commit 943bb9d9fad37c0152c0e95ddda59e8733f25139 Author: ModelHub XC Date: Wed Jul 1 11:42:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: Telugu-LLM-Labs/Indic-gemma-2b-finetuned-sft-Navarasa-2.0 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..329d112 --- /dev/null +++ b/README.md @@ -0,0 +1,172 @@ +--- +license: other +license_name: gemma-terms-of-use +license_link: https://ai.google.dev/gemma/terms +base_model: google/gemma-2b +datasets: +- ravithejads/samvaad-hi-filtered +- Telugu-LLM-Labs/telugu_teknium_GPTeacher_general_instruct_filtered_romanized +- Telugu-LLM-Labs/telugu_alpaca_yahma_cleaned_filtered_romanized +- Telugu-LLM-Labs/sindhi_alpaca_yahma_cleaned_filtered +- Telugu-LLM-Labs/urdu_alpaca_yahma_cleaned_filtered +- Telugu-LLM-Labs/marathi_alpaca_yahma_cleaned_filtered +- Telugu-LLM-Labs/assamese_alpaca_yahma_cleaned_filtered +- Telugu-LLM-Labs/konkani_alpaca_yahma_cleaned_filtered +- Telugu-LLM-Labs/nepali_alpaca_yahma_cleaned_filtered +- abhinand/tamil-alpaca +- Tensoic/airoboros-3.2_kn +- Tensoic/gpt-teacher_kn +- VishnuPJ/Alpaca_Instruct_Malayalam +- Tensoic/Alpaca-Gujarati +- HydraIndicLM/punjabi_alpaca_52K +- HydraIndicLM/bengali_alpaca_dolly_67k +- OdiaGenAI/Odia_Alpaca_instructions_52k +- yahma/alpaca-cleaned +language: +- te +- en +- ta +- ml +- mr +- hi +- kn +- sd +- ne +- ur +- as +- gu +- bn +- pa +- or +library_name: transformers +pipeline_tag: text-generation +--- + +# Indic-gemma-2b-finetuned-sft-Navarasa-2.0 + +This model is based on [google/gemma-2b](https://huggingface.co/google/gemma-2b) and hase been LoRA finetuned on 15 Indian languages and English language instruction datasets: + +1. #### Hindi - [ravithejads/samvaad-hi-filtered](https://huggingface.co/datasets/ravithejads/samvaad-hi-filtered), [HydraIndicLM/hindi_alpaca_dolly_67k](https://huggingface.co/datasets/HydraIndicLM/hindi_alpaca_dolly_67k)(sampled) +2. #### Telugu - [Telugu-LLM-Labs/telugu_alpaca_yahma_cleaned_filtered_romanized](https://huggingface.co/datasets/Telugu-LLM-Labs/telugu_alpaca_yahma_cleaned_filtered_romanized), [Telugu-LLM-Labs/telugu_teknium_GPTeacher_general_instruct_filtered_romanized](https://huggingface.co/datasets/Telugu-LLM-Labs/telugu_teknium_GPTeacher_general_instruct_filtered_romanized) +3. #### Marathi - [Telugu-LLM-Labs/sindhi_alpaca_yahma_cleaned_filtered](https://huggingface.co/datasets/Telugu-LLM-Labs/sindhi_alpaca_yahma_cleaned_filtered) +4. #### Urdu - [Telugu-LLM-Labs/urdu_alpaca_yahma_cleaned_filtered](https://huggingface.co/datasets/Telugu-LLM-Labs/urdu_alpaca_yahma_cleaned_filtered) +5. #### Assamese - [Telugu-LLM-Labs/assamese_alpaca_yahma_cleaned_filtered](https://huggingface.co/datasets/Telugu-LLM-Labs/assamese_alpaca_yahma_cleaned_filtered) +6. #### Konkani - [Telugu-LLM-Labs/konkani_alpaca_yahma_cleaned_filtered](https://huggingface.co/datasets/Telugu-LLM-Labs/konkani_alpaca_yahma_cleaned_filtered) +7. #### Nepali - [Telugu-LLM-Labs/nepali_alpaca_yahma_cleaned_filtered](https://huggingface.co/datasets/Telugu-LLM-Labs/nepali_alpaca_yahma_cleaned_filtered) +8. #### Sindhi - [Telugu-LLM-Labs/sindhi_alpaca_yahma_cleaned_filtered](https://huggingface.co/datasets/Telugu-LLM-Labs/sindhi_alpaca_yahma_cleaned_filtered) +9. #### Tamil - [abhinand/tamil-alpaca](https://huggingface.co/datasets/abhinand/tamil-alpaca) +10. #### Kannada - [Tensoic/airoboros-3.2_kn](https://huggingface.co/datasets/Tensoic/airoboros-3.2_kn), [Tensoic/gpt-teacher_kn](https://huggingface.co/datasets/Tensoic/gpt-teacher_kn) +11. #### Malayalam - [VishnuPJ/Alpaca_Instruct_Malayalam](https://huggingface.co/datasets/VishnuPJ/Alpaca_Instruct_Malayalam) +12. #### Gujarati - [Tensoic/Alpaca-Gujarati](https://huggingface.co/datasets/Tensoic/Alpaca-Gujarati) +13. #### Punjabi - [HydraIndicLM/punjabi_alpaca_52K](https://huggingface.co/datasets/HydraIndicLM/punjabi_alpaca_52K) +14. #### Bengali - [HydraIndicLM/bengali_alpaca_dolly_67k](https://huggingface.co/datasets/HydraIndicLM/bengali_alpaca_dolly_67k)(alpaca filtered) +15. #### Odia - [OdiaGenAI/Odia_Alpaca_instructions_52k](https://huggingface.co/datasets/OdiaGenAI/Odia_Alpaca_instructions_52k), [OdiaGenAI/gpt-teacher-roleplay-odia-3k](https://huggingface.co/datasets/OdiaGenAI/gpt-teacher-roleplay-odia-3k) +16. #### English - [yahma/alpaca-cleaned](https://huggingface.co/datasets/yahma/alpaca-cleaned) + +The model is finetuned using [unsloth](https://github.com/unslothai/unsloth) library and we provide inference code using the same for faster inference. Alternatively you can use HuggingFace Library for inference. + +# Training Details: + +The model is trained on approx 650K instruction samples. +1. GPU: 1 A100, 80GB +2. Time: 45 Hours +3. Platform: [E2E Networks](https://www.e2enetworks.com/) +# Installation + +`!pip install -U xformers --index-url https://download.pytorch.org/whl/cu121` +`!pip install "unsloth[kaggle-new] @git+https://github.com/unslothai/unsloth.git@nightly"` + +# Input Text Format + +``` +### Instruction: {instruction} + +### Input: {input} + +## Response: {response} +``` + +# Inference With Unsloth + +```python3 +from unsloth import FastLanguageModel +import torch +max_seq_length = 2048 +dtype = None # None for auto detection. Float16 for Tesla T4, V100, Bfloat16 for Ampere+ +load_in_4bit = False +model, tokenizer = FastLanguageModel.from_pretrained( + model_name = "Telugu-LLM-Labs/Indic-gemma-2b-finetuned-sft-Navarasa-2.0", + max_seq_length = max_seq_length, + dtype = dtype, + load_in_4bit = load_in_4bit, + device_map="auto" +) +FastLanguageModel.for_inference(model) # Enable native 2x faster inference + +input_prompt = """ +### Instruction: +{} + +### Input: +{} + +### Response: +{}""" + +input_text = input_prompt.format( + "Tranlsate following sentence to Hindi.", # instruction + "India is a great country.", # input + "", # output - leave this blank for generation! + ) + +inputs = tokenizer([input_text], return_tensors = "pt").to("cuda") + +outputs = model.generate(**inputs, max_new_tokens = 300, use_cache = True) +response = tokenizer.batch_decode(outputs) +``` + +# Inference with HuggingFace + +```python3 +from transformers import AutoTokenizer, AutoModelForCausalLM +import torch + +model = AutoModelForCausalLM.from_pretrained( + "Telugu-LLM-Labs/Indic-gemma-2b-finetuned-sft-Navarasa-2.0", + load_in_4bit = False, + token = hf_token +) +model.to("cuda") + +tokenizer = AutoTokenizer.from_pretrained("Telugu-LLM-Labs/Indic-gemma-2b-finetuned-sft-Navarasa-2.0") + +input_prompt = """ +### Instruction: +{} + +### Input: +{} + +### Response: +{}""" + +input_text = input_prompt.format( + "Tranlsate following sentence to Hindi.", # instruction + "India is a great country.", # input + "", # output - leave this blank for generation! + ) + +inputs = tokenizer([input_text], return_tensors = "pt").to("cuda") + +outputs = model.generate(**inputs, max_new_tokens = 300, use_cache = True) +response = tokenizer.batch_decode(outputs)[0] +``` + +Refer to the [blog post](https://ravidesetty.medium.com/introducing-navarasa-2-0-indic-gemma-7b-2b-instruction-tuned-model-on-15-indian-languages-31f6565b2750) for sample examples. + +Please check our [Code Repository](https://github.com/TeluguLLMLabs/Indic-gemma-7b-Navarasa) for training and inference scripts. + + +# Developers: + +The model is a collaborative effort by [Ravi Theja](https://twitter.com/ravithejads) and [Ramsri Goutham](https://twitter.com/ramsri_goutham). Feel free to DM either of us if you have any questions. \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..3537785 --- /dev/null +++ b/config.json @@ -0,0 +1,28 @@ +{ + "_name_or_path": "google/gemma-2b", + "architectures": [ + "GemmaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 2, + "eos_token_id": 1, + "head_dim": 256, + "hidden_act": "gelu", + "hidden_size": 