commit 3162bee503d5b1c0a6f6b95c809ff881b303c0b1 Author: ModelHub XC Date: Wed May 6 10:46:41 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: ND911/Mistralv0.2-Erosumikav2-Franken-Sonya-10.5B Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..e17c8f3 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,50 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bin.* filter=lfs diff=lfs merge=lfs -text +*.bz2 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 +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack 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 +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +saved_model/**/* 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 +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zstandard filter=lfs diff=lfs merge=lfs -text +*.tfevents* filter=lfs diff=lfs merge=lfs -text +*.db* filter=lfs diff=lfs merge=lfs -text +*.ark* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.gguf* filter=lfs diff=lfs merge=lfs -text +*.ggml filter=lfs diff=lfs merge=lfs -text +*.llamafile* filter=lfs diff=lfs merge=lfs -text +*.pt2 filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text + +mefs.png filter=lfs diff=lfs merge=lfs -text +tokenizer.json filter=lfs diff=lfs merge=lfs -text \ No newline at end of file diff --git a/README.md b/README.md new file mode 100644 index 0000000..2130399 --- /dev/null +++ b/README.md @@ -0,0 +1,50 @@ +--- +base_model: [] +library_name: transformers +tags: +- mergekit +- merge +- not-for-all-audiences +--- + +![](mefs.png) + +# Mistralv0.2-Erosumikav2-Franken-Sonya-10.5B + +This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit). + +## Merge Details + +See Below + +### Merge Method + +This model was merged using the passthrough merge method. + +### Models Merged + +The following models were included in the merge: +* Franken-Sonya +* Erosumika-7B-v2 +* Mistral-7B-Instruct-v0.2 + +### Configuration + +The following YAML configuration was used to produce this model: + +```yaml +slices: + - sources: + - model: "Franken-Sonya" + layer_range: [0, 16] + - sources: + - model: "Erosumika-7B-v2" + layer_range: [8, 24] + - sources: + - model: "Mistral-7B-Instruct-v0.2" + layer_range: [17, 32] + +merge_method: passthrough +dtype: float16 + +``` \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..0088837 --- /dev/null +++ b/config.json @@ -0,0 +1,26 @@ +{ + "_name_or_path": "Franken-Sonya", + "architectures": [ + "MistralForCausalLM" + ], + "attention_dropout": 0.0, + "bos_token_id": 1, + "eos_token_id": 2, + "hidden_act": "silu", + "hidden_size": 4096, + "initializer_range": 0.02, + "intermediate_size": 14336, + "max_position_embeddings": 8192, + "model_type": "mistral", + "num_attention_heads": 32, + "num_hidden_layers": 47, + "num_key_value_heads": 8, + "rms_norm_eps": 1e-05, + "rope_theta": 10000.0, + "sliding_window": 4096, + "tie_word_embeddings": false, + "torch_dtype": "float16", + "transformers_version": "4.38.2", + "use_cache": true, + "vocab_size": 32000 +} 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/mefs.png b/mefs.png new file mode 100644 index 0000000..2891f2c --- /dev/null +++ b/mefs.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b8ad890c1e4c12dab1416c537cb0c08fc7ddf6a7b6f12ba6d94bf783957b63f5 +size 2230820 diff --git a/mergekit_config.yml b/mergekit_config.yml new file mode 100644 index 0000000..c4da513 --- /dev/null +++ b/mergekit_config.yml @@ -0,0 +1,13 @@ +slices: + - sources: + - model: "Franken-Sonya" + layer_range: [0, 16] + - sources: + - model: "Erosumika-7B-v2" + layer_range: [8, 24] + - sources: + - model: "Mistral-7B-Instruct-v0.2" + layer_range: [17, 32] + +merge_method: passthrough +dtype: float16 diff --git a/model-00001-of-00011.safetensors b/model-00001-of-00011.safetensors new file mode 100644 index 0000000..824f5ba --- /dev/null +++ b/model-00001-of-00011.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f98ff95648f5b922ac0628b76dedb64b777b16ac33ee79862f16fb8a86597b2a +size 1946210728 diff --git a/model-00002-of-00011.safetensors b/model-00002-of-00011.safetensors new file mode 100644 index 0000000..2cd9cc0 --- /dev/null +++ b/model-00002-of-00011.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a4a1e594135ee7c30119b71a2a3fac19e068aff3ec56683d2b7bb97fa74bd56 +size 1996567632 diff --git a/model-00003-of-00011.safetensors b/model-00003-of-00011.safetensors new file mode 100644 index 0000000..2841257 --- /dev/null +++ b/model-00003-of-00011.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a995d737e42ed790fad9a21cb7a16e35a005c5c5ffe54e3094043ae4c768496 +size 1895903640 diff --git a/model-00004-of-00011.safetensors b/model-00004-of-00011.safetensors new file mode 100644 index 0000000..7d32855 --- /dev/null +++ b/model-00004-of-00011.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9d6011b7ff411da33a5e1c3c9f431098a24c2a1fb5d0df218e1c14cc3821b3b3 +size 1979789736 diff --git a/model-00005-of-00011.safetensors b/model-00005-of-00011.safetensors new file mode 100644 index 0000000..4c4ee53 --- /dev/null +++ b/model-00005-of-00011.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3708e4f72c4526726ddfb7c75da466e6527c5797680ba366c9bc8556fc839782 +size 1946252248 diff --git a/model-00006-of-00011.safetensors b/model-00006-of-00011.safetensors new file mode 100644 index 0000000..aaa34d3 --- /dev/null +++ b/model-00006-of-00011.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b15fc0ea45011893d19f7513d5a85a5973da8cbd0bdc968ede83beb9b7aff87f +size 1923157704 diff --git a/model-00007-of-00011.safetensors b/model-00007-of-00011.safetensors new file mode 100644 index 0000000..fce10e6 --- /dev/null +++ b/model-00007-of-00011.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c1bb96b5c076e18ce3ddeaf6c9b7c0fe71ce1122418c1aae42f4fb88785b0068 +size 1979781432 diff --git a/model-00008-of-00011.safetensors b/model-00008-of-00011.safetensors new file mode 100644 index 0000000..1a0f840 --- /dev/null +++ b/model-00008-of-00011.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d7b291b7da28f31d2c315223e3d8a99ee77f2c2be692798484a5d6b5f589599 +size 1979806328 diff --git a/model-00009-of-00011.safetensors b/model-00009-of-00011.safetensors new file mode 100644 index 0000000..359b4f9 --- /dev/null +++ b/model-00009-of-00011.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c4e118953c1bb7b64ac7e3dcdb891266e7bc42ba3fd818d46c5b895a933a905 +size 1979789696 diff --git a/model-00010-of-00011.safetensors b/model-00010-of-00011.safetensors new file mode 100644 index 0000000..a650718 --- /dev/null +++ b/model-00010-of-00011.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be91aa92c03466842eefb6565cfd6446d5a4a5c99e8a7bcb42dabc0767157772 +size 1946235600 diff --git a/model-00011-of-00011.safetensors b/model-00011-of-00011.safetensors new file mode 100644 index 0000000..7488bc3 --- /dev/null +++ b/model-00011-of-00011.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fce49365c9948ddfeb5b5c8b7b164402ae1ff183786b789c9818a9dba6441c35 +size 1453378584 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000..ee607ac --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1 @@ +{"metadata": {"mergekit_version": "0.0.4.1"}, "weight_map": {"model.layers.30.self_attn.o_proj.weight": "model-00001-of-00011.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00001-of-00011.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00001-of-00011.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00001-of-00011.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00001-of-00011.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00001-of-00011.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00001-of-00011.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00001-of-00011.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00001-of-00011.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00001-of-00011.