Update README.md
Browse files
README.md
CHANGED
@@ -1,202 +1,117 @@
|
|
1 |
---
|
2 |
base_model: EleutherAI/pythia-70m-deduped
|
|
|
3 |
library_name: peft
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
4 |
---
|
5 |
|
6 |
-
# Model Card for
|
7 |
-
|
8 |
-
<!-- Provide a quick summary of what the model is/does. -->
|
9 |
-
|
10 |
|
|
|
11 |
|
12 |
## Model Details
|
13 |
|
14 |
### Model Description
|
15 |
|
16 |
-
|
17 |
-
|
18 |
|
19 |
-
|
20 |
-
- **
|
21 |
-
- **
|
22 |
-
- **
|
23 |
-
- **
|
24 |
-
- **Language(s) (NLP):** [More Information Needed]
|
25 |
-
- **License:** [More Information Needed]
|
26 |
-
- **Finetuned from model [optional]:** [More Information Needed]
|
27 |
|
28 |
### Model Sources [optional]
|
29 |
|
30 |
-
|
31 |
-
|
32 |
-
- **
|
33 |
-
- **
|
34 |
-
- **Demo [optional]:** [More Information Needed]
|
35 |
|
36 |
## Uses
|
37 |
|
38 |
-
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
39 |
-
|
40 |
### Direct Use
|
41 |
|
42 |
-
|
|
|
|
|
|
|
43 |
|
44 |
-
|
45 |
|
46 |
### Downstream Use [optional]
|
47 |
|
48 |
-
|
49 |
-
|
50 |
-
[More Information Needed]
|
51 |
|
52 |
### Out-of-Scope Use
|
53 |
|
54 |
-
|
55 |
-
|
56 |
-
|
|
|
57 |
|
58 |
## Bias, Risks, and Limitations
|
59 |
|
60 |
-
|
61 |
-
|
62 |
-
|
|
|
|
|
63 |
|
64 |
### Recommendations
|
65 |
|
66 |
-
|
67 |
-
|
68 |
-
|
|
|
69 |
|
70 |
## How to Get Started with the Model
|
71 |
|
72 |
-
|
73 |
-
|
74 |
-
|
75 |
-
|
76 |
-
|
77 |
-
|
78 |
-
|
79 |
-
|
80 |
-
|
81 |
-
|
82 |
-
|
83 |
-
|
84 |
-
|
85 |
-
|
86 |
-
|
87 |
-
|
88 |
-
|
89 |
-
|
90 |
-
|
91 |
-
|
92 |
-
|
93 |
-
|
94 |
-
|
95 |
-
|
96 |
-
|
97 |
-
|
98 |
-
|
99 |
-
|
100 |
-
|
101 |
-
|
102 |
-
|
103 |
-
|
104 |
-
|
105 |
-
|
106 |
-
|
107 |
-
|
108 |
-
|
109 |
-
#### Testing Data
|
110 |
-
|
111 |
-
<!-- This should link to a Dataset Card if possible. -->
|
112 |
-
|
113 |
-
[More Information Needed]
|
114 |
-
|
115 |
-
#### Factors
|
116 |
-
|
117 |
-
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
118 |
-
|
119 |
-
[More Information Needed]
|
120 |
-
|
121 |
-
#### Metrics
|
122 |
-
|
123 |
-
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
124 |
-
|
125 |
-
[More Information Needed]
|
126 |
-
|
127 |
-
### Results
|
128 |
-
|
129 |
-
[More Information Needed]
|
130 |
-
|
131 |
-
#### Summary
|
132 |
-
|
133 |
-
|
134 |
-
|
135 |
-
## Model Examination [optional]
|
136 |
-
|
137 |
-
<!-- Relevant interpretability work for the model goes here -->
|
138 |
-
|
139 |
-
[More Information Needed]
|
140 |
-
|
141 |
-
## Environmental Impact
|
142 |
-
|
143 |
-
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
144 |
-
|
145 |
-
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
146 |
-
|
147 |
-
- **Hardware Type:** [More Information Needed]
|
148 |
-
- **Hours used:** [More Information Needed]
|
149 |
-
- **Cloud Provider:** [More Information Needed]
|
150 |
-
- **Compute Region:** [More Information Needed]
|
151 |
-
- **Carbon Emitted:** [More Information Needed]
|
152 |
-
|
153 |
-
## Technical Specifications [optional]
|
154 |
-
|
155 |
-
### Model Architecture and Objective
|
156 |
-
|
157 |
-
[More Information Needed]
|
158 |
-
|
159 |
-
### Compute Infrastructure
|
160 |
-
|
161 |
-
[More Information Needed]
|
162 |
-
|
163 |
-
#### Hardware
|
164 |
-
|
165 |
-
[More Information Needed]
|
166 |
-
|
167 |
-
#### Software
|
168 |
-
|
169 |
-
[More Information Needed]
|
170 |
-
|
171 |
-
## Citation [optional]
|
172 |
-
|
