Upload 10 files

config.json

@@ -0,0 +1,81 @@
+{
+  "_name_or_path": "KoboldAI/GPT-J-6B-Adventure",
+  "activation_function": "gelu_new",
+  "adventure": true,
+  "architectures": [
+    "GPTJForCausalLM"
+  ],
+  "attn_pdrop": 0.0,
+  "bos_token_id": 50256,
+  "compression_config": {
+    "config_groups": {
+      "group_0": {
+        "input_activations": {
+          "block_structure": null,
+          "dynamic": true,
+          "group_size": null,
+          "num_bits": 8,
+          "observer": "memoryless",
+          "observer_kwargs": {},
+          "strategy": "token",
+          "symmetric": true,
+          "type": "float"
+        },
+        "output_activations": null,
+        "targets": [
+          "Linear"
+        ],
+        "weights": {
+          "block_structure": null,
+          "dynamic": false,
+          "group_size": null,
+          "num_bits": 8,
+          "observer": "minmax",
+          "observer_kwargs": {},
+          "strategy": "channel",
+          "symmetric": true,
+          "type": "float"
+        }
+      }
+    },
+    "format": "float-quantized",
+    "global_compression_ratio": 1.2120992879625097,
+    "ignore": [
+      "lm_head"
+    ],
+    "kv_cache_scheme": null,
+    "quant_method": "compressed-tensors",
+    "quantization_status": "frozen"
+  },
+  "embd_pdrop": 0.0,
+  "eos_token_id": 50256,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gptj",
+  "n_embd": 4096,
+  "n_head": 16,
+  "n_inner": null,
+  "n_layer": 28,
+  "n_positions": 2048,
+  "rep_pen": 1.2,
+  "resid_pdrop": 0.0,
+  "rotary_dim": 64,
+  "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
+    }
+  },
+  "tie_word_embeddings": false,
+  "tokenizer_class": "GPT2Tokenizer",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.44.1",
+  "use_cache": true,
+  "vocab_size": 50400
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.44.1"
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ff24e484f920ae5752864442c69106f02705145e786020daad8b6e8ebe927c0
+size 4979317728

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1afe20cdcc96e454eb593eb67103e51b8471cfc120cff682dade22f004552830
+size 1487417240

model.safetensors.index.json

@@ -0,0 +1,460 @@
+{
+  "metadata": {
+    "total_size": 6466685376
+  },
+  "weight_map": {
+    "lm_head.bias": "model-00002-of-00002.safetensors",
+    "lm_head.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.0.attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.0.attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "transformer.h.0.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.0.attn.out_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "transformer.h.0.attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.0.attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "transformer.h.0.attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.0.attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "transformer.h.0.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.0.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.0.mlp.fc_in.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.0.mlp.fc_in.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.0.mlp.fc_in.weight_scale": "model-00001-of-00002.safetensors",
+    "transformer.h.0.mlp.fc_out.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.0.mlp.fc_out.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.0.mlp.fc_out.weight_scale": "model-00001-of-00002.safetensors",
+    "transformer.h.1.attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.1.attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "transformer.h.1.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.1.attn.out_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "transformer.h.1.attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.1.attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "transformer.h.1.attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.1.attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "transformer.h.1.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.1.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.1.mlp.fc_in.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.1.mlp.fc_in.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.1.mlp.fc_in.weight_scale": "model-00001-of-00002.safetensors",
+    "transformer.h.1.mlp.fc_out.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.1.mlp.fc_out.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.1.mlp.fc_out.weight_scale": "model-00001-of-00002.safetensors",
+    "transformer.h.10.attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.10.attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "transformer.h.10.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.10.attn.out_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "transformer.h.10.attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.10.attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "transformer.h.10.attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.10.attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "transformer.h.10.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.10.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.10.mlp.fc_in.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.10.mlp.fc_in.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.10.mlp.fc_in.weight_scale": "model-00001-of-00002.safetensors",
+    "transformer.h.10.mlp.fc_out.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.10.mlp.fc_out.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.10.mlp.fc_out.weight_scale": "model-00001-of-00002.safetensors",
+    "transformer.h.11.attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.11.attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "transformer.h.11.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.11.attn.out_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "transformer.h.11.attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.11.attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "transformer.h.11.attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.11.attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "transformer.h.11.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.11.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.11.mlp.fc_in.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.11.mlp.fc_in.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.11.mlp.fc_in.weight_scale": "model-00001-of-00002.safetensors",
+    "transformer.h.11.mlp.fc_out.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.11.mlp.fc_out.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.11.mlp.fc_out.weight_scale": "model-00001-of-00002.safetensors",
