commit e0cd6b179b7c8fd8797b93d4d9390a4c495a07b1 Author: ModelHub XC Date: Wed Jun 3 09:06:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: pkupie/lawyer-llama-13b-v2 Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..a6344aa --- /dev/null +++ b/.gitattributes @@ -0,0 +1,35 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..d34a744 --- /dev/null +++ b/README.md @@ -0,0 +1,11 @@ +--- +license: llama2 +language: +- zh +--- + +See details on Github Repo: https://github.com/AndrewZhe/lawyer-llama + +Usage: https://github.com/AndrewZhe/lawyer-llama/blob/main/demo/run_inference_v2.md + +Technical Report: https://arxiv.org/abs/2305.15062 \ No newline at end of file diff --git a/added_tokens.json b/added_tokens.json new file mode 100644 index 0000000..99e6230 --- /dev/null +++ b/added_tokens.json @@ -0,0 +1,3 @@ +{ + "[PAD]": 59672 +} diff --git a/config.json b/config.json new file mode 100644 index 0000000..5aad27d --- /dev/null +++ b/config.json @@ -0,0 +1,24 @@ +{ + "_name_or_path": "/newdisk/lawyer/models/lawyer_llama_v2/zixun_alpaca_1_1_based_on_fakao/checkpoint-1018", + "architectures": [ + "LlamaForCausalLM" + ], + "bos_token_id": 1, + "eos_token_id": 2, + "hidden_act": "silu", + "hidden_size": 5120, + "initializer_range": 0.02, + "intermediate_size": 13824, + "max_position_embeddings": 4096, + "model_type": "llama", + "num_attention_heads": 40, + "num_hidden_layers": 40, + "pad_token_id": 0, + "rms_norm_eps": 1e-06, + "tie_word_embeddings": false, + "tokenizer_class": "LlamaTokenizer", + "torch_dtype": "float16", + "transformers_version": "4.30.0", + "use_cache": false, + "vocab_size": 59673 +} diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..372ef6f --- /dev/null +++ b/generation_config.json @@ -0,0 +1,8 @@ +{ + "_from_model_config": true, + "bos_token_id": 1, + "eos_token_id": 2, + "pad_token_id": 0, + "transformers_version": "4.30.0", + "use_cache": false +} diff --git a/model-00001-of-00014.safetensors b/model-00001-of-00014.safetensors new file mode 100644 index 0000000..79634b6 --- /dev/null +++ b/model-00001-of-00014.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c4026832e22a7007721c7f4de2eb82c90b81e8e236807299dd3b6a036650dc6c +size 2037159096 diff --git a/model-00002-of-00014.safetensors b/model-00002-of-00014.safetensors new file mode 100644 index 0000000..4df40a9 --- /dev/null +++ b/model-00002-of-00014.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a340c39e127b6b0780dda43546a0c4da8fe61520a2d89a1b7f923870c5f516a +size 1955660328 diff --git a/model-00003-of-00014.safetensors b/model-00003-of-00014.safetensors new file mode 100644 index 0000000..ef51651 --- /dev/null +++ b/model-00003-of-00014.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d7560667cf5e2b57215725bd4cc5bc81aa614dbc7138f2d3d94a0e935b1d4647 +size 2044788928 diff --git a/model-00004-of-00014.safetensors b/model-00004-of-00014.safetensors new file mode 100644 index 0000000..9706e83 --- /dev/null +++ b/model-00004-of-00014.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:95b28d25975e3fc7aea45eab69d22582734413aef404e07c0f2f91fcbcccae6c +size 2044788944 diff --git a/model-00005-of-00014.safetensors b/model-00005-of-00014.safetensors new file mode 100644 index 0000000..9edd8b7 --- /dev/null +++ b/model-00005-of-00014.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:18db8ddbb98ae7bb3985e396d97d0ef22acfd10cf36727e01eedf77787278832 +size 2044809664 diff --git a/model-00006-of-00014.safetensors b/model-00006-of-00014.safetensors new file mode 100644 index 0000000..3544f09 --- /dev/null +++ b/model-00006-of-00014.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c1d6cbb544ccb85d86ea353af87e4c561a11fcd96eea84df75188b9a35c492cd +size 2008088920 diff --git a/model-00007-of-00014.safetensors b/model-00007-of-00014.safetensors new file mode 100644 index 0000000..a6c337e --- /dev/null +++ b/model-00007-of-00014.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a4699954c9d925280feaecb41da0e09afc8f38c3e66a562ecef058d98ca35fd7 +size 2008089280 diff --git a/model-00008-of-00014.safetensors b/model-00008-of-00014.safetensors new file mode 100644 index 0000000..0fc5b04 --- /dev/null +++ b/model-00008-of-00014.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:29e8530eaa6db5d78b3b46c020a5cc932698ccc154ae5f1f386988f41a752465 +size 2044788960 diff --git a/model-00009-of-00014.safetensors b/model-00009-of-00014.safetensors new file mode 100644 index 0000000..bfb5fce --- /dev/null +++ b/model-00009-of-00014.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8de26fc34f07162bb8fc750b263ca44813cc34144c89c370aa0f72d57c708577 +size 2044788952 diff --git a/model-00010-of-00014.safetensors b/model-00010-of-00014.safetensors new file mode 100644 index 0000000..103dd23 --- /dev/null +++ b/model-00010-of-00014.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:78dd9349b6f621607084ac8e5ea61222df45866e463272048acfdcb1c1c9e91c +size 2044809664 diff --git a/model-00011-of-00014.safetensors b/model-00011-of-00014.safetensors new file mode 100644 index 0000000..9fea6ec --- /dev/null +++ b/model-00011-of-00014.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6649fe8955ce2ccbeb4750eac8c49a43d15bc8b8c3733795ed29e081c5d780a2 +size 2008088920 diff --git a/model-00012-of-00014.safetensors b/model-00012-of-00014.safetensors new file mode 100644 index 0000000..4732698 --- /dev/null +++ b/model-00012-of-00014.