Upload folder using huggingface_hub (#7)

- d12922830bac2033b908a8d9d210fe0478fe6b2662ac1c7e675d1f54648e3d44 (339455a79075eb34cf0f7d826601579fb563bafb)
- a0dd77bbd3ad5a61ab8695d30118db0d18729f34fdfbea8fb6d4d79e58647704 (8f7659702f88fcc1afabc3f3113acc6b96148013)

config.json

@@ -1,6 +1,6 @@
 {
   "_attn_implementation_autoset": true,
-  "_name_or_path": "/tmp/models/tmpgl7uz6ih/tmp4p2khk6w",
+  "_name_or_path": "/tmp/models/tmp3fjrifao/tmpizgz2wn6",
   "architectures": [
     "LlamaForCausalLM"
   ],
@@ -47,9 +47,14 @@
   "tie_word_embeddings": true,
   "torch_dtype": "bfloat16",
   "transformers.js_config": {
+    "dtype": "q4",
     "kv_cache_dtype": {
       "fp16": "float16",
       "q4f16": "float16"
+    },
+    "use_external_data_format": {
+      "model.onnx": true,
+      "model_fp16.onnx": true
     }
   },
   "transformers_version": "4.48.2",

qmodel.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d54f27b8eec5c7e905958321aee5898dae3a5223ee7775ca2fba42ffd20cd1a0
+oid sha256:8fb62cbc0610971af8d46dce37ed1b33d49c0ba267aec3cd5f5805bb65dec6e0
 size 2215166128

smash_config.json

@@ -11,7 +11,7 @@
     "quant_hqq_weight_bits": 8,
     "max_batch_size": 1,
     "device": "cuda",
-    "cache_dir": "/tmp/models/tmpgl7uz6ih",
+    "cache_dir": "/tmp/models/tmp3fjrifao",
     "task": "",
     "save_load_fn": "hqq",
     "save_load_fn_args": {},