Upload model

config.json

@@ -0,0 +1,60 @@
+{
+  "_name_or_path": "AI-Sweden-Models/gpt-sw3-6.7b-v2-instruct",
+  "activation_function": "gelu",
+  "apply_query_key_layer_scaling": true,
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 1,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 1,
+  "initializer_range": 0.01,
+  "layer_norm_epsilon": 1e-05,
+  "max_length": 2048,
+  "model_type": "gpt2",
+  "n_embd": 4096,
+  "n_head": 32,
+  "n_inner": 16384,
+  "n_layer": 32,
+  "n_positions": 2048,
+  "normalize_attention_scores": true,
+  "pad_token_id": 0,
+  "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,
+    "max_input_length": null,
+    "model_seqlen": 2048,
+    "module_name_preceding_first_block": [
+      "transformer.wte",
+      "transformer.wpe",
+      "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": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "tokenizer_class": "GPTSw3Tokenizer",
+  "torch_dtype": "float16",
+  "transformers_version": "4.34.1",
+  "use_cache": true,
+  "vocab_size": 64000
+}

generation_config.json

@@ -0,0 +1,8 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 1,
+  "max_length": 2048,
+  "pad_token_id": 0,
+  "transformers_version": "4.34.1"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6049c381eafc586d200df111645514eb021c75f2857e750250612ace23c03d3e
+size 3895468698