Upload folder using huggingface_hub

cal_data.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5fcb42ff7427408b7a2f971bc556032860c1c4939503eb30deb2c102babfba49
+size 1884248

config.json

@@ -0,0 +1,49 @@
+{
+    "architectures": [
+        "DbrxForCausalLM"
+    ],
+    "attn_config": {
+        "clip_qkv": 8,
+        "kv_n_heads": 8,
+        "model_type": "",
+        "rope_theta": 500000
+    },
+    "auto_map": {
+        "AutoConfig": "configuration_dbrx.DbrxConfig",
+        "AutoModelForCausalLM": "modeling_dbrx.DbrxForCausalLM"
+    },
+    "d_model": 6144,
+    "emb_pdrop": 0.0,
+    "ffn_config": {
+        "ffn_hidden_size": 10752,
+        "model_type": "",
+        "moe_jitter_eps": 0.01,
+        "moe_loss_weight": 0.05,
+        "moe_num_experts": 16,
+        "moe_top_k": 4
+    },
+    "initializer_range": 0.02,
+    "max_seq_len": 32768,
+    "model_type": "dbrx",
+    "n_heads": 48,
+    "n_layers": 40,
+    "output_router_logits": false,
+    "resid_pdrop": 0.0,
+    "router_aux_loss_coef": 0.05,
+    "tie_word_embeddings": false,
+    "torch_dtype": "bfloat16",
+    "transformers_version": "4.38.2",
+    "use_cache": true,
+    "vocab_size": 100352,
+    "quantization_config": {
+        "quant_method": "exl2",
+        "version": "0.0.17",
+        "bits": 2.5,
+        "head_bits": 6,
+        "calibration": {
+            "rows": 100,
+            "length": 2048,
+            "dataset": "(default)"
+        }
+    }
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "eos_token_id": [
+    100257
+  ],
+  "transformers_version": "4.38.2"
+}

hidden_states.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92e584c8cf5c819ab59d8b5958c1e3a69eb76e8f156e8605ef5c8ddb78968dd1
+size 2894079912

model.safetensors.index.json

@@ -0,0 +1,330 @@
+{
+  "metadata": {
+    "total_size": 263193047040
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00061-of-00061.safetensors",
+    "transformer.blocks.0.ffn.experts.mlp.v1": "model-00002-of-00061.safetensors",
+    "transformer.blocks.0.ffn.experts.mlp.w1": "model-00001-of-00061.safetensors",
+    "transformer.blocks.0.ffn.experts.mlp.w2": "model-00002-of-00061.safetensors",
+    "transformer.blocks.0.ffn.router.layer.weight": "model-00001-of-00061.safetensors",
+    "transformer.blocks.0.norm_attn_norm.attn.Wqkv.weight": "model-00001-of-00061.safetensors",
+    "transformer.blocks.0.norm_attn_norm.attn.out_proj.weight": "model-00001-of-00061.safetensors",
+    "transformer.blocks.0.norm_attn_norm.norm_1.weight": "model-00001-of-00061.safetensors",
+    "transformer.blocks.0.norm_attn_norm.norm_2.weight": "model-00001-of-00061.safetensors",
+    "transformer.blocks.1.ffn.experts.mlp.v1": "model-00003-of-00061.safetensors",
+    "transformer.blocks.1.ffn.experts.mlp.w1": "model-00003-of-00061.safetensors",
+    "transformer.blocks.1.ffn.experts.mlp.w2": "model-00004-of-00061.safetensors",
+    "transformer.blocks.1.ffn.router.layer.weight": "model-00002-of-00061.safetensors",
+    "transformer.blocks.1.norm_attn_norm.attn.Wqkv.weight": "model-00002-of-00061.safetensors",
+    "transformer.blocks.1.norm_attn_norm.attn.out_proj.weight": "model-00002-of-00061.safetensors",
+    "transformer.blocks.1.norm_attn_norm.norm_1.weight": "model-00002-of-00061.safetensors",
+    "transformer.blocks.1.norm_attn_norm.norm_2.weight": "model-00002-of-00061.safetensors",
+    "transformer.blocks.10.ffn.experts.mlp.v1": "model-00017-of-00061.safetensors",
+    "transformer.blocks.10.ffn.experts.mlp.w1": "model-00016-of-00061.safetensors",
+    "transformer.blocks.10.ffn.experts.mlp.w2": "model-00017-of-00061.safetensors",
+    "transformer.blocks.10.ffn.router.layer.weight": "model-00016-of-00061.safetensors",
+    "transformer.blocks.10.norm_attn_norm.attn.Wqkv.weight": "model-00016-of-00061.safetensors",
+    "transformer.blocks.10.norm_attn_norm.attn.out_proj.weight": "model-00016-of-00061.safetensors",
+    "transformer.blocks.10.norm_attn_norm.norm_1.weight": "model-00016-of-00061.safetensors",
+    "transformer.blocks.10.norm_attn_norm.norm_2.weight": "model-00016-of-00061.safetensors",
+    "transformer.blocks.11.ffn.experts.mlp.v1": "model-00018-of-00061.safetensors",
+    "transformer.blocks.11.ffn.experts.mlp.w1": "model-00018-of-00061.safetensors",
+    "transformer.blocks.11.ffn.experts.mlp.w2": "model-00019-of-00061.safetensors",
