commit 34bcc9de89018533862961cbd54eff198effe6a9 Author: ModelHub XC Date: Thu Jul 2 22:54:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: vihangd/smartyplats-3b-v1 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..154df82 --- /dev/null +++ b/README.md @@ -0,0 +1,3 @@ +--- +license: apache-2.0 +--- diff --git a/config.json b/config.json new file mode 100644 index 0000000..1cec8e2 --- /dev/null +++ b/config.json @@ -0,0 +1,26 @@ +{ + "_name_or_path": "openlm-research/open_llama_3b_v2", + "architectures": [ + "LlamaForCausalLM" + ], + "bos_token_id": 1, + "eos_token_id": 2, + "hidden_act": "silu", + "hidden_size": 3200, + "initializer_range": 0.02, + "intermediate_size": 8640, + "max_position_embeddings": 2048, + "model_type": "llama", + "num_attention_heads": 32, + "num_hidden_layers": 26, + "num_key_value_heads": 32, + "pad_token_id": 0, + "pretraining_tp": 1, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "tie_word_embeddings": false, + "torch_dtype": "float16", + "transformers_version": "4.31.0", + "use_cache": true, + "vocab_size": 32000 +} diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..2b10330 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,7 @@ +{ + "_from_model_config": true, + "bos_token_id": 1, + "eos_token_id": 2, + "pad_token_id": 0, + "transformers_version": "4.31.0" +} diff --git a/pytorch_model-00001-of-00019.bin b/pytorch_model-00001-of-00019.bin new file mode 100644 index 0000000..2d56e8e --- /dev/null +++ b/pytorch_model-00001-of-00019.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b2b1da8c25d03ebf25c042bf846f78c240afb19a63808b147d326401fc01a1b1 +size 397315297 diff --git a/pytorch_model-00002-of-00019.bin b/pytorch_model-00002-of-00019.bin new file mode 100644 index 0000000..1c03951 --- /dev/null +++ b/pytorch_model-00002-of-00019.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7cbb9ffea0e1be866fa7af25a8488c9f61e8024d5472039bd5f4df33401f805a +size 385056275 diff --git a/pytorch_model-00003-of-00019.bin b/pytorch_model-00003-of-00019.bin new file mode 100644 index 0000000..dae0d38 --- /dev/null +++ b/pytorch_model-00003-of-00019.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:036a7eb3abf55402824f0f7d125f0d8ccd441f6bf07af880c685d94eb5e37705 +size 358417383 diff --git a/pytorch_model-00004-of-00019.bin b/pytorch_model-00004-of-00019.bin new file mode 100644 index 0000000..dfb38b5 --- /dev/null +++ b/pytorch_model-00004-of-00019.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3651f529931039ddc625c3a469da1543f7b9908c64196c3b7223c03579226323 +size 385056275 diff --git a/pytorch_model-00005-of-00019.bin b/pytorch_model-00005-of-00019.bin new file mode 100644 index 0000000..54b1480 --- /dev/null +++ b/pytorch_model-00005-of-00019.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ee851a16b1627921409c214a0e2f7c3da37d06d2fdf2097209f31bf9bd3b3539 +size 358417383 diff --git a/pytorch_model-00006-of-00019.bin b/pytorch_model-00006-of-00019.bin new file mode 100644 index 0000000..a73550d --- /dev/null +++ b/pytorch_model-00006-of-00019.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:86937e59e637196fc4ecf1aee9c61c0620dc3e986eaeeca7e3fbe0840cb8e125 +size 385056275 diff --git a/pytorch_model-00007-of-00019.bin b/pytorch_model-00007-of-00019.bin new file mode 100644 index 0000000..14ab85c --- /dev/null +++ b/pytorch_model-00007-of-00019.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6dfe9c453ba8e9df3069e2ecea620401a2404c4b5f610cec80b96550cb85c813 +size 358417383 diff --git a/pytorch_model-00008-of-00019.bin b/pytorch_model-00008-of-00019.bin new file mode 100644 index 0000000..f9bc566 --- /dev/null +++ b/pytorch_model-00008-of-00019.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:803716ddec8b10880333fa15ecc4235163efa60e87ad6b5dfccfdf012966cadf +size 385056275 diff --git a/pytorch_model-00009-of-00019.bin b/pytorch_model-00009-of-00019.bin new file mode 100644 index 0000000..3a48f18 --- /dev/null +++ b/pytorch_model-00009-of-00019.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:82cef3900db468065dd6950a1620ccb354088259b45c2d28a4779429940a4506 +size 358417383 diff --git a/pytorch_model-00010-of-00019.bin b/pytorch_model-00010-of-00019.bin new file mode 100644 index 0000000..4c13dec --- /dev/null +++ b/pytorch_model-00010-of-00019.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:863c10483db09fb4e45fdf1ac21b0d8fc4e81c065e457b69208240ad5f3f79e6 +size 385056275 diff --git a/pytorch_model-00011-of-00019.bin b/pytorch_model-00011-of-00019.bin new file mode 100644 index 0000000..8faf93d --- /dev/null +++ b/pytorch_model-00011-of-00019.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:73c7ef0c97212090cd67717f22b7804587d84e54ab1b5edc824cedb51acd7728 +size 358417383 diff --git a/pytorch_model-00012-of-00019.bin b/pytorch_model-00012-of-00019.bin new file mode 100644 index 0000000..d3ade42 --- /dev/null +++ b/pytorch_model-00012-of-00019.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d18c0826178e660fb0104dd1f5b99a5b7a9ae19a26f86407873c8e23806faf62 +size 385056275 diff --git a/pytorch_model-00013-of-00019.bin b/pytorch_model-00013-of-00019.bin new file mode 100644 index 0000000..262f52b --- /dev/null +++ b/pytorch_model-00013-of-00019.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:70ad41103a7f9b93e431defe21c0866b18ed1842bc5cc0504bf78b4390068e57 +size 358417383 diff --git a/pytorch_model-00014-of-00019.bin b/pytorch_model-00014-of-00019.bin new file mode 100644 index 0000000..98bd7e5 --- /dev/null +++ b/pytorch_model-00014-of-00019.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:62e1cd45053d365aab9985a9c563af0542bc91b3a97f2b646604a71bb1ff1040 +size 385056275 diff --git a/pytorch_model-00015-of-00019.bin b/pytorch_model-00015-of-00019.bin new file mode 100644 index 0000000..aeb4e6e --- /dev/null +++ b/pytorch_model-00015-of-00019.