+    "transformer.h.12.attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.12.attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "transformer.h.12.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.12.attn.out_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "transformer.h.12.attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.12.attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "transformer.h.12.attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.12.attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "transformer.h.12.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.12.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.12.mlp.fc_in.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.12.mlp.fc_in.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.12.mlp.fc_in.weight_scale": "model-00001-of-00002.safetensors",
+    "transformer.h.12.mlp.fc_out.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.12.mlp.fc_out.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.12.mlp.fc_out.weight_scale": "model-00001-of-00002.safetensors",
+    "transformer.h.13.attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.13.attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "transformer.h.13.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.13.attn.out_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "transformer.h.13.attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.13.attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "transformer.h.13.attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.13.attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "transformer.h.13.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.13.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.13.mlp.fc_in.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.13.mlp.fc_in.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.13.mlp.fc_in.weight_scale": "model-00001-of-00002.safetensors",
+    "transformer.h.13.mlp.fc_out.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.13.mlp.fc_out.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.13.mlp.fc_out.weight_scale": "model-00001-of-00002.safetensors",
+    "transformer.h.14.attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.14.attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "transformer.h.14.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.14.attn.out_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "transformer.h.14.attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.14.attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "transformer.h.14.attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.14.attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "transformer.h.14.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.14.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.14.mlp.fc_in.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.14.mlp.fc_in.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.14.mlp.fc_in.weight_scale": "model-00001-of-00002.safetensors",
+    "transformer.h.14.mlp.fc_out.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.14.mlp.fc_out.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.14.mlp.fc_out.weight_scale": "model-00001-of-00002.safetensors",
+    "transformer.h.15.attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.15.attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "transformer.h.15.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.15.attn.out_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "transformer.h.15.attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.15.attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "transformer.h.15.attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.15.attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "transformer.h.15.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.15.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.15.mlp.fc_in.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.15.mlp.fc_in.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.15.mlp.fc_in.weight_scale": "model-00001-of-00002.safetensors",
+    "transformer.h.15.mlp.fc_out.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.15.mlp.fc_out.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.15.mlp.fc_out.weight_scale": "model-00001-of-00002.safetensors",
+    "transformer.h.16.attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.16.attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "transformer.h.16.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.16.attn.out_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "transformer.h.16.attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.16.attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "transformer.h.16.attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.16.attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "transformer.h.16.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.16.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.16.mlp.fc_in.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.16.mlp.fc_in.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.16.mlp.fc_in.weight_scale": "model-00001-of-00002.safetensors",
+    "transformer.h.16.mlp.fc_out.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.16.mlp.fc_out.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.16.mlp.fc_out.weight_scale": "model-00001-of-00002.safetensors",
+    "transformer.h.17.attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.17.attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "transformer.h.17.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.17.attn.out_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "transformer.h.17.attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.17.attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "transformer.h.17.attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.17.attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "transformer.h.17.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.17.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.17.mlp.fc_in.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.17.mlp.fc_in.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.17.mlp.fc_in.weight_scale": "model-00001-of-00002.safetensors",
+    "transformer.h.17.mlp.fc_out.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.17.mlp.fc_out.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.17.mlp.fc_out.weight_scale": "model-00001-of-00002.safetensors",
