commit 74eab3be3e18759753e1c61b2fbc968a6aeee17b Author: ModelHub XC Date: Mon Aug 24 11:05:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: wandgibaut/periquito-3B 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..18d3c3c --- /dev/null +++ b/README.md @@ -0,0 +1,374 @@ +--- +language: +- pt +license: apache-2.0 +library_name: transformers +datasets: +- wikimedia/wikipedia +metrics: +- accuracy +model-index: +- name: periquito-3B + results: + - task: + type: text-generation + name: Text Generation + dataset: + name: ENEM Challenge (No Images) + type: eduagarcia/enem_challenge + split: train + args: + num_few_shot: 3 + metrics: + - type: acc + value: 17.98 + name: accuracy + source: + url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=wandgibaut/periquito-3B + name: Open Portuguese LLM Leaderboard + - task: + type: text-generation + name: Text Generation + dataset: + name: BLUEX (No Images) + type: eduagarcia-temp/BLUEX_without_images + split: train + args: + num_few_shot: 3 + metrics: + - type: acc + value: 21.14 + name: accuracy + source: + url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=wandgibaut/periquito-3B + name: Open Portuguese LLM Leaderboard + - task: + type: text-generation + name: Text Generation + dataset: + name: OAB Exams + type: eduagarcia/oab_exams + split: train + args: + num_few_shot: 3 + metrics: + - type: acc + value: 22.69 + name: accuracy + source: + url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=wandgibaut/periquito-3B + name: Open Portuguese LLM Leaderboard + - task: + type: text-generation + name: Text Generation + dataset: + name: Assin2 RTE + type: assin2 + split: test + args: + num_few_shot: 15 + metrics: + - type: f1_macro + value: 43.01 + name: f1-macro + source: + url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=wandgibaut/periquito-3B + name: Open Portuguese LLM Leaderboard + - task: + type: text-generation + name: Text Generation + dataset: + name: Assin2 STS + type: eduagarcia/portuguese_benchmark + split: test + args: + num_few_shot: 15 + metrics: + - type: pearson + value: 8.92 + name: pearson + source: + url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=wandgibaut/periquito-3B + name: Open Portuguese LLM Leaderboard + - task: + type: text-generation + name: Text Generation + dataset: + name: FaQuAD NLI + type: ruanchaves/faquad-nli + split: test + args: + num_few_shot: 15 + metrics: + - type: f1_macro + value: 43.97 + name: f1-macro + source: + url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=wandgibaut/periquito-3B + name: Open Portuguese LLM Leaderboard + - task: + type: text-generation + name: Text Generation + dataset: + name: HateBR Binary + type: ruanchaves/hatebr + split: test + args: + num_few_shot: 25 + metrics: + - type: f1_macro + value: 50.46 + name: f1-macro + source: + url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=wandgibaut/periquito-3B + name: Open Portuguese LLM Leaderboard + - task: + type: text-generation + name: Text Generation + dataset: + name: PT Hate Speech Binary + type: hate_speech_portuguese + split: test + args: + num_few_shot: 25 + metrics: + - type: f1_macro + value: 41.19 + name: f1-macro + source: + url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=wandgibaut/periquito-3B + name: Open Portuguese LLM Leaderboard + - task: + type: text-generation + name: Text Generation + dataset: + name: tweetSentBR + type: eduagarcia-temp/tweetsentbr + split: test + args: + num_few_shot: 25 + metrics: + - type: f1_macro + value: 47.96 + name: f1-macro + source: + url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=wandgibaut/periquito-3B + name: Open Portuguese LLM Leaderboard +--- +# Model Card for Model ID + + +![periquito](periquito.webp "periquito") + +## Model Details + +### Model Description + + Periquito-3B is a large language model (LLM) trained by Wandgibaut. It is built upon the OpenLlama-3B architecture and specifically fine-tuned using Portuguese Wikipedia (pt-br) data. This specialization makes it particularly adept at understanding and generating text in Brazilian Portuguese. + +- **Developed by:** Wandemberg Gibaut +- **Model type:** Llama +- **Language(s) (NLP):** Portuguese +- **License:** Apache License 2.0 +- **Finetuned from model [optional]:** openlm-research/open_llama_3b + + +### Loading the Weights with Hugging Face Transformers + +```python +import torch +from transformers import LlamaTokenizer, LlamaForCausalLM +model_path = 'wandgibaut/periquito-3B' +tokenizer = LlamaTokenizer.from_pretrained(model_path) +model = LlamaForCausalLM.from_pretrained( + model_path, torch_dtype=torch.float16, device_map='auto', +) +prompt = 'Q: Qual o maior animal terrestre?