+    "transformer.blocks.11.ffn.router.layer.weight": "model-00017-of-00061.safetensors",
+    "transformer.blocks.11.norm_attn_norm.attn.Wqkv.weight": "model-00017-of-00061.safetensors",
+    "transformer.blocks.11.norm_attn_norm.attn.out_proj.weight": "model-00017-of-00061.safetensors",
+    "transformer.blocks.11.norm_attn_norm.norm_1.weight": "model-00017-of-00061.safetensors",
+    "transformer.blocks.11.norm_attn_norm.norm_2.weight": "model-00017-of-00061.safetensors",
+    "transformer.blocks.12.ffn.experts.mlp.v1": "model-00020-of-00061.safetensors",
+    "transformer.blocks.12.ffn.experts.mlp.w1": "model-00019-of-00061.safetensors",
+    "transformer.blocks.12.ffn.experts.mlp.w2": "model-00020-of-00061.safetensors",
+    "transformer.blocks.12.ffn.router.layer.weight": "model-00019-of-00061.safetensors",
+    "transformer.blocks.12.norm_attn_norm.attn.Wqkv.weight": "model-00019-of-00061.safetensors",
+    "transformer.blocks.12.norm_attn_norm.attn.out_proj.weight": "model-00019-of-00061.safetensors",
+    "transformer.blocks.12.norm_attn_norm.norm_1.weight": "model-00019-of-00061.safetensors",
+    "transformer.blocks.12.norm_attn_norm.norm_2.weight": "model-00019-of-00061.safetensors",
+    "transformer.blocks.13.ffn.experts.mlp.v1": "model-00021-of-00061.safetensors",
+    "transformer.blocks.13.ffn.experts.mlp.w1": "model-00021-of-00061.safetensors",
+    "transformer.blocks.13.ffn.experts.mlp.w2": "model-00022-of-00061.safetensors",
+    "transformer.blocks.13.ffn.router.layer.weight": "model-00020-of-00061.safetensors",
+    "transformer.blocks.13.norm_attn_norm.attn.Wqkv.weight": "model-00020-of-00061.safetensors",
+    "transformer.blocks.13.norm_attn_norm.attn.out_proj.weight": "model-00020-of-00061.safetensors",
+    "transformer.blocks.13.norm_attn_norm.norm_1.weight": "model-00020-of-00061.safetensors",
+    "transformer.blocks.13.norm_attn_norm.norm_2.weight": "model-00020-of-00061.safetensors",
+    "transformer.blocks.14.ffn.experts.mlp.v1": "model-00023-of-00061.safetensors",
+    "transformer.blocks.14.ffn.experts.mlp.w1": "model-00022-of-00061.safetensors",
+    "transformer.blocks.14.ffn.experts.mlp.w2": "model-00023-of-00061.safetensors",
+    "transformer.blocks.14.ffn.router.layer.weight": "model-00022-of-00061.safetensors",
+    "transformer.blocks.14.norm_attn_norm.attn.Wqkv.weight": "model-00022-of-00061.safetensors",
+    "transformer.blocks.14.norm_attn_norm.attn.out_proj.weight": "model-00022-of-00061.safetensors",
+    "transformer.blocks.14.norm_attn_norm.norm_1.weight": "model-00022-of-00061.safetensors",
+    "transformer.blocks.14.norm_attn_norm.norm_2.weight": "model-00022-of-00061.safetensors",
+    "transformer.blocks.15.ffn.experts.mlp.v1": "model-00024-of-00061.safetensors",
+    "transformer.blocks.15.ffn.experts.mlp.w1": "model-00024-of-00061.safetensors",
+    "transformer.blocks.15.ffn.experts.mlp.w2": "model-00025-of-00061.safetensors",
+    "transformer.blocks.15.ffn.router.layer.weight": "model-00023-of-00061.safetensors",
+    "transformer.blocks.15.norm_attn_norm.attn.Wqkv.weight": "model-00023-of-00061.safetensors",
+    "transformer.blocks.15.norm_attn_norm.attn.out_proj.weight": "model-00023-of-00061.safetensors",
+    "transformer.blocks.15.norm_attn_norm.norm_1.weight": "model-00023-of-00061.safetensors",
+    "transformer.blocks.15.norm_attn_norm.norm_2.weight": "model-00023-of-00061.safetensors",
+    "transformer.blocks.16.ffn.experts.mlp.v1": "model-00026-of-00061.safetensors",
+    "transformer.blocks.16.ffn.experts.mlp.w1": "model-00025-of-00061.safetensors",
+    "transformer.blocks.16.ffn.experts.mlp.w2": "model-00026-of-00061.safetensors",
+    "transformer.blocks.16.ffn.router.layer.weight": "model-00025-of-00061.safetensors",
+    "transformer.blocks.16.norm_attn_norm.attn.Wqkv.weight": "model-00025-of-00061.safetensors",
+    "transformer.blocks.16.norm_attn_norm.attn.out_proj.weight": "model-00025-of-00061.safetensors",
+    "transformer.blocks.16.norm_attn_norm.norm_1.weight": "model-00025-of-00061.safetensors",
+    "transformer.blocks.16.norm_attn_norm.norm_2.weight": "model-00025-of-00061.safetensors",
+    "transformer.blocks.17.ffn.experts.mlp.v1": "model-00027-of-00061.safetensors",
+    "transformer.blocks.17.ffn.experts.mlp.w1": "model-00027-of-00061.safetensors",
