Upload folder using huggingface_hub

config.json

@@ -0,0 +1,77 @@
+{
+  "_remove_final_layer_norm": false,
+  "activation_dropout": 0.0,
+  "activation_function": "relu",
+  "architectures": [
+    "OPTForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 2,
+  "do_layer_norm_before": true,
+  "dropout": 0.1,
+  "enable_bias": true,
+  "eos_token_id": 2,
+  "ffn_dim": 36864,
+  "hidden_size": 9216,
+  "init_std": 0.02,
+  "layer_norm_elementwise_affine": true,
+  "layerdrop": 0.0,
+  "max_position_embeddings": 2048,
+  "model_type": "opt",
+  "num_attention_heads": 72,
+  "num_hidden_layers": 64,
+  "pad_token_id": 1,
+  "prefix": "</s>",
+  "quantization_config": {
+    "config_groups": {
+      "group_0": {
+        "format": "float-quantized",
+        "input_activations": {
+          "actorder": null,
+          "block_structure": null,
+          "dynamic": true,
+          "group_size": 32,
+          "num_bits": 8,
+          "observer": null,
+          "observer_kwargs": {},
+          "strategy": "group",
+          "symmetric": true,
+          "type": "float"
+        },
+        "output_activations": null,
+        "targets": [
+          "Linear"
+        ],
+        "weights": {
+          "actorder": null,
+          "block_structure": null,
+          "dynamic": false,
+          "group_size": 32,
+          "num_bits": 8,
+          "observer": "minmax",
+          "observer_kwargs": {},
+          "strategy": "group",
+          "symmetric": true,
+          "type": "float"
+        }
+      }
+    },
+    "format": "float-quantized",
+    "global_compression_ratio": null,
+    "ignore": [
+      "lm_head"
+    ],
+    "kv_cache_scheme": null,
+    "quant_method": "compressed-tensors",
+    "quantization_status": "compressed",
+    "sparsity_config": {},
+    "transform_config": {},
+    "version": "0.11.1.dev0"
+  },
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.55.2",
+  "use_cache": true,
+  "vocab_size": 50272,
+  "word_embed_proj_dim": 9216
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 2,
+  "eos_token_id": 2,
+  "pad_token_id": 1,
+  "transformers_version": "4.55.2"
+}

model-00001-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a3fc2c76ead13bf75a76d6a60eea2b2709ed360cbba27c7e9f408875965c2ea
+size 4936044824

model-00002-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf15d436d292a4c31cadb8641cb3665c54928d8a348e5fcbb9b0c728a8dec3b2
+size 4964450176

model-00003-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2b811453120672697aa239b786580f3209f5f8e1429a379119f43b02a433291
+size 4783981800

model-00004-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fdb8111ac4fa31aec2c4a6e263ed453d23c6ffcdca3d733a2f2a4888c6ba8d42
+size 4964450272

model-00005-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75b739949773a04502edcfb53f57fbefdee9b85f68448324855e60e1f7e207f0
+size 4783981840

model-00006-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8beb865e368c7497bc74bb005f73eafe4a5179fb28387fc8b2dae1ff958286d0
+size 4964450272

model-00007-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1671954c87c705da6cdb1f473522e501bb3c1e9417f0c3902132660af6a6e0c
+size 4783981840

model-00008-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a462a48a51c7589dbba631fa589a8d0512a8ad436b43f6db04655206dfb3812c
+size 4964450272

model-00009-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8c9ebd16929a7950bd78974ce994234e862a851143f66c45a5e71aedabc0907
+size 4783981840

model-00010-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6e5ae2e11f6e4d67e9110558afcedf69ffdcc119c79a90fd2277acf287f2295
+size 4964450272

model-00011-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfb930e988905a9927e252ecc85b5978a37278c42b72eb68fc7a3abf13f869d7
+size 4783981840

model-00012-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a89fa258aa37c2d8578497594c6295979d2d7101b30820d8a375c834468e3c2a
+size 4964450272

model-00013-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c16c58809a8f7b9d2d7ed9011930b21943474b160162118fe1a8273171f6898
+size 4783981840

model-00014-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c326450ee73e92bb1345422671ac87b3d929a53e4b8431da137dedd4adf11d0d
+size 4964450272

model-00015-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:569da3d1f7d45e97cbd09e4b1b9bd309caaaec325c4b416f965b82ad7e047048
+size 2822146280

recipe.yaml

@@ -0,0 +1,32 @@
+quant_stage:
+  quant_modifiers:
+    QuantizationModifier:
+      config_groups:
+        group_0:
+          targets: [Linear]
+          weights:
+            num_bits: 8
+            type: float
+            symmetric: true
+            group_size: 32
+            strategy: group
+            block_structure: null
+            dynamic: false
+            actorder: null
+            observer: minmax
+            observer_kwargs: {}
+          input_activations:
+            num_bits: 8
+            type: float
+            symmetric: true
+            group_size: 32
+            strategy: group
+            block_structure: null
+            dynamic: true
+            actorder: null
+            observer: null
+            observer_kwargs: {}
+          output_activations: null
+          format: null
+      targets: [Linear]
+      ignore: [lm_head]

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,31 @@
+{
+  "add_bos_token": true,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "</s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "</s>"
+}