\nA:' +input_ids = tokenizer(prompt, return_tensors="pt").input_ids +generation_output = model.generate( + input_ids=input_ids, max_new_tokens=32 +) +print(tokenizer.decode(generation_output[0])) +``` + +For more advanced usage, please follow the [transformers LLaMA documentation](https://huggingface.co/docs/transformers/main/model_doc/llama). + +### Evaluating with LM-Eval-Harness +The model can be evaluated with [lm-eval-harness](https://github.com/EleutherAI/lm-evaluation-harness). However, we used a custom version, that has some translated tasks and the ENEM suit. This can be found in [wandgibaut/lm-evaluation-harness-PTBR](https://github.com/wandgibaut/lm-evaluation-harness-PTBR). + + + +## Dataset and Training + +We finetunned the model on Wikipedia-pt dataset with LoRA, in Google's TPU-v3 in the [Google's TPU Research program](https://sites.research.google/trc/about/). + + +## Evaluation +We evaluated OpenLLaMA on a wide range of tasks using [lm-evaluation-harness](https://github.com/EleutherAI/lm-evaluation-harness). The LLaMA results are generated by running the original LLaMA model on the same evaluation metrics. We note that our results for the LLaMA model differ slightly from the original LLaMA paper, which we believe is a result of different evaluation protocols. Similar differences have been reported in [this issue of lm-evaluation-harness](https://github.com/EleutherAI/lm-evaluation-harness/issues/443). Additionally, we present the results of GPT-J, a 6B parameter model trained on the [Pile](https://pile.eleuther.ai/) dataset by [EleutherAI](https://www.eleuther.ai/). + +hf-causal (pretrained=wandgibaut/periquito-3B), limit: None, provide_description: False, num_fewshot: 0, batch_size: None + +| Task |Version| Metric | Value | |Stderr| +|---------|------:|------------|------:|---|-----:| +|agnews_pt| 0|acc | 0.6184|± |0.0056| +|boolq_pt | 1|acc | 0.6333|± |0.0084| +|faquad | 1|exact | 7.9365| | | +| | |f1 |45.6971| | | +| | |HasAns_exact| 7.9365| | | +| | |HasAns_f1 |45.6971| | | +| | |NoAns_exact | 0.0000| | | +| | |NoAns_f1 | 0.0000| | | +| | |best_exact | 7.9365| | | +| | |best_f1 |45.6971| | | +|imdb_pt | 0|acc | 0.6338|± |0.0068| +|sst2_pt | 1|acc | 0.6823|± |0.0158| +|toldbr | 0|acc | 0.4629|± |0.0109| +| | |f1_macro | 0.3164| | | + + +hf-causal (pretrained=wandgibaut/periquito-3B,dtype=float), limit: None, provide_description: False, num_fewshot: 3, batch_size: None + +| Task |Version| Metric | Value | |Stderr| +|---------|------:|------------|------:|---|-----:| +|agnews_pt| 0|acc | 0.6242|± |0.0056| +|boolq_pt | 1|acc | 0.6477|± |0.0084| +|faquad | 1|exact |34.9206| | | +| | |f1 |70.3968| | | +| | |HasAns_exact|34.9206| | | +| | |HasAns_f1 |70.3968| | | +| | |NoAns_exact | 0.0000| | | +| | |NoAns_f1 | 0.0000| | | +| | |best_exact |34.9206| | | +| | |best_f1 |70.3968| | | +|imdb_pt | 0|acc | 0.8408|± |0.0052| +|sst2_pt | 1|acc | 0.7775|± |0.0141| +|toldbr | 0|acc | 0.5143|± |0.0109| +| | |f1_macro | 0.5127| | | + + +hf-causal (pretrained=wandgibaut/periquito-3B), limit: None, provide_description: False, num_fewshot: 0, batch_size: None + +| Task |Version| Metric |Value | |Stderr| +|-------------|------:|----------------|-----:|---|-----:| +|enem | 0|acc |0.1976|± |0.0132| +| | |2009 |0.2022|± |0.0428| +| | |2016 |0.1809|± |0.0399| +| | |2015 |0.1348|± |0.0364| +| | |2016_2_ |0.2366|± |0.0443| +| | |2017 |0.2022|± |0.0428| +| | |2013 |0.1647|± |0.0405| +| | |2012 |0.2174|± |0.0432| +| | |2011 |0.2292|± |0.0431| +| | |2010 |0.2157|± |0.0409| +| | |2014 |0.1839|± |0.0418| +|enem_2022 | 0|acc |0.2373|± |0.0393| +| | |2022 |0.2373|± |0.0393| +| | |human-sciences |0.2703|± |0.0740| +| | |mathematics |0.1818|± |0.0842| +| | |natural-sciences|0.1538|± |0.0722| +| | |languages |0.3030|± |0.0812| +|enem_CoT | 0|acc |0.1812|± |0.0127| +| | |2009 |0.1348|± |0.0364| +| | |2016 |0.1596|± |0.0380| +| | |2015 |0.1124|± |0.0337| +| | |2016_2_ |0.1290|± |0.0350| +| | |2017 |0.2247|± |0.0445| +| | |2013 |0.1765|± |0.0416| +| | |2012 |0.2391|± |0.0447| +| | |2011 |0.1979|± |0.0409| +| | |2010 |0.2451|± |0.0428| +| | |2014 |0.1839|± |0.0418| +|enem_CoT_2022| 0|acc |0.2119|± |0.0378| +| | |2022 |0.2119|± |0.0378| +| | |human-sciences |0.2703|± |0.0740| +| | |mathematics |0.1818|± |0.0842| +| | |natural-sciences|0.2308|± |0.0843| +| | |languages |0.1515|± |0.0634| + +hf-causal (pretrained=wandgibaut/periquito-3B,dtype=float), limit: None, provide_description: False, num_fewshot: 1, batch_size: None + +| Task |Version| Metric |Value | |Stderr| +|-------------|------:|----------------|-----:|---|-----:| +|enem | 0|acc |0.1790|± |0.0127| +| | |2009 |0.1573|± |0.0388| +| | |2016 |0.2021|± |0.0416| +| | |2015 |0.1573|± |0.0388| +| | |2016_2_ |0.1935|± |0.0412| +| | |2017 |0.2247|± |0.0445| +| | |2013 |0.1412|± |0.0380| +| | |2012 |0.1739|± |0.0397| +| | |2011 |0.1979|± |0.0409| +| | |2010 |0.1961|± |0.0395| +| | |2014 |0.1379|± |0.0372| +|enem_2022 | 0|acc |0.1864|± |0.0360| +| | |2022 |0.1864|± |0.0360| +| | |human-sciences |0.2432|± |0.0715| +| | |mathematics |0.1364|± |0.0749| +| | |natural-sciences|0.1154|± |0.0639| +| | |languages |0.2121|± |0.0723| +|enem_CoT | 0|acc |0.2009|± |0.0132| +| | |2009 |0.2135|± |0.0437| +| | |2016 |0.2340|± |0.0439| +| | |2015 |0.1348|± |0.0364| +| | |2016_2_ |0.2258|± |0.0436| +| | |2017 |0.2360|± |0.0453| +| | |2013 |0.1529|± |0.0393| +| | |2012 |0.1957|± |0.0416| +| | |2011 |0.2500|± |0.0444| +| | |2010 |0.1667|± |0.0371| +| | |2014 |0.1954|± |0.0428| +|enem_CoT_2022| 0|acc |0.2542|± |0.0403| +| | |2022 |0.2542|± |0.0403| +| | |human-sciences |0.2703|± |0.0740| +| | |mathematics |0.2273|± |0.0914| +| | |natural-sciences|0.3846|± |0.0973| +| | |languages |0.1515|± |0.0634| + + +## Use Cases: +The model is suitable for text generation, language understanding, and various natural language processing tasks in Brazilian Portuguese. + +## Limitations: +Like many language models, Periquito-3B might exhibit biases present in its training data. Additionally, its performance is primarily optimized for Portuguese, potentially limiting its effectiveness with other languages. + +## Ethical Considerations: +Users are encouraged to use the model ethically, particularly by avoiding the generation of harmful or biased content. + + +## Acknowledgment +We thank the [Google TPU Research Cloud](https://sites.research.google/trc/about/) program for providing part of the computation resources. + + + +## Citation [optional] + +If you found periquito-3B useful in your research or applications, please cite using the following BibTeX: + +**BibTeX:** + +``` +@software{wandgibautperiquito3B, + author = {Gibaut, Wandemberg}, + title = {Periquito-3B}, + month = Sep, + year = 2023, + url = {https://huggingface.co/wandgibaut/periquito-3B} +} +``` + +# [Open Portuguese LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard) +Detailed results can be found [here](https://huggingface.co/datasets/eduagarcia-temp/llm_pt_leaderboard_raw_results/tree/main/wandgibaut/periquito-3B) + +| Metric | Value | +|--------------------------|---------| +|Average |**33.04**| +|ENEM Challenge (No Images)| 17.98| +|BLUEX (No Images) | 21.14| +|OAB Exams | 22.69| +|Assin2 RTE | 43.01| +|Assin2 STS | 8.92| +|FaQuAD NLI | 43.97| +|HateBR Binary | 50.46| +|PT Hate Speech Binary | 41.19| +|tweetSentBR | 47.96| + diff --git a/config.json b/config.json new file mode 100644 index 0000000..d8d1890 --- /dev/null +++ b/config.json @@ -0,0 +1,26 @@ +{ + "_name_or_path": "periquito-3B/", + "architectures": [ + "LlamaForCausalLM" + ], + "bos_token_id": 1, + "eos_token_id": 2, + "hidden_act": "silu", + "hidden_size": 3200, + "initializer_range": 0.02, + "intermediate_size": 8640, + "max_position_embeddings": 2048, + "model_type": "llama", + "num_attention_heads": 32, + "num_hidden_layers": 26, + "num_key_value_heads": 32, + "pad_token_id": 0, + "pretraining_tp": 1, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "tie_word_embeddings": false, + "torch_dtype": "float32", + "transformers_version": "4.31.0", + "use_cache": true, + "vocab_size": 52000 +} diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..de5b5ba --- /dev/null +++ b/generation_config.json @@ -0,0 +1,7 @@ +{ + "_from_model_config": true, + "bos_token_id": 1, + "eos_token_id": 2, + "pad_token_id": 0, + "transformers_version": "4.31.0" +} \ No newline at end of file diff --git a/model-00001-of-00002.safetensors b/model-00001-of-00002.safetensors new file mode 100644 index 0000000..e009db3 --- /dev/null +++ b/model-00001-of-00002.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bbd42383184648ad6b7531796f3dd5782602a3a077a69524d62b547079f27838 +size 9972198224 diff --git a/model-00002-of-00002.safetensors b/model-00002-of-00002.safetensors new file mode 100644 index 0000000..8405fcb --- /dev/null +++ b/model-00002-of-00002.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:793d86d1489cff6f37a8da4be67bfc4105a4e7be52989004ac03ba96eaf0421c +size 4245731632 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000..d023e8c --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,270 @@ +{ + "metadata": { + "total_size": 14217899600 + }, + "weight_map": { + "lm_head.weight": "model-00002-of-00002.safetensors", + "model.embed_tokens.weight": "model-00001-of-00002.safetensors", + "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.rotary_emb.inv_freq": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.rotary_emb.inv_freq": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.rotary_emb.inv_freq": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.rotary_emb.inv_freq": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.rotary_emb.inv_freq": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.rotary_emb.inv_freq": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.rotary_emb.inv_freq": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.rotary_emb.inv_freq": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.rotary_emb.inv_freq": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.rotary_emb.inv_freq": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.18.