Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "hpcai-tech/grok-1",
+  "architectures": [
+    "Grok1ModelForCausalLM"
+  ],
+  "attn_output_multiplier": 0.08838834764831845,
+  "auto_map": {
+    "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_size": 4,
+  "intermediate_size": 8,
+  "max_attn_value": 30.0,
+  "max_position_embeddings": 8192,
+  "model_type": "grok-1",
+  "num_attention_heads": 2,
+  "num_experts": 8,
+  "num_experts_per_tok": 2,
+  "num_hidden_layers": 2,
+  "num_key_value_heads": 1,
+  "output_multiplier_scale": 0.5773502691896257,
+  "output_router_logits": false,
+  "pad_token_id": 0,
+  "rms_norm_eps": 1e-05,
+  "router_aux_loss_coef": 0.001,
+  "torch_dtype": "float16",
+  "transformers_version": "4.48.3",
+  "use_cache": true,
+  "vocab_size": 131072
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 0,
+  "transformers_version": "4.48.3"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ca9c4544a031f317c5270637af645c713a878ac4cdf36bdc6ae9ac15c61d61f
+size 1059568

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "[BOS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "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]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b67c4107f6650e0590aa4d5e88d8b2c22a86fda97242b9e5242521b3ab82e7fc
+size 18072898

tokenizer_config.json

@@ -0,0 +1,50 @@
+{
+  "add_bos_token": false,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[BOS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[EOS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "[BOS]",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "[EOS]",
+  "extra_special_tokens": {},
+  "legacy": true,
+  "model_max_length": 8192,
+  "pad_token": "[PAD]",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "[UNK]",
+  "use_default_system_prompt": false
+}