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:42f4d674036214674dee84bc0060230dd2e17523448f29bc8c271ad144679214 +size 358417383 diff --git a/pytorch_model-00016-of-00019.bin b/pytorch_model-00016-of-00019.bin new file mode 100644 index 0000000..3b455d9 --- /dev/null +++ b/pytorch_model-00016-of-00019.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7444ef77cfbe59551924e88e89692599cce54473be268bc242b200f261b63ef7 +size 385056275 diff --git a/pytorch_model-00017-of-00019.bin b/pytorch_model-00017-of-00019.bin new file mode 100644 index 0000000..9f4e1e8 --- /dev/null +++ b/pytorch_model-00017-of-00019.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd7eb8ff746838ced7925799ad166202485c55ffc39da4cb36a820ea595a2657 +size 358417383 diff --git a/pytorch_model-00018-of-00019.bin b/pytorch_model-00018-of-00019.bin new file mode 100644 index 0000000..0265c56 --- /dev/null +++ b/pytorch_model-00018-of-00019.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b722eb37e1b2d5cb2564a3e217764eabb8af883d3eea10b35b72b06b702f663f +size 303141195 diff --git a/pytorch_model-00019-of-00019.bin b/pytorch_model-00019-of-00019.bin new file mode 100644 index 0000000..ad5c4e7 --- /dev/null +++ b/pytorch_model-00019-of-00019.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a17055b85ca12ecda0f8d3496084fa7650d0812284141e4f7fef64880a1d9c54 +size 204800938 diff --git a/pytorch_model.bin.index.json b/pytorch_model.bin.index.json new file mode 100644 index 0000000..9067304 --- /dev/null +++ b/pytorch_model.bin.index.json @@ -0,0 +1,270 @@ +{ + "metadata": { + "total_size": 6852952400 + }, + "weight_map": { + "lm_head.weight": "pytorch_model-00019-of-00019.bin", + "model.embed_tokens.weight": "pytorch_model-00001-of-00019.bin", + "model.layers.0.input_layernorm.weight": "pytorch_model-00002-of-00019.bin", + "model.layers.0.mlp.down_proj.weight": "pytorch_model-00002-of-00019.bin", + "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00019.bin", + "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00019.bin", + "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00002-of-00019.bin", + "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00019.bin", + "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00019.bin", + "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00019.bin", + "model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00019.bin", + "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00019.bin", + "model.layers.1.input_layernorm.weight": "pytorch_model-00002-of-00019.bin", + "model.layers.1.mlp.down_proj.weight": "pytorch_model-00002-of-00019.bin", + "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00002-of-00019.bin", + "model.layers.1.mlp.up_proj.weight": "pytorch_model-00002-of-00019.bin", + "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00002-of-00019.bin", + "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00002-of-00019.bin", + "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00002-of-00019.bin", + "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00002-of-00019.bin", + "model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00019.bin", + "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00002-of-00019.bin", + "model.layers.10.input_layernorm.weight": "pytorch_model-00008-of-00019.bin", + "model.layers.10.mlp.down_proj.weight": "pytorch_model-00008-of-00019.bin", + "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00008-of-00019.bin", + "model.layers.10.mlp.up_proj.weight": "pytorch_model-00008-of-00019.bin", + "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00008-of-00019.bin", + "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00008-of-00019.bin", + "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00008-of-00019.bin", + "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00008-of-00019.bin", + "model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-00008-of-00019.bin", + "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00008-of-00019.bin", + "model.layers.11.input_layernorm.weight": "pytorch_model-00009-of-00019.bin", + "model.layers.11.mlp.down_proj.weight": "pytorch_model-00009-of-00019.bin", + "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00009-of-00019.bin", + "model.layers.11.mlp.up_proj.weight": "pytorch_model-00009-of-00019.bin", + "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00009-of-00019.bin", + "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00008-of-00019.bin", + "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00008-of-00019.bin", + "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00008-of-00019.bin", + "model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-00008-of-00019.bin", + "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00008-of-00019.bin", + "model.layers.12.input_layernorm.weight": "pytorch_model-00010-of-00019.bin", + "model.layers.12.mlp.down_proj.weight": "pytorch_model-00010-of-00019.bin", + "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00009-of-00019.bin", + "model.layers.12.mlp.up_proj.weight": "pytorch_model-00009-of-00019.bin", + "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00010-of-00019.bin", + "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00009-of-00019.bin", + "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00009-of-00019.bin", + "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00009-of-00019.bin", + "model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00009-of-00019.bin", + "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