commit e1efdabf0653c88dbc001d9d42ef0c1715ee3bf5 Author: ModelHub XC Date: Thu Jun 11 00:50:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: SAWithanage/SinLlama-Llama-3-8B-Merged Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..52373fe --- /dev/null +++ b/.gitattributes @@ -0,0 +1,36 @@ +*.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 +tokenizer.json filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..18acb6b --- /dev/null +++ b/README.md @@ -0,0 +1,77 @@ +--- +language: +- si +- en +base_model: meta-llama/Meta-Llama-3-8B +tags: +- llama-3 +- sinhala +- nlp +- text-generation +- merged +license: llama3 +--- + +# SinLlama Llama-3-8B Merged + +This repository contains a continuous pre-trained (CPT) base model for the Sinhala language. It was created by mathematically merging the official `meta-llama/Meta-Llama-3-8B` base model with the `polyglots/SinLlama_v01` LoRA adapter. + +**This model has been fully merged into standalone FP16 weights**, meaning it can be loaded directly in libraries like `transformers` or `vLLM` without needing to download or manage separate Peft adapters. + +## 🏆 Acknowledgments, Credits & Disclaimer +**My contribution to this repository is strictly limited to merging the weights to provide a convenient standalone model.** + +All credit for the foundational machine learning research, tokenizer vocabulary expansion, dataset curation, and continuous pre-training (CPT) belongs entirely to the **[Polyglots](https://huggingface.co/polyglots)** team and the authors of the SinLlama paper. + +* **Researchers/Authors:** H. W. K. Aravinda, Rashad Sirajudeen, Samith Karunathilake, Nisansa de Silva, Surangika Ranathunga, Rishemjit Kaur +* **Original Adapter:** [polyglots/SinLlama_v01](https://huggingface.co/polyglots/SinLlama_v01) +* **Original Tokenizer:** [polyglots/Extended-Sinhala-LLaMA](https://huggingface.co/polyglots/Extended-Sinhala-LLaMA) +* **Paper:** *SinLlama: A Large Language Model for Sinhala* + +If you use this model in your research or applications, please ensure you cite their original work: +```bibtex +@article{aravinda2025sinllama, + title={SinLlama-A Large Language Model for Sinhala}, + author={Aravinda, H W K and Sirajudeen, Rashad and Karunathilake, Samith and de Silva, Nisansa and Ranathunga, Surangika and Kaur, Rishemjit}, + journal={arXiv preprint arXiv:2508.09115}, + year={2025} +} +``` + +## ⚙️ Model Details +* **Base Model:** [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) +* **Language:** Sinhala (si), English (en) +* **Architecture:** Llama 3 (8 Billion Parameters) +* **Format:** Safetensors (Unquantized FP16) + +## ⚠️ Important Limitations (Base Model vs. Chat Model) +**This is a Base Model, not an Instruction-Tuned (Chat) Model.** +Because it has not undergone Supervised Fine-Tuning (SFT), it is optimized for text completion, not interactive conversation. + +If you prompt it with a question, it may attempt to complete the document by writing more questions (acting like an FAQ page). To use it effectively for Q&A, you must format your prompts strictly and use stopping criteria (like regex or EOS tokens) to prevent looping and run-on generations. + +### Example Prompt Format: +```text +Question: කෘතිම බුද්ධිය (AI) යනු කුමක්දැයි සරලව පැහැදිලි කරන්න. +Answer: +``` + +## 💻 How to Load in 4-bit (Google Colab / T4 GPU) +```python +from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig +import torch + +bnb_config = BitsAndBytesConfig( + load_in_4bit=True, + bnb_4bit_use_double_quant=True, + bnb_4bit_quant_type="nf4", + bnb_4bit_compute_dtype=torch.float16 +) + +tokenizer = AutoTokenizer.from_pretrained("SAWithanage/SinLlama-Llama-3-8B-Merged") +model = AutoModelForCausalLM.from_pretrained( + "SAWithanage/SinLlama-Llama-3-8B-Merged", + quantization_config=bnb_config, + device_map="auto" +) +``` diff --git a/config.json b/config.json new file mode 100644 index 0000000..8c0d2c4 --- /dev/null +++ b/config.json @@ -0,0 +1,32 @@ +{ + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 128000, + "dtype": "float16", + "eos_token_id": 128001, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 4096, + "initializer_range": 0.02, + "intermediate_size": 14336, + "max_position_embeddings": 8192, + "mlp_bias": false, + "model_type": "llama", + "num_attention_heads": 32, + "num_hidden_layers": 32, + "num_key_value_heads": 8, + "pad_token_id": null, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_parameters": { + "rope_theta": 500000.0, + "rope_type": "default" + }, + "tie_word_embeddings": false, + "transformers_version": "5.0.0", + "use_cache": true, + "vocab_size": 139336 +} \ No newline at end of file diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..d1169ce --- /dev/null +++ b/generation_config.json @@ -0,0 +1,9 @@ +{ + "bos_token_id": 128000, + "do_sample": true, + "eos_token_id": 128001, + "max_length": 4096, + "temperature": 0.6, + "top_p": 0.9, + "transformers_version": "5.0.0" +} \ No newline at end of file diff --git a/model-00001-of-00009.safetensors b/model-00001-of-00009.safetensors new file mode 100644 index 0000000..4c555ee --- /dev/null +++ b/model-00001-of-00009.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d7d79a9c5ae8ac3137937af5c3b4661508bfc4a379bd0c485c213602237b704e +size 1141440640 diff --git a/model-00002-of-00009.safetensors b/model-00002-of-00009.safetensors new file mode 100644 index 0000000..4149ecf --- /dev/null +++ b/model-00002-of-00009.