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00001-of-00011.safetensors", "model.layers.29.input_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00001-of-00011.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00001-of-00011.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00001-of-00011.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00001-of-00011.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00001-of-00011.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00011.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00011.safetensors", "model.layers.28.input_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00011.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00001-of-00011.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00011.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00011.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00011.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00011.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00001-of-00011.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00011.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00001-of-00011.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00011.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00011.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00011.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00011.safetensors", "model.layers.17.input_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00001-of-00011.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00011.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00002-of-00011.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00011.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00011.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00011.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00011.safetensors", "model.layers.16.input_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00002-of-00011.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00002-of-00011.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00002-of-00011.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00002-of-00011.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00002-of-00011.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00002-of-00011.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00002-of-00011.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00002-of-00011.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00002-of-00011.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00002-of-00011.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00002-of-00011.safetensors", "model.layers.36.input_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00002-of-00011.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00002-of-00011.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00002-of-00011.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00002-of-00011.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00002-of-00011.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00002-of-00011.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00002-of-00011.safetensors", "model.layers.35.input_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00002-of-00011.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00002-of-00011.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00002-of-00011.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00002-of-00011.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00002-of-00011.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00002-of-00011.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00002-of-00011.safetensors", "model.layers.34.input_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00002-of-00011.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00002-of-00011.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00002-of-00011.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00002-of-00011.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00002-of-00011.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00002-of-00011.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00003-of-00011.safetensors", "model.layers.33.input_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00003-of-00011.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00003-of-00011.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00003-of-00011.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00003-of-00011.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00003-of-00011.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00003-of-00011.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00003-of-00011.safetensors", "model.layers.32.input_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00003-of-00011.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00011.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00003-of-00011.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00011.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00011.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00011.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00011.safetensors", "model.layers.27.input_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00003-of-00011.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00011.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00003-of-00011.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00011.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00011.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00011.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00011.safetensors", "model.layers.26.input_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00003-of-00011.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00011.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00003-of-00011.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00011.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00011.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00011.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00011.safetensors", "model.layers.25.input_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00003-of-00011.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00004-of-00011.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00004-of-00011.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00004-of-00011.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00004-of-00011.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00004-of-00011.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00004-of-00011.safetensors", "model.layers.24.input_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00004-of-00011.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00004-of-00011.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00004-of-00011.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00004-of-00011.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00004-of-00011.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00004-of-00011.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00004-of-00011.safetensors", "model.layers.23.input_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00004-of-00011.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00004-of-00011.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00004-of-00011.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00011.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00011.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00011.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00011.safetensors", "model.layers.22.input_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00004-of-00011.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00004-of-00011.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00004-of-00011.