Upload model

config.json

@@ -0,0 +1,58 @@
+{
+  "_name_or_path": "inception-mbzuai/jais-13b-chat",
+  "activation_function": "swiglu",
+  "architectures": [
+    "JAISLMHeadModel"
+  ],
+  "attn_pdrop": 0.0,
+  "auto_map": {
+    "AutoConfig": "inception-mbzuai/jais-13b-chat--configuration_jais.JAISConfig",
+    "AutoModel": "inception-mbzuai/jais-13b-chat--modeling_jais.JAISModel",
+    "AutoModelForCausalLM": "inception-mbzuai/jais-13b-chat--modeling_jais.JAISLMHeadModel"
+  },
+  "bos_token_id": 0,
+  "embd_pdrop": 0.0,
+  "embeddings_scale": 14.6,
+  "eos_token_id": 0,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "jais",
+  "n_embd": 5120,
+  "n_head": 40,
+  "n_inner": 13653,
+  "n_layer": 40,
+  "n_positions": 2048,
+  "pad_token_id": 0,
+  "position_embedding_type": "alibi",
+  "quantization_config": {
+    "batch_size": 1,
+    "bits": 4,
+    "block_name_to_quantize": "transformer.h",
+    "damp_percent": 0.1,
+    "dataset": "c4",
+    "desc_act": false,
+    "disable_exllama": true,
+    "group_size": 128,
+    "model_seqlen": 2048,
+    "module_name_preceding_first_block": [
+      "transformer.wte",
+      "transformer.drop"
+    ],
+    "pad_token_id": null,
+    "quant_method": "gptq",
+    "sym": true,
+    "tokenizer": null,
+    "true_sequential": true,
+    "use_cuda_fp16": true
+  },
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.0,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "scale_qk_dot_by_d": true,
+  "torch_dtype": "float16",
+  "transformers_version": "4.33.0.dev0",
+  "use_cache": true,
+  "vocab_size": 84992,
+  "width_scale": 0.11100000000000002
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "pad_token_id": 0,
+  "transformers_version": "4.33.0.dev0"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2f12997f84ed9d7682f523afadd21d254c29c4c8f727073c310fa2ca94865ed
+size 7417139889