fishaudio/fish-agent-v0.1-3b
Audio-to-Audio
β’
Updated
β’
649
β’
240
Dietrich Trautmann
trtm
Β·
AI & ML interests
Natural Language Processing; Robotics
Organizations
None yet
trtm's activity
liked
a
model
2 months ago
liked
2
models
6 months ago
liked
a
dataset
7 months ago
reacted to
macadeliccc's
post with π
8 months ago
Post
4521
Fine tune Phi-3 using samatha themed dataset and Huggingface SFT trainer!
In this colab, we simply apply a supervised finetune to phi-3 using the sharegpt format.
Opus Samantha consists of 1848 samples with the samantha personality. The dataset covers a wide variety of topics such as logical reasoning, mathematics, legal, and rp.
This notebook serves as a viable option to finetune Phi-3 until Unsloth supports phi-3, which should be very soon. When that happens check out AutoSloth for both SFT, DPO, and langfuse format RAG fine tuning on free tier colab hardware.
Resources:
Dataset: macadeliccc/opus_samantha
Colab: https://colab.research.google.com/drive/1e8LILflDQ2Me52hwS7uIfuJ9DxE2oQzM?usp=sharing
AutoSloth: https://colab.research.google.com/drive/1Zo0sVEb2lqdsUm9dy2PTzGySxdF9CNkc#scrollTo=bpimlPXVz-CZ
In this colab, we simply apply a supervised finetune to phi-3 using the sharegpt format.
def formatting_prompts_func(examples):
convos = examples["conversations"]
texts = []
mapper = {"system": "system\n", "human": "\nuser\n", "gpt": "\nassistant\n"}
end_mapper = {"system": "", "human": "", "gpt": ""}
for convo in convos:
text = "".join(f"{mapper[(turn := x['from'])]} {x['value']}\n{end_mapper[turn]}" for x in convo)
texts.append(f"{text}{EOS_TOKEN}")
return {"text": texts}
dataset = dataset.map(formatting_prompts_func, batched=True)
print(dataset['text'][8])Opus Samantha consists of 1848 samples with the samantha personality. The dataset covers a wide variety of topics such as logical reasoning, mathematics, legal, and rp.
This notebook serves as a viable option to finetune Phi-3 until Unsloth supports phi-3, which should be very soon. When that happens check out AutoSloth for both SFT, DPO, and langfuse format RAG fine tuning on free tier colab hardware.
Resources:
Dataset: macadeliccc/opus_samantha
Colab: https://colab.research.google.com/drive/1e8LILflDQ2Me52hwS7uIfuJ9DxE2oQzM?usp=sharing
AutoSloth: https://colab.research.google.com/drive/1Zo0sVEb2lqdsUm9dy2PTzGySxdF9CNkc#scrollTo=bpimlPXVz-CZ
upvoted
a
collection
8 months ago
reacted to
macadeliccc's
post with π
8 months ago
Post
4521
Fine tune Phi-3 using samatha themed dataset and Huggingface SFT trainer!
In this colab, we simply apply a supervised finetune to phi-3 using the sharegpt format.
Opus Samantha consists of 1848 samples with the samantha personality. The dataset covers a wide variety of topics such as logical reasoning, mathematics, legal, and rp.
This notebook serves as a viable option to finetune Phi-3 until Unsloth supports phi-3, which should be very soon. When that happens check out AutoSloth for both SFT, DPO, and langfuse format RAG fine tuning on free tier colab hardware.
Resources:
Dataset: macadeliccc/opus_samantha
Colab: https://colab.research.google.com/drive/1e8LILflDQ2Me52hwS7uIfuJ9DxE2oQzM?usp=sharing
AutoSloth: https://colab.research.google.com/drive/1Zo0sVEb2lqdsUm9dy2PTzGySxdF9CNkc#scrollTo=bpimlPXVz-CZ
In this colab, we simply apply a supervised finetune to phi-3 using the sharegpt format.
def formatting_prompts_func(examples):
convos = examples["conversations"]
texts = []
mapper = {"system": "system\n", "human": "\nuser\n", "gpt": "\nassistant\n"}
end_mapper = {"system": "", "human": "", "gpt": ""}
for convo in convos:
text = "".join(f"{mapper[(turn := x['from'])]} {x['value']}\n{end_mapper[turn]}" for x in convo)
texts.append(f"{text}{EOS_TOKEN}")
return {"text": texts}
dataset = dataset.map(formatting_prompts_func, batched=True)
print(dataset['text'][8])Opus Samantha consists of 1848 samples with the samantha personality. The dataset covers a wide variety of topics such as logical reasoning, mathematics, legal, and rp.