+    "transformer.h.18.attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.18.attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "transformer.h.18.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.18.attn.out_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "transformer.h.18.attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.18.attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "transformer.h.18.attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.18.attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "transformer.h.18.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.18.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.18.mlp.fc_in.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.18.mlp.fc_in.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.18.mlp.fc_in.weight_scale": "model-00001-of-00002.safetensors",
+    "transformer.h.18.mlp.fc_out.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.18.mlp.fc_out.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.18.mlp.fc_out.weight_scale": "model-00001-of-00002.safetensors",
+    "transformer.h.19.attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.19.attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "transformer.h.19.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.19.attn.out_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "transformer.h.19.attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.19.attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "transformer.h.19.attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.19.attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "transformer.h.19.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.19.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.19.mlp.fc_in.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.19.mlp.fc_in.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.19.mlp.fc_in.weight_scale": "model-00001-of-00002.safetensors",
+    "transformer.h.19.mlp.fc_out.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.19.mlp.fc_out.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.19.mlp.fc_out.weight_scale": "model-00001-of-00002.safetensors",
+    "transformer.h.2.attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.2.attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "transformer.h.2.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.2.attn.out_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "transformer.h.2.attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.2.attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "transformer.h.2.attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.2.attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "transformer.h.2.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.2.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.2.mlp.fc_in.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.2.mlp.fc_in.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.2.mlp.fc_in.weight_scale": "model-00001-of-00002.safetensors",
+    "transformer.h.2.mlp.fc_out.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.2.mlp.fc_out.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.2.mlp.fc_out.weight_scale": "model-00001-of-00002.safetensors",
+    "transformer.h.20.attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.20.attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "transformer.h.20.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.20.attn.out_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "transformer.h.20.attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.20.attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "transformer.h.20.attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.20.attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "transformer.h.20.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.20.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.20.mlp.fc_in.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.20.mlp.fc_in.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.20.mlp.fc_in.weight_scale": "model-00001-of-00002.safetensors",
+    "transformer.h.20.mlp.fc_out.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.20.mlp.fc_out.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.20.mlp.fc_out.weight_scale": "model-00001-of-00002.safetensors",
+    "transformer.h.21.attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.21.attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "transformer.h.21.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.21.attn.out_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "transformer.h.21.attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.21.attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "transformer.h.21.attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.21.attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "transformer.h.21.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.21.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.21.mlp.fc_in.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.21.mlp.fc_in.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.21.mlp.fc_in.weight_scale": "model-00001-of-00002.safetensors",
+    "transformer.h.21.mlp.fc_out.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.21.mlp.fc_out.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.21.mlp.fc_out.weight_scale": "model-00001-of-00002.safetensors",
+    "transformer.h.22.attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.22.attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "transformer.h.22.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.22.attn.out_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "transformer.h.22.attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.22.attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "transformer.h.22.attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.22.attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "transformer.h.22.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.22.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.22.mlp.fc_in.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.22.mlp.fc_in.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.22.mlp.fc_in.weight_scale": "model-00001-of-00002.safetensors",
+    "transformer.h.22.mlp.fc_out.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.22.mlp.fc_out.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.22.mlp.fc_out.weight_scale": "model-00002-of-00002.safetensors",
+    "transformer.h.23.attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.23.attn.k_proj.weight_scale": "model-00002-of-00002.safetensors",
