commit 8d72914fcfbb4ae377d1d86979623bf1f53d2437 Author: ModelHub XC Date: Sat Apr 18 16:12:21 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: yys/gemma-7B-it-firefly 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..9f5f965 --- /dev/null +++ b/README.md @@ -0,0 +1,41 @@ +--- +library_name: transformers +license: apache-2.0 +basemodel: google/gemma-7b-it +--- + +## Model Card for Firefly-Gemma + +[gemma-7B-it-firefly](https://huggingface.co/yys/gemma-7B-it-firefly) is trained based on [gemma-7b-it](https://huggingface.co/google/gemma-7b-it) to act as a helpful and harmless AI assistant. +we trained the model on [firefly-train-1.1M](https://huggingface.co/datasets/YeungNLP/firefly-train-1.1M) dataset using LoRA. + + + + + +## Performance +we evaluate the model on [Open LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard) + +## Usage +The chat template of our chat models is same as Official gemma-7b-it: +```text +user +Write a hello world program +model +``` + +You can also use the following code: +```python +from transformers import AutoTokenizer, AutoModelForCausalLM + +model_name_or_path = "yys/gemma-7B-it-firefly" +tokenizer = AutoTokenizer.from_pretrained(model_name_or_path) +model = AutoModelForCausalLM.from_pretrained(model_name_or_path) + +input_text = "给我写一首关于机器学习的诗歌。" +input_ids = tokenizer(input_text, return_tensors="pt") + +outputs = model.generate(**input_ids) +print(tokenizer.decode(outputs[0])) + +``` diff --git a/config.json b/config.json new file mode 100644 index 0000000..50fd3d8 --- /dev/null +++ b/config.json @@ -0,0 +1,27 @@ +{ + "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 +} \ No newline at end of file diff --git a/configuration.json b/configuration.json new file mode 100644 index 0000000..f9291c3 --- /dev/null +++ b/configuration.json @@ -0,0 +1 @@ +{"framework":"Pytorch","task":"text-generation"} \ No newline at end of file diff --git a/gemma-7B-it-firefly.jpg b/gemma-7B-it-firefly.jpg new file mode 100644 index 0000000..7c20093 Binary files /dev/null and b/gemma-7B-it-firefly.jpg differ 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-00009.safetensors b/model-00001-of-00009.safetensors new file mode 100644 index 0000000..fc1a505 --- /dev/null +++ b/model-00001-of-00009.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d5fce47ce004f8254e44a9302903aea938dc682aa9092a38d4bc971f2cd224c2 +size 1975518024 diff --git a/model-00002-of-00009.safetensors b/model-00002-of-00009.safetensors new file mode 100644 index 0000000..7089458 --- /dev/null +++ b/model-00002-of-00009.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d3bbb82c30efd5346cfbd5e633faf9f2d97a10cb87ad35cb97a8a8c9859bd8e +size 1912655712 diff --git a/model-00003-of-00009.safetensors b/model-00003-of-00009.safetensors new file mode 100644 index 0000000..3021bb4 --- /dev/null +++ b/model-00003-of-00009.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe4503921553fc4e1f346d0ca38003e982b18020d295b13332423bf56ef1bed2 +size 1962974488 diff --git a/model-00004-of-00009.safetensors b/model-00004-of-00009.safetensors new file mode 100644 index 0000000..f8fd0fb --- /dev/null +++ b/model-00004-of-00009.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:449abe972ce0775c7cc42767ce4bc47f29249874ee2c3540cde486d1f4be7e4a +size 1912655720 diff --git a/model-00005-of-00009.safetensors b/model-00005-of-00009.safetensors new file mode 100644 index 0000000..c2eb90b --- /dev/null +++ b/model-00005-of-00009.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:99dc77674a2a7c093ac1b92aa141ee9f7ea66ac7c537a2da12d732896ff482a1 +size 1962974520 diff --git a/model-00006-of-00009.safetensors b/model-00006-of-00009.safetensors new file mode 100644 index 0000000..1a40bdd --- /dev/null +++ b/model-00006-of-00009.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e9e46f54b9b0d637ec6aa511a025d2b7efb9c458308a1369b2477a8ca1268063 +size 1912655744 diff --git a/model-00007-of-00009.safetensors b/model-00007-of-00009.safetensors new file mode 100644 index 0000000..0ea0d9a --- /dev/null +++ b/model-00007-of-00009.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e2b044cc870eefa65177bec6e16295cc2a473f14278e167fa682063a7e1b39e4 +size 1962974520 diff --git a/model-00008-of-00009.safetensors b/model-00008-of-00009.safetensors new file mode 100644 index 0000000..f0b46d8 --- /dev/null +++ b/model-00008-of-00009.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:604e2de041633dca3a0f2249a91267188fc80692ea1c9a8895e63edbab6ff0e1 +size 1912655744 diff --git a/model-00009-of-00009.safetensors b/model-00009-of-00009.safetensors new file mode 100644 index 0000000..1e889e6 --- /dev/null +++ b/model-00009-of-00009.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b3ce8031e2f1755f123e568898d8ab5153a6de2a507f27bc81377d3aadfc2bb0 +size 1560326864 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000..6c56b60 --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,261 @@ +{ + "metadata": { + "total_size": 17075361792 + }, + "weight_map": { + "model.embed_tokens.weight": "model-00001-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-00001-of-00009.safetensors", + "model.layers.0.mlp.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00009.safetensors", + "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.0.self_attn.v_proj.weight": "model-00001-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-00002-of-00009.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model-00002-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-00004-of-00009.