Upload folder using huggingface_hub

config.json

@@ -1,33 +1,38 @@
 {
-    "attn_pdrop": 0.0,
-    "scale_attn_weights": true,
-    "resid_pdrop": 0.0,
-    "mup_embeddings_scale": 14.6,
-    "n_inner": 10922,
-    "n_embd": 4096,
-    "layer_norm_epsilon": 1e-05,
-    "n_positions": 2048,
-    "activation_function": "swiglu",
-    "n_head": 32,
-    "n_layer": 32,
-    "mup_output_alpha": 2.22,
-    "mup_width_scale": 0.0625,
-    "position_embedding_type": "rotary",
-    "rotary_dim": 32,
-    "mup_scale_qk_dot_by_d": true,
-    "tie_word_embeddings": true,
-    "vocab_size": 32032,
-    "embd_pdrop": 0.0,
-    "model_type": "crystalcoder",
-    "use_cache": true,
-    "bos_token_id": 1,
-    "eos_token_id": 2,
-    "auto_map": {
-        "AutoConfig": "configuration_crystalcoder.CrystalCoderConfig",
-        "AutoModel": "modeling_crystalcoder.CrystalCoderModel",
-        "AutoModelForCausalLM": "modeling_crystalcoder.CrystalCoderLMHeadModel"
-    },
-    "architectures": [
-        "CrystalCoderLMHeadModel"
-    ]
-}
+  "_name_or_path": "LLM360/CrystalCoder",
+  "activation_function": "swiglu",
+  "architectures": [
+    "CrystalCoderLMHeadModel"
+  ],
+  "attn_pdrop": 0.0,
+  "auto_map": {
+    "AutoConfig": "LLM360/CrystalCoder--configuration_crystalcoder.CrystalCoderConfig",
+    "AutoModel": "LLM360/CrystalCoder--modeling_crystalcoder.CrystalCoderModel",
+    "AutoModelForCausalLM": "LLM360/CrystalCoder--modeling_crystalcoder.CrystalCoderLMHeadModel"
+  },
+  "bos_token_id": 1,
+  "embd_pdrop": 0.0,
+  "eos_token_id": 2,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "crystalcoder",
+  "mup_embeddings_scale": 14.6,
+  "mup_output_alpha": 2.22,
+  "mup_scale_qk_dot_by_d": true,
+  "mup_width_scale": 0.0625,
+  "n_embd": 4096,
+  "n_head": 32,
+  "n_inner": 10922,
+  "n_layer": 32,
+  "n_positions": 2048,
+  "position_embedding_type": "rotary",
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.0,
+  "rotary_dim": 32,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.35.2",
+  "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": "4.33.0.dev0"
+  "transformers_version": "4.35.2"
 }

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e5c6dc69f4715ab32c5990c8700f96a1f304b6d3102fdb4954d90d4ec80a3eb
+size 4916498172

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31921aef135ba5f555d6543c280315ebf47073aa1e9abfaab4a43e075221270a
+size 4922563684

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02f6a402eb41a0073b6dd46caa4e8603efc0c51c8e40e8d54593802cd470bc3e
+size 3311543728

