From 06aea1a5e56987694acdfeede9a55b1729bda3d1 Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Mon, 27 Jul 2026 20:59:09 +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: BigRatz/LOL-AI-2026-V2 Source: Original Platform --- .gitattributes | 36 + README.md | 3 + config.json | 37 + generation_config.json | 8 + model-00001-of-00002.safetensors | 3 + model-00002-of-00002.safetensors | 3 + model.safetensors.index.json | 1258 ++++++++++++++++++++++++++++++ requirements.txt | 6 + script.py | 353 +++++++++ special_tokens_map.json | 23 + tokenizer.json | 3 + tokenizer_config.json | 195 +++++ 12 files changed, 1928 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-00002.safetensors create mode 100644 model-00002-of-00002.safetensors create mode 100644 model.safetensors.index.json create mode 100644 requirements.txt create mode 100644 script.py create mode 100644 special_tokens_map.json create mode 100644 tokenizer.json create mode 100644 tokenizer_config.json diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..52373fe --- /dev/null +++ b/.gitattributes @@ -0,0 +1,36 @@ +*.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 +tokenizer.json filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..acb132c --- /dev/null +++ b/README.md @@ -0,0 +1,3 @@ +--- +license: mit +--- \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..3e35e93 --- /dev/null +++ b/config.json @@ -0,0 +1,37 @@ +{ + "_name_or_path": ".", + "architectures": [ + "Qwen2ForCausalLM" + ], + "attention_dropout": 0.0, + "bos_token_id": 151643, + "eos_token_id": 151643, + "hidden_act": "silu", + "hidden_size": 5120, + "initializer_range": 0.02, + "intermediate_size": 13824, + "max_position_embeddings": 131072, + "max_window_layers": 48, + "model_type": "qwen2", + "num_attention_heads": 40, + "num_hidden_layers": 48, + "num_key_value_heads": 8, + "quantization_config": { + "bits": 4, + "group_size": 128, + "modules_to_not_convert": null, + "quant_method": "awq", + "version": "gemm", + "zero_point": true + }, + "rms_norm_eps": 1e-05, + "rope_scaling": null, + "rope_theta": 1000000.0, + "sliding_window": null, + "tie_word_embeddings": false, + "torch_dtype": "float16", + "transformers_version": "4.47.1", + "use_cache": true, + "use_sliding_window": false, + "vocab_size": 152064 +} \ No newline at end of file diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..d079819 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,8 @@ +{ + "_from_model_config": true, + "bos_token_id": 151643, + "do_sample": true, + "eos_token_id": 151643, + "transformers_version": "4.47.1", + "use_cache": false +} diff --git a/model-00001-of-00002.safetensors b/model-00001-of-00002.safetensors new file mode 100644 index 0000000..2ddb209 --- /dev/null +++ b/model-00001-of-00002.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a7920b5250103287efca7e32394736c3a9d72689e2ff196d6d6659115f730630 +size 4990080088 diff --git a/model-00002-of-00002.safetensors b/model-00002-of-00002.safetensors new file mode 100644 index 0000000..120903e --- /dev/null +++ b/model-00002-of-00002.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e2ed5556c89c46d4d77738657e1989d232fddad715eee02c186aa09a3849d89 +size 4990090664 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000..13d674c --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,1258 @@ +{ + "metadata": { + "total_size": 9980028928 + }, + "weight_map": { + "model.embed_tokens.weight": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.q_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.k_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.v_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.o_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.0.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.0.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.0.mlp.gate_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.0.mlp.up_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.0.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.0.mlp.up_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.0.mlp.down_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.0.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.0.mlp.down_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.q_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.k_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.v_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.o_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.1.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.1.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.1.mlp.gate_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.1.mlp.up_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.1.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.1.mlp.up_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.1.mlp.down_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.1.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.1.mlp.down_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.q_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.k_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.v_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.o_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.2.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.2.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.2.mlp.gate_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.2.mlp.up_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.2.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.2.mlp.up_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.2.mlp.down_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.2.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.2.mlp.down_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.q_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.k_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.v_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.o_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.3.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.3.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.3.mlp.gate_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.3.mlp.up_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.3.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.3.mlp.up_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.3.mlp.down_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.3.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.3.mlp.down_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.q_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.k_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.v_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.o_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.4.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.4.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.4.mlp.gate_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.4.mlp.up_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.4.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.4.mlp.up_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.4.mlp.down_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.4.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.4.mlp.down_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.q_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.k_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.v_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.o_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.5.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.5.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.5.mlp.gate_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.5.mlp.up_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.5.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.5.mlp.up_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.5.mlp.down_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.5.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.5.mlp.down_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.q_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.k_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.v_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.o_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.6.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.6.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.6.mlp.gate_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.6.mlp.up_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.6.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.6.mlp.up_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.6.mlp.down_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.6.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.6.mlp.down_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.q_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.k_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.v_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.o_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.7.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.7.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.7.mlp.gate_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.7.mlp.up_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.7.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.7.mlp.up_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.7.mlp.down_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.7.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.7.mlp.down_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.q_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.k_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.v_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.o_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.8.