Upload folder using huggingface_hub (#3)

- fdb53d2e90c3da8df0fe9f0b23e033952548242f6ee5c69ef041c6a196307d56 (2bef3962b40d9c7a8b16b64d0e816b2a942090e3)
- 121ec7baa904570547b3fa34cb5efdd7e98abb5283a6270d2219154c25eaa10b (c00beae2b54fe84374fb6320dc8ebb176b9ec543)
- 8cae25045aa27337dafb37b78cbe02fadbc78167291c52bdad59cda956993549 (eb38baa59b499a20e8a8362c4df738c1dc3db246)

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "/covalent/.cache/models/tmp905d1b9pt94gnbuk",
+  "_name_or_path": "/covalent/.cache/models/tmp6cox54sy70vwnjyh",
   "architectures": [
     "LlamaForCausalLM"
   ],

smash_config.json

@@ -0,0 +1,37 @@
+{
+    "comp_cgenerate_active": false,
+    "comp_ctranslate_active": false,
+    "comp_cwhisper_active": false,
+    "comp_diffusers2_active": false,
+    "comp_ifw_active": false,
+    "comp_onediff_active": false,
+    "comp_step_caching_active": false,
+    "comp_torch_compile_active": false,
+    "comp_ws2t_active": false,
+    "comp_x-fast_active": false,
+    "prune_torch-structured_active": false,
+    "quant_aqlm_active": false,
+    "quant_awq_active": false,
+    "quant_gptq_active": false,
+    "quant_half_active": false,
+    "quant_hqq_active": false,
+    "quant_llm-int8_active": true,
+    "quant_quanto_active": false,
+    "quant_torch_dynamic_active": false,
+    "quant_torch_static_active": false,
+    "quant_llm-int8_compute_dtype": "bfloat16",
+    "quant_llm-int8_double_quant": false,
+    "quant_llm-int8_enable_fp32_cpu_offload": false,
+    "quant_llm-int8_has_fp16_weight": false,
+    "quant_llm-int8_quant_type": "fp4",
+    "quant_llm-int8_threshold": 6.0,
+    "quant_llm-int8_weight_bits": 8,
+    "max_batch_size": 1,
+    "device": "cuda",
+    "cache_dir": "/covalent/.cache/models/tmp6cox54sy",
+    "task": "",
+    "save_load_fn": "bitsandbytes",
+    "save_load_fn_args": {
+        "weight_quantization_bits": "param.dtype"
+    }
+}