2048, + "initializer_range": 0.02, + "intermediate_size": 16384, + "max_position_embeddings": 8192, + "model_type": "gemma", + "num_attention_heads": 8, + "num_hidden_layers": 18, + "num_key_value_heads": 1, + "pad_token_id": 0, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 10000.0, + "torch_dtype": "float32", + "transformers_version": "4.38.2", + "use_cache": true, + "vocab_size": 256000 +} diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..82035d2 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,7 @@ +{ + "_from_model_config": true, + "bos_token_id": 2, + "eos_token_id": 1, + "pad_token_id": 0, + "transformers_version": "4.38.2" +} diff --git a/model-00001-of-00003.safetensors b/model-00001-of-00003.safetensors new file mode 100644 index 0000000..498d14b --- /dev/null +++ b/model-00001-of-00003.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6fb7b01443799403f4fe8336085a22f19edc0f274324bf69c0ad8e4939d72db9 +size 4911635192 diff --git a/model-00002-of-00003.safetensors b/model-00002-of-00003.safetensors new file mode 100644 index 0000000..c554abb --- /dev/null +++ b/model-00002-of-00003.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e877085fb8135a9cb6aee9f6a22d530292b37ea0910aaf4c54e592cb0880fac7 +size 4978830584 diff --git a/model-00003-of-00003.safetensors b/model-00003-of-00003.safetensors new file mode 100644 index 0000000..f126a8a --- /dev/null +++ b/model-00003-of-00003.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:71e65a199d2547d4612dff7d09f8a0d8754d8873d2400d57dc21d3ed960a52c1 +size 134242760 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000..83cce8a --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,171 @@ +{ + "metadata": { + "total_size": 10024689664 + }, + "weight_map": { + "model.embed_tokens.weight": "model-00001-of-00003.safetensors", + "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.10.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.17.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.6.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.7.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.7.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.8.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.8.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.8.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.9.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.9.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.9.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.norm.weight": "model-00003-of-00003.safetensors" + } +} diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..f611958 --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,30 @@ +{ + "bos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "unk_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..7d526fa --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d0d908b4f9326e0998815690e325b6abbd378978553e10627924dd825db7e243 +size 17477553 diff --git a/tokenizer.model b/tokenizer.model new file mode 100644 index 0000000..796efe9 --- /dev/null +++ b/tokenizer.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2 +size 4241003 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..980e5a4 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,50 @@ +{ + "add_bos_token": true, + "add_eos_token": false, + "added_tokens_decoder": { + "0": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "1": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "2": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "3": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "bos_token": "", + "clean_up_tokenization_spaces": false, + "eos_token": "", + "legacy": null, + "model_max_length": 8192, + "pad_token": "", + "padding_side": "right", + "sp_model_kwargs": {}, + "spaces_between_special_tokens": false, + "tokenizer_class": "GemmaTokenizer", + "unk_token": "", + "use_default_system_prompt": false +}