From c1b602f082619d9f71304a8e6cc3e91040f806fe Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Sat, 18 Jul 2026 03:54:10 +0800 Subject: [PATCH] =?UTF-8?q?=E5=88=9D=E5=A7=8B=E5=8C=96=E9=A1=B9=E7=9B=AE?= =?UTF-8?q?=EF=BC=8C=E7=94=B1ModelHub=20XC=E7=A4=BE=E5=8C=BA=E6=8F=90?= =?UTF-8?q?=E4=BE=9B=E6=A8=A1=E5=9E=8B?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Model: 4season/alignment-model-test9 Source: Original Platform --- .gitattributes | 35 +++ README.md | 14 + config.json | 30 ++ generation_config.json | 8 + model-00001-of-00009.safetensors | 3 + model-00002-of-00009.safetensors | 3 + model-00003-of-00009.safetensors | 3 + model-00004-of-00009.safetensors | 3 + model-00005-of-00009.safetensors | 3 + model-00006-of-00009.safetensors | 3 + model-00007-of-00009.safetensors | 3 + model-00008-of-00009.safetensors | 3 + model-00009-of-00009.safetensors | 3 + model.safetensors.index.json | 478 +++++++++++++++++++++++++++++++ special_tokens_map.json | 30 ++ tokenizer.model | 3 + tokenizer_config.json | 45 +++ 17 files changed, 670 insertions(+) create mode 100644 .gitattributes create mode 100644 README.md create mode 100644 config.json create mode 100644 generation_config.json create mode 100644 model-00001-of-00009.safetensors create mode 100644 model-00002-of-00009.safetensors create mode 100644 model-00003-of-00009.safetensors create mode 100644 model-00004-of-00009.safetensors create mode 100644 model-00005-of-00009.safetensors create mode 100644 model-00006-of-00009.safetensors create mode 100644 model-00007-of-00009.safetensors create mode 100644 model-00008-of-00009.safetensors create mode 100644 model-00009-of-00009.safetensors create mode 100644 model.safetensors.index.json create mode 100644 special_tokens_map.json create mode 100644 tokenizer.model create mode 100644 tokenizer_config.json 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..b7f07af --- /dev/null +++ b/README.md @@ -0,0 +1,14 @@ +--- +license: apache-2.0 +language: + - en +--- + +# 4season/model_eval_test + + +# **Introduction** +This model is test version, alignment-tuned model. + +We utilize state-of-the-art instruction fine-tuning methods including direct preference optimization (DPO). +After DPO training, we linearly merged models to boost performance. \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..eb83100 --- /dev/null +++ b/config.json @@ -0,0 +1,30 @@ +{ + "_name_or_path": "4season/alignment-model-test9", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bias": false, + "bos_token_id": 1, + "eos_token_id": 2, + "hidden_act": "silu", + "hidden_size": 6144, + "initializer_range": 0.02, + "intermediate_size": 16384, + "max_position_embeddings": 32768, + "model_type": "llama", + "num_attention_heads": 48, + "num_hidden_layers": 52, + "num_key_value_heads": 8, + "pad_token_id": 2, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": null, + "rope_theta": 1000000, + "tie_word_embeddings": false, + "torch_dtype": "bfloat16", + "transformers_version": "4.37.2", + "use_cache": false, + "vocab_size": 92544 +} diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..d53483f --- /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": 2, + "transformers_version": "4.37.2", + "use_cache": false +} diff --git a/model-00001-of-00009.safetensors b/model-00001-of-00009.safetensors new file mode 100644 index 0000000..888cb3f --- /dev/null +++ b/model-00001-of-00009.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f78f027bc7664a0b4ce8df93c6c79cc3aa25de64f4eda9bed0464dadef7ab9c4 +size 4836660104 diff --git a/model-00002-of-00009.safetensors b/model-00002-of-00009.safetensors new file mode 100644 index 0000000..c9d9d0d --- /dev/null +++ b/model-00002-of-00009.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2fa3403ce9bcd4d8fe71aa81e9b4ad7350b21e6252fb12bf5e14a80b788ad61d +size 4983012144 diff --git a/model-00003-of-00009.safetensors b/model-00003-of-00009.safetensors new file mode 100644 index 0000000..d42228b --- /dev/null +++ b/model-00003-of-00009.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7bb11c9d9e46c7dac7f3ec4b72f8cfe28537d4129279b83492394c2c45b8c232 +size 4957821336 diff --git a/model-00004-of-00009.safetensors b/model-00004-of-00009.safetensors new file mode 100644 index 0000000..abc79c5 --- /dev/null +++ b/model-00004-of-00009.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c0e77a00ce4c407ce2fa3fc5c4987c8bc601d1ee98bb4ee1260f177de73a4c8 +size 4882323744 diff --git a/model-00005-of-00009.safetensors b/model-00005-of-00009.safetensors new file mode 100644 index 0000000..ae40e7c --- /dev/null +++ b/model-00005-of-00009.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:400c78520e5b5c03641e12809567ddd44e34a8660b292d9739d693c126b44a6e +size 4983012192 diff --git a/model-00006-of-00009.safetensors b/model-00006-of-00009.safetensors new file mode 100644 index 0000000..9921433 --- /dev/null +++ b/model-00006-of-00009.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:178a8db946be88e07f2503969ebf260748042852b42f6a6f31297fff2102a5b2 +size 4957821336 diff --git a/model-00007-of-00009.safetensors b/model-00007-of-00009.safetensors new file mode 100644 index 0000000..46c116c --- /dev/null +++ b/model-00007-of-00009.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d56d6a04d49770d7dda733d43e4be5b76af6f7d19afbc4c405d2ec04d724bde +size 4882323744 diff --git a/model-00008-of-00009.safetensors b/model-00008-of-00009.safetensors new file mode 100644 index 0000000..56b81c8 --- /dev/null +++ b/model-00008-of-00009.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f4b0bbb70b2d4eec5bb4574b8598010d5de0879d8432d148d70ed96618c28fba +size 4983012192 diff --git a/model-00009-of-00009.safetensors b/model-00009-of-00009.safetensors new file mode 100644 index 0000000..e8e99e4 --- /dev/null +++ b/model-00009-of-00009.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c6844972d5903b75c32f3f9ce0f2cd007a9c2ad2f16e9fb18063b96052ef56f +size 3377028040 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000..5f45b9b --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,478 @@ +{ + "metadata": { + "total_size": 42842959872 + }, + "weight_map": { + "lm_head.weight": "model-00009-of-00009.safetensors", + "model.embed_tokens.weight": "model-00001-of-00009.safetensors", + "model.layers.0.input_layernorm.weight": "model-00001-of-00009.safetensors", + "model.layers.0.mlp.