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00011.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00011.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00011.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00011.safetensors", "model.layers.21.input_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00004-of-00011.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00004-of-00011.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00004-of-00011.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00011.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00011.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00005-of-00011.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00011.safetensors", "model.layers.20.input_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00005-of-00011.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00005-of-00011.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00005-of-00011.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00011.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00011.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00011.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00011.safetensors", "model.layers.19.input_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00005-of-00011.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.18.input_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00005-of-00011.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00005-of-00011.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00005-of-00011.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00005-of-00011.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00005-of-00011.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00005-of-00011.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00005-of-00011.safetensors", "model.layers.15.input_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00005-of-00011.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00005-of-00011.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00005-of-00011.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00005-of-00011.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00005-of-00011.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00005-of-00011.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00005-of-00011.safetensors", "model.layers.14.input_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00005-of-00011.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00005-of-00011.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00005-of-00011.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00005-of-00011.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00005-of-00011.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00005-of-00011.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00005-of-00011.safetensors", "model.layers.13.input_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00006-of-00011.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00006-of-00011.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00006-of-00011.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00006-of-00011.safetensors", "lm_head.weight": "model-00006-of-00011.safetensors", "model.norm.weight": "model-00006-of-00011.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00006-of-00011.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00006-of-00011.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00006-of-00011.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00006-of-00011.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00006-of-00011.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00006-of-00011.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00006-of-00011.safetensors", "model.layers.46.input_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00006-of-00011.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00006-of-00011.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00006-of-00011.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00006-of-00011.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00006-of-00011.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00006-of-00011.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00006-of-00011.safetensors", "model.layers.45.input_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00006-of-00011.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00006-of-00011.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00006-of-00011.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00006-of-00011.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00006-of-00011.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00006-of-00011.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00006-of-00011.safetensors", "model.layers.44.input_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00007-of-00011.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00007-of-00011.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00007-of-00011.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00007-of-00011.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00007-of-00011.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00007-of-00011.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00007-of-00011.safetensors", "model.layers.43.input_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00007-of-00011.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00007-of-00011.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00007-of-00011.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00007-of-00011.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00007-of-00011.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00007-of-00011.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00007-of-00011.safetensors", "model.layers.42.input_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00007-of-00011.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00007-of-00011.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00007-of-00011.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00007-of-00011.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00007-of-00011.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00007-of-00011.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00007-of-00011.safetensors", "model.layers.41.input_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00007-of-00011.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00007-of-00011.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00007-of-00011.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00007-of-00011.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00007-of-00011.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00007-of-00011.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00007-of-00011.safetensors", "model.layers.40.input_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00007-of-00011.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00007-of-00011.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00008-of-00011.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00008-of-00011.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00008-of-00011.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00008-of-00011.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00008-of-00011.safetensors", "model.layers.39.input_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00008-of-00011.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00008-of-00011.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00008-of-00011.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00008-of-00011.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00008-of-00011.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00008-of-00011.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00008-of-00011.safetensors", "model.layers.38.input_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00008-of-00011.