This notebook serves as a viable option to finetune Phi-3 until Unsloth supports phi-3, which should be very soon. When that happens check out AutoSloth for both SFT, DPO, and langfuse format RAG fine tuning on free tier colab hardware.
Resources:
Dataset: macadeliccc/opus_samantha
Colab: https://colab.research.google.com/drive/1e8LILflDQ2Me52hwS7uIfuJ9DxE2oQzM?usp=sharing
AutoSloth: https://colab.research.google.com/drive/1Zo0sVEb2lqdsUm9dy2PTzGySxdF9CNkc#scrollTo=bpimlPXVz-CZ
liked
a
model
8 months ago
liked
a
Space
8 months ago
liked
a
dataset
9 months ago
reacted to
ppierzc's
post with π
10 months ago
Post
Excited to share my latest preprint with
@oliveiracaio
and
@fabee
: "Platypose: Calibrated Zero-Shot Multi-Hypothesis 3D Human Motion Estimation"! ππΊ
Platypose is our new approach to estimating 3D human motions from 2D observations. What makes it special? π€© Well, we're able to estimate multiple hypotheses for motion, which is pretty cool!
But here's the best part: our model is not only accurate but also well-calibrated. We've made sure that the predicted uncertainty matches the models confidence, so you can have a better understanding of Platypose's predictions.
Project Page: https://sinzlab.org/publications/2024-platypose.html
Paper: Platypose: Calibrated Zero-Shot Multi-Hypothesis 3D Human Motion Estimation (2403.06164)
Model Weights: sinzlab/platypose
The code is open-source, so please leave a star β
https://github.com/sinzlab/platypose
Platypose is our new approach to estimating 3D human motions from 2D observations. What makes it special? π€© Well, we're able to estimate multiple hypotheses for motion, which is pretty cool!
But here's the best part: our model is not only accurate but also well-calibrated. We've made sure that the predicted uncertainty matches the models confidence, so you can have a better understanding of Platypose's predictions.
Project Page: https://sinzlab.org/publications/2024-platypose.html
Paper: Platypose: Calibrated Zero-Shot Multi-Hypothesis 3D Human Motion Estimation (2403.06164)
Model Weights: sinzlab/platypose
The code is open-source, so please leave a star β
https://github.com/sinzlab/platypose
- 1 reply
reacted to
KnutJaegersberg's
post with π
10 months ago
Post
Shocking: 2/3 of LLMs fail at 2K context length
code_your_own_ai makes a great vlog about mostly LLM related AI content.
As I watched the video below, I wondered about current best practices on LLM evaluation. We have benchmarks, we have sota LLMs evaluating LLMs, we have tools evaluating based on human comparison.
Often, I hear, just play with the LLM for 15 mins to form an opinion.
While I think for a specific use case and clear expectations, this could yield signal carrying experiences, I also see that one prompt is used to judge models.
While benchmarks have their weaknesses, and are by themselves not enough to judge model quality, I still think systematic methods that try to reduce various scientifically known errs should be the way forward, even for qualitative estimates.
What do you think? How can we make a public tool for judging models like lmsys/chatbot-arena-leaderboard help to leverage standards known in social science?
https://www.youtube.com/watch?v=mWrivekFZMM
code_your_own_ai makes a great vlog about mostly LLM related AI content.
As I watched the video below, I wondered about current best practices on LLM evaluation. We have benchmarks, we have sota LLMs evaluating LLMs, we have tools evaluating based on human comparison.
Often, I hear, just play with the LLM for 15 mins to form an opinion.
While I think for a specific use case and clear expectations, this could yield signal carrying experiences, I also see that one prompt is used to judge models.
While benchmarks have their weaknesses, and are by themselves not enough to judge model quality, I still think systematic methods that try to reduce various scientifically known errs should be the way forward, even for qualitative estimates.
What do you think? How can we make a public tool for judging models like lmsys/chatbot-arena-leaderboard help to leverage standards known in social science?
https://www.youtube.com/watch?v=mWrivekFZMM
- 6 replies
liked
a
Space
10 months ago
liked
a
Space
11 months ago
liked
a
model
12 months ago
liked
2
datasets
about 1 year ago
Missing transcripts webcast_id in documents
1
#1 opened about 1 year ago
by
trtm
liked
a
dataset
about 1 year ago
liked
a
model
about 1 year ago
