commit 5caea54ca8613ec9d7a39655fe980197b9626a89 Author: ModelHub XC Date: Tue May 5 14:38:47 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: arcee-ai/Gemma-Zephyr-Dolly-Chat-Slerp Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..f65f19a --- /dev/null +++ b/.gitattributes @@ -0,0 +1,45 @@ +*.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 +model-00001-of-00009.safetensors filter=lfs diff=lfs merge=lfs -text +model-00002-of-00009.safetensors filter=lfs diff=lfs merge=lfs -text +model-00003-of-00009.safetensors filter=lfs diff=lfs merge=lfs -text +model-00004-of-00009.safetensors filter=lfs diff=lfs merge=lfs -text +model-00005-of-00009.safetensors filter=lfs diff=lfs merge=lfs -text +model-00006-of-00009.safetensors filter=lfs diff=lfs merge=lfs -text +model-00007-of-00009.safetensors filter=lfs diff=lfs merge=lfs -text +model-00008-of-00009.safetensors filter=lfs diff=lfs merge=lfs -text +model-00009-of-00009.safetensors filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..78cf0f8 --- /dev/null +++ b/README.md @@ -0,0 +1,37 @@ +--- +license: apache-2.0 +tags: +- merge +- mergekit +- HuggingFaceH4/zephyr-7b-gemma-v0.1 +- google/gemma-7b+philschmid/gemma-7b-dolly-chatml +--- + +# Gemma-Zephyr-Dolly-Chat-Slerp + +Gemma-Zephyr-Dolly-Chat-Slerp is a merge of the following models using [mergekit](https://github.com/cg123/mergekit): +* [HuggingFaceH4/zephyr-7b-gemma-v0.1](https://huggingface.co/HuggingFaceH4/zephyr-7b-gemma-v0.1) +* [google/gemma-7b+philschmid/gemma-7b-dolly-chatml](https://huggingface.co/google/gemma-7b+philschmid/gemma-7b-dolly-chatml) + +## 🧩 Configuration + +```yaml + slices: + - sources: + - model: HuggingFaceH4/zephyr-7b-gemma-v0.1 + layer_range: [0, 28] + - model: google/gemma-7b+philschmid/gemma-7b-dolly-chatml + layer_range: [0, 28] + merge_method: slerp + base_model: HuggingFaceH4/zephyr-7b-gemma-v0.1 + parameters: + t: + - filter: self_attn + value: [0, 0.5, 0.3, 0.7, 1] + - filter: mlp + value: [1, 0.5, 0.7, 0.3, 0] + - value: 0.5 + dtype: bfloat16 + + +``` \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..4020d95 --- /dev/null +++ b/config.json @@ -0,0 +1,28 @@ +{ + "_name_or_path": "HuggingFaceH4/zephyr-7b-gemma-v0.1", + "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/configuration.json b/configuration.json new file mode 100644 index 0000000..bbeeda1 --- /dev/null +++ b/configuration.json @@ -0,0 +1 @@ +{"framework": "pytorch", "task": "text-generation", "allow_remote": true} \ No newline at end of file diff --git a/mergekit_config.yml b/mergekit_config.yml new file mode 100644 index 0000000..6277978 --- /dev/null +++ b/mergekit_config.yml @@ -0,0 +1,19 @@ + + slices: + - sources: + - model: HuggingFaceH4/zephyr-7b-gemma-v0.1 + layer_range: [0, 28] + - model: google/gemma-7b+philschmid/gemma-7b-dolly-chatml + layer_range: [0, 28] + merge_method: slerp + base_model: HuggingFaceH4/zephyr-7b-gemma-v0.1 + parameters: + t: + - filter: self_attn + value: [0, 0.5, 0.3, 0.7, 1] + - filter: mlp + value: [1, 0.5, 0.7, 0.3, 0] + - value: 0.5 + dtype: bfloat16 + + diff --git a/model-00001-of-00009.safetensors b/model-00001-of-00009.safetensors new file mode 100644 index 0000000..037842f --- /dev/null +++ b/model-00001-of-00009.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:947467ddea219700c2af7fef002088bb47686fbb95b902f30da32b455936da4a +size 1912643208 diff --git a/model-00002-of-00009.safetensors b/model-00002-of-00009.safetensors new file mode 100644 index 0000000..8b232f4 --- /dev/null +++ b/model-00002-of-00009.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:67b9161269c19544731ff5b6327d1f8868d965ece602fed4280806d797c562d8 +size 1509989312 diff --git a/model-00003-of-00009.safetensors b/model-00003-of-00009.safetensors new file mode 100644 index 0000000..18d6bde --- /dev/null +++ b/model-00003-of-00009.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c7eb9d542ce539f0375fa63a9ae444b7e70aea8a4f55b2d1d69d1b614c5c0405 +size 1975518032 diff --git a/model-00004-of-00009.safetensors b/model-00004-of-00009.safetensors new file mode 100644 index 0000000..5618e74 --- /dev/null +++ b/model-00004-of-00009.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d489e86004f58fa15af33f7d00bf3e8df6d3bf1d9fee8e8344bc6a9f2c813fb0 +size 1912655752 diff --git a/model-00005-of-00009.safetensors b/model-00005-of-00009.safetensors new file mode 100644 index 0000000..f02379f --- /dev/null +++ b/model-00005-of-00009.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac618541d0f2fc319b0481225112f4dc19675e59c9979e57c9b2ec91e8951276 +size 1962974504 diff --git a/model-00006-of-00009.safetensors b/model-00006-of-00009.safetensors new file mode 100644 index 0000000..73879d6 --- /dev/null +++ b/model-00006-of-00009.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:922b6a9f17c7c64bc7ad076e87c1112818cf4df79170d3ec3f9fee63d8a90c38 +size 1912655736 diff --git a/model-00007-of-00009.safetensors b/model-00007-of-00009.safetensors new file mode 100644 index 0000000..8268147 --- /dev/null +++ b/model-00007-of-00009.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b4a5fa05b5949ce2965338c0483366eb4bd0e1f5ed02e2656edad86b157d3cc3 +size 1962974528 diff --git a/model-00008-of-00009.safetensors b/model-00008-of-00009.safetensors new file mode 100644 index 0000000..fc4973a --- /dev/null +++ b/model-00008-of-00009.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c8c76969e0bae02cff97a80a72f91f7b7acdeac8afc5861440f500a55221465 +size 1962993272 diff --git a/model-00009-of-00009.safetensors b/model-00009-of-00009.safetensors new file mode 100644 index 0000000..75e7d28 --- /dev/null +++ b/model-00009-of-00009.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:767855820816b1933a9460d13b25ea0759fbc5304d07c5052ace91b8ebd016e4 +size 1962987040 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000..888def6 --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1 @@ +{"metadata": {"mergekit_version": "0.0.4.1"}, "weight_map": {"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00009.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00009.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00009.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00009.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00001-of-00009.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00009.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00001-of-00009.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00009.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00009.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00009.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00009.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00009.safetensors", "model.layers.5.input_layernorm.weight": "model-00001-of-00009.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00001-of-00009.