initial add

README.md

@@ -0,0 +1,10 @@
+---
+library_name: transformers
+tags: []
+---
+
+# Model Card for parasail-ai/aya-23-8B-GPTQ-4-bit
+
+GPTQ quantized 4-bit version of [CohereForAI/aya-23-8B](https://huggingface.co/CohereForAI/aya-23-8B), calibrated using [aya_dataset](https://huggingface.co/datasets/CohereForAI/aya_dataset).
+See original model card for more information. 
+

config.json

@@ -0,0 +1,52 @@
+{
+  "_name_or_path": "parasail-ai/aya-23-8B-GPTQ-4bit",
+  "architectures": [
+    "CohereForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 5,
+  "eos_token_id": 255001,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "layer_norm_eps": 1e-05,
+  "logit_scale": 0.0625,
+  "max_position_embeddings": 8192,
+  "model_type": "cohere",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pad_token_id": 0,
+  "quantization_config": {
+    "batch_size": 1,
+    "bits": 4,
+    "block_name_to_quantize": null,
+    "cache_block_outputs": true,
+    "damp_percent": 0.1,
+    "dataset": null,
+    "desc_act": false,
+    "exllama_config": {
+      "version": 1
+    },
+    "group_size": 128,
+    "max_input_length": null,
+    "model_seqlen": null,
+    "module_name_preceding_first_block": null,
+    "modules_in_block_to_quantize": null,
+    "pad_token_id": null,
+    "quant_method": "gptq",
+    "sym": true,
+    "tokenizer": null,
+    "true_sequential": true,
+    "use_cuda_fp16": false,
+    "use_exllama": true
+  },
+  "rope_theta": 10000,
+  "torch_dtype": "float16",
+  "transformers_version": "4.42.4",
+  "use_cache": true,
+  "use_qk_norm": false,
+  "vocab_size": 256000
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 5,
+  "eos_token_id": 255001,
+  "pad_token_id": 0,
+  "transformers_version": "4.42.4"
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9344fee4ce1662147a6d5d6b561c99458e29ac05f2f30222e6a4e049c039bb8
+size 4986545816

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f57102944dcdaad8494e5420da7490f5244c3ff8f9acf79bd7ce743d6713734
+size 741937056