173 |
-
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
174 |
-
|
175 |
-
**BibTeX:**
|
176 |
-
|
177 |
-
[More Information Needed]
|
178 |
-
|
179 |
-
**APA:**
|
180 |
-
|
181 |
-
[More Information Needed]
|
182 |
-
|
183 |
-
## Glossary [optional]
|
184 |
-
|
185 |
-
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
186 |
-
|
187 |
-
[More Information Needed]
|
188 |
-
|
189 |
-
## More Information [optional]
|
190 |
-
|
191 |
-
[More Information Needed]
|
192 |
-
|
193 |
-
## Model Card Authors [optional]
|
194 |
-
|
195 |
-
[More Information Needed]
|
196 |
-
|
197 |
-
## Model Card Contact
|
198 |
-
|
199 |
-
[More Information Needed]
|
200 |
-
### Framework versions
|
201 |
-
|
202 |
-
- PEFT 0.7.1
|
|
|
1 |
---
|
2 |
base_model: EleutherAI/pythia-70m-deduped
|
3 |
+
model_name: "Pythia-70M Sarcasm LoRA by hyvve"
|
4 |
library_name: peft
|
5 |
+
tags:
|
6 |
+
- text-generation
|
7 |
+
- lora
|
8 |
+
- peft
|
9 |
+
- sarcasm
|
10 |
+
- pythia
|
11 |
+
- fine-tuning
|
12 |
+
- causal-lm
|
13 |
+
- EleutherAI
|
14 |
+
license: apache-2.0
|
15 |
+
pipeline_tag: text-generation
|
16 |
---
|
17 |
|
18 |
+
# Model Card for Pythia-70M Sarcasm LoRA
|
|
|
|
|
|
|
19 |
|
20 |
+
This model is a LoRA (Low-Rank Adaptation) fine-tune of the `EleutherAI/pythia-70m-deduped` model, specifically adapted for tasks related to sarcasm.
|
21 |
|
22 |
## Model Details
|
23 |
|
24 |
### Model Description
|
25 |
|
26 |
+
This is a PEFT LoRA adapter for the `EleutherAI/pythia-70m-deduped` model. It has been fine-tuned on a dataset related to sarcasm. As a Causal Language Model (CLM), its primary function is to predict the next token in a sequence. This fine-tuning aims to imbue the model with an understanding or stylistic representation of sarcastic language.
|
|
|
27 |
|
28 |
+
- **Developed by:** [hyvve](https://hyvve.xyz) (based on job configurations)
|
29 |
+
- **Model type:** Causal Language Model (specifically, a LoRA adapter for a GPT-NeoX based model)
|
30 |
+
- **Language(s) (NLP):** English (derived from the base model and assumed dataset language)
|
31 |
+
- **License:** Apache-2.0 (inherited from the base model `EleutherAI/pythia-70m-deduped`)
|
32 |
+
- **Finetuned from model:** `EleutherAI/pythia-70m-deduped`
|
|
|
|
|
|
|
33 |
|
34 |
### Model Sources [optional]
|
35 |
|
36 |
+
- **Repository (LoRA Adapter):** `https://huggingface.co/manny-uncharted/pythia-70m-sarcasm-lora` (based on `hf_target_model_repo_id`)
|
37 |
+
- **Base Model Repository:** `https://huggingface.co/EleutherAI/pythia-70m-deduped`
|
38 |
+
- **Paper [optional]:** For Pythia suite: [arXiv:2304.01373](https://arxiv.org/abs/2304.01373)
|
39 |
+
- **Demo [optional]:** [Not Provided]
|
|
|
40 |
|
41 |
## Uses
|
42 |
|
|
|
|
|
43 |
### Direct Use
|
44 |
|
45 |
+
This LoRA adapter is intended to be loaded on top of the `EleutherAI/pythia-70m-deduped` base model. It can be used for:
|
46 |
+
* Generating text with a sarcastic tone or style.
|
47 |
+
* Completing prompts in a sarcastic manner.
|
48 |
+
* Research into modeling nuanced aspects of language like sarcasm with smaller LMs.
|
49 |
|
50 |
+
**Note:** Due to the extremely small dataset size used for fine-tuning (14 examples), the model's ability to robustly generate or understand sarcasm will be very limited. It primarily serves as a pipeline and integration test.
|
51 |
|
52 |
### Downstream Use [optional]
|
53 |
|
54 |
+
* Further fine-tuning on larger, more diverse sarcasm datasets.