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d385aa27eb2dd444d015f5cc2320f9496654a106b7ace0744de20b4f74919a19 +size 2008089280 diff --git a/model-00013-of-00014.safetensors b/model-00013-of-00014.safetensors new file mode 100644 index 0000000..56f7aa9 --- /dev/null +++ b/model-00013-of-00014.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:efb38a14e35e52a04dd4709f91cc4c3a280b2ad1131f7c26369eee446d0e698a +size 1693525384 diff --git a/model-00014-of-00014.safetensors b/model-00014-of-00014.safetensors new file mode 100644 index 0000000..58737d8 --- /dev/null +++ b/model-00014-of-00014.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef1b07b6ace1ea75d27636eeeb5043a8e3eb1f16ead6b3cecd8d906a007fa6d6 +size 611051648 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000..5973059 --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,410 @@ +{ + "metadata": { + "total_size": 26598481920 + }, + "weight_map": { + "lm_head.weight": "model-00014-of-00014.safetensors", + "model.embed_tokens.weight": "model-00001-of-00014.safetensors", + "model.layers.0.input_layernorm.weight": "model-00001-of-00014.safetensors", + "model.layers.0.mlp.down_proj.weight": "model-00001-of-00014.safetensors", + "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00014.safetensors", + "model.layers.0.mlp.up_proj.weight": "model-00001-of-00014.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00014.safetensors", + "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00014.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00014.safetensors", + "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00014.safetensors", + "model.layers.0.self_attn.rotary_emb.inv_freq": "model-00001-of-00014.safetensors", + "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00014.safetensors", + "model.layers.1.input_layernorm.weight": "model-00001-of-00014.safetensors", + "model.layers.1.mlp.down_proj.weight": "model-00001-of-00014.safetensors", + "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00014.safetensors", + "model.layers.1.mlp.up_proj.weight": "model-00001-of-00014.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00014.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00014.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00014.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00014.safetensors", + "model.layers.1.self_attn.rotary_emb.inv_freq": "model-00001-of-00014.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00014.safetensors", + "model.layers.10.input_layernorm.weight": "model-00004-of-00014.safetensors", + "model.layers.10.mlp.down_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.10.mlp.gate_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.10.mlp.up_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00004-of-00014.safetensors", + "model.layers.10.self_attn.k_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.10.self_attn.rotary_emb.inv_freq": "model-00004-of-00014.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.11.input_layernorm.weight": "model-00005-of-00014.safetensors", + "model.layers.11.mlp.down_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.11.mlp.gate_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.11.mlp.up_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00005-of-00014.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.11.self_attn.rotary_emb.inv_freq": "model-00004-of-00014.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.12.input_layernorm.weight": "model-00005-of-00014.safetensors", + "model.layers.12.mlp.down_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.12.mlp.gate_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.12.mlp.up_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00005-of-00014.safetensors", + "model.layers.12.self_attn.k_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.12.self_attn.rotary_emb.inv_freq": "model-00005-of-00014.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.13.input_layernorm.weight": "model-00005-of-00014.safetensors", + "model.layers.13.mlp.down_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.13.mlp.gate_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.13.mlp.up_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00005-of-00014.safetensors", + "model.layers.13.self_attn.k_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.13.self_attn.rotary_emb.inv_freq": "model-00005-of-00014.safetensors", + "model.layers.13.self_attn.v_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.14.input_layernorm.weight": "model-00005-of-00014.safetensors", + "model.layers.14.mlp.down_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.14.mlp.gate_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.14.mlp.up_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00005-of-00014.