model.safetensors.index.json

@@ -0,0 +1,937 @@
+{
+  "metadata": {
+    "total_size": 5728378880
+  },
+  "weight_map": {
+    "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.down_proj.g_idx": "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.mlp.gate_proj.g_idx": "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.g_idx": "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.self_attn.k_proj.g_idx": "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.o_proj.g_idx": "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.self_attn.q_proj.g_idx": "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.v_proj.g_idx": "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.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.down_proj.g_idx": "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.mlp.gate_proj.g_idx": "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.g_idx": "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.self_attn.k_proj.g_idx": "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.o_proj.g_idx": "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.self_attn.q_proj.g_idx": "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.v_proj.g_idx": "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.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.down_proj.g_idx": "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.mlp.gate_proj.g_idx": "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.g_idx": "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.self_attn.k_proj.g_idx": "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.o_proj.g_idx": "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.self_attn.q_proj.g_idx": "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.v_proj.g_idx": "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.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.down_proj.g_idx": "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.mlp.gate_proj.g_idx": "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.g_idx": "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.self_attn.k_proj.g_idx": "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.o_proj.g_idx": "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.self_attn.q_proj.g_idx": "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.v_proj.g_idx": "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.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.down_proj.g_idx": "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.mlp.gate_proj.g_idx": "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.g_idx": "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.self_attn.k_proj.g_idx": "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.o_proj.g_idx": "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.self_attn.q_proj.g_idx": "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.v_proj.g_idx": "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.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.g_idx": "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.mlp.gate_proj.g_idx": "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.g_idx": "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.self_attn.k_proj.g_idx": "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.o_proj.g_idx": "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.self_attn.q_proj.g_idx": "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.v_proj.g_idx": "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.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.g_idx": "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.mlp.gate_proj.g_idx": "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.g_idx": "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.self_attn.k_proj.g_idx": "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.o_proj.g_idx": "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.self_attn.q_proj.g_idx": "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.v_proj.g_idx": "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.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.down_proj.g_idx": "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.mlp.gate_proj.g_idx": "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.g_idx": "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.self_attn.k_proj.g_idx": "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.o_proj.g_idx": "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.self_attn.q_proj.g_idx": "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.v_proj.g_idx": "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.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.down_proj.g_idx": "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.mlp.gate_proj.g_idx": "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.g_idx": "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.self_attn.k_proj.g_idx": "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.o_proj.g_idx": "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.self_attn.q_proj.g_idx": "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.v_proj.g_idx": "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.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.down_proj.g_idx": "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.mlp.gate_proj.g_idx": "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.g_idx": "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.self_attn.k_proj.g_idx": "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.o_proj.g_idx": "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.self_attn.q_proj.g_idx": "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.v_proj.g_idx": "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.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.down_proj.g_idx": "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.mlp.gate_proj.g_idx": "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.g_idx": "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.self_attn.k_proj.g_idx": "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.o_proj.g_idx": "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.self_attn.q_proj.g_idx": "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.v_proj.g_idx": "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.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.down_proj.g_idx": "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.mlp.gate_proj.g_idx": "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.g_idx": "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.self_attn.k_proj.g_idx": "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.o_proj.g_idx": "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.self_attn.q_proj.g_idx": "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.v_proj.g_idx": "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.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.down_proj.g_idx": "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.mlp.gate_proj.g_idx": "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.g_idx": "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.self_attn.k_proj.g_idx": "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.o_proj.g_idx": "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.self_attn.q_proj.g_idx": "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.v_proj.g_idx": "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.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.down_proj.g_idx": "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.mlp.gate_proj.g_idx": "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.g_idx": "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.self_attn.k_proj.g_idx": "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.o_proj.g_idx": "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.self_attn.q_proj.g_idx": "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.v_proj.g_idx": "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.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.g_idx": "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.mlp.gate_proj.g_idx": "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.g_idx": "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.self_attn.k_proj.g_idx": "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.o_proj.g_idx": "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.self_attn.q_proj.g_idx": "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.v_proj.g_idx": "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.