Upload folder using huggingface_hub

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "/network/sadkins/llama7b_sparse_24_w4a16_group128",
+  "_name_or_path": "/root/.cache/huggingface/hub/models--neuralmagic--SparseLlama-2-7b-cnn-daily-mail-pruned_50.2of4/snapshots/9f5abdaba734b6ff492723a824ee4c9c269da61a",
   "architectures": [
     "LlamaForCausalLM"
   ],
@@ -27,7 +27,7 @@
         }
       }
     },
-    "format": "marlin-24",
+    "format": "dense",
     "global_compression_ratio": 1.896287597650382,
     "ignore": [
       "lm_head"
@@ -36,7 +36,7 @@
     "quantization_status": "frozen",
     "sparsity_config": {
       "format": "dense",
-      "global_sparsity": 50.79734011764465,
+      "global_sparsity": 50.7973355023164,
       "registry_requires_subclass": false,
       "sparsity_structure": "unstructured"
     }
@@ -56,8 +56,8 @@
   "rope_scaling": null,
   "rope_theta": 10000.0,
   "tie_word_embeddings": false,
-  "torch_dtype": "float16",
-  "transformers_version": "4.40.0",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.40.2",
   "use_cache": true,
   "vocab_size": 32000
 }

generation_config.json

@@ -2,5 +2,5 @@
   "_from_model_config": true,
   "bos_token_id": 1,
   "eos_token_id": 2,
-  "transformers_version": "4.40.0"
+  "transformers_version": "4.40.2"
 }

recipe.yaml

@@ -0,0 +1,9 @@
+quant_stage:
+  quant_modifiers:
+    GPTQModifier:
+      sequential_update: false
+      ignore: [lm_head]
+      config_groups:
+        group_0:
+          weights: {num_bits: 4, type: int, symmetric: true, strategy: group, group_size: 128}
+          targets: [Linear]

special_tokens_map.json

@@ -0,0 +1,29 @@
+{
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,46 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 4096,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}