sreemanti-abacus commited on
Commit
3167656
1 Parent(s): 09c4eeb

Add model card numbers to Dracarys2-Llama3.1-70B-Instruct model (#1)

Browse files

- Add model card numbers to Dracarys2-Llama3.1-70B-Instruct model (3ca8e6bb93d32b4f6ef6c5274c9c75104b59b728)

Files changed (1) hide show
  1. README.md +76 -164
README.md CHANGED
@@ -1,199 +1,111 @@
1
  ---
 
2
  library_name: transformers
3
  tags: []
4
  ---
5
 
6
- # Model Card for Model ID
7
 
8
- <!-- Provide a quick summary of what the model is/does. -->
9
 
 
10
 
 
 
11
 
12
- ## Model Details
13
 
14
- ### Model Description
15
-
16
- <!-- Provide a longer summary of what this model is. -->
17
-
18
- This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
19
-
20
- - **Developed by:** [More Information Needed]
21
- - **Funded by [optional]:** [More Information Needed]
22
- - **Shared by [optional]:** [More Information Needed]
23
- - **Model type:** [More Information Needed]
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
- <!-- Provide the basic links for the model. -->
31
-
32
- - **Repository:** [More Information Needed]
33
- - **Paper [optional]:** [More Information Needed]
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
- <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
-
44
- [More Information Needed]
45
-
46
- ### Downstream Use [optional]
47
-
48
- <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
-
50
- [More Information Needed]
51
-
52
- ### Out-of-Scope Use
53
-
54
- <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
-
56
- [More Information Needed]
57
-
58
- ## Bias, Risks, and Limitations
59
-
60
- <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
-
62
- [More Information Needed]
63
-
64
- ### Recommendations
65
-
66
- <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
-
68
- Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
-
70
- ## How to Get Started with the Model
71
-
72
- Use the code below to get started with the model.
73
-
74
- [More Information Needed]
75
-
76
- ## Training Details
77
-
78
- ### Training Data
79
-
80
- <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
81
-
82
- [More Information Needed]
83
-
84
- ### Training Procedure
85
-
86
- <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
 
88
- #### Preprocessing [optional]
89
-
90
- [More Information Needed]
91
-
92
-
93
- #### Training Hyperparameters
94
-
95
- - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
-
97
- #### Speeds, Sizes, Times [optional]
98
-
99
- <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
-
101
- [More Information Needed]
102
-
103
- ## Evaluation
104
-
105
- <!-- This section describes the evaluation protocols and provides the results. -->
106
-
107
- ### Testing Data, Factors & Metrics
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]
 
 
 
 
1
  ---
2
+ license: llama3
3
  library_name: transformers
4
  tags: []
5
  ---
6
 
7
+ # Dracarys2-Llama-3.1-70B-Instruct
8
 
9
+ ### Built with Meta Llama 3
10
 
11
+ # Introduction
12
 
13
+ We introduce the latest in the Smaug series, the Dracarys family of finetunes targeting coding performance improvements
14
+ across a variety of base models.
15
 
16
+ This variant is a finetune of [meta-llama/Meta-Llama-3.1-70B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-70B-Instruct)
17
 
18
+ Compared to meta-llama/Meta-Llama-3.1-70B-Instruct, Dracarys has better LiveCodeBench scores (see evaluation results below).
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
19
 
20
+ ### Model Description
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
21
 
22
+ - **Developed by:** [Abacus.AI](https://abacus.ai)
23
+ - **License:** https://llama.meta.com/llama3/license/
24
+ - **Finetuned from model:** [meta-llama/Meta-Llama-3.1-70B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-70B-Instruct).
25
 
26
+ ## How to use
27
 
28
+ The prompt format is unchanged from Llama 3 70B Instruct (see evaluations for prompt details for LCB)
29
 
