├── CM_llm_genomics.pdf ├── CM_llm_genomics.pptx ├── README.md ├── data ├── GUE.tar.xz ├── SNP │ ├── SNPexon_alt_201b.fasta.gz │ ├── SNPexon_ref_201b.fasta.gz │ ├── SNPintron_alt_201b.fasta.gz │ └── SNPintron_ref_201b.fasta.gz ├── genome_sequences │ └── hg38 │ │ └── sequences_hg38_200b_verysmall.csv.gz └── models │ ├── Mistral-Codon-v1-1M-finetuned-mRFP │ ├── config.json │ ├── model.safetensors │ ├── rng_state.pth │ ├── scheduler.pt │ ├── special_tokens_map.json │ ├── tokenizer.json │ ├── tokenizer_config.json │ ├── trainer_state.json │ └── training_args.bin │ ├── Mistral-DNA-v1-1M-hg38-finetuned-prom │ ├── config.json │ ├── model.safetensors │ ├── rng_state.pth │ ├── scheduler.pt │ ├── tokenizer.json │ ├── tokenizer_config.json │ ├── trainer_state.json │ └── training_args.bin │ ├── Mistral-DNA-v1-1M-hg38-finetuned-tf0 │ ├── config.json │ ├── model.safetensors │ ├── rng_state.pth │ ├── scheduler.pt │ ├── tokenizer.json │ ├── tokenizer_config.json │ ├── trainer_state.json │ └── training_args.bin │ ├── Mistral-DNA-v1-1M-hg38-finetuned-tf1 │ ├── config.json │ ├── model.safetensors │ ├── rng_state.pth │ ├── scheduler.pt │ ├── tokenizer.json │ ├── tokenizer_config.json │ ├── trainer_state.json │ └── training_args.bin │ └── Mixtral-8x7B-v0.1 │ ├── README.md │ ├── config.json │ ├── config_original.json │ ├── generation_config.json │ ├── model.safetensors.index.json │ ├── special_tokens_map.json │ ├── tokenizer.json │ └── tokenizer_config.json ├── dna_seq_200b.png ├── illustration.odg └── illustration.png /CM_llm_genomics.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/raphaelmourad/LLM-for-genomics-training/HEAD/CM_llm_genomics.pdf -------------------------------------------------------------------------------- /CM_llm_genomics.pptx: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/raphaelmourad/LLM-for-genomics-training/HEAD/CM_llm_genomics.pptx -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/raphaelmourad/LLM-for-genomics-training/HEAD/README.md -------------------------------------------------------------------------------- /data/GUE.tar.xz: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/raphaelmourad/LLM-for-genomics-training/HEAD/data/GUE.tar.xz -------------------------------------------------------------------------------- /data/SNP/SNPexon_alt_201b.fasta.gz: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/raphaelmourad/LLM-for-genomics-training/HEAD/data/SNP/SNPexon_alt_201b.fasta.gz -------------------------------------------------------------------------------- /data/SNP/SNPexon_ref_201b.fasta.gz: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/raphaelmourad/LLM-for-genomics-training/HEAD/data/SNP/SNPexon_ref_201b.fasta.gz -------------------------------------------------------------------------------- /data/SNP/SNPintron_alt_201b.fasta.gz: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/raphaelmourad/LLM-for-genomics-training/HEAD/data/SNP/SNPintron_alt_201b.fasta.gz -------------------------------------------------------------------------------- /data/SNP/SNPintron_ref_201b.fasta.gz: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/raphaelmourad/LLM-for-genomics-training/HEAD/data/SNP/SNPintron_ref_201b.fasta.gz -------------------------------------------------------------------------------- /data/genome_sequences/hg38/sequences_hg38_200b_verysmall.csv.gz: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/raphaelmourad/LLM-for-genomics-training/HEAD/data/genome_sequences/hg38/sequences_hg38_200b_verysmall.csv.gz -------------------------------------------------------------------------------- /data/models/Mistral-Codon-v1-1M-finetuned-mRFP/config.