+    "transformer.blocks.17.ffn.experts.mlp.w2": "model-00028-of-00061.safetensors",
+    "transformer.blocks.17.ffn.router.layer.weight": "model-00026-of-00061.safetensors",
+    "transformer.blocks.17.norm_attn_norm.attn.Wqkv.weight": "model-00026-of-00061.safetensors",
+    "transformer.blocks.17.norm_attn_norm.attn.out_proj.weight": "model-00026-of-00061.safetensors",
+    "transformer.blocks.17.norm_attn_norm.norm_1.weight": "model-00026-of-00061.safetensors",
+    "transformer.blocks.17.norm_attn_norm.norm_2.weight": "model-00026-of-00061.safetensors",
+    "transformer.blocks.18.ffn.experts.mlp.v1": "model-00029-of-00061.safetensors",
+    "transformer.blocks.18.ffn.experts.mlp.w1": "model-00028-of-00061.safetensors",
+    "transformer.blocks.18.ffn.experts.mlp.w2": "model-00029-of-00061.safetensors",
+    "transformer.blocks.18.ffn.router.layer.weight": "model-00028-of-00061.safetensors",
+    "transformer.blocks.18.norm_attn_norm.attn.Wqkv.weight": "model-00028-of-00061.safetensors",
+    "transformer.blocks.18.norm_attn_norm.attn.out_proj.weight": "model-00028-of-00061.safetensors",
+    "transformer.blocks.18.norm_attn_norm.norm_1.weight": "model-00028-of-00061.safetensors",
+    "transformer.blocks.18.norm_attn_norm.norm_2.weight": "model-00028-of-00061.safetensors",
+    "transformer.blocks.19.ffn.experts.mlp.v1": "model-00030-of-00061.safetensors",
+    "transformer.blocks.19.ffn.experts.mlp.w1": "model-00030-of-00061.safetensors",
+    "transformer.blocks.19.ffn.experts.mlp.w2": "model-00031-of-00061.safetensors",
+    "transformer.blocks.19.ffn.router.layer.weight": "model-00029-of-00061.safetensors",
+    "transformer.blocks.19.norm_attn_norm.attn.Wqkv.weight": "model-00029-of-00061.safetensors",
+    "transformer.blocks.19.norm_attn_norm.attn.out_proj.weight": "model-00029-of-00061.safetensors",
+    "transformer.blocks.19.norm_attn_norm.norm_1.weight": "model-00029-of-00061.safetensors",
+    "transformer.blocks.19.norm_attn_norm.norm_2.weight": "model-00029-of-00061.safetensors",
+    "transformer.blocks.2.ffn.experts.mlp.v1": "model-00005-of-00061.safetensors",
+    "transformer.blocks.2.ffn.experts.mlp.w1": "model-00004-of-00061.safetensors",
+    "transformer.blocks.2.ffn.experts.mlp.w2": "model-00005-of-00061.safetensors",
+    "transformer.blocks.2.ffn.router.layer.weight": "model-00004-of-00061.safetensors",
+    "transformer.blocks.2.norm_attn_norm.attn.Wqkv.weight": "model-00004-of-00061.safetensors",
+    "transformer.blocks.2.norm_attn_norm.attn.out_proj.weight": "model-00004-of-00061.safetensors",
+    "transformer.blocks.2.norm_attn_norm.norm_1.weight": "model-00004-of-00061.safetensors",
+    "transformer.blocks.2.norm_attn_norm.norm_2.weight": "model-00004-of-00061.safetensors",
+    "transformer.blocks.20.ffn.experts.mlp.v1": "model-00032-of-00061.safetensors",
+    "transformer.blocks.20.ffn.experts.mlp.w1": "model-00031-of-00061.safetensors",
+    "transformer.blocks.20.ffn.experts.mlp.w2": "model-00032-of-00061.safetensors",
+    "transformer.blocks.20.ffn.router.layer.weight": "model-00031-of-00061.safetensors",
+    "transformer.blocks.20.norm_attn_norm.attn.Wqkv.weight": "model-00031-of-00061.safetensors",
+    "transformer.blocks.20.norm_attn_norm.attn.out_proj.weight": "model-00031-of-00061.safetensors",
+    "transformer.blocks.20.norm_attn_norm.norm_1.weight": "model-00031-of-00061.safetensors",
+    "transformer.blocks.20.norm_attn_norm.norm_2.weight": "model-00031-of-00061.safetensors",
+    "transformer.blocks.21.ffn.experts.mlp.v1": "model-00033-of-00061.safetensors",
+    "transformer.blocks.21.ffn.experts.mlp.w1": "model-00033-of-00061.safetensors",
+    "transformer.blocks.21.ffn.experts.mlp.w2": "model-00034-of-00061.safetensors",
+    "transformer.blocks.21.ffn.router.layer.weight": "model-00032-of-00061.safetensors",
+    "transformer.blocks.21.norm_attn_norm.attn.Wqkv.weight": "model-00032-of-00061.safetensors",
+    "transformer.blocks.21.norm_attn_norm.attn.out_proj.weight": "model-00032-of-00061.safetensors",
+    "transformer.blocks.21.norm_attn_norm.norm_1.weight": "model-00032-of-00061.safetensors",
+    "transformer.blocks.21.norm_attn_norm.norm_2.weight": "model-00032-of-00061.safetensors",
+    "transformer.blocks.22.ffn.experts.mlp.v1": "model-00035-of-00061.safetensors",
