Upload 7 files

Uploading model files

config.json

@@ -0,0 +1,41 @@
+{
+  "_name_or_path": "./model_checkpoints/progen2-large",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "ProGenForCausalLM"
+  ],
+  "attn_pdrop": 0.0,
+  "bos_token_id": 1,
+  "embd_pdrop": 0.0,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "progen",
+  "n_ctx": 2048,
+  "n_embd": 2560,
+  "n_head": 32,
+  "n_inner": null,
+  "n_layer": 32,
+  "n_positions": 1024,
+  "resid_pdrop": 0.0,
+  "rotary_dim": 64,
+  "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,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50,
+      "temperature": 1.0
+    }
+  },
+  "tokenizer_class": "GPT2Tokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.2",
+  "use_cache": true,
+  "vocab_size": 51200
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.35.2"
+}

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:260466a492a15af4a872926f030ecf2fa9d14c689e418f13a5e245e3e2bcdd5b
+size 4945075332

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af89a540da7a63b62b3ebe0621748ab033201dfba488403bde47b330b508f25e
+size 4945168628

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:114e378ddcce0c59a1f266addbb1a187c27eb30804d90863ddc1e0a31c516567
+size 1260769976

model.safetensors.index.json

@@ -0,0 +1,332 @@
+{
+  "metadata": {
+    "total_size": 11121619072.0
+  },
+  "weight_map": {
+    "lm_head.bias": "model-00003-of-00003.safetensors",
+    "lm_head.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.0.attn.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.0.attn.masked_bias": "model-00001-of-00003.safetensors",
+    "transformer.h.0.attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.0.attn.qkv_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.0.ln_1.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.0.ln_1.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.0.mlp.fc_in.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.0.mlp.fc_in.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.0.mlp.fc_out.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.0.mlp.fc_out.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.1.attn.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.1.attn.masked_bias": "model-00001-of-00003.safetensors",
+    "transformer.h.1.attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.1.attn.qkv_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.1.ln_1.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.1.ln_1.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.1.mlp.fc_in.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.1.mlp.fc_in.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.1.mlp.fc_out.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.1.mlp.fc_out.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.10.attn.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.10.attn.masked_bias": "model-00001-of-00003.safetensors",
+    "transformer.h.10.attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.10.attn.qkv_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.10.ln_1.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.10.ln_1.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.10.mlp.fc_in.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.10.mlp.fc_in.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.10.mlp.fc_out.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.10.mlp.fc_out.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.11.attn.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.11.attn.masked_bias": "model-00001-of-00003.safetensors",
+    "transformer.h.11.attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.11.attn.qkv_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.11.ln_1.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.11.ln_1.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.11.mlp.fc_in.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.11.mlp.fc_in.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.11.mlp.fc_out.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.11.mlp.fc_out.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.12.attn.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.12.attn.masked_bias": "model-00001-of-00003.safetensors",
+    "transformer.h.12.attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.12.attn.qkv_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.12.ln_1.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.12.ln_1.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.12.mlp.fc_in.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.12.mlp.fc_in.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.12.mlp.fc_out.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.12.mlp.fc_out.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.13.attn.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.13.attn.masked_bias": "model-00001-of-00003.safetensors",
+    "transformer.h.13.attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.13.attn.qkv_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.13.ln_1.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.13.ln_1.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.13.mlp.fc_in.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.13.mlp.fc_in.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.13.mlp.fc_out.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.13.mlp.fc_out.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.14.attn.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.14.attn.masked_bias": "model-00001-of-00003.safetensors",
+    "transformer.h.14.attn.out_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.14.attn.qkv_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.14.ln_1.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.14.ln_1.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.14.mlp.fc_in.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.14.mlp.fc_in.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.14.mlp.fc_out.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.14.mlp.fc_out.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.15.attn.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.15.attn.masked_bias": "model-00002-of-00003.safetensors",
+    "transformer.h.15.attn.out_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.15.attn.qkv_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.15.ln_1.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.15.ln_1.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.15.mlp.fc_in.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.15.mlp.fc_in.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.15.mlp.fc_out.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.15.mlp.fc_out.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.16.attn.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.16.attn.masked_bias": "model-00002-of-00003.safetensors",
+    "transformer.h.16.attn.out_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.16.attn.qkv_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.16.ln_1.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.16.ln_1.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.16.mlp.fc_in.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.16.mlp.fc_in.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.16.mlp.fc_out.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.16.mlp.fc_out.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.17.attn.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.17.attn.masked_bias": "model-00002-of-00003.safetensors",
+    "transformer.h.17.attn.out_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.17.attn.qkv_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.17.ln_1.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.17.ln_1.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.17.mlp.fc_in.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.17.mlp.fc_in.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.17.mlp.fc_out.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.17.mlp.fc_out.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.18.attn.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.18.attn.masked_bias": "model-00002-of-00003.safetensors",
+    "transformer.h.18.attn.out_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.18.attn.qkv_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.18.ln_1.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.18.ln_1.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.18.mlp.fc_in.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.18.mlp.fc_in.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.18.mlp.fc_out.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.18.mlp.fc_out.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.19.attn.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.19.attn.masked_bias": "model-00002-of-00003.safetensors",
+    "transformer.h.19.attn.out_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.19.attn.qkv_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.19.ln_1.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.19.ln_1.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.19.mlp.fc_in.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.19.mlp.fc_in.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.19.mlp.fc_out.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.19.mlp.fc_out.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.2.attn.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.2.attn.masked_bias": "model-00001-of-00003.safetensors",
+    "transformer.h.2.attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.2.attn.qkv_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.2.ln_1.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.2.ln_1.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.2.mlp.fc_in.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.2.mlp.fc_in.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.2.mlp.fc_out.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.2.mlp.fc_out.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.20.attn.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.20.attn.masked_bias": "model-00002-of-00003.safetensors",
+    "transformer.h.20.attn.out_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.20.attn.qkv_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.20.ln_1.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.20.ln_1.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.20.mlp.fc_in.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.20.mlp.fc_in.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.20.mlp.fc_out.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.20.mlp.fc_out.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.21.attn.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.21.attn.masked_bias": "model-00002-of-00003.safetensors",
+    "transformer.h.21.attn.out_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.21.attn.qkv_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.21.ln_1.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.21.ln_1.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.21.mlp.fc_in.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.21.mlp.fc_in.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.21.mlp.fc_out.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.21.mlp.fc_out.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.22.attn.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.22.attn.masked_bias": "model-00002-of-00003.safetensors",
