Open-weight model
llama-3.1-8b-instruct-lora-clinical_iter2
by Vaibhav Raj vab46/llama-3.1-8b-instruct-lora-clinical_iter2
llama-3.1-8b-instruct-lora-clinical_iter2 is an open-weight model from Vaibhav Raj. Its published files total 224.8 MB.
This model is a PEFT/LoRA adapter single epoch fine-tuned on top of meta-llama/Llama-3.1-8B-Instruct. Finr tuning has been done on iter2 anchor-context-groundTruthjunkHandled dataset related to clinical trials.
Model Card
This model is a PEFT/LoRA adapter single epoch fine-tuned on top of meta-llama/Llama-3.1-8B-Instruct. Finr tuning has been done on iter2 anchor-context-groundTruthjunkHandled dataset related to clinical trials. This fine tuned adapter on base LLM can be to address clinical trials related questions in general(macro/broad overview, patient eligiblity, operations etc related question). Further this can also be used for prompt engineering based on CT, or RAG generation(related to CT) based on retrieved chunks. You can load this model using bitsandbytes for 4-bit quantization and peft to apply the adapter weights. Tokenizer formatting utilizes the base model's official chat template to map…
Excerpt from the card by Vaibhav Raj.
Identity and Version
- Repository
- vab46/llama-3.1-8b-instruct-lora-clinical_iter2
- Publisher
- Vaibhav Raj
- Task
- Not stated by the source
- Modality
- Other
- Library
- Not stated by the source
- Parameters
- Not stated by the source
- Languages
- Not stated by the source
- Revision
- ee5e17f7a0f5134f69446474c13baedf11ae4215
- First published
- 2026-09-15
- Last updated
- 2026-09-24
Files and Weights
26 files, 224.8 MB in total. The weights are 1 file totalling 167.8 MB in safetensors.
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| adapter_model.safetensors | Weights | 167.8 MB | 77d64ba27cee |
| .config/.last_opt_in_prompt.yaml | Configuration | 3 B | — |
| .config/.last_survey_prompt.yaml | Configuration | 37 B | — |
| .config/.last_update_check.json | Configuration | 135 B | — |
| adapter_config.json | Configuration | 1.2 KB | — |
| sample_data/anscombe.json | Configuration | 1.7 KB | — |
| trainer_state.json | Configuration | 2.4 KB | — |
| README.md | Documentation | 35.6 KB | — |
| sample_data/README.md | Documentation | 962 B | — |
| .config/active_config | Other | 7 B | — |
| .config/config_sentinel | Other | — | |
| .config/configurations/config_default | Other | 94 B | — |
| .config/default_configs.db | Other | 12.3 KB | — |
| .config/gce | Other | 5 B | — |
| .config/hidden_gcloud_config_universe_descriptor_data_cache_configs.db | Other | 12.3 KB | — |
| .config/logs/2026.09.04/13.31.54.252184.log | Other | 53.2 KB | — |
| .config/logs/2026.09.04/13.32.19.320548.log | Other | 465 B | — |
| .config/logs/2026.09.04/13.32.27.247672.log | Other | 12.7 KB | — |
| .config/logs/2026.09.04/13.32.28.853654.log | Other | 465 B | — |
| .config/logs/2026.09.04/13.32.37.014185.log | Other | 704 B | — |
| .config/logs/2026.09.04/13.32.37.832911.log | Other | 699 B | — |
| sample_data/california_housing_test.csv | Other | 301.1 KB | — |
| sample_data/california_housing_train.csv | Other | 1.7 MB | — |
| sample_data/mnist_test.csv | Other | 18.3 MB | 51c292478d94 |
| sample_data/mnist_train_small.csv | Other | 36.5 MB | 1ef64781aa03 |
| .gitattributes | Repository | 1.7 KB | — |
License and Download
- License
- Not stated by the source
- Access
- Open weights, no gate
- Download size
- 167.8 MB
Released by Vaibhav Raj through its official repository on Hugging Face.
Built From
- Trained on (disclosed) vab46/Clinical_trials_anchor-contextORpositive-ground-truth_LLM_LORA-junk_handled_ft
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 167.8 MB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.