00009-of-00019.bin", + "model.layers.13.input_layernorm.weight": "pytorch_model-00010-of-00019.bin", + "model.layers.13.mlp.down_proj.weight": "pytorch_model-00010-of-00019.bin", + "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00010-of-00019.bin", + "model.layers.13.mlp.up_proj.weight": "pytorch_model-00010-of-00019.bin", + "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00010-of-00019.bin", + "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00010-of-00019.bin", + "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00010-of-00019.bin", + "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00010-of-00019.bin", + "model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00010-of-00019.bin", + "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00010-of-00019.bin", + "model.layers.14.input_layernorm.weight": "pytorch_model-00011-of-00019.bin", + "model.layers.14.mlp.down_proj.weight": "pytorch_model-00011-of-00019.bin", + "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00011-of-00019.bin", + "model.layers.14.mlp.up_proj.weight": "pytorch_model-00011-of-00019.bin", + "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00011-of-00019.bin", + "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00010-of-00019.bin", + "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00010-of-00019.bin", + "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00010-of-00019.bin", + "model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00010-of-00019.bin", + "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00010-of-00019.bin", + "model.layers.15.input_layernorm.weight": "pytorch_model-00012-of-00019.bin", + "model.layers.15.mlp.down_proj.weight": "pytorch_model-00012-of-00019.bin", + "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00011-of-00019.bin", + "model.layers.15.mlp.up_proj.weight": "pytorch_model-00011-of-00019.bin", + "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00012-of-00019.bin", + "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00011-of-00019.bin", + "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00011-of-00019.bin", + "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00011-of-00019.bin", + "model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00011-of-00019.bin", + "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00011-of-00019.bin", + "model.layers.16.input_layernorm.weight": "pytorch_model-00012-of-00019.bin", + "model.layers.16.mlp.down_proj.weight": "pytorch_model-00012-of-00019.bin", + "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00012-of-00019.bin", + "model.layers.16.mlp.up_proj.weight": "pytorch_model-00012-of-00019.bin", + "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00012-of-00019.bin", + "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00012-of-00019.bin", + "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00012-of-00019.bin", + "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00012-of-00019.bin", + "model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-00012-of-00019.bin", + "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00012-of-00019.bin", + "model.layers.17.input_layernorm.weight": "pytorch_model-00013-of-00019.bin", + "model.layers.17.mlp.down_proj.weight": "pytorch_model-00013-of-00019.bin", + "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00013-of-00019.bin", + "model.layers.17.mlp.up_proj.weight": "pytorch_model-00013-of-00019.bin", + "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00013-of-00019.bin", + "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00012-of-00019.bin", + "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00012-of-00019.bin", + "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00012-of-00019.bin", + "model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-00012-of-00019.bin", + "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00012-of-00019.bin", + "model.layers.18.input_layernorm.weight": "pytorch_model-00014-of-00019.bin", + "model.layers.18.mlp.down_proj.weight": "pytorch_model-00014-of-00019.bin", + "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00013-of-00019.bin", + "model.layers.18.mlp.up_proj.weight": "pytorch_model-00013-of-00019.bin", + "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00014-of-00019.bin", + "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00013-of-00019.bin", + "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00013-of-00019.bin", + "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00013-of-00019.bin", + "model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-00013-of-00019.bin", + "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00013-of-00019.bin", + "model.layers.19.input_layernorm.weight": "pytorch_model-00014-of-00019.bin", + "model.layers.19.mlp.down_proj.weight": "pytorch_model-00014-of-00019.bin", + "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00014-of-00019.bin", + "model.layers.19.mlp.up_proj.weight": "pytorch_model-00014-of-00019.bin", + "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00014-of-00019.bin", + "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00014-of-00019.bin", + "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00014-of-00019.bin", + "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00014-of-00019.bin", + "model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-00014-of-00019.bin", + "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00014-of-00019.bin", + "model.layers.2.input_layernorm.weight": "pytorch_model-00003-of-00019.bin", + "model.layers.2.mlp.down_proj.weight": "pytorch_model-00003-of-00019.bin", + "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