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.g_idx": "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.mlp.gate_proj.g_idx": "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.g_idx": "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.self_attn.k_proj.g_idx": "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.o_proj.g_idx": "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.self_attn.q_proj.g_idx": "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.v_proj.g_idx": "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.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.g_idx": "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.mlp.gate_proj.g_idx": "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.g_idx": "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.self_attn.k_proj.g_idx": "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.o_proj.g_idx": "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.self_attn.q_proj.g_idx": "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.v_proj.g_idx": "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.24.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.gate_proj.g_idx": "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.g_idx": "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.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.down_proj.g_idx": "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.mlp.gate_proj.g_idx": "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.g_idx": "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.self_attn.k_proj.g_idx": "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.o_proj.g_idx": "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.self_attn.q_proj.g_idx": "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.v_proj.g_idx": "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.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.down_proj.g_idx": "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.mlp.gate_proj.g_idx": "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.g_idx": "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.self_attn.k_proj.g_idx": "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.o_proj.g_idx": "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.self_attn.q_proj.g_idx": "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.v_proj.g_idx": "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.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.down_proj.g_idx": "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.mlp.gate_proj.g_idx": "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.g_idx": "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.self_attn.k_proj.g_idx": "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.o_proj.g_idx": "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.self_attn.q_proj.g_idx": "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.v_proj.g_idx": "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.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.down_proj.g_idx": "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.mlp.gate_proj.g_idx": "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.g_idx": "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.self_attn.k_proj.g_idx": "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.o_proj.g_idx": "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.self_attn.q_proj.g_idx": "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.v_proj.g_idx": "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.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.down_proj.g_idx": "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.mlp.gate_proj.g_idx": "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.g_idx": "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.self_attn.k_proj.g_idx": "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.o_proj.g_idx": "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.self_attn.q_proj.g_idx": "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.v_proj.g_idx": "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.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.down_proj.g_idx": "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.mlp.gate_proj.g_idx": "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.g_idx": "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.self_attn.k_proj.g_idx": "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.o_proj.g_idx": "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.self_attn.q_proj.g_idx": "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.v_proj.g_idx": "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.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.down_proj.g_idx": "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.mlp.gate_proj.g_idx": "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.g_idx": "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.self_attn.k_proj.g_idx": "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.o_proj.g_idx": "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.self_attn.q_proj.g_idx": "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.v_proj.g_idx": "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.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.down_proj.g_idx": "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.mlp.gate_proj.g_idx": "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.g_idx": "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.self_attn.k_proj.g_idx": "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.o_proj.g_idx": "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.self_attn.q_proj.g_idx": "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.v_proj.g_idx": "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.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.down_proj.g_idx": "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.mlp.gate_proj.g_idx": "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.g_idx": "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.self_attn.k_proj.g_idx": "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.o_proj.g_idx": "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.self_attn.q_proj.g_idx": "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.v_proj.g_idx": "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.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.down_proj.g_idx": "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.mlp.gate_proj.g_idx": "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.g_idx": "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.self_attn.k_proj.g_idx": "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.o_proj.g_idx": "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.self_attn.q_proj.g_idx": "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.v_proj.g_idx": "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.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.down_proj.g_idx": "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.mlp.gate_proj.g_idx": "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.g_idx": "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.self_attn.k_proj.g_idx": "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.o_proj.g_idx": "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.self_attn.q_proj.g_idx": "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.v_proj.g_idx": "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.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.down_proj.g_idx": "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.mlp.gate_proj.g_idx": "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.g_idx": "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.self_attn.k_proj.g_idx": "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.o_proj.g_idx": "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.self_attn.q_proj.g_idx": "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.v_proj.g_idx": "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.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.down_proj.g_idx": "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.mlp.gate_proj.g_idx": "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.g_idx": "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.self_attn.k_proj.g_idx": "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.o_proj.g_idx": "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.self_attn.q_proj.g_idx": "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.v_proj.g_idx": "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.norm.weight": "model-00002-of-00002.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<BOS_TOKEN>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|END_OF_TURN_TOKEN|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<PAD>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c69a7ea6c0927dfac8c349186ebcf0466a4723c21cbdb2e850cf559f0bee92b8
+size 12777433

