Hugging Face's logo

cortecs
/
Llama-3.3-70B-Instruct-FP8-Dynamic

Safetensors
llama
compressed-tensors
Model card Files Community
1
markoarnauto commited on
Commit
ca180a7
•
1 Parent(s): 7860f43

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +64 -197
README.md CHANGED
@@ -1,199 +1,66 @@
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: other
3
+ license_link: https://llama.meta.com/llama3/license/
4
+ base_model: meta-llama/Llama-3.3-70B-Instruct
5
 
6
+ ---
7
+ This is a quantization of the [Llama-3.3-70B-Instruct](https://huggingface.co/meta-llama--Llama-3.3-70B-Instruct).
8
+
9
+ The Meta Llama 3.3 is a state-of-the-art multilingual large language model (LLM) with 70 billion parameters, pretrained and instruction-tuned for exceptional performance in generative text-based tasks. Optimized for multilingual dialogue, it supports English and seven additional languages: French, German, Hindi, Italian, Portuguese, Spanish, and Thai, enabling seamless communication across diverse audiences. The model consistently outperforms both open-source and proprietary chat models on key industry benchmarks, delivering superior quality, safety, and helpfulness. Its advanced features and multilingual support position Llama 3.3 as a powerful tool for building innovative AI applications.
10
+ ## Evaluations
11
+ This model provides an accuracy recovery of 99.67%.
12
+
13
+ | __English__ | __[Llama-3.3-70B-Instruct](https://huggingface.co/meta-llama--Llama-3.3-70B-Instruct)__ | __[Llama-3.3-70B-Instruct-FP8-Dynamic (this)](https://huggingface.co/cortecs--Llama-3.3-70B-Instruct-FP8-Dynamic)__ |
14
+ |:--------------|:------------------------------------------------------------------------------------------|:----------------------------------------------------------------------------------------------------------------------|
15
+ | Avg. | 74.1 | 73.75 |
16
+ | Arc | 71.7 | 71.6 |
17
+ | Hellaswag | 76.5 | 75.9 |
18
+ | | | |
19
+ | __French__ | __[Llama-3.3-70B-Instruct](https://huggingface.co/meta-llama--Llama-3.3-70B-Instruct)__ | __[Llama-3.3-70B-Instruct-FP8-Dynamic (this)](https://huggingface.co/cortecs--Llama-3.3-70B-Instruct-FP8-Dynamic)__ |
20
+ | Avg. | 73.07 | 72.87 |
21
+ | Arc | 64.7 | 64.5 |
22
+ | Hellaswag | 76.6 | 76.6 |
23
+ | MMLU | 77.9 | 77.5 |
24
+ | | | |
25
+ | __German__ | __[Llama-3.3-70B-Instruct](https://huggingface.co/meta-llama--Llama-3.3-70B-Instruct)__ | __[Llama-3.3-70B-Instruct-FP8-Dynamic (this)](https://huggingface.co/cortecs--Llama-3.3-70B-Instruct-FP8-Dynamic)__ |
26
+ | Avg. | 70.07 | 69.83 |
27
+ | Arc | 61.8 | 61.2 |
28
+ | Hellaswag | 71.2 | 71.1 |
29
+ | MMLU | 77.2 | 77.2 |
30
+ | | | |
31
+ | __Italian__ | __[Llama-3.3-70B-Instruct](https://huggingface.co/meta-llama--Llama-3.3-70B-Instruct)__ | __[Llama-3.3-70B-Instruct-FP8-Dynamic (this)](https://huggingface.co/cortecs--Llama-3.3-70B-Instruct-FP8-Dynamic)__ |
32
+ | Avg. | 73.67 | 73.37 |
33
+ | Arc | 66.5 | 65.7 |
34
+ | Hellaswag | 76.0 | 76.2 |
35
+ | MMLU | 78.5 | 78.2 |
36
+ | | | |
37
+ | __Portuguese__ | __[Llama-3.3-70B-Instruct](https://huggingface.co/meta-llama--Llama-3.3-70B-Instruct)__ | __[Llama-3.3-70B-Instruct-FP8-Dynamic (this)](https://huggingface.co/cortecs--Llama-3.3-70B-Instruct-FP8-Dynamic)__ |
38
+ | Avg. | 74.4 | 73.87 |
39
+ | Arc | 66.4 | 65.5 |
40
+ | Hellaswag | 77.2 | 76.9 |
41
+ | MMLU | 79.6 | 79.2 |
42
+ | | | |
43
+ | __Spanish__ | __[Llama-3.3-70B-Instruct](https://huggingface.co/meta-llama--Llama-3.3-70B-Instruct)__ | __[Llama-3.3-70B-Instruct-FP8-Dynamic (this)](https://huggingface.co/cortecs--Llama-3.3-70B-Instruct-FP8-Dynamic)__ |
44
+ | Avg. | 74 | 74.13 |
45
+ | Arc | 65.8 | 65.8 |
46
+ | Hellaswag | 77.1 | 77.2 |
47
+ | MMLU | 79.1 | 79.4 |
48
+
49
+ We did not check for data contamination.
50
+ Evaluation was done using [Eval. Harness](https://github.com/EleutherAI/lm-evaluation-harness) with `limit=1000`.
51
+
52
+ ## Usage
53
+ Install **vLLM** and
54
+ run the [server](https://docs.vllm.ai/en/latest/serving/openai_compatible_server.html#openai-compatible-server):
55
+
56
+ ```
57
+ python -m vllm.entrypoints.openai.api_server --model cortecs/Llama-3.3-70B-Instruct-FP8-Dynamic
58
+ ```
59
+ Access the model:
60
+ ```
61
+ curl http://localhost:8000/v1/completions -H "Content-Type: application/json" -d ' {
62
+ "model": "cortecs/Llama-3.3-70B-Instruct-FP8-Dynamic",
63
+ "prompt": "San Francisco is a"
64
+ } '
65
+ ```
66
+ This model is optimized to handle heavy workloads providing a total throughput of ️**1485 tokens per second** using one NVIDIA H100 ⚡