Upload folder using huggingface_hub

config.json

@@ -1,37 +1,34 @@
 {
-  "_name_or_path": "keyfan/grok-1-hf",
+  "_name_or_path": "hpcai-tech/grok-1",
   "architectures": [
-    "GrokForCausalLM"
+    "Grok1ModelForCausalLM"
   ],
-  "attention_dropout": 0.0,
   "attn_output_multiplier": 0.08838834764831845,
   "auto_map": {
-    "AutoConfig": "keyfan/grok-1-hf--configuration_grok.GrokConfig",
-    "AutoModelForCausalLM": "keyfan/grok-1-hf--modeling_grok.GrokForCausalLM"
+    "AutoConfig": "hpcai-tech/grok-1--configuration_grok1.Grok1Config",
+    "AutoModel": "hpcai-tech/grok-1--modeling_grok1.Grok1Model",
+    "AutoModelForCausalLM": "hpcai-tech/grok-1--modeling_grok1.Grok1ModelForCausalLM"
   },
   "bos_token_id": 1,
   "embedding_multiplier_scale": 78.38367176906169,
   "eos_token_id": 2,
-  "hidden_act": "gelu_new",
   "hidden_size": 4,
-  "initializer_range": 0.02,
   "intermediate_size": 8,
+  "max_attn_value": 30.0,
   "max_position_embeddings": 8192,
-  "model_type": "grok",
-  "num_attention_heads": 4,
+  "model_type": "grok-1",
+  "num_attention_heads": 2,
+  "num_experts": 8,
   "num_experts_per_tok": 2,
   "num_hidden_layers": 2,
-  "num_key_value_heads": 2,
-  "num_local_experts": 8,
+  "num_key_value_heads": 1,
   "output_multiplier_scale": 0.5773502691896257,
   "output_router_logits": false,
   "pad_token_id": 0,
   "rms_norm_eps": 1e-05,
-  "rope_theta": 10000.0,
-  "router_aux_loss_coef": 0.02,
-  "sliding_window": null,
+  "router_aux_loss_coef": 0.001,
   "torch_dtype": "float16",
-  "transformers_version": "4.38.1",
+  "transformers_version": "4.39.2",
   "use_cache": true,
   "vocab_size": 131072
 }

generation_config.json

@@ -3,5 +3,5 @@
   "bos_token_id": 1,
   "eos_token_id": 2,
   "pad_token_id": 0,
-  "transformers_version": "4.38.1"
+  "transformers_version": "4.39.2"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:446c87c0d9bbd043a587abcf8cc916d2f9c88af13c9e75382ef4e919624ec4e9
-size 1059424
+oid sha256:1ca9c4544a031f317c5270637af645c713a878ac4cdf36bdc6ae9ac15c61d61f
+size 1059568

special_tokens_map.json

@@ -1,20 +1,27 @@
 {
   "bos_token": {
-    "content": "<s>",
+    "content": "[BOS]",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
   "eos_token": {
-    "content": "</s>",
+    "content": "[EOS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
   "unk_token": {
-    "content": "<unk>",
+    "content": "[UNK]",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,

tokenizer.json

@@ -5,7 +5,7 @@
   "added_tokens": [
     {
       "id": 0,
-      "content": "<unk>",
+      "content": "[PAD]",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
@@ -14,7 +14,7 @@
     },
     {
       "id": 1,
-      "content": "<s>",
+      "content": "[BOS]",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
@@ -23,7 +23,16 @@
     },
     {
       "id": 2,
-      "content": "</s>",
+      "content": "[EOS]",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 3,
+      "content": "[UNK]",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
@@ -107,9 +116,9 @@
     "fuse_unk": true,
     "byte_fallback": true,
     "vocab": {
-      "<unk>": 0,
-      "<s>": 1,
-      "</s>": 2,
+      "[PAD]": 0,
+      "[BOS]": 1,
+      "[EOS]": 2,
       "[UNK]": 3,
       "\n": 4,
       "\n\n": 5,
@@ -131254,97 +131263,6 @@
       "\t\t\t\t\t \t\t\t",
       "\t\t\t\t\t\t \t\t",
       "\t\t\t\t\t\t\t \t",
-      "     ",
-      "      ",
-      "      ",
-      "       ",
-      "       ",
-      "       ",
-      "        ",
-      "        ",
-      "        ",
-      "        ",
-      "         ",
-      "         ",
-      "         ",
-      "         ",
-      "         ",
-      "          ",
-      "          ",
-      "          ",
-      "          ",
-      "          ",
-      "          ",
-      "           ",
-      "           ",
-      "           ",
-      "           ",
-      "           ",
-      "           ",
-      "           ",
-      "            ",
-      "            ",
-      "            ",
-      "            ",
-      "            ",
-      "            ",
-      "            ",
-      "            ",
-      "             ",
-      "             ",
-      "             ",
-      "             ",
-      "             ",
-      "             ",
-      "             ",
-      "             ",
-      "             ",
-      "              ",
-      "              ",
-      "              ",
-      "              ",
-      "              ",
-      "              ",
-      "              ",
-      "              ",
-      "              ",
-      "              ",
-      "               ",
-      "               ",
-      "               ",
-      "               ",
-      "               ",
-      "               ",
-      "               ",
-      "               ",
-      "               ",
-      "               ",
-      "               ",
-      "                ",
-      "                ",
-      "                ",
-      "                ",
-      "                ",
-      "                ",
-      "                ",
-      "                ",
-      "                ",
-      "                ",
-      "                ",
-      "                ",
-      "                 ",
-      "                 ",
-      "                 ",
-      "                 ",
-      "                 ",
-      "                 ",
-      "                 ",
-      "                 ",
-      "                 ",
-      "                 ",
-      "                 ",
-      "                 ",
-      "                 ",
       "▁ ▁",
       "▁ t",
       "▁ a",

tokenizer_config.json

@@ -1,10 +1,9 @@
 {
   "add_bos_token": false,
   "add_eos_token": false,
-  "add_prefix_space": true,
   "added_tokens_decoder": {
     "0": {
-      "content": "<unk>",
+      "content": "[PAD]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -12,7 +11,7 @@
       "special": true
     },
     "1": {
-      "content": "<s>",
+      "content": "[BOS]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -20,7 +19,15 @@
       "special": true
     },
     "2": {
-      "content": "</s>",
+      "content": "[EOS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[UNK]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -28,16 +35,13 @@
       "special": true
     }
   },
-  "additional_special_tokens": [],
-  "bos_token": "<s>",
+  "bos_token": "[BOS]",
   "clean_up_tokenization_spaces": false,
-  "eos_token": "</s>",
-  "legacy": true,
-  "model_max_length": 1000000000000000019884624838656,
-  "pad_token": null,
+  "eos_token": "[EOS]",
+  "model_max_length": 8192,
+  "pad_token": "[PAD]",
   "sp_model_kwargs": {},
-  "spaces_between_special_tokens": false,
   "tokenizer_class": "LlamaTokenizer",
-  "unk_token": "<unk>",
+  "unk_token": "[UNK]",
   "use_default_system_prompt": false
 }