Instructions to use bhenrym14/mistral-7b-platypus-fp16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use bhenrym14/mistral-7b-platypus-fp16 with Transformers:

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

pipe = pipeline("text-generation", model="bhenrym14/mistral-7b-platypus-fp16")

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("bhenrym14/mistral-7b-platypus-fp16")
model = AutoModelForMultimodalLM.from_pretrained("bhenrym14/mistral-7b-platypus-fp16")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use bhenrym14/mistral-7b-platypus-fp16 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "bhenrym14/mistral-7b-platypus-fp16"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "bhenrym14/mistral-7b-platypus-fp16",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/bhenrym14/mistral-7b-platypus-fp16

SGLang

How to use bhenrym14/mistral-7b-platypus-fp16 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 "bhenrym14/mistral-7b-platypus-fp16" \
    --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": "bhenrym14/mistral-7b-platypus-fp16",
		"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 "bhenrym14/mistral-7b-platypus-fp16" \
        --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": "bhenrym14/mistral-7b-platypus-fp16",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use bhenrym14/mistral-7b-platypus-fp16 with Docker Model Runner:
```
docker model run hf.co/bhenrym14/mistral-7b-platypus-fp16
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Instruction tune of Mistral-7B-v0.1 with Open-Platypus (fp16)

Overview

This is mistralai/Mistral-7B-v0.1, with instruction tuning performed with the garage-bAInd/Open-Platypus dataset.

This is a (merged) QLoRA fine-tune (rank 64).

The finetune was performed with 1x RTX 6000 Ada (~9 hours).

How to Use

As of writing, the Mistral architecture requires installation of transformers from source. With this done, load like any other model.

Benchmarks

ARC (25 shot): 62.80

Hellaswag (10 shot): 84.12

MMLU (5 shot): 64.20

Context Length - Relative Performance (wikitext perplexity)

Context (tokens)	bhenrym14/mistral-7b-platypus-fp16	bhenrym14/airoboros-l2-13b-2.1-YaRN-64k	bhenrym14/airophin-13b-pntk-16k-fp16	bhenrym14/airoboros-33b-gpt4-1.4.1-lxctx-PI-16384-fp16	jondurbin/airoboros-l2-13b-gpt4-1.4.1
512	7.22	7.64	7.62	7.90	7.23
1024	6.04	6.15	6.20	6.17	5.85
2048	5.50	5.29	5.38	5.23	5.07
4096	5.05	4.93	5.08	4.91	4.77
8192	4.96	4.69	4.90	Not Tested	57.1
12000	Not Tested	4.53	4.82	Not Tested	Not Tested

While the mistral model is very impressive for its size, particularly on benchmarks, the sliding window attention and/or model size impacts its competitiveness with other context extension techniques applied to larger llama2 and llama variants. Is this is more to do with sliding window attention or model size?

Prompting:

Model was trained with legacy airoboros <2.0 system prompt. See bhenrym14/airoboros-33b-gpt4-1.4.1-lxctx-PI-16384-fp16 model card for details.

Downloads last month: 201

Safetensors

Model size

7B params

Tensor type

F16

Model tree for bhenrym14/mistral-7b-platypus-fp16

Merges

1 model

Quantizations

4 models

bhenrym14
/

mistral-7b-platypus-fp16