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.0.mlp.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00009.safetensors", + "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.input_layernorm.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00009.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.10.input_layernorm.weight": "model-00002-of-00009.safetensors", + "model.layers.10.mlp.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.10.mlp.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00009.safetensors", + "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.11.input_layernorm.weight": "model-00003-of-00009.safetensors", + "model.layers.11.mlp.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.11.mlp.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00009.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.12.input_layernorm.weight": "model-00003-of-00009.safetensors", + "model.layers.12.mlp.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.12.mlp.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00009.safetensors", + "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.13.input_layernorm.weight": "model-00003-of-00009.safetensors", + "model.layers.13.mlp.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.13.mlp.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00009.safetensors", + "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.14.input_layernorm.weight": "model-00003-of-00009.safetensors", + "model.layers.14.mlp.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.14.mlp.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00009.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.15.input_layernorm.weight": "model-00003-of-00009.safetensors", + "model.layers.15.mlp.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.15.mlp.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00009.safetensors", + "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.16.input_layernorm.weight": "model-00003-of-00009.safetensors", + "model.layers.16.mlp.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.16.mlp.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00009.safetensors", + "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.17.input_layernorm.weight": "model-00004-of-00009.safetensors", + "model.layers.17.mlp.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.17.mlp.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00009.safetensors", + "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.18.input_layernorm.weight": "model-00004-of-00009.safetensors", + "model.layers.18.mlp.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.18.mlp.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00009.safetensors", + "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.19.input_layernorm.weight": "model-00004-of-00009.safetensors", + "model.layers.19.mlp.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.19.mlp.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.19.mlp.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00009.safetensors", + "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.2.input_layernorm.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00009.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.20.input_layernorm.weight": "model-00004-of-00009.safetensors", + "model.layers.20.mlp.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.20.mlp.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.20.mlp.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00009.safetensors", + "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.21.input_layernorm.weight": "model-00004-of-00009.safetensors", + "model.layers.21.mlp.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.21.mlp.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.21.mlp.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00009.safetensors", + "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.22.input_layernorm.weight": "model-00004-of-00009.safetensors", + "model.layers.22.mlp.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.22.mlp.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.22.mlp.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00004-of-00009.safetensors", + "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.23.input_layernorm.weight": "model-00005-of-00009.safetensors", + "model.layers.23.mlp.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.23.mlp.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.23.mlp.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00009.safetensors", + "model.layers.23.self_attn.k_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.23.self_attn.q_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.23.self_attn.v_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.24.input_layernorm.weight": "model-00005-of-00009.safetensors", + "model.layers.24.mlp.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.24.mlp.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.24.mlp.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00005-of-00009.safetensors", + "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.24.self_attn.o_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.25.input_layernorm.weight": "model-00005-of-00009.safetensors", + "model.layers.25.mlp.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.25.mlp.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.25.mlp.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00005-of-00009.safetensors", + "model.layers.25.self_attn.k_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.25.self_attn.o_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.25.self_attn.q_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.25.self_attn.v_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.26.input_layernorm.weight": "model-00005-of-00009.safetensors", + "model.layers.26.mlp.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.26.mlp.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.26.mlp.