|
55 |
+
* Integration into applications requiring conditional text generation with a sarcastic flavor (e.g., chatbots, creative writing tools), though extensive further tuning would be necessary.
|
|
|
56 |
|
57 |
### Out-of-Scope Use
|
58 |
|
59 |
+
* Reliable sarcasm detection or classification without significant further development and evaluation.
|
60 |
+
* Generating harmful, biased, or offensive content, even if framed as sarcasm.
|
61 |
+
* Use in critical applications where misinterpretation of sarcasm could have negative consequences.
|
62 |
+
* Generating fluent, coherent, and factually accurate long-form text beyond the capabilities of the 70M parameter base model.
|
63 |
|
64 |
## Bias, Risks, and Limitations
|
65 |
|
66 |
+
* **Limited Scope:** Fine-tuned on a very small dataset (1000 examples), so its understanding and generation of sarcasm will be superficial and not generalizable.
|
67 |
+
* **Inherited Biases:** Inherits biases from the `EleutherAI/pythia-70m-deduped` base model, which was trained on The Pile. These can include societal, gender, and racial biases.
|
68 |
+
* **Misinterpretation of Sarcasm:** Sarcasm is highly context-dependent and subjective. The model may generate text that is inappropriately sarcastic or fail to understand sarcastic prompts correctly.
|
69 |
+
* **Potential for Harmful Sarcasm:** Sarcasm can be used to convey negativity or veiled aggression. The model might inadvertently generate such content.
|
70 |
+
* **Numerical Instability:** During the logged training run, an `eval_loss: nan` was observed, indicating potential issues with evaluation on the tiny validation set or numerical instability under the given configuration. The `train_loss: 0.0` also suggests extreme overfitting or issues with the learning process on such limited data.
|
71 |
|
72 |
### Recommendations
|
73 |
|
74 |
+
* **Thorough Evaluation:** Before any production use, the model (after further fine-tuning on a substantial dataset) would require rigorous evaluation for both sarcasm generation quality and potential biases.
|
75 |
+
* **Content Moderation:** Downstream applications should implement content moderation and safety filters.
|
76 |
+
* **Context is Key:** Use with clear context and be aware that its sarcastic capabilities are likely very brittle due to the limited training data.
|
77 |
+
* **Do Not Use for Critical Decisions:** This model, in its current state, is not suitable for any critical applications.
|
78 |
|
79 |
## How to Get Started with the Model
|
80 |
|
81 |
+
To use this LoRA adapter, you'll need to load the base model and then apply the adapter using the PEFT library.
|
82 |
+
|
83 |
+
```python
|
84 |
+
from transformers import AutoModelForCausalLM, AutoTokenizer
|
85 |
+
from peft import PeftModel
|
86 |
+
import torch
|
87 |
+
|
88 |
+
base_model_id = "EleutherAI/pythia-70m-deduped"
|
89 |
+
adapter_model_id = "manny-uncharted/pythia-70m-sarcasm-lora" # Replace with your actual model ID
|
90 |
+
|
91 |
+
# Load the tokenizer
|
92 |
+
tokenizer = AutoTokenizer.from_pretrained(base_model_id)
|
93 |
+
if tokenizer.pad_token is None:
|
94 |
+
tokenizer.pad_token = tokenizer.eos_token
|
95 |
+
|
96 |
+
# Load the base model (e.g., in 4-bit if that's how the adapter was trained/intended)
|
97 |
+
# For QLoRA, BitsAndBytesConfig would be needed here as during training
|
98 |
+
# For simplicity, this example loads without quantization. Adapt as needed.
|
99 |
+
base_model = AutoModelForCausalLM.from_pretrained(
|
100 |
+
base_model_id,
|
101 |
+
# quantization_config=BitsAndBytesConfig(...) # Add if loading in 4-bit/8-bit
|
102 |
+
# torch_dtype=torch.float16, # Or torch.bfloat16
|
103 |
+
device_map="auto"
|
104 |
+
)
|
105 |
+
|
106 |
+
# Load the PEFT LoRA model (adapter)
|
107 |
+
model = PeftModel.from_pretrained(base_model, adapter_model_id)
|
108 |
+
model = model.merge_and_unload() # Optional: merge adapter into base model for faster inference
|
109 |
+
|
110 |
+
# Now you can use the model for generation
|
111 |
+
prompt = "The weather today is just " # Example prompt
|
112 |
+
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
|
113 |
+
|
114 |
+
# Generate text
|
115 |
+
# Adjust generation parameters as needed
|
116 |
+
outputs = model.generate(**inputs, max_new_tokens=50, do_sample=True, top_k=50, top_p=0.95, temperature=0.7)
|
117 |
+
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|