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/raphaelmourad/LLM-for-genomics-training/HEAD/data/models/Mistral-Codon-v1-1M-finetuned-mRFP/config.json -------------------------------------------------------------------------------- /data/models/Mistral-Codon-v1-1M-finetuned-mRFP/model.safetensors: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/raphaelmourad/LLM-for-genomics-training/HEAD/data/models/Mistral-Codon-v1-1M-finetuned-mRFP/model.safetensors -------------------------------------------------------------------------------- /data/models/Mistral-Codon-v1-1M-finetuned-mRFP/rng_state.pth: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/raphaelmourad/LLM-for-genomics-training/HEAD/data/models/Mistral-Codon-v1-1M-finetuned-mRFP/rng_state.pth -------------------------------------------------------------------------------- /data/models/Mistral-Codon-v1-1M-finetuned-mRFP/scheduler.pt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/raphaelmourad/LLM-for-genomics-training/HEAD/data/models/Mistral-Codon-v1-1M-finetuned-mRFP/scheduler.pt -------------------------------------------------------------------------------- /data/models/Mistral-Codon-v1-1M-finetuned-mRFP/special_tokens_map.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/raphaelmourad/LLM-for-genomics-training/HEAD/data/models/Mistral-Codon-v1-1M-finetuned-mRFP/special_tokens_map.json -------------------------------------------------------------------------------- /data/models/Mistral-Codon-v1-1M-finetuned-mRFP/tokenizer.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/raphaelmourad/LLM-for-genomics-training/HEAD/data/models/Mistral-Codon-v1-1M-finetuned-mRFP/tokenizer.json -------------------------------------------------------------------------------- /data/models/Mistral-Codon-v1-1M-finetuned-mRFP/tokenizer_config.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/raphaelmourad/LLM-for-genomics-training/HEAD/data/models/Mistral-Codon-v1-1M-finetuned-mRFP/tokenizer_config.json -------------------------------------------------------------------------------- /data/models/Mistral-Codon-v1-1M-finetuned-mRFP/trainer_state.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/raphaelmourad/LLM-for-genomics-training/HEAD/data/models/Mistral-Codon-v1-1M-finetuned-mRFP/trainer_state.json -------------------------------------------------------------------------------- /data/models/Mistral-Codon-v1-1M-finetuned-mRFP/training_args.bin: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/raphaelmourad/LLM-for-genomics-training/HEAD/data/models/Mistral-Codon-v1-1M-finetuned-mRFP/training_args.bin -------------------------------------------------------------------------------- /data/models/Mistral-DNA-v1-1M-hg38-finetuned-prom/config.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/raphaelmourad/LLM-for-genomics-training/HEAD/data/models/Mistral-DNA-v1-1M-hg38-finetuned-prom/config.json -------------------------------------------------------------------------------- /data/models/Mistral-DNA-v1-1M-hg38-finetuned-prom/model.safetensors: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/raphaelmourad/LLM-for-genomics-training/HEAD/data/models/Mistral-DNA-v1-1M-hg38-finetuned-prom/model.safetensors -------------------------------------------------------------------------------- /data/models/Mistral-DNA-v1-1M-hg38-finetuned-prom/rng_state.pth: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/raphaelmourad/LLM-for-genomics-training/HEAD/data/models/Mistral-DNA-v1-1M-hg38-finetuned-prom/rng_state.pth -------------------------------------------------------------------------------- /data/models/Mistral-DNA-v1-1M-hg38-finetuned-prom/scheduler.pt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/raphaelmourad/LLM-for-genomics-training/HEAD/data/models/Mistral-DNA-v1-1M-hg38-finetuned-prom/scheduler.pt -------------------------------------------------------------------------------- /data/models/Mistral-DNA-v1-1M-hg38-finetuned-prom/tokenizer.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/raphaelmourad/LLM-for-genomics-training/HEAD/data/models/Mistral-DNA-v1-1M-hg38-finetuned-prom/tokenizer.json -------------------------------------------------------------------------------- /data/models/Mistral-DNA-v1-1M-hg38-finetuned-prom/tokenizer_config.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/raphaelmourad/LLM-for-genomics-training/HEAD/data/models/Mistral-DNA-v1-1M-hg38-finetuned-prom/tokenizer_config.json -------------------------------------------------------------------------------- /data/models/Mistral-DNA-v1-1M-hg38-finetuned-prom/trainer_state.