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00005-of-00009.safetensors", + "model.layers.26.self_attn.k_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.26.self_attn.o_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.26.self_attn.q_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.26.self_attn.v_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.27.input_layernorm.weight": "model-00005-of-00009.safetensors", + "model.layers.27.mlp.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.27.mlp.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.27.mlp.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00005-of-00009.safetensors", + "model.layers.27.self_attn.k_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.27.self_attn.o_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.27.self_attn.q_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.27.self_attn.v_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.28.input_layernorm.weight": "model-00005-of-00009.safetensors", + "model.layers.28.mlp.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.28.mlp.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.28.mlp.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.28.post_attention_layernorm.weight": "model-00005-of-00009.safetensors", + "model.layers.28.self_attn.k_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.28.self_attn.o_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.28.self_attn.q_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.28.self_attn.v_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.29.input_layernorm.weight": "model-00005-of-00009.safetensors", + "model.layers.29.mlp.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.29.mlp.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.29.mlp.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.29.post_attention_layernorm.weight": "model-00005-of-00009.safetensors", + "model.layers.29.self_attn.k_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.29.self_attn.o_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.29.self_attn.q_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.29.self_attn.v_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.3.input_layernorm.weight": "model-00001-of-00009.safetensors", + "model.layers.3.mlp.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.3.mlp.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00009.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.30.input_layernorm.weight": "model-00006-of-00009.safetensors", + "model.layers.30.mlp.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.30.mlp.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.30.mlp.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.30.post_attention_layernorm.weight": "model-00006-of-00009.safetensors", + "model.layers.30.self_attn.k_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.30.self_attn.o_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.30.self_attn.q_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.30.self_attn.v_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.31.input_layernorm.weight": "model-00006-of-00009.safetensors", + "model.layers.31.mlp.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.31.mlp.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.31.mlp.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.31.post_attention_layernorm.weight": "model-00006-of-00009.safetensors", + "model.layers.31.self_attn.k_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.31.self_attn.o_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.31.self_attn.q_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.31.self_attn.v_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.32.input_layernorm.weight": "model-00006-of-00009.safetensors", + "model.layers.32.mlp.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.32.mlp.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.32.mlp.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.32.post_attention_layernorm.weight": "model-00006-of-00009.safetensors", + "model.layers.32.self_attn.k_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.32.self_attn.o_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.32.self_attn.q_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.32.self_attn.v_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.33.input_layernorm.weight": "model-00006-of-00009.safetensors", + "model.layers.33.mlp.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.33.mlp.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.33.mlp.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.33.post_attention_layernorm.weight": "model-00006-of-00009.safetensors", + "model.layers.33.self_attn.k_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.33.self_attn.o_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.33.self_attn.q_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.33.self_attn.v_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.34.input_layernorm.weight": "model-00006-of-00009.safetensors", + "model.layers.34.mlp.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.34.mlp.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.34.mlp.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.34.post_attention_layernorm.weight": "model-00006-of-00009.safetensors", + "model.layers.34.self_attn.k_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.34.self_attn.o_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.34.self_attn.q_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.34.self_attn.v_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.35.input_layernorm.weight": "model-00006-of-00009.safetensors", + "model.layers.35.mlp.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.35.mlp.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.35.mlp.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.35.post_attention_layernorm.weight": "model-00006-of-00009.safetensors", + "model.layers.35.self_attn.k_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.35.self_attn.o_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.35.self_attn.q_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.35.self_attn.v_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.36.input_layernorm.weight": "model-00007-of-00009.safetensors", + "model.layers.36.mlp.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.36.mlp.