+    "transformer.blocks.22.ffn.experts.mlp.w1": "model-00034-of-00061.safetensors",
+    "transformer.blocks.22.ffn.experts.mlp.w2": "model-00035-of-00061.safetensors",
+    "transformer.blocks.22.ffn.router.layer.weight": "model-00034-of-00061.safetensors",
+    "transformer.blocks.22.norm_attn_norm.attn.Wqkv.weight": "model-00034-of-00061.safetensors",
+    "transformer.blocks.22.norm_attn_norm.attn.out_proj.weight": "model-00034-of-00061.safetensors",
+    "transformer.blocks.22.norm_attn_norm.norm_1.weight": "model-00034-of-00061.safetensors",
+    "transformer.blocks.22.norm_attn_norm.norm_2.weight": "model-00034-of-00061.safetensors",
+    "transformer.blocks.23.ffn.experts.mlp.v1": "model-00036-of-00061.safetensors",
+    "transformer.blocks.23.ffn.experts.mlp.w1": "model-00036-of-00061.safetensors",
+    "transformer.blocks.23.ffn.experts.mlp.w2": "model-00037-of-00061.safetensors",
+    "transformer.blocks.23.ffn.router.layer.weight": "model-00035-of-00061.safetensors",
+    "transformer.blocks.23.norm_attn_norm.attn.Wqkv.weight": "model-00035-of-00061.safetensors",
+    "transformer.blocks.23.norm_attn_norm.attn.out_proj.weight": "model-00035-of-00061.safetensors",
+    "transformer.blocks.23.norm_attn_norm.norm_1.weight": "model-00035-of-00061.safetensors",
+    "transformer.blocks.23.norm_attn_norm.norm_2.weight": "model-00035-of-00061.safetensors",
+    "transformer.blocks.24.ffn.experts.mlp.v1": "model-00038-of-00061.safetensors",
+    "transformer.blocks.24.ffn.experts.mlp.w1": "model-00037-of-00061.safetensors",
+    "transformer.blocks.24.ffn.experts.mlp.w2": "model-00038-of-00061.safetensors",
+    "transformer.blocks.24.ffn.router.layer.weight": "model-00037-of-00061.safetensors",
+    "transformer.blocks.24.norm_attn_norm.attn.Wqkv.weight": "model-00037-of-00061.safetensors",
+    "transformer.blocks.24.norm_attn_norm.attn.out_proj.weight": "model-00037-of-00061.safetensors",
+    "transformer.blocks.24.norm_attn_norm.norm_1.weight": "model-00037-of-00061.safetensors",
+    "transformer.blocks.24.norm_attn_norm.norm_2.weight": "model-00037-of-00061.safetensors",
+    "transformer.blocks.25.ffn.experts.mlp.v1": "model-00039-of-00061.safetensors",
+    "transformer.blocks.25.ffn.experts.mlp.w1": "model-00039-of-00061.safetensors",
+    "transformer.blocks.25.ffn.experts.mlp.w2": "model-00040-of-00061.safetensors",
+    "transformer.blocks.25.ffn.router.layer.weight": "model-00038-of-00061.safetensors",
+    "transformer.blocks.25.norm_attn_norm.attn.Wqkv.weight": "model-00038-of-00061.safetensors",
+    "transformer.blocks.25.norm_attn_norm.attn.out_proj.weight": "model-00038-of-00061.safetensors",
+    "transformer.blocks.25.norm_attn_norm.norm_1.weight": "model-00038-of-00061.safetensors",
+    "transformer.blocks.25.norm_attn_norm.norm_2.weight": "model-00038-of-00061.safetensors",
+    "transformer.blocks.26.ffn.experts.mlp.v1": "model-00041-of-00061.safetensors",
+    "transformer.blocks.26.ffn.experts.mlp.w1": "model-00040-of-00061.safetensors",
+    "transformer.blocks.26.ffn.experts.mlp.w2": "model-00041-of-00061.safetensors",
+    "transformer.blocks.26.ffn.router.layer.weight": "model-00040-of-00061.safetensors",
+    "transformer.blocks.26.norm_attn_norm.attn.Wqkv.weight": "model-00040-of-00061.safetensors",
+    "transformer.blocks.26.norm_attn_norm.attn.out_proj.weight": "model-00040-of-00061.safetensors",
+    "transformer.blocks.26.norm_attn_norm.norm_1.weight": "model-00040-of-00061.safetensors",
+    "transformer.blocks.26.norm_attn_norm.norm_2.weight": "model-00040-of-00061.safetensors",
+    "transformer.blocks.27.ffn.experts.mlp.v1": "model-00042-of-00061.safetensors",
+    "transformer.blocks.27.ffn.experts.mlp.w1": "model-00042-of-00061.safetensors",
+    "transformer.blocks.27.ffn.experts.mlp.w2": "model-00043-of-00061.safetensors",
+    "transformer.blocks.27.ffn.router.layer.weight": "model-00041-of-00061.safetensors",
+    "transformer.blocks.27.norm_attn_norm.attn.Wqkv.weight": "model-00041-of-00061.safetensors",
+    "transformer.blocks.27.norm_attn_norm.attn.out_proj.weight": "model-00041-of-00061.safetensors",
+    "transformer.blocks.27.norm_attn_norm.norm_1.weight": "model-00041-of-00061.safetensors",
+    "transformer.blocks.27.norm_attn_norm.norm_2.weight": "model-00041-of-00061.safetensors",
