Upload ProGenForCausalLM

config.json

@@ -1,4 +1,5 @@
 {
+  "_name_or_path": "hugohrban/progen2-small-mix7",
   "activation_function": "gelu_new",
   "architectures": [
     "ProGenForCausalLM"
@@ -6,6 +7,7 @@
   "attn_pdrop": 0.0,
   "bos_token_id": 1,
   "embd_pdrop": 0.0,
+  "embed_dim": 1024,
   "eos_token_id": 2,
   "gradient_checkpointing": false,
   "initializer_range": 0.02,
@@ -13,25 +15,28 @@
   "model_type": "progen",
   "n_embd": 1024,
   "n_head": 16,
+  "n_inner": null,
   "n_layer": 12,
   "n_positions": 1024,
+  "resid_pdrop": 0.0,
   "rotary_dim": 32,
+  "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,
-  "transformers_version": "4.16.2",
-  "tokenizer_class": "GPT2Tokenizer",
   "task_specific_params": {
     "text-generation": {
       "do_sample": true,
-      "temperature": 1.0,
-      "max_length": 50
+      "max_length": 50,
+      "temperature": 1.0
     }
   },
+  "tokenizer_class": "GPT2Tokenizer",
   "torch_dtype": "float32",
+  "transformers_version": "4.40.0",
   "use_cache": true,
   "vocab_size_emb": 37,
   "vocab_size_lm_head": 32
-}
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.40.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26a519767e3ad388d1403b683421a8c1f6cb3b68018654b8632a91d732c352ca
+size 617210712