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.18.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.rotary_emb.inv_freq": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.19.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.19.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.19.self_attn.rotary_emb.inv_freq": "model-00002-of-00002.safetensors", + "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.rotary_emb.inv_freq": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.20.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.20.self_attn.rotary_emb.inv_freq": "model-00002-of-00002.safetensors", + "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.21.self_attn.rotary_emb.inv_freq": "model-00002-of-00002.safetensors", + "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.22.self_attn.rotary_emb.inv_freq": "model-00002-of-00002.safetensors", + "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.23.self_attn.rotary_emb.inv_freq": "model-00002-of-00002.safetensors", + "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.24.self_attn.rotary_emb.inv_freq": "model-00002-of-00002.safetensors", + "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.25.self_attn.rotary_emb.inv_freq": "model-00002-of-00002.safetensors", + "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.rotary_emb.inv_freq": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.rotary_emb.inv_freq": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.rotary_emb.inv_freq": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.rotary_emb.inv_freq": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.rotary_emb.inv_freq": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.rotary_emb.inv_freq": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.rotary_emb.inv_freq": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.norm.weight": "model-00002-of-00002.safetensors" + } +} \ No newline at end of file diff --git a/periquito.webp b/periquito.webp new file mode 100644 index 0000000..6d98295 Binary files /dev/null and b/periquito.webp differ diff --git a/pytorch_model-00001-of-00002.bin b/pytorch_model-00001-of-00002.bin new file mode 100644 index 0000000..ce92208 --- /dev/null +++ b/pytorch_model-00001-of-00002.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8bb33ca605c8e9e087786c5b67b37e36e63da117b2541e6f9ba96109ee89c60d +size 9972241191 diff --git a/pytorch_model-00002-of-00002.bin b/pytorch_model-00002-of-00002.bin new file mode 100644 index 0000000..efd81d3 --- /dev/null +++ b/pytorch_model-00002-of-00002.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:09d7b37ef4e4b6e72807eb3600f98954c7bc23cea9bd793fedfb61e4dcba25c4 +size 4245748053 diff --git a/pytorch_model.bin.index.json b/pytorch_model.bin.index.json new file mode 100644 index 0000000..73453aa --- /dev/null +++ b/pytorch_model.bin.index.json @@ -0,0 +1,270 @@ +{ + "metadata": { + "total_size": 14217899600 + }, + "weight_map": { + "lm_head.weight": "pytorch_model-00002-of-00002.bin", + "model.embed_tokens.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin", + "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin", + "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.10.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.10.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin", + "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.11.input_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.11.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.11.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin", + "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.12.input_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.12.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.12.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin", + "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.13.input_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.13.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.13.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin", + "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.14.input_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.14.