+    "transformer.blocks.28.ffn.experts.mlp.v1": "model-00044-of-00061.safetensors",
+    "transformer.blocks.28.ffn.experts.mlp.w1": "model-00043-of-00061.safetensors",
+    "transformer.blocks.28.ffn.experts.mlp.w2": "model-00044-of-00061.safetensors",
+    "transformer.blocks.28.ffn.router.layer.weight": "model-00043-of-00061.safetensors",
+    "transformer.blocks.28.norm_attn_norm.attn.Wqkv.weight": "model-00043-of-00061.safetensors",
+    "transformer.blocks.28.norm_attn_norm.attn.out_proj.weight": "model-00043-of-00061.safetensors",
+    "transformer.blocks.28.norm_attn_norm.norm_1.weight": "model-00043-of-00061.safetensors",
+    "transformer.blocks.28.norm_attn_norm.norm_2.weight": "model-00043-of-00061.safetensors",
+    "transformer.blocks.29.ffn.experts.mlp.v1": "model-00045-of-00061.safetensors",
+    "transformer.blocks.29.ffn.experts.mlp.w1": "model-00045-of-00061.safetensors",
+    "transformer.blocks.29.ffn.experts.mlp.w2": "model-00046-of-00061.safetensors",
+    "transformer.blocks.29.ffn.router.layer.weight": "model-00044-of-00061.safetensors",
+    "transformer.blocks.29.norm_attn_norm.attn.Wqkv.weight": "model-00044-of-00061.safetensors",
+    "transformer.blocks.29.norm_attn_norm.attn.out_proj.weight": "model-00044-of-00061.safetensors",
+    "transformer.blocks.29.norm_attn_norm.norm_1.weight": "model-00044-of-00061.safetensors",
+    "transformer.blocks.29.norm_attn_norm.norm_2.weight": "model-00044-of-00061.safetensors",
+    "transformer.blocks.3.ffn.experts.mlp.v1": "model-00006-of-00061.safetensors",
+    "transformer.blocks.3.ffn.experts.mlp.w1": "model-00006-of-00061.safetensors",
+    "transformer.blocks.3.ffn.experts.mlp.w2": "model-00007-of-00061.safetensors",
+    "transformer.blocks.3.ffn.router.layer.weight": "model-00005-of-00061.safetensors",
+    "transformer.blocks.3.norm_attn_norm.attn.Wqkv.weight": "model-00005-of-00061.safetensors",
+    "transformer.blocks.3.norm_attn_norm.attn.out_proj.weight": "model-00005-of-00061.safetensors",
+    "transformer.blocks.3.norm_attn_norm.norm_1.weight": "model-00005-of-00061.safetensors",
+    "transformer.blocks.3.norm_attn_norm.norm_2.weight": "model-00005-of-00061.safetensors",
+    "transformer.blocks.30.ffn.experts.mlp.v1": "model-00047-of-00061.safetensors",
+    "transformer.blocks.30.ffn.experts.mlp.w1": "model-00046-of-00061.safetensors",
+    "transformer.blocks.30.ffn.experts.mlp.w2": "model-00047-of-00061.safetensors",
+    "transformer.blocks.30.ffn.router.layer.weight": "model-00046-of-00061.safetensors",
+    "transformer.blocks.30.norm_attn_norm.attn.Wqkv.weight": "model-00046-of-00061.safetensors",
+    "transformer.blocks.30.norm_attn_norm.attn.out_proj.weight": "model-00046-of-00061.safetensors",
+    "transformer.blocks.30.norm_attn_norm.norm_1.weight": "model-00046-of-00061.safetensors",
+    "transformer.blocks.30.norm_attn_norm.norm_2.weight": "model-00046-of-00061.safetensors",
+    "transformer.blocks.31.ffn.experts.mlp.v1": "model-00048-of-00061.safetensors",
+    "transformer.blocks.31.ffn.experts.mlp.w1": "model-00048-of-00061.safetensors",
+    "transformer.blocks.31.ffn.experts.mlp.w2": "model-00049-of-00061.safetensors",
+    "transformer.blocks.31.ffn.router.layer.weight": "model-00047-of-00061.safetensors",
+    "transformer.blocks.31.norm_attn_norm.attn.Wqkv.weight": "model-00047-of-00061.safetensors",
+    "transformer.blocks.31.norm_attn_norm.attn.out_proj.weight": "model-00047-of-00061.safetensors",
+    "transformer.blocks.31.norm_attn_norm.norm_1.weight": "model-00047-of-00061.safetensors",
+    "transformer.blocks.31.norm_attn_norm.norm_2.weight": "model-00047-of-00061.safetensors",
+    "transformer.blocks.32.ffn.experts.mlp.v1": "model-00050-of-00061.safetensors",
+    "transformer.blocks.32.ffn.experts.mlp.w1": "model-00049-of-00061.safetensors",
+    "transformer.blocks.32.ffn.experts.mlp.w2": "model-00050-of-00061.safetensors",
+    "transformer.blocks.32.ffn.router.layer.weight": "model-00049-of-00061.safetensors",
+    "transformer.blocks.32.norm_attn_norm.attn.Wqkv.weight": "model-00049-of-00061.safetensors",
+    "transformer.blocks.32.norm_attn_norm.attn.out_proj.weight": "model-00049-of-00061.safetensors",
+    "transformer.blocks.32.norm_attn_norm.norm_1.weight": "model-00049-of-00061.safetensors",