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.8.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.8.mlp.gate_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.8.mlp.up_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.8.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.8.mlp.up_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.8.mlp.down_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.8.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.8.mlp.down_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.q_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.k_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.v_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.o_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.9.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.9.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.9.mlp.gate_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.9.mlp.up_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.9.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.9.mlp.up_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.9.mlp.down_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.9.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.9.mlp.down_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.q_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.k_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.v_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.o_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.10.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.10.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.10.mlp.gate_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.10.mlp.up_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.10.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.10.mlp.up_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.10.mlp.down_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.10.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.10.mlp.down_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.q_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.k_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.v_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.o_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.11.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.11.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.11.mlp.gate_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.11.mlp.up_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.11.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.11.mlp.up_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.11.mlp.down_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.11.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.11.mlp.down_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.q_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.k_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.v_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.o_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.12.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.12.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.12.mlp.gate_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.12.mlp.up_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.12.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.12.mlp.up_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.12.mlp.down_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.12.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.12.mlp.down_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.q_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.k_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.v_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.o_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.13.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.13.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.13.mlp.gate_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.13.mlp.up_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.13.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.13.mlp.up_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.13.mlp.down_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.13.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.13.mlp.down_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.q_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.k_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.v_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.o_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.14.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.14.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.14.mlp.gate_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.14.mlp.up_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.14.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.14.mlp.up_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.14.mlp.down_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.14.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.14.mlp.down_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.q_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.k_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.v_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.o_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.15.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.15.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.15.mlp.gate_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.15.mlp.up_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.15.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.15.mlp.up_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.15.mlp.down_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.15.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.15.mlp.down_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.q_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.k_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.v_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.o_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.16.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.16.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.16.mlp.gate_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.16.mlp.up_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.16.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.16.mlp.up_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.16.mlp.down_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.16.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.16.mlp.down_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.q_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.k_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.v_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.o_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.17.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.17.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.17.mlp.gate_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.17.mlp.up_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.17.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.17.mlp.up_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.17.mlp.down_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.17.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.17.mlp.down_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.q_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.k_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.v_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.o_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.18.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.18.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.18.mlp.gate_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.18.mlp.up_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.18.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.18.mlp.up_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.18.mlp.down_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.18.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.18.mlp.down_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.q_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.k_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.v_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.o_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.19.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.19.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.19.mlp.gate_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.19.mlp.up_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.19.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.19.mlp.up_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.19.mlp.down_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.19.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.19.mlp.down_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.20.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.20.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.20.self_attn.q_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.20.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.20.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.20.self_attn.k_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.20.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.20.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.20.self_attn.v_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.20.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.20.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.20.self_attn.o_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.20.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.20.