[WIP] Upload folder using huggingface_hub (multi-commit 060de48e91a3cb5255e66404ec7c1e3fae97e7b5496b82d24f9500a2953d9279)

README.md

@@ -1,80 +0,0 @@
----
-base_model: meta-llama/Llama-2-7b-hf
-library_name: peft
----
-
-# Reproduced RepLLaMA
-
-This is a reproduced version of the RepLLaMA model.  See [this thread](https://github.com/texttron/tevatron/issues/129) for details of the reproduction process, which changed from their original version.
-
-# Other Links
-| Binary | Description |
-|:-------|:------------|
-| [samaya-ai/promptriever-llama2-7b-v1](https://huggingface.co/samaya-ai/promptriever-llama2-7b-v1) | A Promptriever bi-encoder model based on LLaMA 2 (7B parameters).|
-| [samaya-ai/promptriever-llama3.1-8b-instruct-v1](https://huggingface.co/samaya-ai/promptriever-llama3.1-8b-instruct-v1) | A Promptriever bi-encoder model based on LLaMA 3.1 Instruct (8B parameters).|
-| [samaya-ai/promptriever-llama3.1-8b-v1](https://huggingface.co/samaya-ai/promptriever-llama3.1-8b-v1) | A Promptriever bi-encoder model based on LLaMA 3.1 (8B parameters).|
-| [samaya-ai/promptriever-mistral-v0.1-7b-v1](https://huggingface.co/samaya-ai/promptriever-mistral-v0.1-7b-v1) | A Promptriever bi-encoder model based on Mistral v0.1 (7B parameters). |
-| [samaya-ai/RepLLaMA-reproduced](https://huggingface.co/samaya-ai/RepLLaMA-reproduced) | A reproduction of the RepLLaMA model (no instructions). A bi-encoder based on LLaMA 2, trained on the [tevatron/msmarco-passage-aug](https://huggingface.co/datasets/Tevatron/msmarco-passage-aug) dataset. |
-| [samaya-ai/msmarco-w-instructions](https://huggingface.co/samaya-ai/msmarco-w-instructions) | A dataset of MS MARCO with added instructions and instruction-negatives, used for training the above models. |
-
-
-# Usage
-
-You can use this with the RepLLaMA example code in [tevatron](https://github.com/texttron/tevatron) or with mteb:
-
-```python
-import mteb
-model = mteb.get_model("samaya-ai/RepLLaMA-reproduced")
-tasks = mteb.get_tasks(tasks=["NFCorpus"], languages=["eng"])
-evaluation = mteb.MTEB(tasks=tasks)
-evaluation.run(model, batch_size=16)
-```
-
-The command used to create this reproduction was the Tevatron codebase (commit 9bb8381) with command:
-
-```
-#!/bin/bash
-deepspeed --include localhost:0,1,2,3 --master_port 60000 --module tevatron.retriever.driver.train \
-  --deepspeed deepspeed/ds_zero3_config.json \
-  --output_dir retriever-llama2-4gpu \
-  --model_name_or_path meta-llama/Llama-2-7b-hf \
-  --lora \
-  --lora_r 32 \
-  --lora_target_modules q_proj,k_proj,v_proj,o_proj,down_proj,up_proj,gate_proj \
-  --save_steps 200 \
-  --dataset_name Tevatron/msmarco-passage-aug \
-  --query_prefix "query: " \
-  --passage_prefix "passage: " \
-  --bf16 \
-  --pooling eos \
-  --append_eos_token \
-  --normalize \
-  --temperature 0.01 \
-  --per_device_train_batch_size 8 \
-  --gradient_checkpointing \
-  --train_group_size 16 \
-  --learning_rate 1e-4 \
-  --query_max_len 32 \
-  --passage_max_len 196 \
-  --num_train_epochs 1 \
-  --logging_steps 10 \
-  --overwrite_output_dir \
-  --warmup_steps 100 \
-  --gradient_accumulation_steps 4
-```
-
-
-# Citation
-For citation, please also see the [original RepLLaMA paper](https://arxiv.org/abs/2310.08319) and feel free to cite Promptriever as well:
-
-```bibtex
-@article{weller2024promptriever,
-      title={Promptriever: Instruction-Trained Retrievers Can Be Prompted Like Language Models}, 
-      author={Orion Weller and Benjamin Van Durme and Dawn Lawrie and Ashwin Paranjape and Yuhao Zhang and Jack Hessel},
-      year={2024},
-      eprint={2409.11136},
-      archivePrefix={arXiv},
-      primaryClass={cs.IR},
-      url={https://arxiv.org/abs/2409.11136}, 
-}
-```

adapter_config.json

@@ -1,34 +0,0 @@
-{
-  "alpha_pattern": {},
-  "auto_mapping": null,
-  "base_model_name_or_path": "meta-llama/Llama-2-7b-hf",
-  "bias": "none",
-  "fan_in_fan_out": false,
-  "inference_mode": true,
-  "init_lora_weights": true,
-  "layer_replication": null,
-  "layers_pattern": null,
-  "layers_to_transform": null,
-  "loftq_config": {},
-  "lora_alpha": 64,
-  "lora_dropout": 0.1,
-  "megatron_config": null,
-  "megatron_core": "megatron.core",
-  "modules_to_save": null,
-  "peft_type": "LORA",
-  "r": 32,
-  "rank_pattern": {},
-  "revision": null,
-  "target_modules": [
-    "v_proj",
-    "up_proj",
-    "down_proj",
-    "o_proj",
-    "q_proj",
-    "gate_proj",
-    "k_proj"
-  ],
-  "task_type": "FEATURE_EXTRACTION",
-  "use_dora": false,
-  "use_rslora": false
-}

adapter_model.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:427e98cbebcc7c87284cd361c7f3573515d5f8d070019f9ef52a1209dec2e7c6
-size 159965640

special_tokens_map.json

@@ -1,24 +0,0 @@
-{
-  "bos_token": {
-    "content": "<s>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "eos_token": {
-    "content": "</s>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "pad_token": "</s>",
-  "unk_token": {
-    "content": "<unk>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  }
-}

tokenizer.model

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
-size 499723

tokenizer_config.json

@@ -1,42 +0,0 @@
-{
-  "add_bos_token": true,
-  "add_eos_token": false,
-  "add_prefix_space": null,
-  "added_tokens_decoder": {
-    "0": {
-      "content": "<unk>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "1": {
-      "content": "<s>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "2": {
-      "content": "</s>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    }
-  },
-  "bos_token": "<s>",
-  "clean_up_tokenization_spaces": false,
-  "eos_token": "</s>",
-  "legacy": false,
-  "model_max_length": 1000000000000000019884624838656,
-  "pad_token": "</s>",
-  "padding_side": "right",
-  "sp_model_kwargs": {},
-  "tokenizer_class": "LlamaTokenizer",
-  "unk_token": "<unk>",
-  "use_default_system_prompt": false
-}

training_args.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:bbfc3e46a521a56d396f4b7986a8974b72cfad3e69454bf7377bd9cfdb699663
-size 7736