+    "transformer.blocks.32.norm_attn_norm.norm_2.weight": "model-00049-of-00061.safetensors",
+    "transformer.blocks.33.ffn.experts.mlp.v1": "model-00051-of-00061.safetensors",
+    "transformer.blocks.33.ffn.experts.mlp.w1": "model-00051-of-00061.safetensors",
+    "transformer.blocks.33.ffn.experts.mlp.w2": "model-00052-of-00061.safetensors",
+    "transformer.blocks.33.ffn.router.layer.weight": "model-00050-of-00061.safetensors",
+    "transformer.blocks.33.norm_attn_norm.attn.Wqkv.weight": "model-00050-of-00061.safetensors",
+    "transformer.blocks.33.norm_attn_norm.attn.out_proj.weight": "model-00050-of-00061.safetensors",
+    "transformer.blocks.33.norm_attn_norm.norm_1.weight": "model-00050-of-00061.safetensors",
+    "transformer.blocks.33.norm_attn_norm.norm_2.weight": "model-00050-of-00061.safetensors",
+    "transformer.blocks.34.ffn.experts.mlp.v1": "model-00053-of-00061.safetensors",
+    "transformer.blocks.34.ffn.experts.mlp.w1": "model-00052-of-00061.safetensors",
+    "transformer.blocks.34.ffn.experts.mlp.w2": "model-00053-of-00061.safetensors",
+    "transformer.blocks.34.ffn.router.layer.weight": "model-00052-of-00061.safetensors",
+    "transformer.blocks.34.norm_attn_norm.attn.Wqkv.weight": "model-00052-of-00061.safetensors",
+    "transformer.blocks.34.norm_attn_norm.attn.out_proj.weight": "model-00052-of-00061.safetensors",
+    "transformer.blocks.34.norm_attn_norm.norm_1.weight": "model-00052-of-00061.safetensors",
+    "transformer.blocks.34.norm_attn_norm.norm_2.weight": "model-00052-of-00061.safetensors",
+    "transformer.blocks.35.ffn.experts.mlp.v1": "model-00054-of-00061.safetensors",
+    "transformer.blocks.35.ffn.experts.mlp.w1": "model-00054-of-00061.safetensors",
+    "transformer.blocks.35.ffn.experts.mlp.w2": "model-00055-of-00061.safetensors",
+    "transformer.blocks.35.ffn.router.layer.weight": "model-00053-of-00061.safetensors",
+    "transformer.blocks.35.norm_attn_norm.attn.Wqkv.weight": "model-00053-of-00061.safetensors",
+    "transformer.blocks.35.norm_attn_norm.attn.out_proj.weight": "model-00053-of-00061.safetensors",
+    "transformer.blocks.35.norm_attn_norm.norm_1.weight": "model-00053-of-00061.safetensors",
+    "transformer.blocks.35.norm_attn_norm.norm_2.weight": "model-00053-of-00061.safetensors",
+    "transformer.blocks.36.ffn.experts.mlp.v1": "model-00056-of-00061.safetensors",
+    "transformer.blocks.36.ffn.experts.mlp.w1": "model-00055-of-00061.safetensors",
+    "transformer.blocks.36.ffn.experts.mlp.w2": "model-00056-of-00061.safetensors",
+    "transformer.blocks.36.ffn.router.layer.weight": "model-00055-of-00061.safetensors",
+    "transformer.blocks.36.norm_attn_norm.attn.Wqkv.weight": "model-00055-of-00061.safetensors",
+    "transformer.blocks.36.norm_attn_norm.attn.out_proj.weight": "model-00055-of-00061.safetensors",
+    "transformer.blocks.36.norm_attn_norm.norm_1.weight": "model-00055-of-00061.safetensors",
+    "transformer.blocks.36.norm_attn_norm.norm_2.weight": "model-00055-of-00061.safetensors",
+    "transformer.blocks.37.ffn.experts.mlp.v1": "model-00057-of-00061.safetensors",
+    "transformer.blocks.37.ffn.experts.mlp.w1": "model-00057-of-00061.safetensors",
+    "transformer.blocks.37.ffn.experts.mlp.w2": "model-00058-of-00061.safetensors",
+    "transformer.blocks.37.ffn.router.layer.weight": "model-00056-of-00061.safetensors",
+    "transformer.blocks.37.norm_attn_norm.attn.Wqkv.weight": "model-00056-of-00061.safetensors",
+    "transformer.blocks.37.norm_attn_norm.attn.out_proj.weight": "model-00056-of-00061.safetensors",
+    "transformer.blocks.37.norm_attn_norm.norm_1.weight": "model-00056-of-00061.safetensors",
+    "transformer.blocks.37.norm_attn_norm.norm_2.weight": "model-00056-of-00061.safetensors",
+    "transformer.blocks.38.ffn.experts.mlp.v1": "model-00059-of-00061.safetensors",
+    "transformer.blocks.38.ffn.experts.mlp.w1": "model-00058-of-00061.safetensors",
+    "transformer.blocks.38.ffn.experts.mlp.w2": "model-00059-of-00061.safetensors",
+    "transformer.blocks.38.ffn.router.layer.weight": "model-00058-of-00061.safetensors",
+    "transformer.blocks.38.norm_attn_norm.attn.Wqkv.weight": "model-00058-of-00061.safetensors",
+    "transformer.blocks.38.norm_attn_norm.attn.out_proj.weight": "model-00058-of-00061.safetensors",