+    "transformer.h.23.attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.23.attn.out_proj.weight_scale": "model-00002-of-00002.safetensors",
+    "transformer.h.23.attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.23.attn.q_proj.weight_scale": "model-00002-of-00002.safetensors",
+    "transformer.h.23.attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.23.attn.v_proj.weight_scale": "model-00002-of-00002.safetensors",
+    "transformer.h.23.ln_1.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.23.ln_1.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.23.mlp.fc_in.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.23.mlp.fc_in.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.23.mlp.fc_in.weight_scale": "model-00002-of-00002.safetensors",
+    "transformer.h.23.mlp.fc_out.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.23.mlp.fc_out.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.23.mlp.fc_out.weight_scale": "model-00002-of-00002.safetensors",
+    "transformer.h.24.attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.24.attn.k_proj.weight_scale": "model-00002-of-00002.safetensors",
+    "transformer.h.24.attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.24.attn.out_proj.weight_scale": "model-00002-of-00002.safetensors",
+    "transformer.h.24.attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.24.attn.q_proj.weight_scale": "model-00002-of-00002.safetensors",
+    "transformer.h.24.attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.24.attn.v_proj.weight_scale": "model-00002-of-00002.safetensors",
+    "transformer.h.24.ln_1.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.24.ln_1.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.24.mlp.fc_in.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.24.mlp.fc_in.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.24.mlp.fc_in.weight_scale": "model-00002-of-00002.safetensors",
+    "transformer.h.24.mlp.fc_out.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.24.mlp.fc_out.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.24.mlp.fc_out.weight_scale": "model-00002-of-00002.safetensors",
+    "transformer.h.25.attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.25.attn.k_proj.weight_scale": "model-00002-of-00002.safetensors",
+    "transformer.h.25.attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.25.attn.out_proj.weight_scale": "model-00002-of-00002.safetensors",
+    "transformer.h.25.attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.25.attn.q_proj.weight_scale": "model-00002-of-00002.safetensors",
+    "transformer.h.25.attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.25.attn.v_proj.weight_scale": "model-00002-of-00002.safetensors",
+    "transformer.h.25.ln_1.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.25.ln_1.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.25.mlp.fc_in.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.25.mlp.fc_in.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.25.mlp.fc_in.weight_scale": "model-00002-of-00002.safetensors",
+    "transformer.h.25.mlp.fc_out.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.25.mlp.fc_out.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.25.mlp.fc_out.weight_scale": "model-00002-of-00002.safetensors",
+    "transformer.h.26.attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.26.attn.k_proj.weight_scale": "model-00002-of-00002.safetensors",
+    "transformer.h.26.attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.26.attn.out_proj.weight_scale": "model-00002-of-00002.safetensors",
+    "transformer.h.26.attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.26.attn.q_proj.weight_scale": "model-00002-of-00002.safetensors",
+    "transformer.h.26.attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.26.attn.v_proj.weight_scale": "model-00002-of-00002.safetensors",
+    "transformer.h.26.ln_1.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.26.ln_1.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.26.mlp.fc_in.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.26.mlp.fc_in.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.26.mlp.fc_in.weight_scale": "model-00002-of-00002.safetensors",
+    "transformer.h.26.mlp.fc_out.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.26.mlp.fc_out.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.26.mlp.fc_out.weight_scale": "model-00002-of-00002.safetensors",
+    "transformer.h.27.attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.27.attn.k_proj.weight_scale": "model-00002-of-00002.safetensors",
+    "transformer.h.27.attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.27.attn.out_proj.weight_scale": "model-00002-of-00002.safetensors",
+    "transformer.h.27.attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.27.attn.q_proj.weight_scale": "model-00002-of-00002.safetensors",
+    "transformer.h.27.attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.27.attn.v_proj.weight_scale": "model-00002-of-00002.safetensors",
+    "transformer.h.27.ln_1.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.27.ln_1.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.27.mlp.fc_in.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.27.mlp.fc_in.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.27.mlp.fc_in.weight_scale": "model-00002-of-00002.safetensors",
+    "transformer.h.27.mlp.fc_out.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.27.mlp.fc_out.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.27.mlp.fc_out.weight_scale": "model-00002-of-00002.safetensors",
+    "transformer.h.3.attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.3.attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "transformer.h.3.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.3.attn.out_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "transformer.h.3.attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.3.attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "transformer.h.3.attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.3.attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "transformer.h.3.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.3.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.3.mlp.fc_in.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.3.mlp.fc_in.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.3.mlp.fc_in.weight_scale": "model-00001-of-00002.safetensors",
+    "transformer.h.3.mlp.fc_out.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.3.mlp.fc_out.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.3.mlp.fc_out.weight_scale": "model-00001-of-00002.safetensors",