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.20.mlp.gate_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.20.mlp.up_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.20.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.20.mlp.up_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.20.mlp.down_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.20.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.20.mlp.down_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.21.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.21.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.21.self_attn.q_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.21.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.21.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.21.self_attn.k_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.21.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.21.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.21.self_attn.v_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.21.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.21.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.21.self_attn.o_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.21.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.21.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.21.mlp.gate_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.21.mlp.up_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.21.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.21.mlp.up_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.21.mlp.down_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.21.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.21.mlp.down_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.22.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.22.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.22.self_attn.q_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.22.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.22.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.22.self_attn.k_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.22.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.22.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.22.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.22.self_attn.v_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.22.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.22.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.22.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.22.self_attn.o_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.22.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.22.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.22.mlp.gate_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.22.mlp.up_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.22.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.22.mlp.up_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.22.mlp.down_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.22.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.22.mlp.down_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.23.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.23.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.23.self_attn.q_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.23.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.23.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.23.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.23.self_attn.k_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.23.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.23.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.23.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.23.self_attn.v_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.23.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.23.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.23.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.23.self_attn.o_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.23.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.23.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.23.mlp.gate_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.23.mlp.up_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.23.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.23.mlp.up_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.23.mlp.down_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.23.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.23.mlp.down_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.24.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.24.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.24.self_attn.q_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.24.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.24.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.24.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.24.self_attn.k_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.24.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.24.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.24.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.24.self_attn.v_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.24.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.24.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.24.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.24.self_attn.o_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.24.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.24.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.24.mlp.gate_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.24.mlp.up_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.24.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.24.mlp.up_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.24.mlp.down_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.24.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.24.mlp.down_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.25.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.25.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.25.self_attn.q_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.25.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.25.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.25.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.25.self_attn.k_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.25.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.25.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.25.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.25.self_attn.v_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.25.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.25.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.25.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.25.self_attn.o_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.25.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.25.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.25.mlp.gate_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.25.mlp.up_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.25.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.25.mlp.up_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.25.mlp.down_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.25.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.25.mlp.down_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.26.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.26.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.26.self_attn.q_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.26.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.26.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.26.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.26.self_attn.k_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.26.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.26.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.26.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.26.self_attn.v_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.26.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.26.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.26.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.26.self_attn.o_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.26.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.26.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.26.mlp.gate_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.26.mlp.up_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.26.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.26.mlp.up_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.26.mlp.down_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.26.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.26.mlp.down_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.27.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.27.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.27.self_attn.q_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.27.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.27.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.27.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.27.self_attn.k_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.27.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.27.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.27.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.27.self_attn.v_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.27.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.27.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.27.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.27.self_attn.o_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.27.