commit 05e741f440d6c9a53cd44950e5c15c341c6e225e Author: ModelHub XC Date: Mon Apr 13 17:17:03 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: Enno-Ai/ennodata-raw-pankajmathur-13b-peft 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/config.json b/config.json new file mode 100644 index 0000000..cd6fe8f --- /dev/null +++ b/config.json @@ -0,0 +1,28 @@ +{ + "_name_or_path": "pankajmathur/model_007_13b_v2", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "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, + "num_key_value_heads": 40, + "pad_token_id": 0, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": null, + "rope_theta": 10000.0, + "tie_word_embeddings": false, + "torch_dtype": "float16", + "transformers_version": "4.34.0", + "use_cache": true, + "vocab_size": 32000 +} diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..2c6a963 --- /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": "4.34.0" +} diff --git a/model-00001-of-00007.safetensors b/model-00001-of-00007.safetensors new file mode 100644 index 0000000..2e337ad --- /dev/null +++ b/model-00001-of-00007.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:310f3b286b6e2f1e6fdcba1d8c2f06adc95cad34a8d7988543537bb6d0380357 +size 3992561488 diff --git a/model-00002-of-00007.safetensors b/model-00002-of-00007.safetensors new file mode 100644 index 0000000..3011dcf --- /dev/null +++ b/model-00002-of-00007.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d919e80bace8f10efd95e6274a39d330dfa673b8d0b1d4e8fca8f19c550611c5 +size 3948038560 diff --git a/model-00003-of-00007.safetensors b/model-00003-of-00007.safetensors new file mode 100644 index 0000000..ef733a5 --- /dev/null +++ b/model-00003-of-00007.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:63a53e511d0340246284666f1a2925fdd0ee5dfccead5e7060f0b27249af374f +size 3963746768 diff --git a/model-00004-of-00007.safetensors b/model-00004-of-00007.safetensors new file mode 100644 index 0000000..5657bd0 --- /dev/null +++ b/model-00004-of-00007.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8cebc051ed2c2a996ba9b8a07186bc52d18276d0e2c4ed172d84e26da4d6daf8 +size 3858888928 diff --git a/model-00005-of-00007.safetensors b/model-00005-of-00007.safetensors new file mode 100644 index 0000000..60edfb4 --- /dev/null +++ b/model-00005-of-00007.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd2d06e9a4c24ce94dcdfb5365a493fe99806cdf3dcebbeae8862a8bcc796e3e +size 3948017888 diff --git a/model-00006-of-00007.safetensors b/model-00006-of-00007.safetensors new file mode 100644 index 0000000..91330ed --- /dev/null +++ b/model-00006-of-00007.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:defd770b0ee72721d44a72df6a06b58e452840cd9d074bc5d7f958bbf2d4ba7e +size 3948017880 diff --git a/model-00007-of-00007.safetensors b/model-00007-of-00007.safetensors new file mode 100644 index 0000000..f076395 --- /dev/null +++ b/model-00007-of-00007.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f01598aea3af1bc66e106c95136749c58447ecfe1b0afabefc8f6b57af727d64 +size 2372499024 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000..0e704fa --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,370 @@ +{ + "metadata": { + "total_size": 26031728640 + }, + "weight_map": { + "lm_head.weight": "model-00007-of-00007.safetensors", + "model.embed_tokens.weight": "model-00001-of-00007.safetensors", + "model.layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors", + "model.layers.0.mlp.down_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.0.mlp.up_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", + "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors", + "model.layers.1.mlp.down_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.1.mlp.up_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.10.input_layernorm.weight": "model-00002-of-00007.safetensors", + "model.layers.10.mlp.down_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.10.mlp.up_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", + "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.11.input_layernorm.weight": "model-00002-of-00007.safetensors", + "model.layers.11.mlp.down_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.11.mlp.up_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.12.input_layernorm.weight": "model-00003-of-00007.safetensors", + "model.layers.12.mlp.down_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.12.mlp.up_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", + "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.13.input_layernorm.weight": "model-00003-of-00007.safetensors", + "model.layers.13.mlp.down_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.13.mlp.up_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", + "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.14.input_layernorm.weight": "model-00003-of-00007.safetensors", + "model.layers.14.mlp.down_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.14.mlp.up_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.15.input_layernorm.weight": "model-00003-of-00007.safetensors", + "model.layers.15.mlp.down_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.15.mlp.up_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", + "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.16.input_layernorm.weight": "model-00003-of-00007.safetensors", + "model.layers.16.mlp.down_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.16.mlp.up_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", + "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.17.input_layernorm.weight": "model-00003-of-00007.safetensors", + "model.layers.17.mlp.down_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.17.mlp.up_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", + "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.18.input_layernorm.weight": "model-00004-of-00007.safetensors", + "model.layers.18.mlp.down_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.18.mlp.up_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", + "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.19.input_layernorm.weight": "model-00004-of-00007.safetensors", + "model.layers.19.mlp.down_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.19.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.19.mlp.up_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", + "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.2.input_layernorm.weight": "model-00001-of-00007.safetensors", + "model.layers.2.mlp.down_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.2.mlp.up_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.20.input_layernorm.weight": "model-00004-of-00007.safetensors", + "model.layers.20.mlp.down_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.20.