commit 7b948bb70d3777e8cb087ebd953e388d8652ff56 Author: ModelHub XC Date: Wed May 13 23:19:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: maywell/Mini_Synatra_SFT Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..094d034 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,54 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow 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 + +*.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 + +pytorch_model-00003-of-00004.bin filter=lfs diff=lfs merge=lfs -text +tokenizer.model filter=lfs diff=lfs merge=lfs -text +pytorch_model-00004-of-00004.bin filter=lfs diff=lfs merge=lfs -text +pytorch_model-00001-of-00004.bin filter=lfs diff=lfs merge=lfs -text +tokenizer.json filter=lfs diff=lfs merge=lfs -text +pytorch_model-00002-of-00004.bin 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..5501fce --- /dev/null +++ b/README.md @@ -0,0 +1,27 @@ +--- +language: +- ko + +library_name: transformers +pipeline_tag: text-generation +license: cc-by-sa-4.0 +--- + +# **Mini_Synatra_SFT🐧** + +## Support Me +시나트라는 개인 프로젝트로, 1인의 자원으로 개발되고 있습니다. 모델이 마음에 드셨다면 약간의 연구비 지원은 어떨까요? +[Buy me a Coffee](https://www.buymeacoffee.com/mwell) + +Wanna be a sponser? Contact me on Telegram **AlzarTakkarsen** + +# **Model Details** +**Base Model** +[Minirecord/Mini_synatra_7b_02](https://huggingface.co/Minirecord/Mini_synatra_7b_02) + +**Trained On** +A100 80GB * 1 + +**Instruction format** + +It follows [ChatML](https://github.com/openai/openai-python/blob/main/chatml.md) format. \ No newline at end of file diff --git a/added_tokens.json b/added_tokens.json new file mode 100644 index 0000000..e36863d --- /dev/null +++ b/added_tokens.json @@ -0,0 +1,4 @@ +{ + "<|im_end|>": 32000, + "<|im_start|>": 32001 +} diff --git a/config.json b/config.json new file mode 100644 index 0000000..8643a14 --- /dev/null +++ b/config.json @@ -0,0 +1,25 @@ +{ + "_name_or_path": "maywell/Mini_Synatra_SFT", + "architectures": [ + "MistralForCausalLM" + ], + "bos_token_id": 1, + "eos_token_id": 32000, + "hidden_act": "silu", + "hidden_size": 4096, + "initializer_range": 0.02, + "intermediate_size": 14336, + "max_position_embeddings": 32768, + "model_type": "mistral", + "num_attention_heads": 32, + "num_hidden_layers": 32, + "num_key_value_heads": 8, + "rms_norm_eps": 1e-05, + "rope_theta": 10000.0, + "sliding_window": 4096, + "tie_word_embeddings": false, + "torch_dtype": "bfloat16", + "transformers_version": "4.35.1", + "use_cache": false, + "vocab_size": 32002 +} 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/generation_config.json b/generation_config.json new file mode 100644 index 0000000..4f4169f --- /dev/null +++ b/generation_config.json @@ -0,0 +1,7 @@ +{ + "_from_model_config": true, + "bos_token_id": 1, + "eos_token_id": 32000, + "transformers_version": "4.35.1", + "use_cache": false +} diff --git a/pytorch_model-00001-of-00004.bin b/pytorch_model-00001-of-00004.bin new file mode 100644 index 0000000..d95e6a5 --- /dev/null +++ b/pytorch_model-00001-of-00004.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:71f78920795a92c02b0bf669c8d4d06c4ac87bcb10fbb8058e4853dc8999ba8e +size 4970644137 diff --git a/pytorch_model-00002-of-00004.bin b/pytorch_model-00002-of-00004.bin new file mode 100644 index 0000000..dd07aac --- /dev/null +++ b/pytorch_model-00002-of-00004.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c5f5c13e4c89d144ca3829479aab5c944eb18b732e07333501c24021a75011f +size 4916119907 diff --git a/pytorch_model-00003-of-00004.bin b/pytorch_model-00003-of-00004.bin new file mode 100644 index 0000000..4e9d405 --- /dev/null +++ b/pytorch_model-00003-of-00004.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e25d7d9397e51ae0898edf82fd6d48061901d046a1ed318037b363c544ca343e +size 4597367373 diff --git a/pytorch_model-00004-of-00004.bin b/pytorch_model-00004-of-00004.bin new file mode 100644 index 0000000..86fa297 --- /dev/null +++ b/pytorch_model-00004-of-00004.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eaef80fe62b8154b8842faeabb55fc046f38b36b846ea05cb3879629e2222e7f +size 524321706 diff --git a/pytorch_model.bin.index.json b/pytorch_model.bin.index.json new file mode 100644 index 0000000..a906f63 --- /dev/null +++ b/pytorch_model.bin.index.json @@ -0,0 +1,298 @@ +{ + "metadata": { + "total_size": 15008350208 + }, + "weight_map": { + "lm_head.weight": "pytorch_model-00004-of-00004.bin", + "model.embed_tokens.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.10.input_layernorm.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.10.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.10.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.11.input_layernorm.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.11.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.11.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.12.input_layernorm.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.12.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.12.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.13.input_layernorm.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.13.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.13.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.14.input_layernorm.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.14.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.14.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.15.input_layernorm.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.15.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.15.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.16.input_layernorm.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.16.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.16.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.17.input_layernorm.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.17.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.17.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.18.input_layernorm.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.18.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.18.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.19.input_layernorm.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.19.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.19.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.20.input_layernorm.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.20.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.20.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.21.input_layernorm.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.21.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.21.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.22.input_layernorm.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.22.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.22.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.23.input_layernorm.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.23.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.23.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.24.input_layernorm.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.24.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.24.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.25.input_layernorm.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.25.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.25.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.26.input_layernorm.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.26.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.26.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.27.input_layernorm.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.27.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.27.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.28.input_layernorm.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.28.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.28.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.29.input_layernorm.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.29.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.29.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.30.input_layernorm.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.30.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.30.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.31.input_layernorm.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.31.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.31.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.norm.weight": "pytorch_model-00003-of-00004.bin" + } +} diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..eea7942 --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,35 @@ +{ + "additional_special_tokens": [ + "", + "", + "" + ], + "bos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "<|im_end|>", + "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..bc4ac00 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6af1053883a8321feeb320cf42c61eb4ced06511f6a2546d9a879e0c0def91e6 +size 1795678 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..1548b24 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,65 @@ +{ + "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 + }, + "32000": { + "content": "<|im_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32001": { + "content": "<|im_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + } + }, + "additional_special_tokens": [ + "", + "", + "" + ], + "bos_token": "", + "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}", + "clean_up_tokenization_spaces": false, + "eos_token": "<|im_end|>", + "legacy": true, + "model_max_length": 1000000000000000019884624838656, + "pad_token": "", + "sp_model_kwargs": {}, + "spaces_between_special_tokens": false, + "tokenizer_class": "LlamaTokenizer", + "trust_remote_code": false, + "unk_token": "", + "use_default_system_prompt": true, + "use_fast": true +}