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/raphaelmourad/LLM-for-genomics-training/HEAD/data/models/Mistral-DNA-v1-1M-hg38-finetuned-prom/trainer_state.json -------------------------------------------------------------------------------- /data/models/Mistral-DNA-v1-1M-hg38-finetuned-prom/training_args.bin: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/raphaelmourad/LLM-for-genomics-training/HEAD/data/models/Mistral-DNA-v1-1M-hg38-finetuned-prom/training_args.bin -------------------------------------------------------------------------------- /data/models/Mistral-DNA-v1-1M-hg38-finetuned-tf0/config.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/raphaelmourad/LLM-for-genomics-training/HEAD/data/models/Mistral-DNA-v1-1M-hg38-finetuned-tf0/config.json -------------------------------------------------------------------------------- /data/models/Mistral-DNA-v1-1M-hg38-finetuned-tf0/model.safetensors: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/raphaelmourad/LLM-for-genomics-training/HEAD/data/models/Mistral-DNA-v1-1M-hg38-finetuned-tf0/model.safetensors -------------------------------------------------------------------------------- /data/models/Mistral-DNA-v1-1M-hg38-finetuned-tf0/rng_state.pth: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/raphaelmourad/LLM-for-genomics-training/HEAD/data/models/Mistral-DNA-v1-1M-hg38-finetuned-tf0/rng_state.pth -------------------------------------------------------------------------------- /data/models/Mistral-DNA-v1-1M-hg38-finetuned-tf0/scheduler.pt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/raphaelmourad/LLM-for-genomics-training/HEAD/data/models/Mistral-DNA-v1-1M-hg38-finetuned-tf0/scheduler.pt -------------------------------------------------------------------------------- /data/models/Mistral-DNA-v1-1M-hg38-finetuned-tf0/tokenizer.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/raphaelmourad/LLM-for-genomics-training/HEAD/data/models/Mistral-DNA-v1-1M-hg38-finetuned-tf0/tokenizer.json -------------------------------------------------------------------------------- /data/models/Mistral-DNA-v1-1M-hg38-finetuned-tf0/tokenizer_config.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/raphaelmourad/LLM-for-genomics-training/HEAD/data/models/Mistral-DNA-v1-1M-hg38-finetuned-tf0/tokenizer_config.json -------------------------------------------------------------------------------- /data/models/Mistral-DNA-v1-1M-hg38-finetuned-tf0/trainer_state.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/raphaelmourad/LLM-for-genomics-training/HEAD/data/models/Mistral-DNA-v1-1M-hg38-finetuned-tf0/trainer_state.json -------------------------------------------------------------------------------- /data/models/Mistral-DNA-v1-1M-hg38-finetuned-tf0/training_args.bin: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/raphaelmourad/LLM-for-genomics-training/HEAD/data/models/Mistral-DNA-v1-1M-hg38-finetuned-tf0/training_args.bin -------------------------------------------------------------------------------- /data/models/Mistral-DNA-v1-1M-hg38-finetuned-tf1/config.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/raphaelmourad/LLM-for-genomics-training/HEAD/data/models/Mistral-DNA-v1-1M-hg38-finetuned-tf1/config.json -------------------------------------------------------------------------------- /data/models/Mistral-DNA-v1-1M-hg38-finetuned-tf1/model.safetensors: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/raphaelmourad/LLM-for-genomics-training/HEAD/data/models/Mistral-DNA-v1-1M-hg38-finetuned-tf1/model.safetensors -------------------------------------------------------------------------------- /data/models/Mistral-DNA-v1-1M-hg38-finetuned-tf1/rng_state.pth: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/raphaelmourad/LLM-for-genomics-training/HEAD/data/models/Mistral-DNA-v1-1M-hg38-finetuned-tf1/rng_state.pth -------------------------------------------------------------------------------- /data/models/Mistral-DNA-v1-1M-hg38-finetuned-tf1/scheduler.pt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/raphaelmourad/LLM-for-genomics-training/HEAD/data/models/Mistral-DNA-v1-1M-hg38-finetuned-tf1/scheduler.pt -------------------------------------------------------------------------------- /data/models/Mistral-DNA-v1-1M-hg38-finetuned-tf1/tokenizer.