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d509495028216949903f488f9c6490eeded64407a67144e4a6b2db62666291c +size 1971947448 diff --git a/model-00003-of-00009.safetensors b/model-00003-of-00009.safetensors new file mode 100644 index 0000000..f577bca --- /dev/null +++ b/model-00003-of-00009.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:edd222c046cee583fab8724f9c8973452a444a3c8766856cdcb29431fb8b5090 +size 1904292320 diff --git a/model-00004-of-00009.safetensors b/model-00004-of-00009.safetensors new file mode 100644 index 0000000..05b0938 --- /dev/null +++ b/model-00004-of-00009.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:990d630e92d127adad96c636c629f31f9daa7545f4a3eb78754572aec091f90c +size 1988178416 diff --git a/model-00005-of-00009.safetensors b/model-00005-of-00009.safetensors new file mode 100644 index 0000000..3c85c2c --- /dev/null +++ b/model-00005-of-00009.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c564bc6abc8260be39518117d6d718c0d4aa9b05c7b5c5c4d8d05def78e1c05b +size 1937846904 diff --git a/model-00006-of-00009.safetensors b/model-00006-of-00009.safetensors new file mode 100644 index 0000000..d46d2ee --- /dev/null +++ b/model-00006-of-00009.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8efcb71102ffc037dcece15278cbbba7baecad1293746467f3ee9552b9d1acc9 +size 1988178456 diff --git a/model-00007-of-00009.safetensors b/model-00007-of-00009.safetensors new file mode 100644 index 0000000..f551710 --- /dev/null +++ b/model-00007-of-00009.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca76ee8b21780799bbcd9225af9b334cc8e6d0c3e655c1d82175132114387eb0 +size 1937846904 diff --git a/model-00008-of-00009.safetensors b/model-00008-of-00009.safetensors new file mode 100644 index 0000000..dba3f8e --- /dev/null +++ b/model-00008-of-00009.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:848e4fab449d90abec133e05efa5dab41bf1f77d3be4ae492e2679835ebc4158 +size 1988178456 diff --git a/model-00009-of-00009.safetensors b/model-00009-of-00009.safetensors new file mode 100644 index 0000000..c33e431 --- /dev/null +++ b/model-00009-of-00009.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d272d1f976165cf796ba59aa5d82c963b4229a130b4a05289d200af7987bbd41 +size 1384181216 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000..a933130 --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,299 @@ +{ + "metadata": { + "total_parameters": 8121028608, + "total_size": 16242057216 + }, + "weight_map": { + "lm_head.weight": "model-00001-of-00009.safetensors", + "model.embed_tokens.weight": "model-00002-of-00009.safetensors", + "model.layers.0.input_layernorm.weight": "model-00002-of-00009.safetensors", + "model.layers.0.mlp.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.0.mlp.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.0.mlp.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00009.safetensors", + "model.layers.0.self_attn.k_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.0.self_attn.q_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.0.self_attn.v_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.1.input_layernorm.weight": "model-00002-of-00009.safetensors", + "model.layers.1.mlp.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.1.mlp.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00009.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.10.input_layernorm.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00004-of-00009.safetensors", + "model.layers.10.self_attn.k_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.11.input_layernorm.weight": "model-00005-of-00009.safetensors", + "model.layers.11.mlp.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.11.mlp.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.11.mlp.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00005-of-00009.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.12.input_layernorm.weight": "model-00005-of-00009.safetensors", + "model.layers.12.mlp.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.12.mlp.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.12.mlp.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00005-of-00009.safetensors", + "model.layers.12.self_attn.k_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.input_layernorm.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00005-of-00009.safetensors", + "model.layers.13.self_attn.k_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.self_attn.v_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.input_layernorm.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00005-of-00009.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.self_attn.v_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.input_layernorm.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.15.mlp.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00006-of-00009.safetensors", + "model.layers.15.self_attn.k_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.15.self_attn.q_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.15.self_attn.v_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.16.input_layernorm.weight": "model-00006-of-00009.safetensors", + "model.layers.16.mlp.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.16.mlp.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.16.mlp.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00006-of-00009.safetensors", + "model.layers.16.self_attn.k_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.16.self_attn.q_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.16.self_attn.v_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.input_layernorm.