Upload model

config.json

@@ -0,0 +1,290 @@
+{
+  "architectures": [
+    "RetrievalLlamaEncDecModel"
+  ],
+  "decoder": {
+    "_name_or_path": "meta-llama/Llama-2-13b-hf",
+    "add_cross_attention": false,
+    "architectures": [
+      "LlamaForCausalLM"
+    ],
+    "attention_bias": false,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": 1,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": 2,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_act": "silu",
+    "hidden_size": 5120,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_range": 0.02,
+    "intermediate_size": 13824,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "length_penalty": 1.0,
+    "lora_alpha": 16,
+    "lora_rank": 64,
+    "max_doc_len": 512,
+    "max_length": 20,
+    "max_position_embeddings": 4096,
+    "min_length": 0,
+    "model_type": "retrievalllama",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 40,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_hidden_layers": 40,
+    "num_key_value_heads": 40,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": null,
+    "prefix": null,
+    "pretraining_tp": 1,
+    "problem_type": null,
+    "pruned_heads": {},
+    "quantization_config": {
+      "bnb_4bit_compute_dtype": "float32",
+      "bnb_4bit_quant_type": "nf4",
+      "bnb_4bit_use_double_quant": true,
+      "llm_int8_enable_fp32_cpu_offload": false,
+      "llm_int8_has_fp16_weight": false,
+      "llm_int8_skip_modules": null,
+      "llm_int8_threshold": 6.0,
+      "load_in_4bit": true,
+      "load_in_8bit": false,
+      "quant_method": "bitsandbytes"
+    },
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "rms_norm_eps": 1e-05,
+    "rope_scaling": null,
+    "rope_theta": 10000.0,
+    "sep_token_id": null,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": false,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": "float16",
+    "torchscript": false,
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "use_cache": true,
+    "vocab_size": 32000
+  },
+  "encoder": {
+    "_name_or_path": "",
+    "add_cross_attention": false,
+    "architectures": null,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bert_config": {
+      "_name_or_path": "",
+      "add_cross_attention": false,
+      "architectures": null,
+      "attention_probs_dropout_prob": 0.1,
+      "bad_words_ids": null,
+      "begin_suppress_tokens": null,
+      "bos_token_id": null,
+      "chunk_size_feed_forward": 0,
+      "classifier_dropout": null,
+      "cross_attention_hidden_size": null,
+      "decoder_start_token_id": null,
+      "diversity_penalty": 0.0,
+      "do_sample": false,
+      "early_stopping": false,
+      "encoder_no_repeat_ngram_size": 0,
+      "eos_token_id": null,
+      "exponential_decay_length_penalty": null,
+      "finetuning_task": null,
+      "forced_bos_token_id": null,
+      "forced_eos_token_id": null,
+      "gradient_checkpointing": false,
+      "hidden_act": "gelu",
+      "hidden_dropout_prob": 0.1,
+      "hidden_size": 768,
+      "id2label": {
+        "0": "LABEL_0",
+        "1": "LABEL_1"
+      },
+      "intermediate_size": 3072,
+      "is_decoder": false,
+      "is_encoder_decoder": false,
+      "label2id": {
+        "LABEL_0": 0,
+        "LABEL_1": 1
+      },
+      "layer_norm_eps": 1e-12,
+      "length_penalty": 1.0,
+      "max_length": 20,
+      "max_position_embeddings": 512,
+      "min_length": 0,
+      "model_type": "retrievalllama",
+      "no_repeat_ngram_size": 0,
+      "num_attention_heads": 12,
+      "num_beam_groups": 1,
+      "num_beams": 1,
+      "num_hidden_layers": 12,
+      "num_return_sequences": 1,
+      "output_attentions": false,
+      "output_hidden_states": false,
+      "output_scores": false,
+      "pad_token_id": null,
+      "position_embedding_type": "absolute",
+      "prefix": null,
+      "problem_type": null,
+      "pruned_heads": {},
+      "remove_invalid_values": false,
+      "repetition_penalty": 1.0,
+      "return_dict": true,
+      "return_dict_in_generate": false,
+      "sep_token_id": null,
+      "suppress_tokens": null,
+      "task_specific_params": null,
+      "temperature": 1.0,
+      "tf_legacy_loss": false,
+      "tie_encoder_decoder": false,
+      "tie_word_embeddings": true,
+      "tokenizer_class": null,
+      "top_k": 50,
+      "top_p": 1.0,
+      "torch_dtype": null,
+      "torchscript": false,
+      "type_vocab_size": 2,
+      "typical_p": 1.0,
+      "use_bfloat16": false,
+      "use_cache": true,
+      "vocab_size": 32004
+    },
+    "bos_token_id": null,
+    "chunk_size_feed_forward": 0,
+    "colbert_accumsteps": 1,
+    "colbert_amp": true,
+    "colbert_attend_to_mask_tokens": false,
+    "colbert_bsize": 8,
+    "colbert_centroid_score_thresh": null,
+    "colbert_checkpoint": "bert-base-uncased",
+    "colbert_collection": "../data/docs/qa_collection.tsv",
+    "colbert_dim": 128,
+    "colbert_distillation_alpha": 1.0,
+    "colbert_doc_maxlen": 220,
+    "colbert_doc_token": "[D]",
+    "colbert_experiment": "legal_qa_new_equaldist",
+    "colbert_ignore_scores": false,
+    "colbert_index_name": null,
+    "colbert_index_path": null,
+    "colbert_index_root": null,
+    "colbert_interaction": "colbert",
+    "colbert_kmeans_niters": 4,
+    "colbert_lr": 3e-06,
+    "colbert_mask_punctuation": true,
+    "colbert_maxsteps": 500000,
+    "colbert_model_name": null,
+    "colbert_name": "2023-08/03/17.08.17",
+    "colbert_nbits": 1,
+    "colbert_ncells": null,
+    "colbert_ndocs": null,
+    "colbert_nranks": 4,
+    "colbert_nway": 2,
+    "colbert_overwrite": false,
+    "colbert_queries": "../data/docs/qa_queries.tsv",
+    "colbert_query_maxlen": 32,
+    "colbert_query_token": "[Q]",
+    "colbert_rank": 0,
+    "colbert_relu": false,
+    "colbert_reranker": false,
+    "colbert_root": "/home/daniel/retrieval_gpark/ColBERT/experiments",
+    "colbert_save_every": 1000,
+    "colbert_similarity": "cosine",
+    "colbert_triples": "../data/docs/qa_triples.tsv",
+    "colbert_use_ib_negatives": false,
+    "colbert_warmup": null,
+    "colbert_warmup_bert": null,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": null,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "indexer_index_path": "./../../../../../retrieval_gpark/retrieval_data/legal_colbert_llamatok_ckpt/indexes/wiki_docs_all",
+    "initializer_range": 0.02,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "min_length": 0,
+    "model_type": "retrievalllama",
+    "no_repeat_ngram_size": 0,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": null,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "retrieval_file_name": "./../../../../../retrieval_gpark/retrieval_data/tokenized_wiki_docs_all_collection.tsv",
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": null,
+    "torchscript": false,
+    "typical_p": 1.0,
+    "use_bfloat16": false
+  },
+  "is_encoder_decoder": true,
+  "model_type": "retrievalllama",
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.0.dev0"
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.35.0.dev0"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa3e12c8d7f36b1e1a5d300d1bff5a5e5378befb84cd7bd6f509d8bc9f0be6af
+size 9100935505