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.14.self_attn.rotary_emb.inv_freq": "model-00005-of-00014.safetensors", + "model.layers.14.self_attn.v_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.15.input_layernorm.weight": "model-00006-of-00014.safetensors", + "model.layers.15.mlp.down_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.15.mlp.gate_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.15.mlp.up_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00006-of-00014.safetensors", + "model.layers.15.self_attn.k_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.15.self_attn.q_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.15.self_attn.rotary_emb.inv_freq": "model-00006-of-00014.safetensors", + "model.layers.15.self_attn.v_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.16.input_layernorm.weight": "model-00006-of-00014.safetensors", + "model.layers.16.mlp.down_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.16.mlp.gate_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.16.mlp.up_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00006-of-00014.safetensors", + "model.layers.16.self_attn.k_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.16.self_attn.q_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.16.self_attn.rotary_emb.inv_freq": "model-00006-of-00014.safetensors", + "model.layers.16.self_attn.v_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.17.input_layernorm.weight": "model-00006-of-00014.safetensors", + "model.layers.17.mlp.down_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.17.mlp.gate_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.17.mlp.up_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00006-of-00014.safetensors", + "model.layers.17.self_attn.k_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.17.self_attn.q_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.17.self_attn.rotary_emb.inv_freq": "model-00006-of-00014.safetensors", + "model.layers.17.self_attn.v_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.18.input_layernorm.weight": "model-00007-of-00014.safetensors", + "model.layers.18.mlp.down_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.18.mlp.gate_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.18.mlp.up_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00007-of-00014.safetensors", + "model.layers.18.self_attn.k_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.18.self_attn.q_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.18.self_attn.rotary_emb.inv_freq": "model-00007-of-00014.safetensors", + "model.layers.18.self_attn.v_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.19.input_layernorm.weight": "model-00007-of-00014.safetensors", + "model.layers.19.mlp.down_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.19.mlp.gate_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.19.mlp.up_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00007-of-00014.safetensors", + "model.layers.19.self_attn.k_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.19.self_attn.q_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.19.self_attn.rotary_emb.inv_freq": "model-00007-of-00014.safetensors", + "model.layers.19.self_attn.v_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.2.input_layernorm.weight": "model-00002-of-00014.safetensors", + "model.layers.2.mlp.down_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.2.mlp.gate_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.2.mlp.up_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00014.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00014.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00014.safetensors", + "model.layers.2.self_attn.rotary_emb.inv_freq": "model-00002-of-00014.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00014.safetensors", + "model.layers.20.input_layernorm.weight": "model-00007-of-00014.safetensors", + "model.layers.20.mlp.down_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.20.mlp.gate_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.20.mlp.up_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00007-of-00014.safetensors", + "model.layers.20.self_attn.k_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.20.self_attn.q_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.20.self_attn.rotary_emb.inv_freq": "model-00007-of-00014.safetensors", + "model.layers.20.self_attn.v_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.21.input_layernorm.weight": "model-00008-of-00014.safetensors", + "model.layers.21.mlp.down_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.21.mlp.gate_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.21.mlp.up_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00008-of-00014.safetensors", + "model.layers.21.self_attn.k_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.21.self_attn.q_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.21.self_attn.rotary_emb.inv_freq": "model-00007-of-00014.safetensors", + "model.layers.21.self_attn.v_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.22.input_layernorm.weight": "model-00008-of-00014.safetensors", + "model.layers.22.mlp.down_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.22.mlp.gate_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.22.mlp.up_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00008-of-00014.safetensors", + "model.layers.22.self_attn.k_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.22.self_attn.q_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.22.self_attn.rotary_emb.inv_freq": "model-00008-of-00014.safetensors", + "model.layers.22.self_attn.v_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.23.input_layernorm.weight": "model-00008-of-00014.safetensors", + "model.layers.23.mlp.down_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.23.mlp.gate_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.23.mlp.up_