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.27.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.27.mlp.gate_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.27.mlp.up_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.27.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.27.mlp.up_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.27.mlp.down_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.27.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.27.mlp.down_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.28.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.28.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.28.self_attn.q_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.28.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.28.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.28.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.28.self_attn.k_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.28.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.28.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.28.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.28.self_attn.v_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.28.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.28.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.28.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.28.self_attn.o_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.28.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.28.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.28.mlp.gate_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.28.mlp.up_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.28.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.28.mlp.up_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.28.mlp.down_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.28.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.28.mlp.down_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.29.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.29.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.29.self_attn.q_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.29.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.29.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.29.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.29.self_attn.k_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.29.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.29.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.29.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.29.self_attn.v_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.29.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.29.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.29.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.29.self_attn.o_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.29.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.29.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.29.mlp.gate_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.29.mlp.up_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.29.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.29.mlp.up_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.29.mlp.down_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.29.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.29.mlp.down_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.30.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.30.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.30.self_attn.q_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.30.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.30.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.30.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.30.self_attn.k_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.30.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.30.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.30.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.30.self_attn.v_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.30.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.30.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.30.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.30.self_attn.o_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.30.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.30.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.30.mlp.gate_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.30.mlp.up_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.30.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.30.mlp.up_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.30.mlp.down_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.30.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.30.mlp.down_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.31.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.31.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.31.self_attn.q_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.31.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.31.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.31.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.31.self_attn.k_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.31.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.31.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.31.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.31.self_attn.v_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.31.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.31.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.31.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.31.self_attn.o_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.31.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.31.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.31.mlp.gate_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.31.mlp.up_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.31.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.31.mlp.up_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.31.mlp.down_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.31.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.31.mlp.down_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.32.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.32.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.32.self_attn.q_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.32.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.32.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.32.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.32.self_attn.k_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.32.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.32.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.32.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.32.self_attn.v_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.32.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.32.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.32.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.32.self_attn.o_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.32.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.32.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.32.mlp.gate_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.32.mlp.up_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.32.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.32.mlp.up_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.32.mlp.down_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.32.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.32.mlp.down_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.33.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.33.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.33.self_attn.q_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.33.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.33.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.33.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.33.self_attn.k_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.33.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.33.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.33.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.33.self_attn.v_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.33.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.33.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.33.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.33.self_attn.o_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.33.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.33.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.33.mlp.gate_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.33.mlp.up_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.33.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.33.mlp.up_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.33.mlp.down_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.33.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.33.mlp.down_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.34.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.34.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.34.self_attn.q_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.34.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.34.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.34.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.34.self_attn.k_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.34.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.34.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.34.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.34.self_attn.v_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.34.