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00006-of-00009.safetensors", + "model.layers.17.self_attn.k_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.self_attn.q_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.self_attn.v_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.input_layernorm.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00006-of-00009.safetensors", + "model.layers.18.self_attn.k_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.self_attn.q_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.self_attn.v_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.19.input_layernorm.weight": "model-00006-of-00009.safetensors", + "model.layers.19.mlp.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.19.mlp.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.19.mlp.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00006-of-00009.safetensors", + "model.layers.19.self_attn.k_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.19.self_attn.q_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.19.self_attn.v_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.2.input_layernorm.weight": "model-00003-of-00009.safetensors", + "model.layers.2.mlp.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.2.mlp.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.2.mlp.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00009.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.20.input_layernorm.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00007-of-00009.safetensors", + "model.layers.20.self_attn.k_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.self_attn.q_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.self_attn.v_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.input_layernorm.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00007-of-00009.safetensors", + "model.layers.21.self_attn.k_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.self_attn.q_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.self_attn.v_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.22.input_layernorm.weight": "model-00007-of-00009.safetensors", + "model.layers.22.mlp.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.22.mlp.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.22.mlp.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00007-of-00009.safetensors", + "model.layers.22.self_attn.k_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.22.self_attn.q_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.22.self_attn.v_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.23.input_layernorm.weight": "model-00007-of-00009.safetensors", + "model.layers.23.mlp.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.23.mlp.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.23.mlp.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00007-of-00009.safetensors", + "model.layers.23.self_attn.k_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.23.self_attn.q_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.23.self_attn.v_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.24.input_layernorm.weight": "model-00007-of-00009.safetensors", + "model.layers.24.mlp.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.24.mlp.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00008-of-00009.safetensors", + "model.layers.24.self_attn.k_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.self_attn.o_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.self_attn.q_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.self_attn.v_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.25.input_layernorm.weight": "model-00008-of-00009.safetensors", + "model.layers.25.mlp.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.25.mlp.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.25.mlp.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00008-of-00009.safetensors", + "model.layers.25.self_attn.k_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.25.self_attn.o_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.25.self_attn.q_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.25.self_attn.v_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.26.input_layernorm.weight": "model-00008-of-00009.safetensors", + "model.layers.26.mlp.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.26.mlp.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.26.mlp.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00008-of-00009.safetensors", + "model.layers.26.self_attn.k_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.26.self_attn.o_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.26.self_attn.q_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.26.self_attn.v_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.27.input_layernorm.weight": "model-00008-of-00009.safetensors", + "model.layers.27.mlp.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.27.mlp.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.27.mlp.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00008-of-00009.safetensors", + "model.layers.27.self_attn.k_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.27.self_attn.o_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.27.self_attn.q_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.27.self_attn.v_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.28.input_layernorm.weight": "model-00008-of-00009.safetensors", + "model.layers.28.mlp.