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00008-of-00014.safetensors", + "model.layers.23.self_attn.k_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.23.self_attn.q_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.23.self_attn.rotary_emb.inv_freq": "model-00008-of-00014.safetensors", + "model.layers.23.self_attn.v_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.24.input_layernorm.weight": "model-00009-of-00014.safetensors", + "model.layers.24.mlp.down_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.24.mlp.gate_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.24.mlp.up_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00009-of-00014.safetensors", + "model.layers.24.self_attn.k_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.24.self_attn.o_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.24.self_attn.q_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.24.self_attn.rotary_emb.inv_freq": "model-00008-of-00014.safetensors", + "model.layers.24.self_attn.v_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.25.input_layernorm.weight": "model-00009-of-00014.safetensors", + "model.layers.25.mlp.down_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.25.mlp.gate_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.25.mlp.up_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00009-of-00014.safetensors", + "model.layers.25.self_attn.k_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.25.self_attn.o_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.25.self_attn.q_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.25.self_attn.rotary_emb.inv_freq": "model-00009-of-00014.safetensors", + "model.layers.25.self_attn.v_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.26.input_layernorm.weight": "model-00009-of-00014.safetensors", + "model.layers.26.mlp.down_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.26.mlp.gate_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.26.mlp.up_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00009-of-00014.safetensors", + "model.layers.26.self_attn.k_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.26.self_attn.o_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.26.self_attn.q_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.26.self_attn.rotary_emb.inv_freq": "model-00009-of-00014.safetensors", + "model.layers.26.self_attn.v_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.27.input_layernorm.weight": "model-00010-of-00014.safetensors", + "model.layers.27.mlp.down_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.27.mlp.gate_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.27.mlp.up_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00010-of-00014.safetensors", + "model.layers.27.self_attn.k_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.27.self_attn.o_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.27.self_attn.q_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.27.self_attn.rotary_emb.inv_freq": "model-00009-of-00014.safetensors", + "model.layers.27.self_attn.v_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.28.input_layernorm.weight": "model-00010-of-00014.safetensors", + "model.layers.28.mlp.down_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.28.mlp.gate_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.28.mlp.up_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.28.post_attention_layernorm.weight": "model-00010-of-00014.safetensors", + "model.layers.28.self_attn.k_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.28.self_attn.o_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.28.self_attn.q_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.28.self_attn.rotary_emb.inv_freq": "model-00010-of-00014.safetensors", + "model.layers.28.self_attn.v_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.29.input_layernorm.weight": "model-00010-of-00014.safetensors", + "model.layers.29.mlp.down_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.29.mlp.gate_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.29.mlp.up_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.29.post_attention_layernorm.weight": "model-00010-of-00014.safetensors", + "model.layers.29.self_attn.k_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.29.self_attn.o_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.29.self_attn.q_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.29.self_attn.rotary_emb.inv_freq": "model-00010-of-00014.safetensors", + "model.layers.29.self_attn.v_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.3.input_layernorm.weight": "model-00002-of-00014.safetensors", + "model.layers.3.mlp.down_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.3.mlp.up_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00014.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.3.self_attn.rotary_emb.inv_freq": "model-00002-of-00014.