You can deploy this model and start earning money today!

RichardErkhov/
lgaalves_-_gpt2_camel_physics-platypus-gguf

Name: lgaalves_-_gpt2_camel_physics-platypus-gguf
Availability: InStock

endpoints_compatible

gguf

template

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

gpt2_camel_physics-platypus - GGUF

Model creator: https://huggingface.co/lgaalves/
Original model: https://huggingface.co/lgaalves/gpt2_camel_physics-platypus/

Name	Quant method	Size
gpt2_camel_physics-platypus.Q2_K.gguf	Q2_K	0.08GB
gpt2_camel_physics-platypus.IQ3_XS.gguf	IQ3_XS	0.08GB
gpt2_camel_physics-platypus.IQ3_S.gguf	IQ3_S	0.08GB
gpt2_camel_physics-platypus.Q3_K_S.gguf	Q3_K_S	0.08GB
gpt2_camel_physics-platypus.IQ3_M.gguf	IQ3_M	0.09GB
gpt2_camel_physics-platypus.Q3_K.gguf	Q3_K	0.09GB
gpt2_camel_physics-platypus.Q3_K_M.gguf	Q3_K_M	0.09GB
gpt2_camel_physics-platypus.Q3_K_L.gguf	Q3_K_L	0.1GB
gpt2_camel_physics-platypus.IQ4_XS.gguf	IQ4_XS	0.1GB
gpt2_camel_physics-platypus.Q4_0.gguf	Q4_0	0.1GB
gpt2_camel_physics-platypus.IQ4_NL.gguf	IQ4_NL	0.1GB
gpt2_camel_physics-platypus.Q4_K_S.gguf	Q4_K_S	0.1GB
gpt2_camel_physics-platypus.Q4_K.gguf	Q4_K	0.11GB
gpt2_camel_physics-platypus.Q4_K_M.gguf	Q4_K_M	0.11GB
gpt2_camel_physics-platypus.Q4_1.gguf	Q4_1	0.11GB
gpt2_camel_physics-platypus.Q5_0.gguf	Q5_0	0.11GB
gpt2_camel_physics-platypus.Q5_K_S.gguf	Q5_K_S	0.11GB
gpt2_camel_physics-platypus.Q5_K.gguf	Q5_K	0.12GB
gpt2_camel_physics-platypus.Q5_K_M.gguf	Q5_K_M	0.12GB
gpt2_camel_physics-platypus.Q5_1.gguf	Q5_1	0.12GB
gpt2_camel_physics-platypus.Q6_K.gguf	Q6_K	0.13GB
gpt2_camel_physics-platypus.Q8_0.gguf	Q8_0	0.17GB

Original model description:

license: mit datasets:

garage-bAInd/Open-Platypus
lgaalves/camel-ai-physics language:
en pipeline_tag: text-generation

lgaalves/gpt2_camel_physics-platypus

lgaalves/gpt2_camel_physics-platypus is an instruction fine-tuned model based on the GPT-2 transformer architecture.

We use state-of-the-art Language Model Evaluation Harness to run the benchmark tests above, using the same version as the HuggingFace LLM Leaderboard. Please see below for detailed instructions on reproducing benchmark results.

Model Details

Trained by: Luiz G A Alves
Model type: gpt2_open-platypus is an auto-regressive language model based on the GPT-2 transformer architecture.
Language(s): English

How to use:

python

# Use a pipeline as a high-level helper
>>> from transformers import pipeline
>>> pipe = pipeline("text-generation", model="lgaalves/gpt2_camel_physics-platypus")
>>> question = "What is a large language model?"
>>> answer = pipe(question)
>>> print(answer[0]['generated_text'])

or, you can load the model direclty using:

python

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("lgaalves/gpt2_camel_physics-platypus")
model = AutoModelForCausalLM.from_pretrained("lgaalves/gpt2_camel_physics-platypus")

Training Dataset

lgaalves/gpt2_open-platypus trained using STEM and logic based dataset garage-bAInd/Open-Platypus and the GPT4 generated dataset lgaalves/camel-physics.

Training Procedure

lgaalves/gpt2_camel_physics-platypus was instruction fine-tuned using LoRA on 1 v100 GPU on Google Colab. It took about 17 minutes to train it.

Intended uses, limitations & biases

You can use the raw model for text generation or fine-tune it to a downstream task. The model was not extensively tested and may produce false information. It contains a lot of unfiltered content from the internet, which is far from neutral.

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	25.04
ARC (25-shot)	23.04
HellaSwag (10-shot)	31.32
MMLU (5-shot)	26.91
TruthfulQA (0-shot)	39.56
Winogrande (5-shot)	49.64
GSM8K (5-shot)	0.0
DROP (3-shot)	4.79

RichardErkhov/lgaalves_-_gpt2_camel_physics-platypus-gguf