tokenizer_config.json

@@ -0,0 +1,330 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<PAD>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<UNK>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<CLS>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<SEP>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<MASK_TOKEN>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<BOS_TOKEN>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "<EOS_TOKEN>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": "<EOP_TOKEN>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "255000": {
+      "content": "<|START_OF_TURN_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255001": {
+      "content": "<|END_OF_TURN_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "255002": {
+      "content": "<|YES_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255003": {
+      "content": "<|NO_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255004": {
+      "content": "<|GOOD_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255005": {
+      "content": "<|BAD_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255006": {
+      "content": "<|USER_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255007": {
+      "content": "<|CHATBOT_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255008": {
+      "content": "<|SYSTEM_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255009": {
+      "content": "<|USER_0_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255010": {
+      "content": "<|USER_1_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255011": {
+      "content": "<|USER_2_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255012": {
+      "content": "<|USER_3_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255013": {
+      "content": "<|USER_4_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255014": {
+      "content": "<|USER_5_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255015": {
+      "content": "<|USER_6_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255016": {
+      "content": "<|USER_7_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255017": {
+      "content": "<|USER_8_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255018": {
+      "content": "<|USER_9_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255019": {
+      "content": "<|EXTRA_0_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255020": {
+      "content": "<|EXTRA_1_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255021": {
+      "content": "<|EXTRA_2_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255022": {
+      "content": "<|EXTRA_3_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255023": {
+      "content": "<|EXTRA_4_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255024": {
+      "content": "<|EXTRA_5_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255025": {
+      "content": "<|EXTRA_6_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255026": {
+      "content": "<|EXTRA_7_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255027": {
+      "content": "<|EXTRA_8_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255028": {
+      "content": "<|EXTRA_9_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "<BOS_TOKEN>",
+  "chat_template": [
+    {
+      "name": "default",
+      "template": "{{ bos_token }}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% elif false == true %}{% set loop_messages = messages %}{% set system_message = 'You are Command-R, a brilliant, sophisticated, AI-assistant trained to assist human users by providing thorough responses. You are trained by Cohere.' %}{% else %}{% set loop_messages = messages %}{% set system_message = false %}{% endif %}{% if system_message != false %}{{ '<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|>' + system_message + '<|END_OF_TURN_TOKEN|>' }}{% endif %}{% for message in loop_messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|START_OF_TURN_TOKEN|><|USER_TOKEN|>' + content.strip() + '<|END_OF_TURN_TOKEN|>' }}{% elif message['role'] == 'assistant' %}{{ '<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>'  + content.strip() + '<|END_OF_TURN_TOKEN|>' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>' }}{% endif %}"
+    },
+    {
+      "name": "tool_use",
+      "template": "{{ bos_token }}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = '## Task and Context\\nYou help people answer their questions and other requests interactively. You will be asked a very wide array of requests on all kinds of topics. You will be equipped with a wide range of search engines or similar tools to help you, which you use to research your answer. You should focus on serving the user\\'s needs as best you can, which will be wide-ranging.\\n\\n## Style Guide\\nUnless the user asks for a different style of answer, you should answer in full sentences, using proper grammar and spelling.' %}{% endif %}{{ '<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|>' }}{{ '# Safety Preamble' }}{{ '\nThe instructions in this section override those in the task description and style guide sections. Don\\'t answer questions that are harmful or immoral.' }}{{ '\n\n# System Preamble' }}{{ '\n## Basic Rules' }}{{ '\nYou are a powerful conversational AI trained by Cohere to help people. You are augmented by a number of tools, and your job is to use and consume the output of these tools to best help the user. You will see a conversation history between yourself and a user, ending with an utterance from the user. You will then see a specific instruction instructing you what kind of response to generate. When you answer the user\\'s requests, you cite your sources in your answers, according to those instructions.' }}{{ '\n\n# User Preamble' }}{{ '\n' + system_message }}{{'\n\n## Available Tools\nHere is a list of tools that you have available to you:\n\n'}}{% for tool in tools %}{% if loop.index0 != 0 %}{{ '\n\n'}}{% endif %}{{'```python\ndef ' + tool.name + '('}}{% for param_name, param_fields in tool.parameter_definitions.items() %}{% if