00003-of-00019.bin", + "model.layers.2.mlp.up_proj.weight": "pytorch_model-00003-of-00019.bin", + "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00003-of-00019.bin", + "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00002-of-00019.bin", + "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00002-of-00019.bin", + "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00002-of-00019.bin", + "model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00019.bin", + "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00002-of-00019.bin", + "model.layers.20.input_layernorm.weight": "pytorch_model-00015-of-00019.bin", + "model.layers.20.mlp.down_proj.weight": "pytorch_model-00015-of-00019.bin", + "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00015-of-00019.bin", + "model.layers.20.mlp.up_proj.weight": "pytorch_model-00015-of-00019.bin", + "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00015-of-00019.bin", + "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00014-of-00019.bin", + "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00014-of-00019.bin", + "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00014-of-00019.bin", + "model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-00014-of-00019.bin", + "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00014-of-00019.bin", + "model.layers.21.input_layernorm.weight": "pytorch_model-00016-of-00019.bin", + "model.layers.21.mlp.down_proj.weight": "pytorch_model-00016-of-00019.bin", + "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00015-of-00019.bin", + "model.layers.21.mlp.up_proj.weight": "pytorch_model-00015-of-00019.bin", + "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00016-of-00019.bin", + "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00015-of-00019.bin", + "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00015-of-00019.bin", + "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00015-of-00019.bin", + "model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-00015-of-00019.bin", + "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00015-of-00019.bin", + "model.layers.22.input_layernorm.weight": "pytorch_model-00016-of-00019.bin", + "model.layers.22.mlp.down_proj.weight": "pytorch_model-00016-of-00019.bin", + "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00016-of-00019.bin", + "model.layers.22.mlp.up_proj.weight": "pytorch_model-00016-of-00019.bin", + "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00016-of-00019.bin", + "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00016-of-00019.bin", + "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00016-of-00019.bin", + "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00016-of-00019.bin", + "model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-00016-of-00019.bin", + "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00016-of-00019.bin", + "model.layers.23.input_layernorm.weight": "pytorch_model-00017-of-00019.bin", + "model.layers.23.mlp.down_proj.weight": "pytorch_model-00017-of-00019.bin", + "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00017-of-00019.bin", + "model.layers.23.mlp.up_proj.weight": "pytorch_model-00017-of-00019.bin", + "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00017-of-00019.bin", + "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00016-of-00019.bin", + "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00016-of-00019.bin", + "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00016-of-00019.bin", + "model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00016-of-00019.bin", + "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00016-of-00019.bin", + "model.layers.24.input_layernorm.weight": "pytorch_model-00018-of-00019.bin", + "model.layers.24.mlp.down_proj.weight": "pytorch_model-00018-of-00019.bin", + "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00017-of-00019.bin", + "model.layers.24.mlp.up_proj.weight": "pytorch_model-00017-of-00019.bin", + "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00018-of-00019.bin", + "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00017-of-00019.bin", + "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00017-of-00019.bin", + "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00017-of-00019.bin", + "model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00017-of-00019.bin", + "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00017-of-00019.bin", + "model.layers.25.input_layernorm.weight": "pytorch_model-00018-of-00019.bin", + "model.layers.25.mlp.down_proj.weight": "pytorch_model-00018-of-00019.bin", + "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00018-of-00019.bin", + "model.layers.25.mlp.up_proj.weight": "pytorch_model-00018-of-00019.bin", + "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00018-of-00019.bin", + "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00018-of-00019.bin", + "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00018-of-00019.bin", + "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00018-of-00019.bin", + "model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00018-of-00019.bin", + "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00018-of-00019.bin", + "model.layers.3.input_layernorm.weight": "pytorch_model-00004-of-00019.bin", + "model.layers.3.mlp.down_proj.weight": "pytorch_model-00004-of-00019.bin", + "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00003-of-00019.bin", + "model.layers.3.mlp.up_proj.weight": "pytorch_model-00003-of-00019.bin", + "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00004-of-00019.bin", + "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00003-of-00