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model-00004-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-00004-of-00009.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model-00004-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-00006-of-00009.safetensors", + "model.layers.14.mlp.down_proj.weight": "model-00006-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-00006-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-00006-of-00009.safetensors", + "model.layers.15.mlp.down_proj.weight": "model-00006-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-00007-of-00009.safetensors", + "model.layers.18.mlp.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.18.mlp.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.18.mlp.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00007-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-00007-of-00009.safetensors", + "model.layers.19.mlp.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.19.mlp.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.19.mlp.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00007-of-00009.safetensors", + "model.layers.19.self_attn.k_proj.weight": "model-00007-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-00002-of-00009.safetensors", + "model.layers.2.mlp.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.2.mlp.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.2.mlp.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00009.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model-00002-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-00008-of-00009.safetensors", + "model.layers.21.mlp.down_proj.weight": "model-00008-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-00008-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-00008-of-00009.safetensors", + "model.layers.22.mlp.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.22.mlp.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.22.mlp.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00008-of-00009.safetensors", + "model.layers.22.self_attn.k_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.22.self_attn.q_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.22.self_attn.v_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.input_layernorm.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00008-of-00009.safetensors", + "model.layers.23.self_attn.k_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.self_attn.q_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.self_attn.v_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.input_layernorm.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.down_proj.weight": "model-00008-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-00009-of-00009.safetensors", + "model.layers.25.mlp.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.25.mlp.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.25.mlp.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00009-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-00009-of-00009.safetensors", + "model.layers.26.mlp.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00009-of-00009.safetensors", + "model.layers.26.self_attn.k_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.self_attn.o_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.self_attn.q_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.self_attn.v_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.input_layernorm.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00009-of-00009.safetensors", + "model.layers.27.self_attn.k_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.self_attn.o_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.self_attn.q_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.self_attn.v_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.3.input_layernorm.weight": "model-00002-of-00009.safetensors", + "model.layers.3.mlp.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.3.mlp.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00009.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00002-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-00002-of-00009.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model-00002-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-00003-of-00009.safetensors", + "model.layers.6.mlp.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00009.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model-00003-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-00003-of-00009.safetensors", + "model.layers.7.mlp.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00004-of-00009.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model-00003-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/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.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..bed4034 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,72 @@ +{ + "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": "{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{{ '' + system_message }}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ 'user\\n' + content + '\\nmodel\\n' }}{% elif message['role'] == 'assistant' %}{{ content + '\\n' }}{% endif %}{% endfor %}", + "clean_up_tokenization_spaces": false, + "eos_token": "", + "legacy": null, + "model_max_length": 1000000000000000019884624838656, + "pad_token": "", + "padding_side": "left", + "sp_model_kwargs": {}, + "spaces_between_special_tokens": false, + "split_special_tokens": false, + "tokenizer_class": "GemmaTokenizer", + "unk_token": "", + "use_default_system_prompt": false +}