commit 0565a92a71c47d8935140a00cab3124d6af53b37 Author: ModelHub XC Date: Tue Jul 28 20:41:10 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: lemon-mint/gemma-ko-7b-it-v0.40 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..293b099 --- /dev/null +++ b/README.md @@ -0,0 +1,43 @@ +--- +library_name: transformers +license: other +license_name: gemma-terms-of-use +license_link: https://ai.google.dev/gemma/terms +language: +- ko +- en +tags: +- korean +- gemma +- pytorch +pipeline_tag: text-generation +base_model: +- google/gemma-7b-it +--- + +![image/png](https://cdn-uploads.huggingface.co/production/uploads/6332f1a52b866de639ee0279/jYH2isQRcP7LQfydwbOj_.png) + +# Gemma Ko 7B Instruct v0.40 + +- Eval Loss: `1.222` +- lr: `1.5e-5` +- optimizer: adamw +- lr_scheduler_type: cosine + +## Model Details + +### Model Description + +The Gemma 7B Ko Instruct v0.40 model is designed for generating human-like text in the Korean language. +It can be used for a variety of natural language processing tasks, such as language translation, text summarization, question answering, and conversation generation. +This model is particularly well-suited for applications that require high-quality, coherent, and contextually relevant Korean text generation. + +- **Developed by:** `lemon-mint` +- **Model type:** Gemma +- **Language(s) (NLP):** Korean, English +- **License:** [gemma-terms-of-use](https://ai.google.dev/gemma/terms) +- **Finetuned from model:** [google/gemma-7b-it](https://huggingface.co/google/gemma-7b-it) + +# Limitations and Ethical Considerations + +As Gemma Ko 7B has been trained on extensive web data, biases present in the training data may be reflected in the model. Additionally, there is a possibility that it may generate sentences containing errors or incorrect information. Therefore, rather than blindly trusting the model's output, it is necessary to refer to it with caution. \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..1f28eb0 --- /dev/null +++ b/config.json @@ -0,0 +1,28 @@ +{ + "_name_or_path": "lemon-mint/gemma-ko-7b-it-v0.33", + "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": 3072, + "initializer_range": 0.02, + "intermediate_size": 24576, + "max_position_embeddings": 8192, + "model_type": "gemma", + "num_attention_heads": 16, + "num_hidden_layers": 28, + "num_key_value_heads": 16, + "pad_token_id": 0, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 10000.0, + "torch_dtype": "bfloat16", + "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-00006.safetensors b/model-00001-of-00006.safetensors new file mode 100644 index 0000000..f0710fd --- /dev/null +++ b/model-00001-of-00006.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:392b0c5f611dfd12549d44bc1eba2d162249938c703a23b4fd5090d3eac170bb +size 2931845880 diff --git a/model-00002-of-00006.safetensors b/model-00002-of-00006.safetensors new file mode 100644 index 0000000..85c065e --- /dev/null +++ b/model-00002-of-00006.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc00ec50d6629984516de828c1fba69ce34290fdb18e0e1dc9ce9b4ef7932fea +size 2919302344 diff --git a/model-00003-of-00006.safetensors b/model-00003-of-00006.safetensors new file mode 100644 index 0000000..a6897cc --- /dev/null +++ b/model-00003-of-00006.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c8289970814960cf86e42d442901dfc442041054a2963cb3af0130786b7fe8e4 +size 2994812720 diff --git a/model-00004-of-00006.safetensors b/model-00004-of-00006.safetensors new file mode 100644 index 0000000..7b685d6 --- /dev/null +++ b/model-00004-of-00006.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e831932a9de327574a606d3d8953de2da6802f79a068df60782f6d85a5d8e0d +size 2944468336 diff --git a/model-00005-of-00006.safetensors b/model-00005-of-00006.safetensors new file mode 100644 index 0000000..79b77ee --- /dev/null +++ b/model-00005-of-00006.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f0d9555a9961f8e16cab1d82b002481df513793a38e05286705a0180b238942e +size 2919302392 diff --git a/model-00006-of-00006.safetensors b/model-00006-of-00006.safetensors new file mode 100644 index 0000000..3e5593b --- /dev/null +++ b/model-00006-of-00006.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:53f11eca6ae72855f043bb89dfba53580daafe12d72e69d78c5f3137dc3094d7 +size 2365659680 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000..d82b79c --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,261 @@ +{ + "metadata": { + "total_size": 17075361792 + }, + "weight_map": { + "model.embed_tokens.weight": "model-00001-of-00006.safetensors", + "model.layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", + "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.10.input_layernorm.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", + "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.input_layernorm.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.12.input_layernorm.weight": "model-00003-of-00006.safetensors", + "model.layers.12.mlp.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.12.mlp.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", + "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.13.input_layernorm.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", + "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.14.input_layernorm.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.input_layernorm.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", + "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.input_layernorm.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", + "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.17.input_layernorm.weight": "model-00004-of-00006.safetensors", + "model.layers.17.mlp.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.17.mlp.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", + "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.18.input_layernorm.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.18.mlp.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", + "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.19.input_layernorm.