Upload folder using huggingface_hub

README.md

@@ -1,3 +1,12 @@
----
-license: apache-2.0
----
+---
+language: en
+license: apache-2.0
+tags:
+- transformer
+- pytorch
+- causal-lm
+---
+
+# RLLM (Base Model)
+
+This is a base model.

config.json

@@ -0,0 +1,32 @@
+{
+  "architectures": [
+    "RishCoreForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 50256,
+  "dtype": "float32",
+  "eos_token_id": 50256,
+  "hidden_act": "silu",
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 384,
+  "max_position_embeddings": 1024,
+  "model_type": "rish_ai",
+  "norm_topk_prob": false,
+  "num_attention_heads": 12,
+  "num_experts": 16,
+  "num_experts_per_tok": 2,
+  "num_hidden_layers": 12,
+  "num_key_value_heads": 12,
+  "output_router_logits": false,
+  "pad_token_id": 50256,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 500000,
+  "router_aux_loss_coef": 0.01,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.57.3",
+  "use_cache": true,
+  "vocab_size": 50257
+}

generation_config.json

@@ -0,0 +1,10 @@
+{
+  "_from_model_config": true,
+  "do_sample": true,
+  "eos_token_id": [
+    50256,
+    50256
+  ],
+  "pad_token": 50256,
+  "transformers_version": "4.57.3"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0fd03abcfdf7c60712e3d687748ce09ed8d0d088653058c36057a3f50b65d8ee
+size 1102323808

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,21 @@
+{
+  "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": false,
+  "eos_token": "<|endoftext|>",
+  "extra_special_tokens": {},
+  "model_max_length": 1024,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}