commit 3d89ff2f8ad3dacf0d731ecb2401b0c44e87fc21 Author: ModelHub XC Date: Sat May 9 06:44:47 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: Cognitive-Lab/Ambari-7B-base-v0.1 Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..a6344aa --- /dev/null +++ b/.gitattributes @@ -0,0 +1,35 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..54baebf --- /dev/null +++ b/README.md @@ -0,0 +1,43 @@ +--- +license: mit +language: +- en +- kn +metrics: +- accuracy +pipeline_tag: text-generation +tags: +- bilingual +- kannada +- english +--- + +# Ambari-7B-Base-v0.1 + +## Overview + +Ambari-7B-Base-v0.1 is the first bilingual English/Kannada model in the Ambari series, developed and released by [Cognitivelab.in](https://www.cognitivelab.in/). Based on the Llama2 model by Meta, this 7B parameter model is the outcome of the pretraining stage, involving training on approximately 500 million new Kannada tokens. + +## Usage + +To use the Ambari-7B-Base-v0.1 model, you can follow the example code below: + +```python +# Usage +import torch +from transformers import LlamaTokenizer, LlamaForCausalLM + +model = LlamaForCausalLM.from_pretrained('Cognitive-Lab/Ambari-7B-Base-v0.1') +tokenizer = LlamaTokenizer.from_pretrained('Cognitive-Lab/Ambari-7B-Base-v0.1') + +prompt = "ಕನ್ನಡದ ಇತಿಹಾಸವನ್ನು ವಿವರವಾಗಿ ತಿಳಿಸಿ" +inputs = tokenizer(prompt, return_tensors="pt") + +# Generate +generate_ids = model.generate(inputs.input_ids, max_length=30) +decoded_output = tokenizer.batch_decode(generate_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False)[0] + +print(decoded_output) +``` + +**Important:** The provided model serves as a foundation and is not designed for independent use. We strongly advise conducting finetuning tailored to your particular task(s) of interest before deploying it in a production environment. Feel free to customize the code according to your specific use case, ensuring that the model undergoes finetuning for optimal performance in your desired application. \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..96e110c --- /dev/null +++ b/config.json @@ -0,0 +1,28 @@ +{ + "_name_or_path": "./Ambari-7B-base-v0.1/", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 1, + "eos_token_id": 2, + "hidden_act": "silu", + "hidden_size": 4096, + "initializer_range": 0.02, + "intermediate_size": 11008, + "max_position_embeddings": 4096, + "model_type": "llama", + "num_attention_heads": 32, + "num_hidden_layers": 32, + "num_key_value_heads": 32, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": null, + "rope_theta": 10000.0, + "tie_word_embeddings": false, + "torch_dtype": "float32", + "transformers_version": "4.36.2", + "use_cache": false, + "vocab_size": 49600 +} diff --git a/pytorch_model.bin b/pytorch_model.bin new file mode 100644 index 0000000..42ba5ff --- /dev/null +++ b/pytorch_model.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d07078886f230b335fe929eb9033a4ea622b75c5d01eac5b5f0f296dc919127d +size 13765229861 diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..72ecfee --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,24 @@ +{ + "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": "", + "unk_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/tokenizer.model b/tokenizer.model new file mode 100644 index 0000000..de03993 --- /dev/null +++ b/tokenizer.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:02d76a45ce0673e2b1dac635c2b4315ba6e9a778af1a9eab7bf666dbdf1f043b +size 994743 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..6ed45a3 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,43 @@ +{ + "add_bos_token": true, + "add_eos_token": false, + "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": "", + "legacy": true, + "model_max_length": 1000000000000000019884624838656, + "pad_token": "", + "sp_model_kwargs": {}, + "spaces_between_special_tokens": false, + "tokenizer_class": "LlamaTokenizer", + "trust_remote_code": false, + "unk_token": "", + "use_default_system_prompt": false, + "use_fast": true +}