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.30.input_layernorm.weight": "model-00010-of-00014.safetensors", + "model.layers.30.mlp.down_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.30.mlp.gate_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.30.mlp.up_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.30.post_attention_layernorm.weight": "model-00010-of-00014.safetensors", + "model.layers.30.self_attn.k_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.30.self_attn.o_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.30.self_attn.q_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.30.self_attn.rotary_emb.inv_freq": "model-00010-of-00014.safetensors", + "model.layers.30.self_attn.v_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.31.input_layernorm.weight": "model-00011-of-00014.safetensors", + "model.layers.31.mlp.down_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.31.mlp.gate_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.31.mlp.up_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.31.post_attention_layernorm.weight": "model-00011-of-00014.safetensors", + "model.layers.31.self_attn.k_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.31.self_attn.o_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.31.self_attn.q_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.31.self_attn.rotary_emb.inv_freq": "model-00011-of-00014.safetensors", + "model.layers.31.self_attn.v_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.32.input_layernorm.weight": "model-00011-of-00014.safetensors", + "model.layers.32.mlp.down_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.32.mlp.gate_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.32.mlp.up_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.32.post_attention_layernorm.weight": "model-00011-of-00014.safetensors", + "model.layers.32.self_attn.k_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.32.self_attn.o_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.32.self_attn.q_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.32.self_attn.rotary_emb.inv_freq": "model-00011-of-00014.safetensors", + "model.layers.32.self_attn.v_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.33.input_layernorm.weight": "model-00011-of-00014.safetensors", + "model.layers.33.mlp.down_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.33.mlp.gate_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.33.mlp.up_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.33.post_attention_layernorm.weight": "model-00011-of-00014.safetensors", + "model.layers.33.self_attn.k_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.33.self_attn.o_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.33.self_attn.q_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.33.self_attn.rotary_emb.inv_freq": "model-00011-of-00014.safetensors", + "model.layers.33.self_attn.v_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.34.input_layernorm.weight": "model-00012-of-00014.safetensors", + "model.layers.34.mlp.down_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.34.mlp.gate_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.34.mlp.up_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.34.post_attention_layernorm.weight": "model-00012-of-00014.safetensors", + "model.layers.34.self_attn.k_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.34.self_attn.o_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.34.self_attn.q_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.34.self_attn.rotary_emb.inv_freq": "model-00012-of-00014.safetensors", + "model.layers.34.self_attn.v_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.35.input_layernorm.weight": "model-00012-of-00014.safetensors", + "model.layers.35.mlp.down_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.35.mlp.gate_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.35.mlp.up_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.35.post_attention_layernorm.weight": "model-00012-of-00014.safetensors", + "model.layers.35.self_attn.k_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.35.self_attn.o_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.35.self_attn.q_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.35.self_attn.rotary_emb.inv_freq": "model-00012-of-00014.safetensors", + "model.layers.35.self_attn.v_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.36.input_layernorm.weight": "model-00012-of-00014.safetensors", + "model.layers.36.mlp.down_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.36.mlp.gate_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.36.mlp.up_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.36.post_attention_layernorm.weight": "model-00012-of-00014.safetensors", + "model.layers.36.self_attn.k_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.36.self_attn.o_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.36.self_attn.q_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.36.self_attn.rotary_emb.inv_freq": "model-00012-of-00014.safetensors", + "model.layers.36.self_attn.v_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.37.input_layernorm.weight": "model-00013-of-00014.safetensors", + "model.layers.37.mlp.down_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.37.mlp.gate_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.37.mlp.up_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.37.post_attention_layernorm.weight": "model-00013-of-00014.safetensors", + "model.layers.37.self_attn.k_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.37.self_attn.o_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.37.self_attn.q_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.37.self_attn.rotary_emb.inv_freq": "model-00012-of-00014.safetensors", + "model.layers.37.self_attn.v_