Upload folder using huggingface_hub

config.json

@@ -1,14 +1,14 @@
 {
-  "_name_or_path": "CrystalCoder",
+  "_name_or_path": "LLM360/CrystalChat",
   "activation_function": "swiglu",
   "architectures": [
     "CrystalCoderLMHeadModel"
   ],
   "attn_pdrop": 0.0,
   "auto_map": {
-    "AutoConfig": "configuration_crystalcoder.CrystalCoderConfig",
-    "AutoModel": "modeling_crystalcoder.CrystalCoderModel",
-    "AutoModelForCausalLM": "modeling_crystalcoder.CrystalCoderLMHeadModel"
+    "AutoConfig": "LLM360/CrystalChat--configuration_crystalcoder.CrystalCoderConfig",
+    "AutoModel": "LLM360/CrystalChat--modeling_crystalcoder.CrystalCoderModel",
+    "AutoModelForCausalLM": "LLM360/CrystalChat--modeling_crystalcoder.CrystalCoderLMHeadModel"
   },
   "bos_token_id": 1,
   "embd_pdrop": 0.0,
@@ -31,8 +31,8 @@
   "rotary_dim": 32,
   "scale_attn_by_inverse_layer_idx": false,
   "scale_attn_weights": true,
-  "torch_dtype": "float32",
-  "transformers_version": "4.35.2",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.34.0",
   "use_cache": true,
   "vocab_size": 32032
 }

generation_config.json

@@ -2,5 +2,5 @@
   "_from_model_config": true,
   "bos_token_id": 1,
   "eos_token_id": 2,
-  "transformers_version": "4.35.2"
+  "transformers_version": "4.34.0"
 }

pytorch_model-00001-of-00002.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1553103d04cb9cbc921fcc734a02726c01e041a73ae1b777eb60a5dbd6a71a29
+size 9928640972

pytorch_model-00002-of-00002.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ac98828a5f0730d4879c25e1900d8319527ac414775393ad91c72185ea6801b
+size 3222071483

