GGUF
Fine-tuned on: Custom dataset of structured JSONL instructions
Training platform: Google Colab Pro (A100 GPU)
Fine-tuning method: Supervised fine-tuning using 🤗 Transformers + Datasets

📂 Example Use Cases

🛠️ Recommend and explain AI tools for different tasks
💬 Simulate chatbot responses about ML libraries, APIs, and platforms
🧪 Useful for education, technical support, and integration with AI assistants

💻 Usage

from transformers import AutoTokenizer, AutoModelForCausalLM

model = AutoModelForCausalLM.from_pretrained("amalsp/mistral-finetuned-chatbot")
tokenizer = AutoTokenizer.from_pretrained("amalsp/mistral-finetuned-chatbot")

prompt = "What AI tool can I use for image generation?"
inputs = tokenizer(prompt, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=150)

print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Downloads last month: -; Downloads are not tracked for this model. How to track