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00009.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00001-of-00009.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00009.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00009.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00009.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00009.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00009.safetensors", "model.layers.4.input_layernorm.weight": "model-00001-of-00009.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00001-of-00009.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00009.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00001-of-00009.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00009.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00009.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00009.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00009.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00009.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00009.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00001-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.o_proj.weight": "model-00002-of-00009.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00009.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00009.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00009.safetensors", "model.layers.2.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.o_proj.weight": "model-00002-of-00009.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00009.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00009.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00009.safetensors", "model.layers.1.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.o_proj.weight": "model-00002-of-00009.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00002-of-00009.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00002-of-00009.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00002-of-00009.safetensors", "model.layers.0.input_layernorm.weight": "model-00002-of-00009.safetensors", "model.embed_tokens.weight": "model-00003-of-00009.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00009.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00009.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00009.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00009.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00003-of-00009.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00009.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00004-of-00009.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00009.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00009.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00009.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00009.safetensors", "model.layers.14.input_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00004-of-00009.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00004-of-00009.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00004-of-00009.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00004-of-00009.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00004-of-00009.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00004-of-00009.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00004-of-00009.safetensors", "model.layers.13.input_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00004-of-00009.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00004-of-00009.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00004-of-00009.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00004-of-00009.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00004-of-00009.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00004-of-00009.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00004-of-00009.safetensors", "model.layers.12.input_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00004-of-00009.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00004-of-00009.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00004-of-00009.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00004-of-00009.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00004-of-00009.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00004-of-00009.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00004-of-00009.safetensors", "model.layers.11.input_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00005-of-00009.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00005-of-00009.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00005-of-00009.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00005-of-00009.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00005-of-00009.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00005-of-00009.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00005-of-00009.safetensors", "model.layers.10.input_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00005-of-00009.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00005-of-00009.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00005-of-00009.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00005-of-00009.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00005-of-00009.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00005-of-00009.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00005-of-00009.safetensors", "model.layers.9.input_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00005-of-00009.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00005-of-00009.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00005-of-00009.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00005-of-00009.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00005-of-00009.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00005-of-00009.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00005-of-00009.safetensors", "model.layers.8.input_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00005-of-00009.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00005-of-00009.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00006-of-00009.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00006-of-00009.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00006-of-00009.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00006-of-00009.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00006-of-00009.safetensors", "model.layers.7.input_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00006-of-00009.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00006-of-00009.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00006-of-00009.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.6.input_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00006-of-00009.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00006-of-00009.