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.20.mlp.up_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", + "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.21.input_layernorm.weight": "model-00004-of-00007.safetensors", + "model.layers.21.mlp.down_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.21.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.21.mlp.up_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", + "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.22.input_layernorm.weight": "model-00004-of-00007.safetensors", + "model.layers.22.mlp.down_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.22.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.22.mlp.up_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", + "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.23.input_layernorm.weight": "model-00004-of-00007.safetensors", + "model.layers.23.mlp.down_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.23.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.23.mlp.up_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", + "model.layers.23.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.23.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.23.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.24.input_layernorm.weight": "model-00005-of-00007.safetensors", + "model.layers.24.mlp.down_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.24.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.24.mlp.up_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", + "model.layers.24.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.24.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.24.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.24.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.25.input_layernorm.weight": "model-00005-of-00007.safetensors", + "model.layers.25.mlp.down_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.25.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.25.mlp.up_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", + "model.layers.25.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.25.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.25.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.25.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.26.input_layernorm.weight": "model-00005-of-00007.safetensors", + "model.layers.26.mlp.down_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.26.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.26.mlp.up_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", + "model.layers.26.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.26.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.26.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.26.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.27.input_layernorm.weight": "model-00005-of-00007.safetensors", + "model.layers.27.mlp.down_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.27.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.27.mlp.up_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", + "model.layers.27.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.27.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.27.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.27.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.28.input_layernorm.weight": "model-00005-of-00007.safetensors", + "model.layers.28.mlp.down_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.28.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.28.mlp.up_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.28.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", + "model.layers.28.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.28.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.28.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.28.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.29.input_layernorm.weight": "model-00005-of-00007.safetensors", + "model.layers.29.mlp.down_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.29.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.29.mlp.up_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.29.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", + "model.layers.29.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.29.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.29.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.29.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.3.input_layernorm.weight": "model-00001-of-00007.safetensors", + "model.layers.3.mlp.down_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.3.mlp.up_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.30.input_layernorm.weight": "model-00006-of-00007.safetensors", + "model.layers.30.mlp.down_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.30.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.30.mlp.up_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.30.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", + "model.layers.30.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.30.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.30.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.30.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.31.input_layernorm.weight": "model-00006-of-00007.safetensors", + "model.layers.31.mlp.down_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.31.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.31.mlp.up_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.31.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", + "model.layers.31.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.31.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.31.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.31.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.32.input_layernorm.weight": "model-00006-of-00007.safetensors", + "model.layers.32.mlp.down_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.32.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.32.mlp.up_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.32.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", + "model.layers.32.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.32.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.32.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.32.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.33.input_layernorm.weight": "model-00006-of-00007.safetensors", + "model.layers.33.mlp.down_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.33.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.33.mlp.up_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.33.