Add tokenizer and templating config

config.json

@@ -0,0 +1,55 @@
+{
+  "architectures": [
+    "MPTForCausalLM"
+  ],
+  "attn_config": {
+    "alibi": true,
+    "alibi_bias_max": 8,
+    "attn_impl": "torch",
+    "attn_pdrop": 0.0,
+    "attn_type": "grouped_query_attention",
+    "attn_uses_sequence_id": false,
+    "clip_qkv": null,
+    "kv_n_heads": 8,
+    "prefix_lm": false,
+    "qk_ln": false,
+    "softmax_scale": null
+  },
+  "auto_map": {
+    "AutoConfig": "configuration_mpt.MPTConfig",
+    "AutoModelForCausalLM": "modeling_mpt.MPTForCausalLM"
+  },
+  "d_model": 3072,
+  "emb_pdrop": 0.0,
+  "embedding_fraction": 1.0,
+  "expansion_ratio": 4,
+  "fc_type": "torch",
+  "ffn_config": {
+    "fc_type": "torch",
+    "ffn_type": "mptmlp"
+  },
+  "init_config": {
+    "emb_init_std": null,
+    "emb_init_uniform_lim": null,
+    "fan_mode": "fan_in",
+    "init_div_is_residual": true,
+    "init_gain": 0.0,
+    "init_nonlinearity": "relu",
+    "init_std": null,
+    "name": "kaiming_normal_"
+  },
+  "init_device": "cpu",
+  "learned_pos_emb": false,
+  "logit_scale": null,
+  "max_seq_len": 4096,
+  "model_type": "mpt",
+  "n_heads": 24,
+  "n_layers": 32,
+  "no_bias": true,
+  "norm_type": "low_precision_layernorm",
+  "resid_pdrop": 0.0,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.33.3",
+  "use_cache": false,
+  "vocab_size": 32768
+}

tokenizer_config.json

@@ -0,0 +1,27 @@
+{
+  "add_prefix_space": false,
+  "additional_special_tokens": [
+    "<fim_prefix>",
+    "<fim_middle>",
+    "<fim_suffix>",
+    "<fim_eot>",
+    "<fim_pad>",
+    "[INST]",
+    "[/INST]",
+    "<extra_id_2>",
+    "<extra_id_3>",
+    "<extra_id_4>",
+    "<extra_id_5>",
+    "<extra_id_6>",
+    "<extra_id_7>",
+    "<extra_id_8>",
+    "<extra_id_9>",
+    "<extra_id_10>"
+  ],
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 4096,
+  "tokenizer_class": "GPTNeoXTokenizer",
+  "unk_token": "<|endoftext|>"
+}