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00006-of-00009.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00006-of-00009.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00006-of-00009.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00006-of-00009.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00006-of-00009.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00006-of-00009.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00006-of-00009.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00006-of-00009.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00006-of-00009.safetensors", "model.layers.23.input_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00006-of-00009.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00006-of-00009.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00006-of-00009.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00006-of-00009.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00006-of-00009.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00006-of-00009.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00006-of-00009.safetensors", "model.layers.22.input_layernorm.weight": "model-00006-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.o_proj.weight": "model-00007-of-00009.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00007-of-00009.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00007-of-00009.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00007-of-00009.safetensors", "model.layers.21.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.o_proj.weight": "model-00007-of-00009.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00007-of-00009.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00007-of-00009.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00007-of-00009.safetensors", "model.layers.20.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.o_proj.weight": "model-00007-of-00009.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00007-of-00009.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00007-of-00009.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00007-of-00009.safetensors", "model.layers.19.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-00008-of-00009.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00008-of-00009.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00008-of-00009.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00008-of-00009.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00008-of-00009.safetensors", "model.layers.18.input_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00008-of-00009.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00008-of-00009.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00008-of-00009.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00008-of-00009.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00008-of-00009.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00008-of-00009.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00008-of-00009.safetensors", "model.layers.17.input_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00008-of-00009.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00008-of-00009.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00008-of-00009.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00008-of-00009.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00008-of-00009.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00008-of-00009.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00008-of-00009.safetensors", "model.layers.16.input_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00008-of-00009.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00008-of-00009.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00008-of-00009.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.15.input_layernorm.weight": "model-00008-of-00009.safetensors", "model.norm.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-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.o_proj.weight": "model-00009-of-00009.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00009-of-00009.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00009-of-00009.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00009-of-00009.safetensors", "model.layers.27.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.o_proj.weight": "model-00009-of-00009.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00009-of-00009.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00009-of-00009.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00009-of-00009.safetensors", "model.layers.26.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.o_proj.weight": "model-00009-of-00009.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00009-of-00009.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00009-of-00009.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00009-of-00009.safetensors", "model.layers.25.input_layernorm.weight": "model-00009-of-00009.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00009-of-00009.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00009-of-00009.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00009-of-00009.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00009-of-00009.safetensors", "model.layers.24.input_layernorm.weight": "model-00009-of-00009.safetensors"}} \ No newline at end of file diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..fa665d5 --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,34 @@ +{ + "additional_special_tokens": [ + "<|im_start|>", + "<|im_end|>" + ], + "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..4486ab3 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:22449cb9ef4bad0db7dd93b46ddff7ab7d6a654dd4f903e130ddb6361eac3af5 +size 17477473 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..3208450 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,70 @@ +{ + "add_bos_token": false, + "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": "<|im_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "107": { + "content": "<|im_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "additional_special_tokens": [ + "<|im_start|>", + "<|im_end|>" + ], + "bos_token": "", + "chat_template": "{% if messages[0]['role'] == 'user' or messages[0]['role'] == 'system' %}{{ bos_token }}{% endif %}{% for message in messages %}{{ '<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n' }}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% elif messages[-1]['role'] == 'assistant' %}{{ eos_token }}{% endif %}", + "clean_up_tokenization_spaces": false, + "eos_token": "", + "legacy": null, + "model_max_length": 2048, + "pad_token": "", + "sp_model_kwargs": {}, + "spaces_between_special_tokens": false, + "tokenizer_class": "GemmaTokenizer", + "unk_token": "", + "use_default_system_prompt": false +}