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.36.mlp.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.36.post_attention_layernorm.weight": "model-00007-of-00009.safetensors", + "model.layers.36.self_attn.k_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.36.self_attn.o_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.36.self_attn.q_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.36.self_attn.v_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.37.input_layernorm.weight": "model-00007-of-00009.safetensors", + "model.layers.37.mlp.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.37.mlp.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.37.mlp.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.37.post_attention_layernorm.weight": "model-00007-of-00009.safetensors", + "model.layers.37.self_attn.k_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.37.self_attn.o_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.37.self_attn.q_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.37.self_attn.v_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.38.input_layernorm.weight": "model-00007-of-00009.safetensors", + "model.layers.38.mlp.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.38.mlp.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.38.mlp.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.38.post_attention_layernorm.weight": "model-00007-of-00009.safetensors", + "model.layers.38.self_attn.k_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.38.self_attn.o_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.38.self_attn.q_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.38.self_attn.v_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.39.input_layernorm.weight": "model-00007-of-00009.safetensors", + "model.layers.39.mlp.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.39.mlp.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.39.mlp.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.39.post_attention_layernorm.weight": "model-00007-of-00009.safetensors", + "model.layers.39.self_attn.k_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.39.self_attn.o_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.39.self_attn.q_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.39.self_attn.v_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.4.input_layernorm.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.4.mlp.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00009.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.40.input_layernorm.weight": "model-00007-of-00009.safetensors", + "model.layers.40.mlp.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.40.mlp.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.40.mlp.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.40.post_attention_layernorm.weight": "model-00007-of-00009.safetensors", + "model.layers.40.self_attn.k_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.40.self_attn.o_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.40.self_attn.q_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.40.self_attn.v_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.41.input_layernorm.weight": "model-00007-of-00009.safetensors", + "model.layers.41.mlp.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.41.mlp.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.41.mlp.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.41.post_attention_layernorm.weight": "model-00007-of-00009.safetensors", + "model.layers.41.self_attn.k_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.41.self_attn.o_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.41.self_attn.q_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.41.self_attn.v_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.42.input_layernorm.weight": "model-00008-of-00009.safetensors", + "model.layers.42.mlp.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.42.mlp.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.42.mlp.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.42.post_attention_layernorm.weight": "model-00008-of-00009.safetensors", + "model.layers.42.self_attn.k_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.42.self_attn.o_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.42.self_attn.q_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.42.self_attn.v_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.43.input_layernorm.weight": "model-00008-of-00009.safetensors", + "model.layers.43.mlp.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.43.mlp.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.43.mlp.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.43.post_attention_layernorm.weight": "model-00008-of-00009.safetensors", + "model.layers.43.self_attn.k_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.43.self_attn.o_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.43.self_attn.q_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.43.self_attn.v_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.44.input_layernorm.weight": "model-00008-of-00009.safetensors", + "model.layers.44.mlp.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.44.mlp.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.44.mlp.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.44.post_attention_layernorm.weight": "model-00008-of-00009.safetensors", + "model.layers.44.self_attn.k_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.44.self_attn.o_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.44.self_attn.q_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.44.self_attn.v_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.45.input_layernorm.weight": "model-00008-of-00009.safetensors", + "model.layers.45.mlp.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.45.mlp.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.45.mlp.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.45.post_attention_layernorm.weight": "model-00008-of-00009.safetensors", + "model.layers.45.self_attn.k_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.45.self_attn.o_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.45.self_attn.q_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.45.self_attn.v_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.46.input_layernorm.weight": "model-00008-of-00009.safetensors", + "model.layers.46.mlp.