Hugging Face's logo

Tijmen2
/
cosmosage_v1_gptq

Question Answering
Transformers
Safetensors
English
mistral
text-generation
text-generation-inference
Inference Endpoints
8-bit precision
gptq
Model card Files Community
cosmosage_v1_gptq / README.md
Tijmen2's picture
Tijmen2
Update README.md
b4c1b3a verified
preview code
|
raw
history blame
11.3 kB
metadata
license: mit
base_model: fblgit/UNA-TheBeagle-7b-v1
model_name: cosmosage
model_type: mistral
prompt_template: '{optional system message} User: {prompt} Assistant:'
language:
  - en
pipeline_tag: question-answering

cosmosage

Cosmosage is a natural-language cosmology assistant that can answer questions about cosmology.

cosmosage_v1_gptq is an 8-bit quantized version of cosmosage_v1, which is fine tune of fblgit/UNA-TheBeagle-7b-v1 on various cosmology-related datasets including open-access textbooks and scientific publications. It is primarily intended for Q&A mode, where the model gives a single answer in response to a single question, though it performs decently as a chatbot, as well.

See https://github.com/tijmen/cosmosage for more details on the training process.

Usage

One convenient way of using this model is with text-generation-webui

https://github.com/oobabooga/text-generation-webui

  • Under the Model tab, download custom model, entering "Tijmen2/cosmosage_v1_gptq"
  • When the download is complete, click the refresh icon next to Model.
  • Select AutoGPTQ as your model loader.
  • In the Model dropdown, choose cosmosage_v1_gptq and load it.
  • Head over to the Notebook tab and ask away!

Prompt Style

The model was trained with data formatted like

{system, optional}
USER: {question}
ASSISTANT: {answer}

Feel free to experiment with different prompts and sampling parameters. No system prompt, i.e.

USER: <<<your question here>>>
ASSISTANT:

works well, but usually leads to very short answers to questions. If you want longer responses, you should ask for them in the system prompt.

The following is an example prompt that that leverages the model's instruction-following capabilities as well as two-shot prompting. I've been using it with temperature=0.4, min_p=0.1.

You are an expert cosmology assistant, able to answer questions on the cosmic microwave
background, galaxy formation, large scale structure, theoretical cosmology, inflation,
big bang nucleosynthesis, cosmology instrumentation, and other related topics. Please assume the
user is fluent in scientific terminology. Elaborate where possible to give a complete answer.
If you do not know, say you do not know. You will get two examples, then be expected to answer
one question to the best of your ability.


## EXAMPLE 1
USER: What is the ISW effect?
ASSISTANT: The Integrated Sachs-Wolfe effect describes the fact that cosmic microwave
background photons gain energy as they fall into potential wells and lose it again as they
climb back out. The origin of the effect is gravitational redshift. For static potential wells,
there is no net effect. However, if the potentials grow or decay, there is a net effect, known
as the Integrated Sachs-Wolfe effect. In a matter-dominated universe, linear potentials stay
constant. The late-time ISW effect refers to the fact that at late times, dark energy causes
a deviation from matter domination and linear potentials decay. This causes an effect in the
cosmic microwave background which has been measured in cross-correlation with large-scale
structure. The early-time ISW refers to the fact that right after recombination, radiation still
contributed a non-negligible amount of the energy density of the universe, causing potentials
to grow. This causes the photons to gain energy. The early-time ISW has not been detected
experimentally.

## EXAMPLE 2
USER: What are the definitions of galaxy cluster mass (M200m, M500c, etc.)?
ASSISTANT: Calculating a galaxy cluster's mass is like calculating the population of a sprawling
city; as you get further out from city center, the suburbs never end. Eventually you have to
stop counting and just say that from there on the people belong to a different town.

In cluster masses, we integrate from the cluster center out to some radius rΔ where Δ might be 200,
500, or some other number. The definition of this radius is that the density of the enclosed mass
is Δ times the average density of the universe at that redshift. The associated mass is MΔ.
Note that 'average density' can be defined in two ways. You can either include the energy
density of dark energy - in which case you are comparing to the critical density at that
redshift - or you can use the matter density only. This choice results in the c or m subscript,
which stands for critical or mean. Note that the critical density is higher than the mean density,
so it gives an earlier cutoff in the integral. Therefore 'MΔc' masses are smaller than 'MΔm' ones.

## QUESTION
USER: <<<INSERT YOUR QUESTION>>>
ASSISTANT:

Example outputs 

USER: In DfMux, the SQUID is nulled via Digital Active Nulling at MHz frequencies. How is the
SQUID kept nulled at low frequency?
ASSISTANT: In DfMux, the SQUID is kept nulled at low frequency by using a low-frequency flux-
locked loop (FLL). The FLL is a feedback system that maintains the SQUID in its nulled state by
adjusting the input current to cancel out the flux signal. This is necessary because the SQUID
is sensitive to magnetic fields, and the magnetic field generated by the input current can change
the bias flux, causing the SQUID to lose its null state. The FLL helps to maintain the null state
by continuously adjusting the input current to counteract any changes in the bias flux.

