PEFT
Safetensors
English
mistral
Generated from Trainer
nopperl commited on
Commit
a488c75
1 Parent(s): 3055bce

fix errors in readme

Browse files
Files changed (1) hide show
  1. README.md +5 -5
README.md CHANGED
@@ -120,7 +120,7 @@ This is a LoRA for the [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.
120
 
121
  Given text extracted from pages of a sustainability report, this model extracts the scope 1, 2 and 3 emissions in JSON format. The JSON object also contains the pages containing this information. For example, the [2022 sustainability report by the Bristol-Myers Squibb Company](https://www.bms.com/assets/bms/us/en-us/pdf/bmy-2022-esg-report.pdf) leads to the following output: `{"scope_1":202290,"scope_2":161907,"scope_3":1696100,"sources":[88,89]}`.
122
 
123
- Reaches an emission value extraction accuracy of 65\% (up from 46\% of the base model) and a source citation accuracy of 69\% (base model: 52\%) on the [corporate-emission-reports](https://huggingface.co/datasets/nopperl/corporate-emission-reports) dataset. For more information, refer to the [GitHub repo](https://github.com/nopperl/corporate_emission_reports).
124
 
125
  ## Intended uses & limitations
126
 
@@ -132,19 +132,19 @@ The model is intended to be used together with the [mistralai/Mistral-7B-Instruc
132
 
133
  Using [transformers](https://github.com/huggingface/transformers) as inference engine:
134
 
135
- python -m corporate_emissions_reports.inference.py --model_path mistralai/Mistral-7B-Instruct-v0.2 --lora nopperl/emissions-extraction-lora --model_context_size 32768 --engine hf https://www.bms.com/assets/bms/us/en-us/pdf/bmy-2022-esg-report.pdf
136
 
137
  Compare to base model without LoRA:
138
 
139
- python -m corporate_emissions_reports.inference.py --model_path mistralai/Mistral-7B-Instruct-v0.2 --model_context_size 32768 --engine hf https://www.bms.com/assets/bms/us/en-us/pdf/bmy-2022-esg-report.pdf
140
 
141
  Alternatively, it is possible to use [llama.cpp](https://github.com/ggerganov/llama.cpp) as inference engine. In this case, follow the installation instructions of the [package readme](https://github.com/nopperl/corporate_emission_reports/blob/main/README.md). In particular, the model needs to be downloaded beforehand. Then:
142
 
143
- python -m corporate_emissions_reports.inference.py --model mistral --lora ./emissions-extraction-lora/ggml-adapter-model.bin https://www.bms.com/assets/bms/us/en-us/pdf/bmy-2022-esg-report.pdf
144
 
145
  Compare to base model without LoRA:
146
 
147
- python -m corporate_emissions_reports.inference.py --model mistral https://www.bms.com/assets/bms/us/en-us/pdf/bmy-2022-esg-report.pdf
148
 
149
  #### Programmatically
150
 
 
120
 
121
  Given text extracted from pages of a sustainability report, this model extracts the scope 1, 2 and 3 emissions in JSON format. The JSON object also contains the pages containing this information. For example, the [2022 sustainability report by the Bristol-Myers Squibb Company](https://www.bms.com/assets/bms/us/en-us/pdf/bmy-2022-esg-report.pdf) leads to the following output: `{"scope_1":202290,"scope_2":161907,"scope_3":1696100,"sources":[88,89]}`.
122
 
123
+ Reaches an emission value extraction accuracy of 65\% (up from 46\% of the base model) and a source citation accuracy of 77\% (base model: 52\%) on the [corporate-emission-reports](https://huggingface.co/datasets/nopperl/corporate-emission-reports) dataset. For more information, refer to the [GitHub repo](https://github.com/nopperl/corporate_emission_reports).
124
 
125
  ## Intended uses & limitations
126
 
 
132
 
133
  Using [transformers](https://github.com/huggingface/transformers) as inference engine:
134
 
135
+ python -m corporate_emissions_reports.inference --model_path mistralai/Mistral-7B-Instruct-v0.2 --lora nopperl/emissions-extraction-lora --model_context_size 32768 --engine hf https://www.bms.com/assets/bms/us/en-us/pdf/bmy-2022-esg-report.pdf
136
 
137
  Compare to base model without LoRA:
138
 
139
+ python -m corporate_emissions_reports.inference --model_path mistralai/Mistral-7B-Instruct-v0.2 --model_context_size 32768 --engine hf https://www.bms.com/assets/bms/us/en-us/pdf/bmy-2022-esg-report.pdf
140
 
141
  Alternatively, it is possible to use [llama.cpp](https://github.com/ggerganov/llama.cpp) as inference engine. In this case, follow the installation instructions of the [package readme](https://github.com/nopperl/corporate_emission_reports/blob/main/README.md). In particular, the model needs to be downloaded beforehand. Then:
142
 
143
+ python -m corporate_emissions_reports.inference --model mistral --lora ./emissions-extraction-lora/ggml-adapter-model.bin https://www.bms.com/assets/bms/us/en-us/pdf/bmy-2022-esg-report.pdf
144
 
145
  Compare to base model without LoRA:
146
 
147
+ python -m corporate_emissions_reports.inference --model mistral https://www.bms.com/assets/bms/us/en-us/pdf/bmy-2022-esg-report.pdf
148
 
149
  #### Programmatically
150