Instructions to use lewtun/mistral-7b-sft-ultrachat-arithmo-50 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use lewtun/mistral-7b-sft-ultrachat-arithmo-50 with Transformers:

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

pipe = pipeline("text-generation", model="lewtun/mistral-7b-sft-ultrachat-arithmo-50")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("lewtun/mistral-7b-sft-ultrachat-arithmo-50")
model = AutoModelForCausalLM.from_pretrained("lewtun/mistral-7b-sft-ultrachat-arithmo-50", 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 lewtun/mistral-7b-sft-ultrachat-arithmo-50 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "lewtun/mistral-7b-sft-ultrachat-arithmo-50"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "lewtun/mistral-7b-sft-ultrachat-arithmo-50",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/lewtun/mistral-7b-sft-ultrachat-arithmo-50

SGLang

How to use lewtun/mistral-7b-sft-ultrachat-arithmo-50 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 "lewtun/mistral-7b-sft-ultrachat-arithmo-50" \
    --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": "lewtun/mistral-7b-sft-ultrachat-arithmo-50",
		"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 "lewtun/mistral-7b-sft-ultrachat-arithmo-50" \
        --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": "lewtun/mistral-7b-sft-ultrachat-arithmo-50",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use lewtun/mistral-7b-sft-ultrachat-arithmo-50 with Docker Model Runner:
```
docker model run hf.co/lewtun/mistral-7b-sft-ultrachat-arithmo-50
```

mistral-7b-sft-ultrachat-arithmo-50

This model is a fine-tuned version of mistralai/Mistral-7B-v0.1 on the UltraChat and Arithmo (50%) datasets. It achieves the following results on the evaluation set:

Loss: 0.8892

Model description

# Install transformers from source - only needed for versions <= v4.34
# pip install git+https://github.com/huggingface/transformers.git
# pip install accelerate

import torch
from transformers import pipeline

pipe = pipeline("text-generation", model="lewtun/mistral-7b-sft-ultrachat-arithmo-50", torch_dtype=torch.bfloat16, device_map="auto")

# We use the tokenizer's chat template to format each message - see https://huggingface.co/docs/transformers/main/en/chat_templating
messages = [
    {
        "role": "system",
        "content": "You are a friendly chatbot who always responds in the style of a pirate",
    },
    {"role": "user", "content": "How many helicopters can a human eat in one sitting?"},
]
prompt = pipe.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
outputs = pipe(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])
# <|system|>
# You are a friendly chatbot who always responds in the style of a pirate.</s>
# <|user|>
# How many helicopters can a human eat in one sitting?</s>
# <|assistant|>
# Ah, me hearty matey! But yer question be a puzzler! A human cannot eat a helicopter in one sitting, as helicopters are not edible. They be made of metal, plastic, and other materials, not food!

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 2e-05
train_batch_size: 8
eval_batch_size: 16
seed: 42
distributed_type: multi-GPU
num_devices: 16
gradient_accumulation_steps: 4
total_train_batch_size: 512
total_eval_batch_size: 256
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.1
num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss
0.8776	0.47	308	0.8892

Framework versions

Transformers 4.35.0.dev0
Pytorch 2.0.1+cu118
Datasets 2.12.0
Tokenizers 0.14.0

Downloads last month: 9

Model tree for lewtun/mistral-7b-sft-ultrachat-arithmo-50

Base model

mistralai/Mistral-7B-v0.1

Finetuned

(947)

this model

Datasets used to train lewtun/mistral-7b-sft-ultrachat-arithmo-50

Collection including lewtun/mistral-7b-sft-ultrachat-arithmo-50

Mistral 7B + UltraChat + Arithmo checkpoints

Collection

A collection of Mistral 7B fine-tunes on UltraChat and Arithmo to boost the math capabilities of chat models. See https://x.com/_lewtun/status/1715652 • 5 items • Updated Oct 22, 2023 • 2