+    "transformer.h.4.attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.4.attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "transformer.h.4.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.4.attn.out_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "transformer.h.4.attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.4.attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "transformer.h.4.attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.4.attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "transformer.h.4.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.4.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.4.mlp.fc_in.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.4.mlp.fc_in.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.4.mlp.fc_in.weight_scale": "model-00001-of-00002.safetensors",
+    "transformer.h.4.mlp.fc_out.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.4.mlp.fc_out.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.4.mlp.fc_out.weight_scale": "model-00001-of-00002.safetensors",
+    "transformer.h.5.attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.5.attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "transformer.h.5.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.5.attn.out_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "transformer.h.5.attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.5.attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "transformer.h.5.attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.5.attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "transformer.h.5.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.5.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.5.mlp.fc_in.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.5.mlp.fc_in.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.5.mlp.fc_in.weight_scale": "model-00001-of-00002.safetensors",
+    "transformer.h.5.mlp.fc_out.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.5.mlp.fc_out.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.5.mlp.fc_out.weight_scale": "model-00001-of-00002.safetensors",
+    "transformer.h.6.attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.6.attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "transformer.h.6.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.6.attn.out_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "transformer.h.6.attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.6.attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "transformer.h.6.attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.6.attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "transformer.h.6.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.6.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.6.mlp.fc_in.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.6.mlp.fc_in.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.6.mlp.fc_in.weight_scale": "model-00001-of-00002.safetensors",
+    "transformer.h.6.mlp.fc_out.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.6.mlp.fc_out.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.6.mlp.fc_out.weight_scale": "model-00001-of-00002.safetensors",
+    "transformer.h.7.attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.7.attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "transformer.h.7.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.7.attn.out_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "transformer.h.7.attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.7.attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "transformer.h.7.attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.7.attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "transformer.h.7.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.7.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.7.mlp.fc_in.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.7.mlp.fc_in.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.7.mlp.fc_in.weight_scale": "model-00001-of-00002.safetensors",
+    "transformer.h.7.mlp.fc_out.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.7.mlp.fc_out.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.7.mlp.fc_out.weight_scale": "model-00001-of-00002.safetensors",
+    "transformer.h.8.attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.8.attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "transformer.h.8.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.8.attn.out_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "transformer.h.8.attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.8.attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "transformer.h.8.attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.8.attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "transformer.h.8.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.8.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.8.mlp.fc_in.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.8.mlp.fc_in.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.8.mlp.fc_in.weight_scale": "model-00001-of-00002.safetensors",
+    "transformer.h.8.mlp.fc_out.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.8.mlp.fc_out.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.8.mlp.fc_out.weight_scale": "model-00001-of-00002.safetensors",
+    "transformer.h.9.attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.9.attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "transformer.h.9.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.9.attn.out_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "transformer.h.9.attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.9.attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "transformer.h.9.attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.9.attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "transformer.h.9.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.9.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.9.mlp.fc_in.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.9.mlp.fc_in.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.9.mlp.fc_in.weight_scale": "model-00001-of-00002.safetensors",
+    "transformer.h.9.mlp.fc_out.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.9.mlp.fc_out.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.9.mlp.fc_out.weight_scale": "model-00001-of-00002.safetensors",
+    "transformer.ln_f.bias": "model-00002-of-00002.safetensors",
+    "transformer.ln_f.weight": "model-00002-of-00002.safetensors",
+    "transformer.wte.weight": "model-00001-of-00002.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,22 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}