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.34.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.34.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.34.self_attn.o_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.34.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.34.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.34.mlp.gate_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.34.mlp.up_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.34.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.34.mlp.up_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.34.mlp.down_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.34.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.34.mlp.down_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.35.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.35.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.35.self_attn.q_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.35.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.35.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.35.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.35.self_attn.k_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.35.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.35.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.35.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.35.self_attn.v_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.35.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.35.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.35.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.35.self_attn.o_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.35.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.35.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.35.mlp.gate_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.35.mlp.up_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.35.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.35.mlp.up_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.35.mlp.down_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.35.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.35.mlp.down_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.36.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.36.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.36.self_attn.q_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.36.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.36.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.36.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.36.self_attn.k_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.36.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.36.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.36.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.36.self_attn.v_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.36.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.36.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.36.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.36.self_attn.o_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.36.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.36.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.36.mlp.gate_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.36.mlp.up_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.36.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.36.mlp.up_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.36.mlp.down_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.36.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.36.mlp.down_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.36.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.36.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.37.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.37.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.37.self_attn.q_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.37.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.37.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.37.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.37.self_attn.k_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.37.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.37.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.37.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.37.self_attn.v_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.37.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.37.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.37.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.37.self_attn.o_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.37.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.37.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.37.mlp.gate_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.37.mlp.up_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.37.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.37.mlp.up_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.37.mlp.down_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.37.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.37.mlp.down_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.37.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.37.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.38.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.38.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.38.self_attn.q_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.38.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.38.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.38.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.38.self_attn.k_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.38.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.38.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.38.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.38.self_attn.v_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.38.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.38.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.38.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.38.self_attn.o_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.38.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.38.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.38.mlp.gate_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.38.mlp.up_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.38.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.38.mlp.up_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.38.mlp.down_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.38.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.38.mlp.down_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.38.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.38.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.39.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.39.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.39.self_attn.q_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.39.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.39.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.39.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.39.self_attn.k_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.39.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.39.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.39.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.39.self_attn.v_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.39.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.39.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.39.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.39.self_attn.o_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.39.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.39.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.39.mlp.gate_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.39.mlp.up_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.39.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.39.mlp.up_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.39.mlp.down_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.39.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.39.mlp.down_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.39.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.39.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.40.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.40.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.40.self_attn.q_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.40.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.40.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.40.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.40.self_attn.k_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.40.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.40.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.40.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.40.self_attn.v_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.40.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.40.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.40.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.40.self_attn.o_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.40.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.40.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.40.mlp.gate_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.40.mlp.up_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.40.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.40.mlp.up_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.40.mlp.down_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.40.