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", + "model.layers.33.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.33.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.33.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.33.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.34.input_layernorm.weight": "model-00006-of-00007.safetensors", + "model.layers.34.mlp.down_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.34.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.34.mlp.up_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.34.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", + "model.layers.34.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.34.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.34.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.34.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.35.input_layernorm.weight": "model-00006-of-00007.safetensors", + "model.layers.35.mlp.down_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.35.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.35.mlp.up_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.35.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", + "model.layers.35.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.35.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.35.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.35.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.36.input_layernorm.weight": "model-00007-of-00007.safetensors", + "model.layers.36.mlp.down_proj.weight": "model-00007-of-00007.safetensors", + "model.layers.36.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.36.mlp.up_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.36.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", + "model.layers.36.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.36.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.36.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.36.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.37.input_layernorm.weight": "model-00007-of-00007.safetensors", + "model.layers.37.mlp.down_proj.weight": "model-00007-of-00007.safetensors", + "model.layers.37.mlp.gate_proj.weight": "model-00007-of-00007.safetensors", + "model.layers.37.mlp.up_proj.weight": "model-00007-of-00007.safetensors", + "model.layers.37.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", + "model.layers.37.self_attn.k_proj.weight": "model-00007-of-00007.safetensors", + "model.layers.37.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", + "model.layers.37.self_attn.q_proj.weight": "model-00007-of-00007.safetensors", + "model.layers.37.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", + "model.layers.38.input_layernorm.weight": "model-00007-of-00007.safetensors", + "model.layers.38.mlp.down_proj.weight": "model-00007-of-00007.safetensors", + "model.layers.38.mlp.gate_proj.weight": "model-00007-of-00007.safetensors", + "model.layers.38.mlp.up_proj.weight": "model-00007-of-00007.safetensors", + "model.layers.38.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", + "model.layers.38.self_attn.k_proj.weight": "model-00007-of-00007.safetensors", + "model.layers.38.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", + "model.layers.38.self_attn.q_proj.weight": "model-00007-of-00007.safetensors", + "model.layers.38.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", + "model.layers.39.input_layernorm.weight": "model-00007-of-00007.safetensors", + "model.layers.39.mlp.down_proj.weight": "model-00007-of-00007.safetensors", + "model.layers.39.mlp.gate_proj.weight": "model-00007-of-00007.safetensors", + "model.layers.39.mlp.up_proj.weight": "model-00007-of-00007.safetensors", + "model.layers.39.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", + "model.layers.39.self_attn.k_proj.weight": "model-00007-of-00007.safetensors", + "model.layers.39.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", + "model.layers.39.self_attn.q_proj.weight": "model-00007-of-00007.safetensors", + "model.layers.39.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", + "model.layers.4.input_layernorm.weight": "model-00001-of-00007.safetensors", + "model.layers.4.mlp.down_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.4.mlp.up_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.5.input_layernorm.weight": "model-00002-of-00007.safetensors", + "model.layers.5.mlp.down_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.5.mlp.up_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.6.input_layernorm.weight": "model-00002-of-00007.safetensors", + "model.layers.6.mlp.down_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.6.mlp.up_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.7.input_layernorm.weight": "model-00002-of-00007.safetensors", + "model.layers.7.mlp.down_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.7.mlp.up_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.8.input_layernorm.weight": "model-00002-of-00007.safetensors", + "model.layers.8.mlp.down_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.8.mlp.up_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", + "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.9.input_layernorm.weight": "model-00002-of-00007.safetensors", + "model.layers.9.mlp.down_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.9.mlp.up_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", + "model.norm.weight": "model-00007-of-00007.safetensors" + } +} diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..a52c50a --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,5 @@ +{ + "bos_token": "", + "eos_token": "", + "unk_token": "" +} diff --git a/tokenizer.model b/tokenizer.model new file mode 100644 index 0000000..6c00c74 --- /dev/null +++ b/tokenizer.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347 +size 499723 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..cd4e9dc --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,44 @@ +{ + "add_bos_token": true, + "add_eos_token": false, + "added_tokens_decoder": { + "0": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "1": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "2": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + } + }, + "additional_special_tokens": [], + "bos_token": "", + "clean_up_tokenization_spaces": false, + "eos_token": "", + "legacy": false, + "model_max_length": 4096, + "pad_token": null, + "padding_side": "right", + "sp_model_kwargs": {}, + "spaces_between_special_tokens": false, + "tokenizer_class": "LlamaTokenizer", + "tokenizer_file": "/mnt/ssd/models/hf/pankajmathur/model_007_13b_v2/tokenizer.json", + "unk_token": "", + "use_default_system_prompt": true +}