pytorch_model.bin.index.json

@@ -0,0 +1,459 @@
+{
+  "metadata": {
+    "total_size": 13150557440
+  },
+  "weight_map": {
+    "lm_head.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.0.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.0.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.0.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.0.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.0.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.0.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.0.ln_2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.0.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.0.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.0.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.0.mlp.c_fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.0.mlp.c_fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.0.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.0.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.1.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.1.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.1.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.1.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.1.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.1.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.1.ln_2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.1.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.1.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.1.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.1.mlp.c_fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.1.mlp.c_fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.1.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.1.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.10.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.10.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.10.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.10.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.10.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.10.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.10.ln_2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.10.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.10.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.10.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.10.mlp.c_fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.10.mlp.c_fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.10.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.10.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.11.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.11.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.11.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.11.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.11.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.11.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.11.ln_2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.11.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.11.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.11.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.11.mlp.c_fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.11.mlp.c_fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.11.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.11.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.12.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.12.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.12.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.12.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.12.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.12.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.12.ln_2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.12.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.12.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.12.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.12.mlp.c_fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.12.mlp.c_fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.12.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.12.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.13.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.13.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.13.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.13.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.13.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.13.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.13.ln_2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.13.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.13.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.13.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.13.mlp.c_fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.13.mlp.c_fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.13.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.13.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.14.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.14.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.14.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.14.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.14.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.14.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.14.ln_2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.14.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.14.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.14.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.14.mlp.c_fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.14.mlp.c_fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.14.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.14.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.15.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.15.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.15.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.15.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.15.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.15.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.15.ln_2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.15.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.15.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.15.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.15.mlp.c_fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.15.mlp.c_fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.15.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.15.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.16.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.16.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.16.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.16.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.16.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.16.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.16.ln_2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.16.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.16.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.16.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.16.mlp.c_fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.16.mlp.c_fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.16.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.16.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.17.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.17.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.17.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.17.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.17.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.17.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.17.ln_2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.17.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.17.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.17.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.17.mlp.c_fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.17.mlp.c_fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.17.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.17.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.18.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.18.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.18.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.18.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.18.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.18.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.18.ln_2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.18.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.18.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.18.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.18.mlp.c_fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.18.mlp.c_fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.18.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.18.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.19.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.19.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.19.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.19.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.19.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.19.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.19.ln_2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.19.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.19.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.19.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.19.mlp.c_fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.19.mlp.c_fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.19.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.19.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.2.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.2.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.2.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.2.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.2.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.2.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.2.ln_2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.2.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.2.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.2.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.2.mlp.c_fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.2.mlp.c_fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.2.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.2.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.20.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.20.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.20.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.20.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.20.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.20.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.20.ln_2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.20.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.20.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.20.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.20.mlp.c_fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.20.mlp.c_fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.20.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.20.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.21.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.21.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.21.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.21.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.21.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.21.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.21.ln_2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.21.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.21.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.21.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.21.mlp.c_fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.21.mlp.c_fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.21.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.21.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.22.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.22.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.22.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.22.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.22.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.22.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.22.ln_2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.22.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.22.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.22.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.22.mlp.c_fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.22.mlp.c_fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.22.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.22.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.23.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.23.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.23.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.23.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.23.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.23.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.23.ln_2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.23.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.23.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.23.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.23.mlp.c_fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.23.mlp.c_fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.23.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.23.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.24.attn.c_attn.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.24.attn.c_attn.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.24.attn.c_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.24.attn.c_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.24.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.24.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.24.ln_2.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.24.ln_2.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.24.mlp.c_fc.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.24.mlp.c_fc.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.24.mlp.c_fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.24.mlp.c_fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.24.mlp.c_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.24.mlp.c_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.25.attn.c_attn.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.25.attn.c_attn.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.25.attn.c_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.25.attn.c_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.25.ln_1.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.25.ln_1.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.25.ln_2.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.25.ln_2.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.25.mlp.c_fc.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.25.mlp.c_fc.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.25.mlp.c_fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.25.mlp.c_fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.25.mlp.c_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.25.mlp.c_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.26.attn.c_attn.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.26.attn.c_attn.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.26.attn.c_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.26.attn.c_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.26.ln_1.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.26.ln_1.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.26.ln_2.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.26.ln_2.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.26.mlp.c_fc.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.26.mlp.c_fc.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.26.mlp.c_fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.26.mlp.c_fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.26.mlp.c_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.26.mlp.c_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.27.attn.c_attn.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.27.attn.c_attn.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.27.attn.c_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.27.attn.c_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.27.ln_1.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.27.ln_1.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.27.ln_2.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.27.ln_2.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.27.mlp.c_fc.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.27.mlp.c_fc.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.27.mlp.c_fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.27.mlp.c_fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.27.mlp.c_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.27.mlp.c_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.28.attn.c_attn.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.28.attn.c_attn.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.28.attn.c_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.28.attn.c_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.28.ln_1.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.28.ln_1.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.28.ln_2.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.28.ln_2.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.28.mlp.c_fc.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.28.mlp.c_fc.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.28.mlp.c_fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.28.mlp.c_fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.28.mlp.c_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.28.mlp.c_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.29.attn.c_attn.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.29.attn.c_attn.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.29.attn.c_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.29.attn.c_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.29.ln_1.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.29.ln_1.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.29.ln_2.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.29.ln_2.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.29.mlp.c_fc.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.29.mlp.c_fc.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.29.mlp.c_fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.29.mlp.c_fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.29.mlp.c_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.29.mlp.c_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.3.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.3.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.3.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.3.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.3.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.3.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.3.ln_2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.3.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.3.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.3.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.3.mlp.c_fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.3.mlp.c_fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.3.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.3.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.30.attn.c_attn.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.30.attn.c_attn.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.30.attn.c_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.30.attn.c_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.30.ln_1.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.30.ln_1.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.30.ln_2.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.30.ln_2.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.30.mlp.c_fc.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.30.mlp.c_fc.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.30.mlp.c_fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.30.mlp.c_fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.30.mlp.c_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.30.mlp.c_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.31.attn.c_attn.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.31.attn.c_attn.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.31.attn.c_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.31.attn.c_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.31.ln_1.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.31.ln_1.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.31.ln_2.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.31.ln_2.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.31.mlp.c_fc.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.31.mlp.c_fc.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.31.mlp.c_fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.31.mlp.c_fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.31.mlp.c_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.31.mlp.c_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.4.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.4.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.4.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.4.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.4.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.4.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.4.ln_2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.4.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.4.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.4.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.4.mlp.c_fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.4.mlp.c_fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.4.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.4.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.5.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.5.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.5.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.5.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.5.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.5.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.5.ln_2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.5.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.5.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.5.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.5.mlp.c_fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.5.mlp.c_fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.5.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.5.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.6.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.6.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.6.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.6.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.6.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.6.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.6.ln_2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.6.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.6.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.6.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.6.mlp.c_fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.6.mlp.c_fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.6.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.6.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.7.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.7.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.7.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.7.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.7.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.7.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.7.ln_2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.7.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.7.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.7.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.7.mlp.c_fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.7.mlp.c_fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.7.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.7.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.8.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.8.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.8.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.8.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.8.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.8.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.8.ln_2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.8.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.8.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.8.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.8.mlp.c_fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.8.mlp.c_fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.8.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.8.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.9.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.9.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.9.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.9.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.9.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.9.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.9.ln_2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.9.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.9.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.9.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.9.mlp.c_fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.9.mlp.c_fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.9.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.9.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.ln_f.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.ln_f.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.wte.weight": "pytorch_model-00001-of-00002.bin"
+  }
+}

special_tokens_map.json

@@ -1,5 +1,8 @@
 {
   "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>",
     "<|fim_prefix|>",
     "<|fim_middle|>",
     "<|fim_suffix|>",
@@ -23,25 +26,7 @@
     "<|sys_start|>",
     "<|sys_end|>"
   ],
-  "bos_token": {
-    "content": "<s>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "eos_token": {
-    "content": "</s>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "unk_token": {
-    "content": "<unk>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  }
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "unk_token": "<unk>"
 }

tokenizer_config.json

@@ -202,6 +202,9 @@
     }
   },
   "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>",
     "<|fim_prefix|>",
     "<|fim_middle|>",
     "<|fim_suffix|>",
@@ -228,7 +231,7 @@
   "auto_map": {
     "AutoTokenizer": [
       null,
-      "tokenization_crystalcoder_fast.CrystalCoderTokenizerFast"
+      "LLM360/CrystalChat--tokenization_crystalcoder_fast.CrystalCoderTokenizerFast"
     ]
   },
   "bos_token": "<s>",