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.40.mlp.down_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.40.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.40.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.41.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.41.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.41.self_attn.q_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.41.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.41.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.41.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.41.self_attn.k_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.41.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.41.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.41.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.41.self_attn.v_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.41.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.41.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.41.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.41.self_attn.o_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.41.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.41.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.41.mlp.gate_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.41.mlp.up_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.41.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.41.mlp.up_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.41.mlp.down_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.41.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.41.mlp.down_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.41.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.41.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.42.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.42.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.42.self_attn.q_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.42.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.42.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.42.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.42.self_attn.k_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.42.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.42.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.42.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.42.self_attn.v_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.42.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.42.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.42.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.42.self_attn.o_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.42.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.42.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.42.mlp.gate_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.42.mlp.up_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.42.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.42.mlp.up_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.42.mlp.down_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.42.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.42.mlp.down_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.42.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.42.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.43.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.43.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.43.self_attn.q_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.43.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.43.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.43.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.43.self_attn.k_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.43.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.43.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.43.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.43.self_attn.v_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.43.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.43.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.43.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.43.self_attn.o_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.43.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.43.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.43.mlp.gate_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.43.mlp.up_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.43.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.43.mlp.up_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.43.mlp.down_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.43.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.43.mlp.down_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.43.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.43.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.44.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.44.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.44.self_attn.q_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.44.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.44.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.44.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.44.self_attn.k_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.44.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.44.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.44.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.44.self_attn.v_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.44.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.44.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.44.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.44.self_attn.o_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.44.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.44.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.44.mlp.gate_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.44.mlp.up_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.44.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.44.mlp.up_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.44.mlp.down_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.44.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.44.mlp.down_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.44.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.44.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.45.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.45.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.45.self_attn.q_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.45.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.45.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.45.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.45.self_attn.k_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.45.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.45.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.45.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.45.self_attn.v_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.45.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.45.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.45.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.45.self_attn.o_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.45.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.45.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.45.mlp.gate_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.45.mlp.up_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.45.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.45.mlp.up_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.45.mlp.down_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.45.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.45.mlp.down_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.45.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.45.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.46.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.46.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.46.self_attn.q_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.46.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.46.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.46.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.46.self_attn.k_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.46.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.46.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.46.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.46.self_attn.v_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.46.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.46.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.46.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.46.self_attn.o_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.46.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.46.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.46.mlp.gate_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.46.mlp.up_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.46.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.46.mlp.up_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.46.mlp.down_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.46.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.46.mlp.down_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.46.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.46.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.47.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.47.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.47.self_attn.q_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.47.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.47.