model.safetensors.index.json

@@ -0,0 +1,458 @@
+{
+  "metadata": {
+    "total_size": 13150557440
+  },
+  "weight_map": {
+    "transformer.h.0.attn.c_attn.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.0.attn.c_attn.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.0.attn.c_proj.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.0.attn.c_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.ln_2.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.0.ln_2.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.0.mlp.c_fc.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.0.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.0.mlp.c_fc2.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.0.mlp.c_fc2.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.0.mlp.c_proj.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.0.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.1.attn.c_attn.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.1.attn.c_attn.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.1.attn.c_proj.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.1.attn.c_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.ln_2.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.1.ln_2.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.1.mlp.c_fc.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.1.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.1.mlp.c_fc2.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.1.mlp.c_fc2.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.1.mlp.c_proj.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.1.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.10.attn.c_attn.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.10.attn.c_attn.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.10.attn.c_proj.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.10.attn.c_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.ln_2.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.10.ln_2.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.10.mlp.c_fc.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.10.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.10.mlp.c_fc2.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.10.mlp.c_fc2.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.10.mlp.c_proj.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.10.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.11.attn.c_attn.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.11.attn.c_attn.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.11.attn.c_proj.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.11.attn.c_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.ln_2.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.11.ln_2.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.11.mlp.c_fc.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.11.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.11.mlp.c_fc2.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.11.mlp.c_fc2.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.11.mlp.c_proj.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.11.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.12.attn.c_attn.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.12.attn.c_attn.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.12.attn.c_proj.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.12.attn.c_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.12.ln_1.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.12.ln_1.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.12.ln_2.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.12.ln_2.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.12.mlp.c_fc.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.12.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.12.mlp.c_fc2.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.12.mlp.c_fc2.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.12.mlp.c_proj.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.12.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.13.attn.c_attn.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.13.attn.c_attn.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.13.attn.c_proj.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.13.attn.c_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.13.ln_1.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.13.ln_1.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.13.ln_2.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.13.ln_2.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.13.mlp.c_fc.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.13.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.13.mlp.c_fc2.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.13.mlp.c_fc2.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.13.mlp.c_proj.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.13.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.14.attn.c_attn.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.14.attn.c_attn.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.14.attn.c_proj.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.14.attn.c_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.14.ln_1.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.14.ln_1.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.14.ln_2.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.14.ln_2.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.14.mlp.c_fc.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.14.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.14.mlp.c_fc2.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.14.mlp.c_fc2.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.14.mlp.c_proj.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.14.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.15.attn.c_attn.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.15.attn.c_attn.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.15.attn.c_proj.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.15.attn.c_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.ln_2.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.15.ln_2.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.15.mlp.c_fc.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.15.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.15.mlp.c_fc2.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.15.mlp.c_fc2.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.15.mlp.c_proj.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.15.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.16.attn.c_attn.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.16.attn.c_attn.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.16.attn.c_proj.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.16.attn.c_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.ln_2.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.16.ln_2.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.16.mlp.c_fc.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.16.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.16.mlp.c_fc2.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.16.mlp.c_fc2.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.16.mlp.c_proj.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.16.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.17.attn.c_attn.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.17.attn.c_attn.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.17.attn.c_proj.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.17.attn.c_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.ln_2.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.17.ln_2.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.17.mlp.c_fc.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.17.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.17.mlp.c_fc2.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.17.mlp.c_fc2.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.17.mlp.c_proj.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.17.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.18.attn.c_attn.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.18.attn.c_attn.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.18.attn.c_proj.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.18.attn.c_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.ln_2.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.18.ln_2.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.18.mlp.c_fc.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.18.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.18.mlp.c_fc2.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.18.mlp.c_fc2.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.18.mlp.c_proj.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.18.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.19.attn.c_attn.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.19.attn.c_attn.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.19.attn.c_proj.