Upload folder using huggingface_hub

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "/home/runner/.cache/huggingface/hub/models--TinyLlama--TinyLlama-1.1B-Chat-v1.0/snapshots/fe8a4ea1ffedaf415f4da2f062534de366a451e6",
+  "_name_or_path": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
   "architectures": [
     "LlamaForCausalLM"
   ],
@@ -48,14 +48,22 @@
     ],
     "kv_cache_scheme": null,
     "quant_method": "compressed-tensors",
-    "quantization_status": "compressed"
+    "quantization_status": "compressed",
+    "sparsity_config": {
+      "format": "dense",
+      "global_sparsity": 0.14375328644374685,
+      "ignore": [],
+      "registry_requires_subclass": false,
+      "sparsity_structure": "unstructured",
+      "targets": []
+    }
   },
   "rms_norm_eps": 1e-05,
   "rope_scaling": null,
   "rope_theta": 10000.0,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.46.2",
+  "transformers_version": "4.46.3",
   "use_cache": true,
   "vocab_size": 32000
 }

generation_config.json

@@ -3,5 +3,5 @@
   "eos_token_id": 2,
   "max_length": 2048,
   "pad_token_id": 0,
-  "transformers_version": "4.46.2"
+  "transformers_version": "4.46.3"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f5735b95b606742c6d70f5d9631d39ebaba8449d1e53404bec2dd597a713d61
+oid sha256:892873b79abcf66508b526a74179177e303de9b4b1464a6177096348faa7fd76
 size 761968800

recipe.yaml

@@ -0,0 +1,6 @@
+DEFAULT_stage:
+  DEFAULT_modifiers:
+    GPTQModifier:
+      targets: Linear
+      ignore: [lm_head]
+      scheme: W4A16