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.14.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin", + "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.15.input_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.15.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.15.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin", + "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.16.input_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.16.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.16.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin", + "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.17.input_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.17.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.17.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin", + "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.18.input_layernorm.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.18.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.18.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin", + "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.19.input_layernorm.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.19.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.19.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin", + "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin", + "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.20.input_layernorm.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.20.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.20.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin", + "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.21.input_layernorm.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.21.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.21.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin", + "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.22.input_layernorm.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.22.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.22.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin", + "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.23.input_layernorm.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.23.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.23.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin", + "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.24.input_layernorm.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.24.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.24.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin", + "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.25.input_layernorm.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.25.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.25.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin", + "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin", + "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin", + "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin", + "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin", + "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin", + "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin", + "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin", + "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.norm.weight": "pytorch_model-00002-of-00002.bin" + } +} \ No newline at end of file diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..d85ba6c --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,23 @@ +{ + "bos_token": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false + }, + "unk_token": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false + } +} diff --git a/tokenizer.model b/tokenizer.model new file mode 100644 index 0000000..b0add75 --- /dev/null +++ b/tokenizer.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b75399aead1a805169b19bb86d6151539f0220c4b4e2023189c9d4ff776b000 +size 889388 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..bb4faee --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,36 @@ +{ + "add_bos_token": true, + "add_eos_token": false, + "bos_token": { + "__type": "AddedToken", + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false + }, + "clean_up_tokenization_spaces": false, + "eos_token": { + "__type": "AddedToken", + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false + }, + "legacy": true, + "model_max_length": 2048, + "pad_token": null, + "sp_model_kwargs": {}, + "spaces_between_special_tokens": false, + "tokenizer_class": "LlamaTokenizer", + "unk_token": { + "__type": "AddedToken", + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false + }, + "use_default_system_prompt": true +}