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.47.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.47.self_attn.k_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.47.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.47.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.47.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.47.self_attn.v_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.47.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.47.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.47.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.47.self_attn.o_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.47.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.47.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.47.mlp.gate_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.47.mlp.up_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.47.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.47.mlp.up_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.47.mlp.down_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.47.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.47.mlp.down_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.47.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.47.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.norm.weight": "model-00002-of-00002.safetensors", + "lm_head.weight": "model-00002-of-00002.safetensors" + } +} \ No newline at end of file diff --git a/requirements.txt b/requirements.txt new file mode 100644 index 0000000..68040e0 --- /dev/null +++ b/requirements.txt @@ -0,0 +1,6 @@ +torch>=2.0.0 +transformers>=4.38.0 +accelerate>=0.24.0 +bitsandbytes>=0.41.0 +pandas>=2.0.0 +numpy>=1.24.0 \ No newline at end of file diff --git a/script.py b/script.py new file mode 100644 index 0000000..d2e0191 --- /dev/null +++ b/script.py @@ -0,0 +1,353 @@ +# ============================================================ +# IOL-AI 2026: ALGEBRAIC INDUCTION SOLVER (SUBMISSION SCRIPT) +# ============================================================ + +import os +# The evaluation sandbox has no internet access. +# These environment variables force Transformers to use local files only. +os.environ["HF_HUB_OFFLINE"] = "1" +os.environ["TRANSFORMERS_OFFLINE"] = "1" +os.environ["TOKENIZERS_PARALLELISM"] = "false" + +import gc, re, time, torch, json +import pandas as pd +from collections import Counter +from transformers import AutoTokenizer, AutoModelForCausalLM + +# ──────────────────────────────────────────────────── +# 1. CONFIGURATION AND MODEL LOAD +# ──────────────────────────────────────────────────── +try: + del model, tok +except NameError: + pass + +gc.collect() +torch.cuda.empty_cache() + +MODEL_ID = "." # Load weights directly from the repository +MAX_TOKEN_BUDGET = 2048 +INDUCT_MAX_TOKENS = 800 +MAX_ATTEMPTS = 3 +GLOBAL_TIME_LIMIT = 1700 # 28.3 minutes (safe margin under 30 min limit) +SC_TASKS = frozenset({"match_letters", "fill_blanks"}) +SC_K = 3 + +print("Loading tokenizer and model...", flush=True) +tok = AutoTokenizer.from_pretrained(MODEL_ID, trust_remote_code=True) +model = AutoModelForCausalLM.from_pretrained( + MODEL_ID, dtype=torch.float16, device_map="auto", trust_remote_code=True +).eval() +print("Model loaded successfully.", flush=True) + +tok.padding_side = "left" +if tok.pad_token_id is None: + tok.pad_token = tok.eos_token or tok.unk_token + +# ──────────────────────────────────────────────────── +# 2. EOS DISCOVERY +# ──────────────────────────────────────────────────── +def get_eos_ids(tokenizer, model): + eos_ids = set() + if tokenizer.eos_token_id is not None: + eos_ids.add(int(tokenizer.eos_token_id)) + meos = getattr(model.generation_config, "eos_token_id", None) + if meos: + if isinstance(meos, (list, tuple, set)): eos_ids.update(int(x) for x in meos) + else: eos_ids.add(int(meos)) + return sorted(list(eos_ids)) + +EOS_IDS = get_eos_ids(tok, model) +EOS_SET = set(EOS_IDS) +model.generation_config.eos_token_id = EOS_IDS +model.generation_config.pad_token_id = tok.pad_token_id + +# ──────────────────────────────────────────────────── +# 3. DYNAMIC CONTEXT READERS +# ──────────────────────────────────────────────────── +_IPA_HINT = re.compile(r"[\u0250-\u02AF\u02B0-\u02FF\u0300-\u036F\u1D00-\u1D7Føœæðθŋɣʔ]") +_ASKS_NON_PHONETIC = re.compile(r"(?i)translate\s+into\s+english|write\s+(it\s+)?in\s+the\s+[\w'\u2019-]+\s+orthography|in\s+the\s+regular\s+orthography") +_ASKS_TRANSCRIPTION = re.compile(r"(?i)\b(transcribe|transcription|phonetic(ally)?)\b") + +def _bracketed_forms(text: str) -> list[str]: + out = [] + for m in re.finditer(r"\[([^\[\]\n]{1,40})\]", text): + inner = m.group(1).strip() + if not inner or re.fullmatch(r"[\d\s,.\-]+", inner): continue + out.append(inner) + return out + +def is_phonetic_task(context: str, query: str, min_forms: int = 3) -> bool: + if _ASKS_NON_PHONETIC.search(query): return False + if _bracketed_forms(query) and not _ASKS_TRANSCRIPTION.search(query): return False + forms = _bracketed_forms(context) + _bracketed_forms(query) + if len(forms) < min_forms: return False + phonetic_looking = sum(1 for f in forms if _IPA_HINT.search(f) or ":" in f) + return phonetic_looking >= max(2, len(forms) // 4) + +def count_items(query: str) -> int: + n = len(re.findall(r"(?m)^\s*\d+[.)]", query)) + if n: return n + if "blanks" in query.lower(): + m = re.search(r"\((\d+)-(\d+)\)", query) + if m: return int(m.group(2)) - int(m.group(1)) + 1 + return len(re.findall(r"\(\d+\)", query)) or 0 + return 0 + +# ──────────────────────────────────────────────────── +# 4. DEFENSIVE PARSING +# ──────────────────────────────────────────────────── +_TURN_NOISE = re.compile(r"<\|/?END_OF_TURN_TOKEN\|>|<\|/?START_OF_TURN_TOKEN\|>|<\|CHATBOT_TOKEN\|>|||<\|im_end\|>|<\|im_start\|>") +_MARKER = re.compile(r"(?im)^\s*final answers?\s*:?\s*$") + +def _looks_like_prose(line: str) -> bool: + if re.search(r"(?i)^(final answers?|answers?|note|reviewing|summary|explanation|verification)\b.*:$", line): return True + if re.search(r"(?i)^(here (are|is)|the (final )?answers? (are|is)|based on|therefore|thus|in summary)\b", line): return True + if line.rstrip().endswith(":") and len(line) > 3: return True + if len(line) > 120: return True + return False + +def _strip_gloss_keep_form(line: str) -> str: + s = re.sub(r"\*\*", "", (line or "").strip()) + s = re.split(r"\s+_?(?:GCY|NS|N/A)_?\b", s, maxsplit=1, flags=re.I)[0].strip() + m = re.match(r"^(.+?)\s+[-–—]\s+((?:to|the|a|an|in|of|for|being|means?)\b.*)$", s, flags=re.I) + if m: s = m.group(1).strip() + return s.strip() + +def parse_answers(text: str, n_items: int = 0) -> list[str]: + text = _TURN_NOISE.sub("", text or "") + markers = list(_MARKER.finditer(text)) + if markers: + text = text[markers[-1].end():] + else: + m = re.search(r'(.*?)', text, re.DOTALL | re.IGNORECASE) + if m: text = m.group(1) + + answers = [] + for line in text.splitlines(): + line = re.sub(r"^\s*\d+[.)]\s*", "", line).strip().strip("`").strip("*") + if not line or _looks_like_prose(line): continue + + line = _strip_gloss_keep_form(line) + if not line: continue + + if re.fullmatch(r"(?:[A-Za-z]\s+)+[A-Za-z]", line): + answers.extend([p.upper() for p in line.split()]) + continue + answers.append(line) + + if n_items > 0: + answers = answers[:n_items] + if len(answers) < n_items: + answers += [""] * (n_items - len(answers)) + return answers + +def majority_vote(samples: list[list[str]], n_items: int) -> list[str]: + usable = [s for s in samples if any(x.strip() for x in s)] + if not usable: return [""] * max(n_items, 0) + n = n_items or max(len(s) for s in usable) + padded = [(list(s) + [""] * n)[:n] for s in usable] + counts = Counter(tuple(p) for p in padded) + best, c = counts.most_common(1)[0] + if c >= 2: return list(best) + return [Counter(p[i] for p in padded).most_common(1)[0][0] for i in range(n)] + +# ──────────────────────────────────────────────────── +# 5. PROMPT BUILDERS (ALGEBRAIC INDUCTION) +# ──────────────────────────────────────────────────── +SYSTEM_BASE = ( + "You are an elite computational linguist solving International Linguistics Olympiad problems. " + "This is a closed-world puzzle. DO NOT use your knowledge of real-world languages. " + "You may meet a task type you have never seen: read the instruction and the examples, and answer in the same form they use. " + "You MUST output your reasoning inside tags first. " + "After your reasoning is complete, you MUST write a line that says exactly FINAL ANSWERS: and, below it, " + "one answer per line in the order the items are asked -- the bare answer only, no numbering, " + "no quotes, no extra text. After FINAL ANSWERS:, output only the answers, exactly one line per " + "numbered item, then stop." +) + +PHONETIC_INSTRUCTION = ( + "IMPORTANT -- this problem uses PHONETIC TRANSCRIPTION. The examples write forms " + "inside square brackets, like [bø:va]. Your answers must be phonetic transcriptions " + "in exactly that same notation: enclosed in square brackets, using the same phonetic " + "symbols. Do NOT give an English meaning or gloss -- give the transcribed FORM." +) + +def build_system(task_type: str, context: str, query: str) -> str: + parts = [SYSTEM_BASE] + if is_phonetic_task(context, query): + parts.append(PHONETIC_INSTRUCTION) + task_type = str(task_type).strip().lower() + if task_type == "match_letters": + parts.append("This is a MATCHING task. Answer with a SINGLE OPTION LETTER only (e.g., C).") + elif task_type == "text_to_num": + parts.append("This is a TEXT-TO-NUMBER task. Give the number in digits only (e.g., 111).") + return "\n\n".join(parts) + +def build_user(row, n_items: int, rules: str = "", mode: str = "answer", error_feedback: str = None) -> str: + content = f"{str(row['context']).strip()}\n\n{str(row['query']).strip()}" + + if mode == "induct": + content += ( + "\n\nDeduce the linguistic system as a strict ALGEBRAIC EQUATION SHEET. DO NOT write prose. DO NOT answer the QUERY yet. " + "Inside tags, output ONLY the following mathematical notations based on the CONTEXT:\n\n" + "1. ALIGNMENT: Define the abstract structure using variables.