Upload 340M/routpath_routfox_topk8_constant consolidated checkpoint

340M/routpath_routfox_topk8_constant/config.json

@@ -0,0 +1,48 @@
+{
+  "add_gumbel_noise": true,
+  "architectures": [
+    "PaTHAttentionForCausalLM"
+  ],
+  "bos_token_id": 1,
+  "elementwise_affine": true,
+  "eos_token_id": 2,
+  "fuse_cross_entropy": true,
+  "fuse_linear_cross_entropy": false,
+  "fuse_norm": true,
+  "fuse_swiglu": true,
+  "gate_logit_normalizer": 1.0,
+  "gumbel_decay_steps": null,
+  "gumbel_hold_step_ratio": 0.1,
+  "gumbel_hold_steps": null,
+  "gumbel_scale": 1.0,
+  "gumbel_schedule": "constant",
+  "gumbel_zero_step_ratio": 0.5,
+  "hidden_act": "swish",
+  "hidden_ratio": 4,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": null,
+  "log_router_stats": true,
+  "model_type": "path_attn",
+  "norm_eps": 1e-06,
+  "num_heads": 16,
+  "num_hidden_layers": 22,
+  "num_kv_heads": 16,
+  "qk_norm": false,
+  "qkv_bias": false,
+  "router_bias": false,
+  "router_score": "sigmoid",
+  "router_topk": 8,
+  "router_type": "lin",
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.55.4",
+  "use_beta_router": true,
+  "use_cache": true,
+  "use_forget_gate": true,
+  "use_head_router": true,
+  "use_l2warp": false,
+  "use_low_rank_w": true,
+  "use_w_shortconv": true,
+  "vocab_size": 32000
+}

340M/routpath_routfox_topk8_constant/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.55.4"
+}

340M/routpath_routfox_topk8_constant/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1716d43d0dedbc85bc0fe499f903262723dc267bf84322fcaae3a3f04f73513f
+size 1403099784

340M/routpath_routfox_topk8_constant/special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "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
+  }
+}

340M/routpath_routfox_topk8_constant/tokenizer_config.json

@@ -0,0 +1,44 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}