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", + "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.2.input_layernorm.weight": "model-00002-of-00006.safetensors", + "model.layers.2.mlp.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.20.input_layernorm.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", + "model.layers.20.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.21.input_layernorm.weight": "model-00005-of-00006.safetensors", + "model.layers.21.mlp.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.21.mlp.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.21.mlp.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", + "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.22.input_layernorm.weight": "model-00005-of-00006.safetensors", + "model.layers.22.mlp.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.22.mlp.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", + "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.23.input_layernorm.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.23.mlp.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00006-of-00006.safetensors", + "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.24.input_layernorm.weight": "model-00006-of-00006.safetensors", + "model.layers.24.mlp.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.24.mlp.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.24.mlp.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00006-of-00006.safetensors", + "model.layers.24.self_attn.k_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.24.self_attn.o_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.24.self_attn.q_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.24.self_attn.v_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.25.input_layernorm.weight": "model-00006-of-00006.safetensors", + "model.layers.25.mlp.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.25.mlp.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.25.mlp.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00006.safetensors", + "model.layers.25.self_attn.k_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.25.self_attn.o_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.25.self_attn.q_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.25.self_attn.v_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.26.input_layernorm.weight": "model-00006-of-00006.safetensors", + "model.layers.26.mlp.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.26.mlp.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.26.mlp.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00006-of-00006.safetensors", + "model.layers.26.self_attn.k_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.26.self_attn.q_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.27.input_layernorm.weight": "model-00006-of-00006.safetensors", + "model.layers.27.mlp.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.27.mlp.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.27.mlp.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00006.safetensors", + "model.layers.27.self_attn.k_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.27.self_attn.o_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.27.self_attn.q_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.27.self_attn.v_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.3.input_layernorm.weight": "model-00002-of-00006.safetensors", + "model.layers.3.mlp.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.3.mlp.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.input_layernorm.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.input_layernorm.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.input_layernorm.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.input_layernorm.weight": "model-00003-of-00006.safetensors", + "model.layers.7.mlp.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.8.input_layernorm.weight": "model-00003-of-00006.safetensors", + "model.layers.8.mlp.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.8.mlp.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.8.mlp.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", + "model.layers.8.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.input_layernorm.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", + "model.norm.weight": "model-00006-of-00006.safetensors" + } +} diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..8d6368f --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,34 @@ +{ + "additional_special_tokens": [ + "", + "" + ], + "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..5299ac5 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8468b0860292bcb4154d02abcfa5d15e8896bc12e6d1980faa2e0a808529e9e0 +size 17478195 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..aaaea1d --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,77 @@ +{ + "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 + }, + "106": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "107": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "additional_special_tokens": [ + "", + "" + ], + "bos_token": "", + "chat_template": "{{ bos_token }}{% if messages[0]['role'] == 'system' %}{{ raise_exception('System role not supported') }}{% endif %}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if (message['role'] == 'assistant') %}{% set role = 'model' %}{% else %}{% set role = message['role'] %}{% endif %}{{ '' + role + '\n' + message['content'] | trim + '\n' }}{% endfor %}{% if add_generation_prompt %}{{'model\n'}}{% endif %}", + "clean_up_tokenization_spaces": false, + "eos_token": "", + "legacy": null, + "max_length": 1024, + "model_max_length": 1000000000000000019884624838656, + "pad_to_multiple_of": null, + "pad_token": "", + "pad_token_type_id": 0, + "padding_side": "left", + "sp_model_kwargs": {}, + "spaces_between_special_tokens": false, + "stride": 0, + "tokenizer_class": "GemmaTokenizer", + "truncation_side": "right", + "truncation_strategy": "longest_first", + "unk_token": "", + "use_default_system_prompt": false +}