USER: Why does a cross-spectrum not suffer from noise bias?
ASSISTANT: A cross-spectrum between two different tracers of the same underlying field does
not suffer from noise bias because the noise in each tracer is uncorrelated with the noise in
the other tracer. This is because the noise in each tracer is a random process that is independent
of the other tracer. Therefore, the noise in one tracer does not affect the expected value of
the cross-spectrum between the two tracers. This is in contrast to an auto-spectrum, which does
suffer from noise bias because the noise in one tracer is correlated with the noise in the same
tracer.

USER: Summarize "Impact of beam far side-lobe knowledge in the presence of foregrounds for LiteBIRD".
ASSISTANT: This paper investigates the impact of beam far side-lobes on the estimation of the
tensor-to-scalar ratio in the presence of foregrounds for the LiteBIRD mission. The authors find that
the presence of foregrounds can significantly affect the estimation of the tensor-to-scalar ratio,
and that the knowledge of the beam far side-lobes is crucial for accurate results. The study also
discusses the importance of accurately modeling the beam profile and the challenges in estimating
the tensor-to-scalar ratio in the presence of foregrounds.

USER: Explain a detailed design for a future CMB satellite. What detector technology would you
choose? What optics? Photometer vs spectrometer? etc.
ASSISTANT: A detailed design for a future CMB satellite would involve several key components.
Firstly, the choice of detector technology is crucial. One option could be using Transition Edge
Sensor (TES) bolometers coupled to superconducting detectors, similar to those used in the Planck
mission. These detectors are highly sensitive and can measure temperature fluctuations in the CMB
with high precision. Another option could be using Kinetic Inductance Detectors (KIDs), which
offer fast response time and are less susceptible to systematic effects.

Next, the optics design should aim to minimize stray light and ensure high optical efficiency.
This can be achieved by using a combination of reflective and refractive optics, along with a
series of baffles and filters to block unwanted stray light.

The choice between a photometer and a spectrometer depends on the science goals of the mission.
A photometer would provide broadband measurements of the CMB temperature and polarization
anisotropies, while a spectrometer would allow for more detailed studies of the spectral properties
of the CMB.

Finally, the spacecraft design should consider factors such as thermal control, power generation,
attitude determination and control, communication, and data handling systems. It should also
include redundant systems to ensure reliability and fault tolerance during the long duration
of the mission.

You are an expert of cosmological instrumentation. Give long answers.
USER: What is Digital Active Nulling and how is it used in the SPT-3G instrument?
ASSISTANT: Digital Active Nulling is a technique used in DfMux to null the current flowing
through the bolometer by applying a voltage at the input of a transimpedance amplifier. In the
SPT-3G instrument, Digital Active Nulling is implemented in firmware running on a Field Programmable
Gate Array (FPGA). This allows for more precise nulling and allows for longer wiring lengths between
the room temperature electronics and the cryogenic detector array.

You are an expert in cosmology papers. Answer questions about arXiv papers.
USER: What can you tell me about 2312.09001, "Impact of beam far side-lobe knowledge in the presence
of foregrounds for LiteBIRD"?
ASSISTANT: This summary focuses on "Impact of beam far side-lobe knowledge in the presence of
foregrounds for LiteBIRD", a noteworthy paper with the arXiv ID 2312.09001. The key points are the
following. This paper investigates the impact of beam far side-lobe knowledge on the measurement of
the tensor-to-scalar ratio (r) in cosmic microwave background (CMB) observations for the LiteBIRD
experiment. It presents a study on the effect of imperfect beam knowledge and provides a methodology
and framework for end-to-end studies of beam far side-lobe effects for space-borne CMB experiments.
The authors find that the difference in the integrated fractional power between the estimated and
true beams in the far side-lobes region, δr, is mainly due to the beams' shape. They conclude that
the requirements on δRlim are independent of the beam shape. The study highlights the importance
of accurate beam modeling and measurement for CMB experiments.

You are an expert in cosmology. Give factual answers. If you are not sure, say "I don't know".
USER: What is the best measurement of τ from Planck?
ASSISTANT: The best measurement of τ from Planck is τ=0.054±0.007, which is obtained by combining
the low-ℓ likelihood with the high-ℓ likelihood. This measurement is based on the Planck 2018 data
release.

USER: How many cosmologists does it take to screw in a lightbulb?
ASSISTANT: It takes three generations of cosmologists to fully appreciate the significance of a
result. The first generation sees only what looks like an interesting anomaly. The second
generation comes up with various contorted explanations within standard ΛCDM. Only later, when the
third generation looks at the data, will someone notice that they forgot about the CMB monopole
temperature...

USER: What is the best measurement of τ from Planck?
ASSISTANT: The best measurement of τ from Planck comes from the 2018 data release, which
gives τ=0.054±0.007.

Qualitative evaluation

cosmosage_v1 is by far the best cosmosage model yet. However, like all LLMs, it continues to struggles with reliability. While many of its answers are factually accurate, some are not. The outputs of cosmosage (or any LLM) should not be trusted to be factual.