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.38.input_layernorm.weight": "model-00013-of-00014.safetensors", + "model.layers.38.mlp.down_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.38.mlp.gate_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.38.mlp.up_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.38.post_attention_layernorm.weight": "model-00013-of-00014.safetensors", + "model.layers.38.self_attn.k_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.38.self_attn.o_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.38.self_attn.q_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.38.self_attn.rotary_emb.inv_freq": "model-00013-of-00014.safetensors", + "model.layers.38.self_attn.v_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.39.input_layernorm.weight": "model-00013-of-00014.safetensors", + "model.layers.39.mlp.down_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.39.mlp.gate_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.39.mlp.up_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.39.post_attention_layernorm.weight": "model-00013-of-00014.safetensors", + "model.layers.39.self_attn.k_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.39.self_attn.o_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.39.self_attn.q_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.39.self_attn.rotary_emb.inv_freq": "model-00013-of-00014.safetensors", + "model.layers.39.self_attn.v_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.4.input_layernorm.weight": "model-00002-of-00014.safetensors", + "model.layers.4.mlp.down_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.4.mlp.up_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00014.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.4.self_attn.rotary_emb.inv_freq": "model-00002-of-00014.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.5.input_layernorm.weight": "model-00003-of-00014.safetensors", + "model.layers.5.mlp.down_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.5.mlp.gate_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.5.mlp.up_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00014.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.5.self_attn.rotary_emb.inv_freq": "model-00002-of-00014.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.6.input_layernorm.weight": "model-00003-of-00014.safetensors", + "model.layers.6.mlp.down_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.6.mlp.gate_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.6.mlp.up_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00014.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.6.self_attn.rotary_emb.inv_freq": "model-00003-of-00014.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.7.input_layernorm.weight": "model-00003-of-00014.safetensors", + "model.layers.7.mlp.down_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.7.mlp.gate_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.7.mlp.up_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00014.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.7.self_attn.rotary_emb.inv_freq": "model-00003-of-00014.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.8.input_layernorm.weight": "model-00004-of-00014.safetensors", + "model.layers.8.mlp.down_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.8.mlp.gate_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.8.mlp.up_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00004-of-00014.safetensors", + "model.layers.8.self_attn.k_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.8.self_attn.rotary_emb.inv_freq": "model-00003-of-00014.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.9.input_layernorm.weight": "model-00004-of-00014.safetensors", + "model.layers.9.mlp.down_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.9.mlp.gate_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.9.mlp.up_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00004-of-00014.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.9.self_attn.rotary_emb.inv_freq": "model-00004-of-00014.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model-00004-of-00014.safetensors", + "model.norm.weight": "model-00013-of-00014.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..318f913 --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,6 @@ +{ + "bos_token": "", + "eos_token": "", + "pad_token": "[PAD]", + "unk_token": "" +} diff --git a/tokenizer.model b/tokenizer.model new file mode 100644 index 0000000..ed527f5 --- /dev/null +++ b/tokenizer.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ebae33be1f90dc82a0858b2b31b505b39447c92feb8c9099963e711030ed78f2 +size 866293 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..3dbd131 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,34 @@ +{ + "add_bos_token": true, + "add_eos_token": false, + "bos_token": { + "__type": "AddedToken", + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false + }, + "clean_up_tokenization_spaces": false, + "eos_token": { + "__type": "AddedToken", + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false + }, + "model_max_length": 512, + "pad_token": null, + "padding_side": "right", + "sp_model_kwargs": {}, + "tokenizer_class": "LlamaTokenizer", + "unk_token": { + "__type": "AddedToken", + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false + } +}