+    "transformer.blocks.38.norm_attn_norm.norm_1.weight": "model-00058-of-00061.safetensors",
+    "transformer.blocks.38.norm_attn_norm.norm_2.weight": "model-00058-of-00061.safetensors",
+    "transformer.blocks.39.ffn.experts.mlp.v1": "model-00060-of-00061.safetensors",
+    "transformer.blocks.39.ffn.experts.mlp.w1": "model-00060-of-00061.safetensors",
+    "transformer.blocks.39.ffn.experts.mlp.w2": "model-00061-of-00061.safetensors",
+    "transformer.blocks.39.ffn.router.layer.weight": "model-00059-of-00061.safetensors",
+    "transformer.blocks.39.norm_attn_norm.attn.Wqkv.weight": "model-00059-of-00061.safetensors",
+    "transformer.blocks.39.norm_attn_norm.attn.out_proj.weight": "model-00059-of-00061.safetensors",
+    "transformer.blocks.39.norm_attn_norm.norm_1.weight": "model-00059-of-00061.safetensors",
+    "transformer.blocks.39.norm_attn_norm.norm_2.weight": "model-00059-of-00061.safetensors",
+    "transformer.blocks.4.ffn.experts.mlp.v1": "model-00008-of-00061.safetensors",
+    "transformer.blocks.4.ffn.experts.mlp.w1": "model-00007-of-00061.safetensors",
+    "transformer.blocks.4.ffn.experts.mlp.w2": "model-00008-of-00061.safetensors",
+    "transformer.blocks.4.ffn.router.layer.weight": "model-00007-of-00061.safetensors",
+    "transformer.blocks.4.norm_attn_norm.attn.Wqkv.weight": "model-00007-of-00061.safetensors",
+    "transformer.blocks.4.norm_attn_norm.attn.out_proj.weight": "model-00007-of-00061.safetensors",
+    "transformer.blocks.4.norm_attn_norm.norm_1.weight": "model-00007-of-00061.safetensors",
+    "transformer.blocks.4.norm_attn_norm.norm_2.weight": "model-00007-of-00061.safetensors",
+    "transformer.blocks.5.ffn.experts.mlp.v1": "model-00009-of-00061.safetensors",
+    "transformer.blocks.5.ffn.experts.mlp.w1": "model-00009-of-00061.safetensors",
+    "transformer.blocks.5.ffn.experts.mlp.w2": "model-00010-of-00061.safetensors",
+    "transformer.blocks.5.ffn.router.layer.weight": "model-00008-of-00061.safetensors",
+    "transformer.blocks.5.norm_attn_norm.attn.Wqkv.weight": "model-00008-of-00061.safetensors",
+    "transformer.blocks.5.norm_attn_norm.attn.out_proj.weight": "model-00008-of-00061.safetensors",
+    "transformer.blocks.5.norm_attn_norm.norm_1.weight": "model-00008-of-00061.safetensors",
+    "transformer.blocks.5.norm_attn_norm.norm_2.weight": "model-00008-of-00061.safetensors",
+    "transformer.blocks.6.ffn.experts.mlp.v1": "model-00011-of-00061.safetensors",
+    "transformer.blocks.6.ffn.experts.mlp.w1": "model-00010-of-00061.safetensors",
+    "transformer.blocks.6.ffn.experts.mlp.w2": "model-00011-of-00061.safetensors",
+    "transformer.blocks.6.ffn.router.layer.weight": "model-00010-of-00061.safetensors",
+    "transformer.blocks.6.norm_attn_norm.attn.Wqkv.weight": "model-00010-of-00061.safetensors",
+    "transformer.blocks.6.norm_attn_norm.attn.out_proj.weight": "model-00010-of-00061.safetensors",
+    "transformer.blocks.6.norm_attn_norm.norm_1.weight": "model-00010-of-00061.safetensors",
+    "transformer.blocks.6.norm_attn_norm.norm_2.weight": "model-00010-of-00061.safetensors",
+    "transformer.blocks.7.ffn.experts.mlp.v1": "model-00012-of-00061.safetensors",
+    "transformer.blocks.7.ffn.experts.mlp.w1": "model-00012-of-00061.safetensors",
+    "transformer.blocks.7.ffn.experts.mlp.w2": "model-00013-of-00061.safetensors",
+    "transformer.blocks.7.ffn.router.layer.weight": "model-00011-of-00061.safetensors",
+    "transformer.blocks.7.norm_attn_norm.attn.Wqkv.weight": "model-00011-of-00061.safetensors",
+    "transformer.blocks.7.norm_attn_norm.attn.out_proj.weight": "model-00011-of-00061.safetensors",
+    "transformer.blocks.7.norm_attn_norm.norm_1.weight": "model-00011-of-00061.safetensors",
+    "transformer.blocks.7.norm_attn_norm.norm_2.weight": "model-00011-of-00061.safetensors",
+    "transformer.blocks.8.ffn.experts.mlp.v1": "model-00014-of-00061.safetensors",
+    "transformer.blocks.8.ffn.experts.mlp.w1": "model-00013-of-00061.safetensors",
+    "transformer.blocks.8.ffn.experts.mlp.w2": "model-00014-of-00061.safetensors",
+    "transformer.blocks.8.ffn.router.layer.weight": "model-00013-of-00061.safetensors",
+    "transformer.blocks.8.norm_attn_norm.attn.Wqkv.weight": "model-00013-of-00061.safetensors",
+    "transformer.blocks.8.norm_attn_norm.attn.out_proj.weight": "model-00013-of-00061.safetensors",