+    "transformer.h.22.attn.out_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.22.attn.qkv_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.22.ln_1.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.22.ln_1.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.22.mlp.fc_in.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.22.mlp.fc_in.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.22.mlp.fc_out.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.22.mlp.fc_out.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.23.attn.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.23.attn.masked_bias": "model-00002-of-00003.safetensors",
+    "transformer.h.23.attn.out_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.23.attn.qkv_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.23.ln_1.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.23.ln_1.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.23.mlp.fc_in.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.23.mlp.fc_in.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.23.mlp.fc_out.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.23.mlp.fc_out.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.24.attn.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.24.attn.masked_bias": "model-00002-of-00003.safetensors",
+    "transformer.h.24.attn.out_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.24.attn.qkv_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.24.ln_1.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.24.ln_1.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.24.mlp.fc_in.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.24.mlp.fc_in.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.24.mlp.fc_out.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.24.mlp.fc_out.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.25.attn.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.25.attn.masked_bias": "model-00002-of-00003.safetensors",
+    "transformer.h.25.attn.out_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.25.attn.qkv_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.25.ln_1.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.25.ln_1.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.25.mlp.fc_in.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.25.mlp.fc_in.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.25.mlp.fc_out.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.25.mlp.fc_out.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.26.attn.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.26.attn.masked_bias": "model-00002-of-00003.safetensors",
+    "transformer.h.26.attn.out_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.26.attn.qkv_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.26.ln_1.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.26.ln_1.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.26.mlp.fc_in.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.26.mlp.fc_in.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.26.mlp.fc_out.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.26.mlp.fc_out.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.27.attn.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.27.attn.masked_bias": "model-00002-of-00003.safetensors",
+    "transformer.h.27.attn.out_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.27.attn.qkv_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.27.ln_1.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.27.ln_1.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.27.mlp.fc_in.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.27.mlp.fc_in.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.27.mlp.fc_out.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.27.mlp.fc_out.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.28.attn.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.28.attn.masked_bias": "model-00002-of-00003.safetensors",
+    "transformer.h.28.attn.out_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.28.attn.qkv_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.28.ln_1.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.28.ln_1.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.28.mlp.fc_in.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.28.mlp.fc_in.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.28.mlp.fc_out.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.28.mlp.fc_out.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.29.attn.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.29.attn.masked_bias": "model-00002-of-00003.safetensors",
+    "transformer.h.29.attn.out_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.29.attn.qkv_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.29.ln_1.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.29.ln_1.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.29.mlp.fc_in.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.29.mlp.fc_in.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.29.mlp.fc_out.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.29.mlp.fc_out.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.3.attn.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.3.attn.masked_bias": "model-00001-of-00003.safetensors",
+    "transformer.h.3.attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.3.attn.qkv_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.3.ln_1.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.3.ln_1.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.3.mlp.fc_in.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.3.mlp.fc_in.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.3.mlp.fc_out.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.3.mlp.fc_out.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.30.attn.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.30.attn.masked_bias": "model-00003-of-00003.safetensors",
+    "transformer.h.30.attn.out_proj.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.30.attn.qkv_proj.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.30.ln_1.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.30.ln_1.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.30.mlp.fc_in.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.30.mlp.fc_in.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.30.mlp.fc_out.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.30.mlp.fc_out.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.31.attn.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.31.attn.masked_bias": "model-00003-of-00003.safetensors",
+    "transformer.h.31.attn.out_proj.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.31.attn.qkv_proj.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.31.ln_1.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.31.ln_1.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.31.mlp.fc_in.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.31.mlp.fc_in.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.31.mlp.fc_out.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.31.mlp.fc_out.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.4.attn.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.4.attn.masked_bias": "model-00001-of-00003.safetensors",
+    "transformer.h.4.attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.4.attn.qkv_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.4.ln_1.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.4.ln_1.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.4.mlp.fc_in.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.4.mlp.fc_in.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.4.mlp.fc_out.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.4.mlp.fc_out.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.5.attn.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.5.attn.masked_bias": "model-00001-of-00003.safetensors",
+    "transformer.h.5.attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.5.attn.qkv_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.5.ln_1.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.5.ln_1.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.5.mlp.fc_in.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.5.mlp.fc_in.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.5.mlp.fc_out.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.5.mlp.fc_out.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.6.attn.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.6.attn.masked_bias": "model-00001-of-00003.safetensors",
+    "transformer.h.6.attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.6.attn.qkv_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.6.ln_1.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.6.ln_1.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.6.mlp.fc_in.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.6.mlp.fc_in.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.6.mlp.fc_out.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.6.mlp.fc_out.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.7.attn.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.7.attn.masked_bias": "model-00001-of-00003.safetensors",
+    "transformer.h.7.attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.7.attn.qkv_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.7.ln_1.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.7.ln_1.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.7.mlp.fc_in.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.7.mlp.fc_in.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.7.mlp.fc_out.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.7.mlp.fc_out.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.8.attn.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.8.attn.masked_bias": "model-00001-of-00003.safetensors",
+    "transformer.h.8.attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.8.attn.qkv_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.8.ln_1.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.8.ln_1.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.8.mlp.fc_in.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.8.mlp.fc_in.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.8.mlp.fc_out.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.8.mlp.fc_out.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.9.attn.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.9.attn.masked_bias": "model-00001-of-00003.safetensors",
+    "transformer.h.9.attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.9.attn.qkv_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.9.ln_1.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.9.ln_1.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.9.mlp.fc_in.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.9.mlp.fc_in.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.9.mlp.fc_out.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.9.mlp.fc_out.weight": "model-00001-of-00003.safetensors",
+    "transformer.ln_f.bias": "model-00003-of-00003.safetensors",
+    "transformer.ln_f.weight": "model-00003-of-00003.safetensors",
+    "transformer.wte.weight": "model-00001-of-00003.safetensors"
+  }
+}