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.28.mlp.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.28.mlp.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.28.post_attention_layernorm.weight": "model-00008-of-00009.safetensors", + "model.layers.28.self_attn.k_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.28.self_attn.o_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.28.self_attn.q_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.28.self_attn.v_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.29.input_layernorm.weight": "model-00009-of-00009.safetensors", + "model.layers.29.mlp.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.29.mlp.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.29.mlp.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.29.post_attention_layernorm.weight": "model-00009-of-00009.safetensors", + "model.layers.29.self_attn.k_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.29.self_attn.o_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.29.self_attn.q_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.29.self_attn.v_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.3.input_layernorm.weight": "model-00003-of-00009.safetensors", + "model.layers.3.mlp.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.3.mlp.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.3.mlp.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00009.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.30.input_layernorm.weight": "model-00009-of-00009.safetensors", + "model.layers.30.mlp.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.30.mlp.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.30.mlp.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.30.post_attention_layernorm.weight": "model-00009-of-00009.safetensors", + "model.layers.30.self_attn.k_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.30.self_attn.o_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.30.self_attn.q_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.30.self_attn.v_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.31.input_layernorm.weight": "model-00009-of-00009.safetensors", + "model.layers.31.mlp.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.31.mlp.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.31.mlp.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.31.post_attention_layernorm.weight": "model-00009-of-00009.safetensors", + "model.layers.31.self_attn.k_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.31.self_attn.o_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.31.self_attn.q_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.31.self_attn.v_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.4.input_layernorm.weight": "model-00003-of-00009.safetensors", + "model.layers.4.mlp.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.4.mlp.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.4.mlp.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00009.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.5.input_layernorm.weight": "model-00003-of-00009.safetensors", + "model.layers.5.mlp.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.5.mlp.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.5.mlp.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00009.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.6.input_layernorm.weight": "model-00003-of-00009.safetensors", + "model.layers.6.mlp.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.6.mlp.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.6.mlp.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00004-of-00009.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.7.input_layernorm.weight": "model-00004-of-00009.safetensors", + "model.layers.7.mlp.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.7.mlp.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.7.mlp.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00004-of-00009.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.8.input_layernorm.weight": "model-00004-of-00009.safetensors", + "model.layers.8.mlp.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.8.mlp.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.8.mlp.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00004-of-00009.safetensors", + "model.layers.8.self_attn.k_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.9.input_layernorm.weight": "model-00004-of-00009.safetensors", + "model.layers.9.mlp.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.9.mlp.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.9.mlp.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00004-of-00009.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model-00004-of-00009.safetensors", + "model.norm.weight": "model-00009-of-00009.safetensors" + } +} diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..d2dddb0 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:549f579ab85fa6f63fe7d9a4d9e62918011c35bebf45c6bb8000a6ae89a9a3d7 +size 19338079 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..43a6c9d --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,13 @@ +{ + "backend": "tokenizers", + "bos_token": "<|begin_of_text|>", + "clean_up_tokenization_spaces": true, + "eos_token": "<|end_of_text|>", + "is_local": false, + "model_input_names": [ + "input_ids", + "attention_mask" + ], + "model_max_length": 1000000000000000019884624838656, + "tokenizer_class": "PreTrainedTokenizerFast" +} \ No newline at end of file