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.19.attn.c_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.ln_2.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.19.ln_2.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.19.mlp.c_fc.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.19.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.19.mlp.c_fc2.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.19.mlp.c_fc2.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.19.mlp.c_proj.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.19.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.2.attn.c_attn.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.2.attn.c_attn.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.2.attn.c_proj.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.2.attn.c_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.ln_2.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.2.ln_2.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.2.mlp.c_fc.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.2.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.2.mlp.c_fc2.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.2.mlp.c_fc2.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.2.mlp.c_proj.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.2.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.20.attn.c_attn.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.20.attn.c_attn.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.20.attn.c_proj.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.20.attn.c_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.ln_2.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.20.ln_2.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.20.mlp.c_fc.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.20.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.20.mlp.c_fc2.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.20.mlp.c_fc2.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.20.mlp.c_proj.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.20.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.21.attn.c_attn.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.21.attn.c_attn.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.21.attn.c_proj.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.21.attn.c_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.ln_2.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.21.ln_2.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.21.mlp.c_fc.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.21.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.21.mlp.c_fc2.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.21.mlp.c_fc2.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.21.mlp.c_proj.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.21.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.22.attn.c_attn.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.22.attn.c_attn.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.22.attn.c_proj.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.22.attn.c_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.ln_2.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.22.ln_2.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.22.mlp.c_fc.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.22.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.22.mlp.c_fc2.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.22.mlp.c_fc2.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.22.mlp.c_proj.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.22.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.23.attn.c_attn.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.23.attn.c_attn.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.23.attn.c_proj.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.23.attn.c_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.ln_2.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.23.ln_2.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.23.mlp.c_fc.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.23.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.23.mlp.c_fc2.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.23.mlp.c_fc2.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.23.mlp.c_proj.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.23.mlp.c_proj.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.24.attn.c_attn.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.24.attn.c_attn.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.24.attn.c_proj.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.24.attn.c_proj.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.24.ln_1.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.24.ln_1.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.24.ln_2.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.24.ln_2.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.24.mlp.c_fc.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.24.mlp.c_fc.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.24.mlp.c_fc2.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.24.mlp.c_fc2.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.24.mlp.c_proj.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.24.mlp.c_proj.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.25.attn.c_attn.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.25.attn.c_attn.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.25.attn.c_proj.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.25.attn.c_proj.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.25.ln_1.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.25.ln_1.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.25.ln_2.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.25.ln_2.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.25.mlp.c_fc.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.25.mlp.c_fc.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.25.mlp.c_fc2.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.25.mlp.c_fc2.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.25.mlp.c_proj.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.25.mlp.c_proj.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.26.attn.c_attn.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.26.attn.c_attn.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.26.attn.c_proj.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.26.attn.c_proj.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.26.ln_1.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.26.ln_1.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.26.ln_2.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.26.ln_2.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.26.mlp.c_fc.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.26.mlp.c_fc.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.26.mlp.c_fc2.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.26.mlp.c_fc2.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.26.mlp.c_proj.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.26.mlp.c_proj.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.27.attn.c_attn.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.27.attn.c_attn.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.27.attn.c_proj.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.27.attn.c_proj.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.27.ln_1.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.27.ln_1.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.27.ln_2.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.27.ln_2.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.27.mlp.c_fc.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.27.mlp.c_fc.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.27.mlp.c_fc2.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.27.mlp.c_fc2.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.27.mlp.c_proj.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.27.mlp.c_proj.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.28.attn.c_attn.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.28.attn.c_attn.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.28.attn.c_proj.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.28.attn.c_proj.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.28.ln_1.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.28.ln_1.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.28.ln_2.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.28.ln_2.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.28.mlp.c_fc.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.28.mlp.c_fc.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.28.mlp.c_fc2.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.28.mlp.c_fc2.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.28.mlp.c_proj.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.28.mlp.c_proj.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.29.attn.c_attn.