\n" + " - If concatenative: `Word = A + B + C` (e.g., `anguls = angul + s`)\n" + " - If infixing: `Word = A + Infix + B` (e.g., `sumulat = s + um + ulat`)\n" + " - If templatic/ablaut: `Word = F(Root)` (e.g., `sang = Past(sing)`, `kataba = CaCaCa(k,t,b)`)\n" + " - If reduplication: `Word = A + A` (e.g., `bukubuku = buku + buku`)\n" + "2. MORPHOLOGY: Map variables to meanings. (e.g., `A = sing`, `Past = F()`, `s = Plural`)\n" + "3. PHONOLOGY: Write exact sound changes using rule notation: /input/ -> [output] / environment. (e.g., `/v/ -> [g] / ø:_a`)\n" + "4. MATCHING (if applicable): Map forms to options using matrices. (e.g., `u'u = breast = Option A`)\n" + "5. NUMBERS (if applicable): Map bases mathematically. (e.g., `123 = 6 * 20^1 + 3 * 20^0`)\n\n" + "Then write a line that says exactly: RULES:" + ) + return content + + if rules.strip(): + content += ( + f"\n\nINDUCED RULES:\n{rules.strip()}\n\n" + "CRITICAL: You must solve the algebraic equations from the RULES to construct the answers. " + "Do NOT guess. Do NOT blindly copy and paste full words from the context. " + "Apply the exact functions, morpheme slots, and sound changes to derive the final forms." + ) + + if n_items > 0: + content += f"\n\nThere are exactly {n_items} items to answer. Give exactly {n_items} answers after FINAL ANSWERS:, one per line, no more and no fewer." + + if error_feedback: + content += f"\n\nPREVIOUS ATTEMPT FAILED:\n{error_feedback}\n\nFix your equation solving and output the corrected answers again." + + return content + +def extract_rules(text: str) -> str: + text = _TURN_NOISE.sub("", text or "") + m = list(re.finditer(r"(?im)^\s*rules?\s*:?\s*$", text)) + if m: return text[m[-1].end():].strip()[:2000] + return text.strip()[:2000] + +# ──────────────────────────────────────────────────── +# 6. INFERENCE ENGINE +# ──────────────────────────────────────────────────── +@torch.inference_mode() +def generate(prompt_text: str, max_new_tokens: int, sample: bool = False, seed: int = 0): + torch.manual_seed(seed) + if torch.cuda.is_available(): torch.cuda.manual_seed_all(seed) + + enc = tok(prompt_text, return_tensors="pt", add_special_tokens=False).to(model.device) + plen = enc["input_ids"].shape[1] + + kw = dict(do_sample=True, temperature=0.6, top_p=0.95) if sample else dict(do_sample=False) + + out = model.generate( + **enc, max_new_tokens=max_new_tokens, use_cache=True, + eos_token_id=EOS_IDS, pad_token_id=tok.pad_token_id, **kw + ) + gid = out[0, plen:] + + for pos, tid in enumerate(gid.tolist()): + if tid in EOS_SET: + rt = tok.decode(gid[:pos+1], skip_special_tokens=False).strip() + return rt, pos+1 + rt = tok.decode(gid, skip_special_tokens=False).strip() + return rt, gid.shape[0] + +# ──────────────────────────────────────────────────── +# 7. LOAD DATA & DYNAMIC INFERENCE LOOP +# ──────────────────────────────────────────────────── +print("Loading test data...", flush=True) +df = pd.read_csv("/tmp/data/test.csv", dtype=str).fillna("") + +if "id" not in df.columns: + df["id"] = df.index + +results_by_id = {} +run_start = time.time() +order = df.index.tolist() +order.sort(key=lambda idx: len(str(df.loc[idx,"context"]))+len(str(df.loc[idx,"query"]))) + +current_token_budget = MAX_TOKEN_BUDGET + +for i, row_id in enumerate(order): + row = df.loc[row_id] + task_type = str(row.get("task_type", "general")) + n_items = count_items(str(row["query"])) + + t0 = time.time() + messages = [] + final_answers = [] + raw_output = "" + status = "FAIL" + gen_len = 0 + + elapsed = time.time() - run_start + remaining_time = GLOBAL_TIME_LIMIT - elapsed + problems_left = len(order) - i + max_allowed_tokens_for_time = max(256, int((remaining_time - (problems_left * 5)) * 10)) + if max_allowed_tokens_for_time < current_token_budget: + current_token_budget = max_allowed_tokens_for_time + + # PASS 1: Induction (Greedy, strict algebraic extraction) + system_prompt = build_system(task_type, str(row["context"]), str(row["query"])) + induct_user = build_user(row, n_items=0, mode="induct") + induct_prompt = tok.apply_chat_template( + [{"role":"system","content":system_prompt}, {"role":"user","content":induct_user}], + add_generation_prompt=True, tokenize=False + ) + induct_raw, _ = generate(induct_prompt, INDUCT_MAX_TOKENS, sample=False, seed=1) + rules = extract_rules(induct_raw) + + for attempt in range(MAX_ATTEMPTS): + error_feedback = messages[-1] if messages else None + user_prompt = build_user(row, n_items=n_items, rules=rules, mode="answer", error_feedback=error_feedback) + prompt = tok.apply_chat_template( + [{"role":"system","content":system_prompt}, {"role":"user","content":user_prompt}], + add_generation_prompt=True, tokenize=False + ) + + if task_type in SC_TASKS and attempt == 0: + samples = [] + raw_samples = [] + for k in range(SC_K): + raw_out, gen_len = generate(prompt, current_token_budget, sample=True, seed=1000+k*17) + raw_samples.append(raw_out) + samples.append(parse_answers(raw_out, n_items=n_items)) + final_answers = majority_vote(samples, n_items) + raw_output = "\n---\n".join(raw_samples) + else: + raw_output, gen_len = generate(prompt, current_token_budget, sample=False, seed=42+attempt) + final_answers = parse_answers(raw_output, n_items=n_items) + + if len(final_answers) < n_items or not all(final_answers): + msg = f"PARSE ERROR: Expected {n_items} answers, but extracted {len([a for a in final_answers if a])}. Ensure you output exactly {n_items} answers inside FINAL ANSWERS:." + messages.append(msg) + print(f"id={row_id} Attempt {attempt+1}: DENIED - {msg[:80]}", flush=True) + continue + + status = "OK" + print(f"id={row_id} Attempt {attempt+1}: SUCCESS", flush=True) + break + + if status != "OK": + final_answers = [""] * n_items if n_items > 0 else [] + print(f"id={row_id} Failed after {MAX_ATTEMPTS} attempts.", flush=True) + + wt = time.time() - t0 + results_by_id[row_id] = { + "id": row["id"], + "pred": final_answers + } + print(f" tok={gen_len:>4}/{current_token_budget} time={wt:.1f}s total={int(elapsed)}s", flush=True) + +# ──────────────────────────────────────────────────── +# 8. WRITE SUBMISSION +# ──────────────────────────────────────────────────── +out_rows = [] +for res in results_by_id.values(): + out_rows.append({ + "id": res["id"], + "pred": json.dumps(res["pred"], ensure_ascii=False) + }) + +pd.DataFrame(out_rows, columns=["id", "pred"]).to_csv("submission.csv", index=False) +print("wrote submission.csv", flush=True) \ No newline at end of file diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..1d385d6 --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,23 @@ +{ + "bos_token": { + "content": "<｜begin▁of▁sentence｜>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "<｜end▁of▁sentence｜>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "<｜end▁of▁sentence｜>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..1a2db24 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893 +size 11422778 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..b068ffc --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,195 @@ +{ + "add_bos_token": true, + "add_eos_token": false, + "add_prefix_space": null, + "added_tokens_decoder": { + "151643": { + "content": "<｜end▁of▁sentence｜>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151644": { + "content": "<｜User｜>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151645": { + "content": "<｜Assistant｜>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151646": { + "content": "<｜begin▁of▁sentence｜>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151647": { + "content": "<|EOT|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151648": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151649": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151650": { + "content": "<|quad_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151651": { + "content": "<|quad_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151652": { + "content": "<|vision_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151653": { + "content": "<|vision_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151654": { + "content": "<|vision_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151655": { + "content": "<|image_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151656": { + "content": "<|video_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151657": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151658": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151659": { + "content": "<|fim_prefix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151660": { + "content": "<|fim_middle|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151661": { + "content": "<|fim_suffix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151662": { + "content": "<|fim_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151663": { + "content": "<|repo_name|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151664": { + "content": "<|file_sep|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + } + }, + "bos_token": "<｜begin▁of▁sentence｜>", + "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'\\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '' in content %}{% set content = content.split('')[-1] %}{% endif %}{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜>'}}{% endif %}", + "clean_up_tokenization_spaces": false, + "eos_token": "<｜end▁of▁sentence｜>", + "extra_special_tokens": {}, + "legacy": true, + "model_max_length": 16384, + "pad_token": "<｜end▁of▁sentence｜>", + "sp_model_kwargs": {}, + "tokenizer_class": "LlamaTokenizer", + "unk_token": null, + "use_default_system_prompt": false +}