TaskArithmetic___Code-Math___AIM / README.md

nielsr HF Staff

Add library_name, Github link

eae2a1f verified 11 months ago

preview code

raw

history blame

17.5 kB

metadata

license: llama2
base_model:
  - unsloth/llama-2-13b
  - layoric/llama-2-13b-code-alpaca
  - vanillaOVO/WizardMath-13B-V1.0
library_name: transformers
tags:
  - merge

license: llama2 base_model: - unsloth/llama-2-13b - layoric/llama-2-13b-code-alpaca - vanillaOVO/WizardMath-13B-V1.0 tags: - merge library_name: transformers

AIM Paper Checkpoints Uploaded For Replication

This repository includes one of the checkpoints used in the paper "Activation-Informed Merging of Large Language Models" at Hugging Face. Specifics of this model are as follows:

Merging Method: task_arithmetic
Models Used In Merging
- Base Model: unsloth/llama-2-13b
- Code: layoric/llama-2-13b-code-alpaca
- Math: vanillaOVO/WizardMath-13B-V1.0
AIM: True

Benchmark results and paper details can be found at the official GitHub.

File information

The repository contains the following file information:

Filename: tokenizer_config.json Content: { "add_bos_token": true, "add_eos_token": false, "add_prefix_space": null, "added_tokens_decoder": { "0": { "content": "", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "1": { "content": "~~", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "2": { "content": "~~", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true } }, "bos_token": "~~", "clean_up_tokenization_spaces": false, "eos_token": "~~", "extra_special_tokens": {}, "legacy": false, "model_max_length": 1000000000000000019884624838656, "pad_token": "", "padding_side": "left", "sp_model_kwargs": {}, "tokenizer_class": "LlamaTokenizer", "unk_token": "", "use_default_system_prompt": false }

Filename: special_tokens_map.json Content: { "bos_token": { "content": "~~", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false }, "eos_token": { "content": "~~", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false }, "pad_token": { "content": "", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false }, "unk_token": { "content": "", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false } }

Filename: config.json Content: { "_name_or_path": "./FinalSet/AWR_04_task_arithmetic_Math-Code", "architectures": [ "LlamaForCausalLM" ], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 1, "eos_token_id": 2, "head_dim": 128, "hidden_act": "silu", "hidden_size": 5120, "initializer_range": 0.02, "intermediate_size": 13824, "max_position_embeddings": 4096, "mlp_bias": false, "model_type": "llama", "num_attention_heads": 40, "num_hidden_layers": 40, "num_key_value_heads": 40, "pad_token_id": 0, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_scaling": null, "rope_theta": 10000.0, "tie_word_embeddings": false, "torch_dtype": "float16", "transformers_version": "4.48.0", "unsloth_version": "2024.9", "use_cache": true, "vocab_size": 32000 }

Filename: tokenizer.json Content: "Content of the file is larger than 50 KB, too long to display."

Filename: generation_config.json Content: { "_from_model_config": true, "bos_token_id": 1, "eos_token_id": 2, "pad_token_id": 0, "transformers_version": "4.48.0" }

Filename: tokenizer.model Content: "Content of the file is larger than 50 KB, too long to display."

Filename: model.safetensors.index.json Content: { "metadata": { "total_size": 26031728640 }, "weight_map": { "lm_head.weight": "model-00006-of-00006.safetensors", "model.embed_tokens.weight": "model-00001-of-00006.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00006.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00006.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00006.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00001-of-00006.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00006.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00001-of-00006.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", "model.layers.10.input_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00002-of-00006.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00006.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00006.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", "model.layers.11.input_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00002-of-00006.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00006.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00002-of-00006.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", "model.layers.12.input_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00002-of-00006.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00006.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00002-of-00006.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", "model.layers.13.input_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00002-of-00006.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00006.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00002-of-00006.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", "model.layers.14.input_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00002-of-00006.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00006.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00002-of-00006.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", "model.layers.15.input_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00003-of-00006.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00006.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00003-of-00006.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", "model.layers.16.input_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00003-of-00006.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00006.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00003-of-00006.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", "model.layers.17.input_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00003-of-00006.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00006.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00003-of-00006.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", "model.layers.18.input_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00003-of-00006.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00006.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00003-of-00006.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", "model.layers.19.input_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00003-of-00006.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00006.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00003-of-00006.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00001-of-00006.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00006.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00001-of-00006.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", "model.layers.20.input_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00004-of-00006.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00006.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00004-of-00006.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", "model.layers.21.input_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00004-of-00006.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00004-of-00006.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00004-of-00006.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", "model.layers.22.input_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00004-of-00006.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00004-of-00006.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00004-of-00006.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", "model.layers.23.input_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00004-of-00006.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00004-of-00006.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00004-of-00006.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", "model.layers.24.input_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00004-of-00006.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00004-of-00006.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00004-of-00006.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", "model.layers.25.input_layernorm.weight": "model-00004-of