Upload CodeGenForCausalLM

config.json

@@ -0,0 +1,35 @@
+{
+  "_name_or_path": "trl-internal-testing/tiny-random-CodeGenForCausalLM",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "CodeGenForCausalLM"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "attn_pdrop": 0.0,
+  "bos_token_id": 0,
+  "embd_pdrop": 0.0,
+  "eos_token_id": 0,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "initializer_range": 0.02,
+  "intermediate_size": 37,
+  "is_decoder": true,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "codegen",
+  "n_ctx": 2048,
+  "n_embd": 32,
+  "n_head": 4,
+  "n_inner": null,
+  "n_layer": 5,
+  "n_positions": 512,
+  "pad_token_id": 1023,
+  "resid_pdrop": 0.0,
+  "rotary_dim": 4,
+  "scale_attn_weights": true,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.25.1",
+  "type_vocab_size": 16,
+  "use_cache": true,
+  "vocab_size": 1024
+}

pytorch_model-00001-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09a335e8d4b8565cf4606398c7ff1b8d312bf81dc46bd5bbfaa81aae1f3d0646
+size 762697

pytorch_model-00002-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d7b323f5901af24c1f2e6554e457c450d6924873bf4c699f87471a4101107da
+size 945397

pytorch_model-00003-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:656bc6a505163a36daa40712de12b2cb093278388d31e1ec85f4a2795c1f47e6
+size 136379

pytorch_model.bin.index.json

@@ -0,0 +1,57 @@
+{
+  "metadata": {
+    "total_size": 1827456
+  },
+  "weight_map": {
+    "lm_head.bias": "pytorch_model-00003-of-00003.bin",
+    "lm_head.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.0.attn.causal_mask": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.0.attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.0.attn.qkv_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.0.ln_1.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.0.ln_1.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.0.mlp.fc_in.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.0.mlp.fc_in.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.0.mlp.fc_out.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.0.mlp.fc_out.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.1.attn.causal_mask": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.1.attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.1.attn.qkv_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.1.ln_1.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.1.ln_1.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.1.mlp.fc_in.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.1.mlp.fc_in.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.1.mlp.fc_out.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.1.mlp.fc_out.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.2.attn.causal_mask": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.2.attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.2.attn.qkv_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.2.ln_1.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.2.ln_1.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.2.mlp.fc_in.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.2.mlp.fc_in.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.2.mlp.fc_out.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.2.mlp.fc_out.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.3.attn.causal_mask": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.3.attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.3.attn.qkv_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.3.ln_1.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.3.ln_1.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.3.mlp.fc_in.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.3.mlp.fc_in.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.3.mlp.fc_out.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.3.mlp.fc_out.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.4.attn.causal_mask": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.4.attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.4.attn.qkv_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.4.ln_1.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.4.ln_1.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.4.mlp.fc_in.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.4.mlp.fc_in.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.4.mlp.fc_out.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.4.mlp.fc_out.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.ln_f.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.ln_f.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.wte.weight": "pytorch_model-00001-of-00003.bin"
+  }
+}