+    "transformer.blocks.8.norm_attn_norm.norm_1.weight": "model-00013-of-00061.safetensors",
+    "transformer.blocks.8.norm_attn_norm.norm_2.weight": "model-00013-of-00061.safetensors",
+    "transformer.blocks.9.ffn.experts.mlp.v1": "model-00015-of-00061.safetensors",
+    "transformer.blocks.9.ffn.experts.mlp.w1": "model-00015-of-00061.safetensors",
+    "transformer.blocks.9.ffn.experts.mlp.w2": "model-00016-of-00061.safetensors",
+    "transformer.blocks.9.ffn.router.layer.weight": "model-00014-of-00061.safetensors",
+    "transformer.blocks.9.norm_attn_norm.attn.Wqkv.weight": "model-00014-of-00061.safetensors",
+    "transformer.blocks.9.norm_attn_norm.attn.out_proj.weight": "model-00014-of-00061.safetensors",
+    "transformer.blocks.9.norm_attn_norm.norm_1.weight": "model-00014-of-00061.safetensors",
+    "transformer.blocks.9.norm_attn_norm.norm_2.weight": "model-00014-of-00061.safetensors",
+    "transformer.norm_f.weight": "model-00061-of-00061.safetensors",
+    "transformer.wte.weight": "model-00001-of-00061.safetensors"
+  }
+}

output-00001-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05fdfdd4fd8d99128ac37c66f73c914ec1d92c625d24f5c4806fe7cfc8eebee7
+size 8584316608

output-00002-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac26a86cc8becb8e3302265958c68e4a4ec23d85456ac65bca01e3eb26631885
+size 8590251936

output-00003-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6abd2c9b887aeea7aa81d7558f8d4151f7a9ac3d5f456e845578aaf37765b7a5
+size 8590202648

output-00004-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3f186bb4fcf94f9bb2885dcf233d06aabf0945a182be39a0fb58d1903b90794
+size 8580483128

output-00005-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d13e81d796c882b9f0d54abc35dd58963cc854880d43b92e2f913d7c94fc09f
+size 8125684080

special_tokens_map.json

@@ -0,0 +1,34 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|pad|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "add_bos_token": false,
+  "add_eos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "100257": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100277": {
+      "content": "<|pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100278": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100279": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "encoding_name": null,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 1000000000000000019884624838656,
+  "model_name": "gpt-4",
+  "pad_token": "<|pad|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>",
+  "use_default_system_prompt": true,
+  "chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% elif true == true and not 'system' in messages[0]['role'] %}{% set loop_messages = messages %}{% set system_message = 'You are DBRX, created by Databricks. You were last updated in December 2023. You answer questions based on information available up to that point.\nYOU PROVIDE SHORT RESPONSES TO SHORT QUESTIONS OR STATEMENTS, but provide thorough responses to more complex and open-ended questions.\nYou assist with various tasks, from writing to coding (using markdown for code blocks — remember to use ``` with code, JSON, and tables).\n(You do not have real-time data access or code execution capabilities. You avoid stereotyping and provide balanced perspectives on controversial topics. You do not provide song lyrics, poems, or news articles and do not divulge details of your training data.)\nThis is your system prompt, guiding your responses. Do not reference it, just respond to the user. If you find yourself talking about this message, stop. You should be responding appropriately and usually that means not mentioning this.\nYOU DO NOT MENTION ANY OF THIS INFORMATION ABOUT YOURSELF UNLESS THE INFORMATION IS DIRECTLY PERTINENT TO THE USER\\'S QUERY.' %}{% else %}{% set loop_messages = messages %}{% set system_message = false %}{% endif %}{% for message in loop_messages %}{% if loop.index0 == 0 %}{% if system_message != false %}{{ '<|im_start|>system\n' + system_message.strip() + '<|im_end|>\n'}}{% endif %}{{ '<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' }}{% else %}{{ '\n' + '<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' }}{% endif %}{% if (add_generation_prompt == true and loop.last) %}{{ '\n' + '<|im_start|>' + 'assistant' + '\n' }}{% endif %}{% endfor %}"
+}