Upload folder using huggingface_hub (#9)

- b2fb89ce8cec7827b61c1804549b4af41dc5fdb7e1f7b170decf4a5a4a725c9e (f1e84399b76d9c385c007c8b5fa2faf493ad89fd)
- 480c8d9b1c334387551e64e26e24d7e9f0bfbee5f5a22532adcb307e08ec6bd5 (af33719b3db8cf1f86e7ce820c12aa61c4282151)
- 0c8ad235131bccc5c445a3dd85077f2b3082106b01b1150720bd02d3d28703af (72e967f7c6e926f6c25b571b655c34492e47ed2f)

.gitattributes

@@ -35,3 +35,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 models--distributed--optimized-gpt2-1b/blobs/84bd38785e135d735130cb4633155169b1046946034dff6dd9275ef96649e85a filter=lfs diff=lfs merge=lfs -text
 models--distributed--optimized-gpt2-1b/blobs/2525dfc6bc73a28af3c0e9c91ec6e51d2d06ed5043373d6f34559ff9de54c7ff filter=lfs diff=lfs merge=lfs -text
+models--distributed--optimized-gpt2-1b/blobs/f817092111231c54370459c20d8f6f94f3c6227f32eff7230c38aac95a9e74e7 filter=lfs diff=lfs merge=lfs -text

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "/covalent/.cache/models/tmp5unhuka7ffg0pvj0",
+  "_name_or_path": "/covalent/.cache/models/tmprzpy46pucpek6h9q",
   "activation_function": "gelu_new",
   "architectures": [
     "GPTOptim"

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c1055227b3b7fef3dc30fd87ccb6d52f6cf001639b9936f7e9bcc70b35595b1
+oid sha256:aa8fe8365e4b2d57207d05cc02eb618b3dc8b0a9b06ac4cc0b80fb4c7034bd1c
 size 1207575528

models--distributed--optimized-gpt2-1b/blobs/f817092111231c54370459c20d8f6f94f3c6227f32eff7230c38aac95a9e74e7

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f817092111231c54370459c20d8f6f94f3c6227f32eff7230c38aac95a9e74e7
+size 4040701744

models--distributed--optimized-gpt2-1b/refs/main

@@ -1 +1 @@
-0f5f2c85309718087017f97adaabc63a05d6a493
+f5b59fe9dd690b435c6925363bfbd10f2c354a55

models--distributed--optimized-gpt2-1b/snapshots/f5b59fe9dd690b435c6925363bfbd10f2c354a55/config.json

@@ -0,0 +1,37 @@
+{
+  "_name_or_path": "distributed/optimized-gpt2-1b",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPTOptim"
+  ],
+  "attn_pdrop": 0.1,
+  "auto_map": {
+    "AutoConfig": "distributed/optimized-gpt2-500m--configuration_gpt_optimized.GPTOptimConfig",
+    "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
+  },
+  "block_size": 1024,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt_optimized",
+  "n_embd": 1280,
+  "n_head": 32,
+  "n_inner": null,
+  "n_layer": 48,
+  "n_positions": 1024,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.39.3",
+  "use_cache": true,
+  "vocab_size": 50257
+}

models--distributed--optimized-gpt2-1b/snapshots/f5b59fe9dd690b435c6925363bfbd10f2c354a55/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f817092111231c54370459c20d8f6f94f3c6227f32eff7230c38aac95a9e74e7
+size 4040701744

smash_config.json

@@ -28,7 +28,7 @@
     "quant_llm-int8_weight_bits": 8,
     "max_batch_size": 1,
     "device": "cuda",
-    "cache_dir": "/covalent/.cache/models/tmp5unhuka7",
+    "cache_dir": "/covalent/.cache/models/tmprzpy46pu",
     "task": "",
     "save_load_fn": "bitsandbytes",
     "save_load_fn_args": {