loop.index0 != 0 %}{{ ', '}}{% endif %}{{param_name}}: {% if not param_fields.required %}{{'Optional[' + param_fields.type + '] = None'}}{% else %}{{ param_fields.type }}{% endif %}{% endfor %}{{ ') -> List[Dict]:\n    \"\"\"'}}{{ tool.description }}{% if tool.parameter_definitions|length != 0 %}{{ '\n\n    Args:\n        '}}{% for param_name, param_fields in tool.parameter_definitions.items() %}{% if loop.index0 != 0 %}{{ '\n        ' }}{% endif %}{{ param_name + ' ('}}{% if not param_fields.required %}{{'Optional[' + param_fields.type + ']'}}{% else %}{{ param_fields.type }}{% endif %}{{ '): ' + param_fields.description }}{% endfor %}{% endif %}{{ '\n    \"\"\"\n    pass\n```' }}{% endfor %}{{ '<|END_OF_TURN_TOKEN|>'}}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|START_OF_TURN_TOKEN|><|USER_TOKEN|>' + content.strip() + '<|END_OF_TURN_TOKEN|>' }}{% elif message['role'] == 'system' %}{{ '<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|>' + content.strip() + '<|END_OF_TURN_TOKEN|>' }}{% elif message['role'] == 'assistant' %}{{ '<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>'  + content.strip() + '<|END_OF_TURN_TOKEN|>' }}{% endif %}{% endfor %}{{'<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|>Write \\'Action:\\' followed by a json-formatted list of actions that you want to perform in order to produce a good response to the user\\'s last input. You can use any of the supplied tools any number of times, but you should aim to execute the minimum number of necessary actions for the input. You should use the `directly-answer` tool if calling the other tools is unnecessary. The list of actions you want to call should be formatted as a list of json objects, for example:\n```json\n[\n    {\n        \"tool_name\": title of the tool in the specification,\n        \"parameters\": a dict of parameters to input into the tool as they are defined in the specs, or {} if it takes no parameters\n    }\n]```<|END_OF_TURN_TOKEN|>'}}{% if add_generation_prompt %}{{ '<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>' }}{% endif %}"
+    },
+    {
+      "name": "rag",
+      "template": "{{ bos_token }}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = '## Task and Context\\nYou help people answer their questions and other requests interactively. You will be asked a very wide array of requests on all kinds of topics. You will be equipped with a wide range of search engines or similar tools to help you, which you use to research your answer. You should focus on serving the user\\'s needs as best you can, which will be wide-ranging.\\n\\n## Style Guide\\nUnless the user asks for a different style of answer, you should answer in full sentences, using proper grammar and spelling.' %}{% endif %}{{ '<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|>' }}{{ '# Safety Preamble' }}{{ '\nThe instructions in this section override those in the task description and style guide sections. Don\\'t answer questions that are harmful or immoral.' }}{{ '\n\n# System Preamble' }}{{ '\n## Basic Rules' }}{{ '\nYou are a powerful conversational AI trained by Cohere to help people. You are augmented by a number of tools, and your job is to use and consume the output of these tools to best help the user. You will see a conversation history between yourself and a user, ending with an utterance from the user. You will then see a specific instruction instructing you what kind of response to generate. When you answer the user\\'s requests, you cite your sources in your answers, according to those instructions.' }}{{ '\n\n# User Preamble' }}{{ '\n' + system_message }}{{ '<|END_OF_TURN_TOKEN|>'}}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|START_OF_TURN_TOKEN|><|USER_TOKEN|>' + content.strip() + '<|END_OF_TURN_TOKEN|>' }}{% elif message['role'] == 'system' %}{{ '<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|>' + content.strip() + '<|END_OF_TURN_TOKEN|>' }}{% elif message['role'] == 'assistant' %}{{ '<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>'  + content.strip() + '<|END_OF_TURN_TOKEN|>' }}{% endif %}{% endfor %}{{ '<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|>'}}{{ '<results>' }}{% for document in documents %}{{ '\nDocument: ' }}{{ loop.index0 }}\n{% for key, value in document.items() %}{{ key }}: {{value}}\n{% endfor %}{% endfor %}{{ '</results>'}}{{ '<|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|>' }}{{ 'Carefully perform the following instructions, in order, starting each with a new line.\n' }}{{ 'Firstly, Decide which of the retrieved documents are relevant to the user\\'s last input by writing \\'Relevant Documents:\\' followed by comma-separated list of document numbers. If none are relevant, you should instead write \\'None\\'.\n' }}{{ 'Secondly, Decide which of the retrieved documents contain facts that should be cited in a good answer to the user\\'s last input by writing \\'Cited Documents:\\' followed a comma-separated list of document numbers. If you dont want to cite any of them, you should instead write \\'None\\'.\n' }}{% if citation_mode=='accurate' %}{{ 'Thirdly, Write \\'Answer:\\' followed by a response to the user\\'s last input in high quality natural english. Use the retrieved documents to help you. Do not insert any citations or grounding markup.\n' }}{% endif %}{{ 'Finally, Write \\'Grounded answer:\\' followed by a response to the user\\'s last input in high quality natural english. Use the symbols <co: doc> and </co: doc> to indicate when a fact comes from a document in the search result, e.g <co: 0>my fact</co: 0> for a fact from document 0.' }}{{ '<|END_OF_TURN_TOKEN|>' }}{% if add_generation_prompt %}{{ '<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>' }}{% endif %}"
+    }
+  ],
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|END_OF_TURN_TOKEN|>",
+  "legacy": true,
+  "merges_file": null,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<PAD>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "CohereTokenizer",
+  "unk_token": null,
+  "use_default_system_prompt": false,
+  "vocab_file": null
+}