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.46.mlp.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.46.mlp.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.46.post_attention_layernorm.weight": "model-00008-of-00009.safetensors", + "model.layers.46.self_attn.k_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.46.self_attn.o_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.46.self_attn.q_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.46.self_attn.v_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.47.input_layernorm.weight": "model-00008-of-00009.safetensors", + "model.layers.47.mlp.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.47.mlp.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.47.mlp.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.47.post_attention_layernorm.weight": "model-00008-of-00009.safetensors", + "model.layers.47.self_attn.k_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.47.self_attn.o_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.47.self_attn.q_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.47.self_attn.v_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.48.input_layernorm.weight": "model-00008-of-00009.safetensors", + "model.layers.48.mlp.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.48.mlp.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.48.mlp.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.48.post_attention_layernorm.weight": "model-00008-of-00009.safetensors", + "model.layers.48.self_attn.k_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.48.self_attn.o_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.48.self_attn.q_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.48.self_attn.v_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.49.input_layernorm.weight": "model-00009-of-00009.safetensors", + "model.layers.49.mlp.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.49.mlp.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.49.mlp.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.49.post_attention_layernorm.weight": "model-00009-of-00009.safetensors", + "model.layers.49.self_attn.k_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.49.self_attn.o_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.49.self_attn.q_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.49.self_attn.v_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.5.input_layernorm.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00009.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.50.input_layernorm.weight": "model-00009-of-00009.safetensors", + "model.layers.50.mlp.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.50.mlp.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.50.mlp.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.50.post_attention_layernorm.weight": "model-00009-of-00009.safetensors", + "model.layers.50.self_attn.k_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.50.self_attn.o_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.50.self_attn.q_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.50.self_attn.v_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.51.input_layernorm.weight": "model-00009-of-00009.safetensors", + "model.layers.51.mlp.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.51.mlp.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.51.mlp.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.51.post_attention_layernorm.weight": "model-00009-of-00009.safetensors", + "model.layers.51.self_attn.k_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.51.self_attn.o_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.51.self_attn.q_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.51.self_attn.v_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.6.input_layernorm.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00009.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.7.input_layernorm.weight": "model-00002-of-00009.safetensors", + "model.layers.7.mlp.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.7.mlp.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00009.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.8.input_layernorm.weight": "model-00002-of-00009.safetensors", + "model.layers.8.mlp.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.8.mlp.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00009.safetensors", + "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.9.input_layernorm.weight": "model-00002-of-00009.safetensors", + "model.layers.9.mlp.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.9.mlp.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00009.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00009.safetensors", + "model.norm.weight": "model-00009-of-00009.safetensors" + } +} diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..492d4b2 --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,30 @@ +{ + "bos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "unk_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/tokenizer.model b/tokenizer.model new file mode 100644 index 0000000..6600712 --- /dev/null +++ b/tokenizer.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f868398fc4e05ee1e8aeba95ddf18ddcc45b8bce55d5093bead5bbf80429b48b +size 1477754 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..9b1cd65 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,45 @@ +{ + "add_bos_token": true, + "add_eos_token": false, + "add_prefix_space": true, + "added_tokens_decoder": { + "0": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "1": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "2": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "bos_token": "", + "clean_up_tokenization_spaces": true, + "eos_token": "", + "legacy": true, + "model_max_length": 1000000000000000019884624838656, + "pad_token": "", + "padding_side": "right", + "sp_model_kwargs": {}, + "spaces_between_special_tokens": false, + "split_special_tokens": false, + "tokenizer_class": "LlamaTokenizer", + "trust_remote_code": false, + "unk_token": "", + "use_default_system_prompt": false +}