019.bin", + "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00003-of-00019.bin", + "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00003-of-00019.bin", + "model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00019.bin", + "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00003-of-00019.bin", + "model.layers.4.input_layernorm.weight": "pytorch_model-00004-of-00019.bin", + "model.layers.4.mlp.down_proj.weight": "pytorch_model-00004-of-00019.bin", + "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00004-of-00019.bin", + "model.layers.4.mlp.up_proj.weight": "pytorch_model-00004-of-00019.bin", + "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00004-of-00019.bin", + "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00004-of-00019.bin", + "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00004-of-00019.bin", + "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00004-of-00019.bin", + "model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00019.bin", + "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00004-of-00019.bin", + "model.layers.5.input_layernorm.weight": "pytorch_model-00005-of-00019.bin", + "model.layers.5.mlp.down_proj.weight": "pytorch_model-00005-of-00019.bin", + "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00005-of-00019.bin", + "model.layers.5.mlp.up_proj.weight": "pytorch_model-00005-of-00019.bin", + "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00005-of-00019.bin", + "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00004-of-00019.bin", + "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00004-of-00019.bin", + "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00004-of-00019.bin", + "model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00019.bin", + "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00004-of-00019.bin", + "model.layers.6.input_layernorm.weight": "pytorch_model-00006-of-00019.bin", + "model.layers.6.mlp.down_proj.weight": "pytorch_model-00006-of-00019.bin", + "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00005-of-00019.bin", + "model.layers.6.mlp.up_proj.weight": "pytorch_model-00005-of-00019.bin", + "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00006-of-00019.bin", + "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00005-of-00019.bin", + "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00005-of-00019.bin", + "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00005-of-00019.bin", + "model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00019.bin", + "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00005-of-00019.bin", + "model.layers.7.input_layernorm.weight": "pytorch_model-00006-of-00019.bin", + "model.layers.7.mlp.down_proj.weight": "pytorch_model-00006-of-00019.bin", + "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00006-of-00019.bin", + "model.layers.7.mlp.up_proj.weight": "pytorch_model-00006-of-00019.bin", + "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00006-of-00019.bin", + "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00006-of-00019.bin", + "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00006-of-00019.bin", + "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00006-of-00019.bin", + "model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00019.bin", + "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00006-of-00019.bin", + "model.layers.8.input_layernorm.weight": "pytorch_model-00007-of-00019.bin", + "model.layers.8.mlp.down_proj.weight": "pytorch_model-00007-of-00019.bin", + "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00007-of-00019.bin", + "model.layers.8.mlp.up_proj.weight": "pytorch_model-00007-of-00019.bin", + "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00007-of-00019.bin", + "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00006-of-00019.bin", + "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00006-of-00019.bin", + "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00006-of-00019.bin", + "model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00019.bin", + "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00006-of-00019.bin", + "model.layers.9.input_layernorm.weight": "pytorch_model-00008-of-00019.bin", + "model.layers.9.mlp.down_proj.weight": "pytorch_model-00008-of-00019.bin", + "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00007-of-00019.bin", + "model.layers.9.mlp.up_proj.weight": "pytorch_model-00007-of-00019.bin", + "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00008-of-00019.bin", + "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00007-of-00019.bin", + "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00007-of-00019.bin", + "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00007-of-00019.bin", + "model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00019.bin", + "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00007-of-00019.bin", + "model.norm.weight": "pytorch_model-00018-of-00019.bin" + } +} diff --git a/tokenizer.model b/tokenizer.model new file mode 100644 index 0000000..98866ff --- /dev/null +++ b/tokenizer.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91b289e85fa20fd375d8b33dc12f77616f18abc6359804471d1fafcb425fecb8 +size 511574 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..38058a9 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,35 @@ +{ + "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 + }, + "legacy": true, + "model_max_length": 2048, + "pad_token": null, + "padding_side": "left", + "sp_model_kwargs": {}, + "tokenizer_class": "LlamaTokenizer", + "unk_token": { + "__type": "AddedToken", + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false + } +}