tokenizer.json

@@ -0,0 +1,91 @@
+{
+  "version": "1.0",
+  "truncation": null,
+  "padding": null,
+  "added_tokens": [
+    {
+      "id": 0,
+      "special": true,
+      "content": "<|pad|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false
+    },
+    {
+      "id": 1,
+      "special": true,
+      "content": "<|bos|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false
+    },
+    {
+      "id": 2,
+      "special": true,
+      "content": "<|eos|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false
+    }
+  ],
+  "normalizer": null,
+  "pre_tokenizer": {
+    "type": "ByteLevel",
+    "add_prefix_space": false,
+    "trim_offsets": true
+  },
+  "post_processor": {
+    "type": "ByteLevel",
+    "add_prefix_space": true,
+    "trim_offsets": true
+  },
+  "decoder": {
+    "type": "ByteLevel",
+    "add_prefix_space": true,
+    "trim_offsets": true
+  },
+  "model": {
+    "type": "BPE",
+    "dropout": null,
+    "unk_token": null,
+    "continuing_subword_prefix": null,
+    "end_of_word_suffix": null,
+    "fuse_unk": false,
+    "vocab": {
+      "<|pad|>": 0,
+      "<|bos|>": 1,
+      "<|eos|>": 2,
+      "1": 3,
+      "2": 4,
+      "A": 5,
+      "B": 6,
+      "C": 7,
+      "D": 8,
+      "E": 9,
+      "F": 10,
+      "G": 11,
+      "H": 12,
+      "I": 13,
+      "K": 14,
+      "L": 15,
+      "M": 16,
+      "N": 17,
+      "O": 18,
+      "P": 19,
+      "Q": 20,
+      "R": 21,
+      "S": 22,
+      "T": 23,
+      "U": 24,
+      "V": 25,
+      "W": 26,
+      "X": 27,
+      "Y": 28,
+      "Z": 29
+    },
+    "merges": []
+  }
+}