30
+ ### Use with transformers
31
 
32
+ See the snippet below for usage with Transformers:
33
 
34
+ ```python
35
+ import transformers
36
+ import torch
37
 
38
+ model_id = "abacusai/Dracarys-72B-Instruct"
39
 
40
+ pipeline = transformers.pipeline(
41
+ "text-generation",
42
+ model=model_id,
43
+ model_kwargs={"torch_dtype": torch.bfloat16},
44
+ device_map="auto",
45
+ )
46
 
47
+ messages = [
48
+ {"role": "system", "content": "You are data science coding assistant that generates Python code using Pandas and Numpy."},
49
+ {"role": "user", "content": "Write code to select rows from the dataframe `df` having the maximum `temp` for each `city`"},
50
+ ]
51
 
52
+ prompt = pipeline.tokenizer.apply_chat_template(
53
+ messages,
54
+ tokenize=False,
55
+ add_generation_prompt=True
56
+ )
57
 
58
+ terminators = [
59
+ pipeline.tokenizer.eos_token_id,
60
+ pipeline.tokenizer.convert_tokens_to_ids("<|eot_id|>"),
61
+ pipeline.tokenizer.convert_tokens_to_ids("<|end_of_text|>"),
62
+ ]
63
 
64
+ outputs = pipeline(
65
+ prompt,
66
+ max_new_tokens=256,
67
+ eos_token_id=terminators,
68
+ do_sample=True,
69
+ temperature=0.6,
70
+ top_p=0.9,
71
+ )
72
+ print(outputs[0]["generated_text"][len(prompt):])
73
+ ```
74
 
75
+ # Evaluation Results
76
 
 
77
 
78
+ ## LiveCodeBench
79
 
80
+ | Model | Code Generation | Code Execution |Test Output Prediction |
81
+ |-------------------------------------|-----------------|----------------|-----------------------|
82
+ | **Dracarys2-Llama-3.1-70B-Instruct**| **33.44** | 48.26 | **52.10** |
83
+ | Meta-Llama-3.1-70B-Instruct | 32.23 | 48.768 | 41.40 |
84
 
85
+ ## Breakdown of LiveCodeBench CodeGeneration
86
 
87
+ | Model | Easy | Medium | Hard |
88
+ |-------------------------------------|-----------------|----------------|-----------------------|
89
+ | **Dracarys2-Llama-3.1-70B-Instruct**| **71.29** | **18.48** | **3.57** |
90
+ | Meta-Llama-3.1-70B-Instruct | 68.4 | 17.99 | 3.57 |
91
 
92
+ ## Breakdown of LiveCodeBench CodeExecution
93
 
94
+ | Model | COT | Non-COT |
95
+ |-------------------------------------|-----------------|----------------|
96
+ | **Dracarys2-Llama-3.1-70B-Instruct**| **75.55** | 48.26 |
97
+ | Meta-Llama-3.1-70B-Instruct | 70.14 | 48.768 |
98
 
99
+ ## Breakdown of LiveCodeBench TestOutputPrediction
100
 
101
+ | Model | Easy | Medium | Hard |
102
+ |-------------------------------------|-----------------|----------------|-----------------------|
103
+ | **Dracarys2-Llama-3.1-70B-Instruct**| **63.53** | **47.30** | **43.61** |
104
+ | Meta-Llama-3.1-70B-Instruct | 51.22 | 35.91 | 34.30 |
105
 
106
+ ## LiveBench(Aug update)
107
 
108
+ | Model | Global Average | Coding Average | Reasoning Average| Mathematics Average | Data Analysis Average | Language Average | IF Average |
109
+ |-------------------------------------|----------------|----------------|------------------|---------------------|-----------------------|------------------|-------------|
110
+ | **Dracarys2-Llama-3.1-70B-Instruct**| **47.8** | **36.3** | **47.3** | **38.9** | 46.1 | 41.5 | 76.6 |
111
+ | Meta-Llama-3.1-70B-Instruct | 45.1 | 30.7 | 35.3 | 37.0 | 48.4 | 42.1 | 77.2 |