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.29.attn.c_attn.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.29.attn.c_proj.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.29.attn.c_proj.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.29.ln_1.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.29.ln_1.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.29.ln_2.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.29.ln_2.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.29.mlp.c_fc.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.29.mlp.c_fc.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.29.mlp.c_fc2.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.29.mlp.c_fc2.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.29.mlp.c_proj.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.29.mlp.c_proj.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.3.attn.c_attn.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.3.attn.c_attn.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.3.attn.c_proj.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.3.attn.c_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.ln_2.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.3.ln_2.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.3.mlp.c_fc.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.3.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.3.mlp.c_fc2.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.3.mlp.c_fc2.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.3.mlp.c_proj.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.3.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.30.attn.c_attn.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.30.attn.c_attn.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.30.attn.c_proj.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.30.attn.c_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.ln_2.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.30.ln_2.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.30.mlp.c_fc.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.30.mlp.c_fc.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.30.mlp.c_fc2.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.30.mlp.c_fc2.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.30.mlp.c_proj.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.30.mlp.c_proj.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.31.attn.c_attn.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.31.attn.c_attn.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.31.attn.c_proj.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.31.attn.c_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.ln_2.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.31.ln_2.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.31.mlp.c_fc.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.31.mlp.c_fc.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.31.mlp.c_fc2.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.31.mlp.c_fc2.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.31.mlp.c_proj.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.31.mlp.c_proj.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.4.attn.c_attn.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.4.attn.c_attn.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.4.attn.c_proj.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.4.attn.c_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.ln_2.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.4.ln_2.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.4.mlp.c_fc.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.4.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.4.mlp.c_fc2.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.4.mlp.c_fc2.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.4.mlp.c_proj.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.4.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.5.attn.c_attn.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.5.attn.c_attn.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.5.attn.c_proj.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.5.attn.c_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.ln_2.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.5.ln_2.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.5.mlp.c_fc.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.5.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.5.mlp.c_fc2.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.5.mlp.c_fc2.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.5.mlp.c_proj.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.5.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.6.attn.c_attn.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.6.attn.c_attn.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.6.attn.c_proj.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.6.attn.c_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.ln_2.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.6.ln_2.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.6.mlp.c_fc.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.6.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.6.mlp.c_fc2.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.6.mlp.c_fc2.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.6.mlp.c_proj.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.6.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.7.attn.c_attn.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.7.attn.c_attn.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.7.attn.c_proj.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.7.attn.c_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.ln_2.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.7.ln_2.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.7.mlp.c_fc.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.7.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.7.mlp.c_fc2.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.7.mlp.c_fc2.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.7.mlp.c_proj.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.7.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.8.attn.c_attn.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.8.attn.c_attn.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.8.attn.c_proj.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.8.attn.c_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.ln_2.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.8.ln_2.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.8.mlp.c_fc.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.8.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.8.mlp.c_fc2.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.8.mlp.c_fc2.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.8.mlp.c_proj.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.8.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.9.attn.c_attn.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.9.attn.c_attn.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.9.attn.c_proj.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.9.attn.c_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.ln_2.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.9.ln_2.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.9.mlp.c_fc.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.9.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.9.mlp.c_fc2.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.9.mlp.c_fc2.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.9.mlp.c_proj.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.9.mlp.c_proj.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"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,47 @@
+{
+  "additional_special_tokens": [
+    "<|fim_prefix|>",
+    "<|fim_middle|>",
+    "<|fim_suffix|>",
+    "<|fim_pad|>",
+    "<|filename|>",
+    "<|gh_stars|>",
+    "<|issue_start|>",
+    "<|issue_comment|>",
+    "<|issue_closed|>",
+    "<|jupyter_start|>",
+    "<|jupyter_text|>",
+    "<|jupyter_code|>",
+    "<|jupyter_output|>",
+    "<|empty_output|>",
+    "<|commit_before|>",
+    "<|commit_msg|>",
+    "<|commit_after|>",
+    "<|reponame|>",
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|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
+  }
+}

tokenizer_config.json

@@ -225,6 +225,12 @@
     "<|sys_start|>",
     "<|sys_end|>"
   ],
+  "auto_map": {
+    "AutoTokenizer": [
+      null,
+      "LLM360/CrystalCoder--tokenization_crystalcoder_fast.CrystalCoderTokenizerFast"
+    ]
+  },
   "bos_token": "<s>",
   "clean_up_tokenization_spaces": false,
   "eos_token": "</s>",
@@ -233,12 +239,6 @@
   "pad_token": null,
   "padding_side": "right",
   "sp_model_kwargs": {},
-  "auto_map": {
-    "AutoTokenizer": [
-      null,
-      "tokenization_crystalcoder_fast.CrystalCoderTokenizerFast"
-    ]
-  },
   "tokenizer_class": "CrystalCoderTokenizer",
   "unk_token": "<unk>",
   "use_default_system_prompt": false