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00008-of-00011.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00008-of-00011.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.37.input_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00008-of-00011.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00008-of-00011.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00008-of-00011.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00008-of-00011.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00008-of-00011.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00008-of-00011.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00008-of-00011.safetensors", "model.layers.31.input_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00008-of-00011.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00008-of-00011.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00008-of-00011.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.30.input_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00008-of-00011.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00008-of-00011.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00008-of-00011.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00008-of-00011.safetensors", "model.layers.12.input_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00008-of-00011.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00009-of-00011.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00009-of-00011.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00009-of-00011.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00009-of-00011.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00009-of-00011.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00009-of-00011.safetensors", "model.layers.11.input_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00009-of-00011.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00009-of-00011.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00009-of-00011.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00009-of-00011.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00009-of-00011.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00009-of-00011.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00009-of-00011.safetensors", "model.layers.10.input_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00009-of-00011.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00009-of-00011.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00009-of-00011.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00009-of-00011.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00009-of-00011.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00009-of-00011.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00009-of-00011.safetensors", "model.layers.9.input_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00009-of-00011.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00009-of-00011.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00009-of-00011.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00009-of-00011.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00009-of-00011.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00009-of-00011.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00009-of-00011.safetensors", "model.layers.8.input_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00009-of-00011.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00009-of-00011.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00009-of-00011.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00010-of-00011.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.7.input_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00010-of-00011.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00010-of-00011.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00010-of-00011.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00010-of-00011.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.6.input_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00010-of-00011.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00010-of-00011.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00010-of-00011.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00010-of-00011.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.5.input_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00010-of-00011.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00010-of-00011.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00010-of-00011.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00010-of-00011.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.4.input_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00010-of-00011.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00010-of-00011.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00010-of-00011.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00010-of-00011.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.3.input_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00010-of-00011.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00011-of-00011.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00011-of-00011.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00011-of-00011.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00011-of-00011.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00011-of-00011.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00011-of-00011.safetensors", "model.layers.2.input_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00011-of-00011.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00011-of-00011.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00011-of-00011.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00011-of-00011.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00011-of-00011.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00011-of-00011.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00011-of-00011.safetensors", "model.layers.1.input_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00011-of-00011.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00011-of-00011.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00011-of-00011.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00011-of-00011.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00011-of-00011.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00011-of-00011.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00011-of-00011.safetensors", "model.layers.0.input_layernorm.weight": "model-00011-of-00011.safetensors", "model.embed_tokens.weight": "model-00011-of-00011.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..451134b --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,23 @@ +{ + "bos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_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..61607de --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fc4f0bd70b3709312d9d1d9e5ba674794b6bc5abc17429897a540f93882f25fc +size 1795303 diff --git a/tokenizer.model b/tokenizer.model new file mode 100644 index 0000000..8b443ef --- /dev/null +++ b/tokenizer.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055 +size 493443 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..81730cd --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,42 @@ +{ + "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 + } + }, + "additional_special_tokens": [], + "bos_token": "", + "clean_up_tokenization_spaces": false, + "eos_token": "", + "legacy": true, + "model_max_length": 1000000000000000019884624838656, + "pad_token": null, + "sp_model_kwargs": {}, + "spaces_between_special_tokens": false, + "tokenizer_class": "LlamaTokenizer", + "unk_token": "", + "use_default_system_prompt": false +}