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/raphaelmourad/LLM-for-genomics-training/HEAD/data/models/Mistral-DNA-v1-1M-hg38-finetuned-tf1/tokenizer.json -------------------------------------------------------------------------------- /data/models/Mistral-DNA-v1-1M-hg38-finetuned-tf1/tokenizer_config.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/raphaelmourad/LLM-for-genomics-training/HEAD/data/models/Mistral-DNA-v1-1M-hg38-finetuned-tf1/tokenizer_config.json -------------------------------------------------------------------------------- /data/models/Mistral-DNA-v1-1M-hg38-finetuned-tf1/trainer_state.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/raphaelmourad/LLM-for-genomics-training/HEAD/data/models/Mistral-DNA-v1-1M-hg38-finetuned-tf1/trainer_state.json -------------------------------------------------------------------------------- /data/models/Mistral-DNA-v1-1M-hg38-finetuned-tf1/training_args.bin: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/raphaelmourad/LLM-for-genomics-training/HEAD/data/models/Mistral-DNA-v1-1M-hg38-finetuned-tf1/training_args.bin -------------------------------------------------------------------------------- /data/models/Mixtral-8x7B-v0.1/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/raphaelmourad/LLM-for-genomics-training/HEAD/data/models/Mixtral-8x7B-v0.1/README.md -------------------------------------------------------------------------------- /data/models/Mixtral-8x7B-v0.1/config.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/raphaelmourad/LLM-for-genomics-training/HEAD/data/models/Mixtral-8x7B-v0.1/config.json -------------------------------------------------------------------------------- /data/models/Mixtral-8x7B-v0.1/config_original.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/raphaelmourad/LLM-for-genomics-training/HEAD/data/models/Mixtral-8x7B-v0.1/config_original.json -------------------------------------------------------------------------------- /data/models/Mixtral-8x7B-v0.1/generation_config.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/raphaelmourad/LLM-for-genomics-training/HEAD/data/models/Mixtral-8x7B-v0.1/generation_config.json -------------------------------------------------------------------------------- /data/models/Mixtral-8x7B-v0.1/model.safetensors.index.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/raphaelmourad/LLM-for-genomics-training/HEAD/data/models/Mixtral-8x7B-v0.1/model.safetensors.index.json -------------------------------------------------------------------------------- /data/models/Mixtral-8x7B-v0.1/special_tokens_map.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/raphaelmourad/LLM-for-genomics-training/HEAD/data/models/Mixtral-8x7B-v0.1/special_tokens_map.json -------------------------------------------------------------------------------- /data/models/Mixtral-8x7B-v0.1/tokenizer.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/raphaelmourad/LLM-for-genomics-training/HEAD/data/models/Mixtral-8x7B-v0.1/tokenizer.json -------------------------------------------------------------------------------- /data/models/Mixtral-8x7B-v0.1/tokenizer_config.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/raphaelmourad/LLM-for-genomics-training/HEAD/data/models/Mixtral-8x7B-v0.1/tokenizer_config.json -------------------------------------------------------------------------------- /dna_seq_200b.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/raphaelmourad/LLM-for-genomics-training/HEAD/dna_seq_200b.png -------------------------------------------------------------------------------- /illustration.odg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/raphaelmourad/LLM-for-genomics-training/HEAD/illustration.odg -------------------------------------------------------------------------------- /illustration.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/raphaelmourad/LLM-for-genomics-training/HEAD/illustration.png --------------------------------------------------------------------------------