Add files using upload-large-folder tool

.gitattributes

@@ -33,3 +33,19 @@ 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
+delta_net-1.3B-100B/based_fda/[[:space:]]checkpoint_name____mnt__jfzn__msj__delta_net-1.3B-100B_based_fda.jsonl filter=lfs diff=lfs merge=lfs -text
+delta_net-1.3B-100B/based_fda/[[:space:]]checkpoint_name____mnt__jfzn__msj__download_model__delta_net-1.3B-100B_based_fda.jsonl filter=lfs diff=lfs merge=lfs -text
+delta_net-1.3B-100B/based_nq_2048/[[:space:]]checkpoint_name____mnt__jfzn__msj__delta_net-1.3B-100B_based_nq_2048.jsonl filter=lfs diff=lfs merge=lfs -text
+delta_net-1.3B-100B/based_nq_2048/[[:space:]]checkpoint_name____mnt__jfzn__msj__download_model__delta_net-1.3B-100B_based_nq_2048.jsonl filter=lfs diff=lfs merge=lfs -text
+delta_net-1.3B-100B/based_squad/[[:space:]]checkpoint_name____mnt__jfzn__msj__delta_net-1.3B-100B_based_squad.jsonl filter=lfs diff=lfs merge=lfs -text
+delta_net-1.3B-100B/based_squad/[[:space:]]checkpoint_name____mnt__jfzn__msj__download_model__delta_net-1.3B-100B_based_squad.jsonl filter=lfs diff=lfs merge=lfs -text
+gla-1.3B-100B/based_fda/[[:space:]]checkpoint_name____mnt__jfzn__msj__download_model__gla-1.3B-100B_based_fda.jsonl filter=lfs diff=lfs merge=lfs -text
+gla-1.3B-100B/based_fda/[[:space:]]checkpoint_name____mnt__jfzn__msj__gla-1.3B-100B_based_fda.jsonl filter=lfs diff=lfs merge=lfs -text
+gla-1.3B-100B/based_nq_2048/[[:space:]]checkpoint_name____mnt__jfzn__msj__download_model__gla-1.3B-100B_based_nq_2048.jsonl filter=lfs diff=lfs merge=lfs -text
+gla-1.3B-100B/based_nq_2048/[[:space:]]checkpoint_name____mnt__jfzn__msj__gla-1.3B-100B_based_nq_2048.jsonl filter=lfs diff=lfs merge=lfs -text
+gla-1.3B-100B/based_squad/[[:space:]]checkpoint_name____mnt__jfzn__msj__download_model__gla-1.3B-100B_based_squad.jsonl filter=lfs diff=lfs merge=lfs -text
+gla-1.3B-100B/based_squad/[[:space:]]checkpoint_name____mnt__jfzn__msj__gla-1.3B-100B_based_squad.jsonl filter=lfs diff=lfs merge=lfs -text
+hgrn2-1.3B-100B/based_fda/[[:space:]]checkpoint_name____mnt__jfzn__msj__download_model__hgrn2-1.3B-100B_based_fda.jsonl filter=lfs diff=lfs merge=lfs -text
+hgrn2-1.3B-100B/based_nq_2048/[[:space:]]checkpoint_name____mnt__jfzn__msj__download_model__hgrn2-1.3B-100B_based_nq_2048.jsonl filter=lfs diff=lfs merge=lfs -text
+hgrn2-1.3B-100B/based_squad/[[:space:]]checkpoint_name____mnt__jfzn__msj__download_model__hgrn2-1.3B-100B_based_squad.jsonl filter=lfs diff=lfs merge=lfs -text
+retnet-1.3B-100B/based_fda/[[:space:]]checkpoint_name____mnt__jfzn__msj__download_model__retnet-1.3B-100B_based_fda.jsonl filter=lfs diff=lfs merge=lfs -text

delta_net-1.3B-100B/.hfd/last_download_command

@@ -0,0 +1 @@
+REPO_ID=fla-hub/delta_net-1.3B-100B TOOL=aria2c INCLUDE_PATTERNS= EXCLUDE_PATTERNS= DATASET=0 HF_USERNAME= HF_TOKEN= HF_TOKEN=https://huggingface.co REVISION=main

delta_net-1.3B-100B/.hfd/repo_metadata.json

@@ -0,0 +1 @@
+{"_id":"6746ac966e604a92959d3cad","id":"fla-hub/delta_net-1.3B-100B","private":false,"pipeline_tag":"text-generation","library_name":"transformers","tags":["transformers","safetensors","delta_net","text-generation","arxiv:1910.09700","autotrain_compatible","endpoints_compatible","region:us"],"downloads":171,"likes":0,"modelId":"fla-hub/delta_net-1.3B-100B","author":"fla-hub","sha":"b4dcbbafd4fde802717bdec3008d4aba9cb3a1f8","lastModified":"2025-02-09T16:57:54.000Z","gated":false,"disabled":false,"widgetData":[{"text":"My name is Julien and I like to"},{"text":"I like traveling by train because"},{"text":"Paris is an amazing place to visit,"},{"text":"Once upon a time,"}],"model-index":null,"config":{"architectures":["DeltaNetForCausalLM"],"model_type":"delta_net","tokenizer_config":{"bos_token":"<s>","eos_token":"</s>","pad_token":"</s>","unk_token":"<unk>","use_default_system_prompt":false}},"cardData":{"library_name":"transformers","tags":[]},"transformersInfo":{"auto_model":"AutoModelForCausalLM","pipeline_tag":"text-generation"},"siblings":[{"rfilename":".gitattributes"},{"rfilename":"README.md"},{"rfilename":"config.json"},{"rfilename":"generation_config.json"},{"rfilename":"model.safetensors"},{"rfilename":"special_tokens_map.json"},{"rfilename":"tokenizer.json"},{"rfilename":"tokenizer.model"},{"rfilename":"tokenizer_config.json"}],"spaces":[],"createdAt":"2024-11-27T05:22:30.000Z","safetensors":{"parameters":{"BF16":1365677056},"total":1365677056},"usedStorage":5463274107}

delta_net-1.3B-100B/based_drop/results.json

@@ -0,0 +1,51 @@
+{
+  "results": {
+    "based_drop": {
+      "contains,none": 0.2103497843794921,
+      "contains_stderr,none": "N/A",
+      "alias": "based_drop"
+    }
+  },
+  "configs": {
+    "based_drop": {
+      "description": "",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "num_fewshot": 0,
+      "output_type": "generate_until",
+      "generation_kwargs": {
+        "until": [
+          "\n\n"
+        ],
+        "do_sample": false
+      },
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": "default"
+      }
+    }
+  },
+  "versions": {
+    "based_drop": "default"
+  },
+  "n-shot": {
+    "based_drop": 0
+  },
+  "config": {
+    "model": "lm_eval_model",
+    "model_args": " checkpoint_name=/mnt/jfzn/msj/download_model/delta_net-1.3B-100B",
+    "batch_size": "8",
+    "batch_sizes": [],
+    "device": "cuda:0",
+    "use_cache": null,
+    "limit": null,
+    "bootstrap_iters": 100000,
+    "gen_kwargs": null
+  },
+  "git_hash": null,
+  "context_length": 2000,
+  "answer_length": 48,
+  "cutting_context": true,
+  "decode_mode": "default"
+}

delta_net-1.3B-100B/based_fda/ checkpoint_name____mnt__jfzn__msj__delta_net-1.3B-100B_based_fda.jsonl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1ea6d2a565d3cffe65ec49c5c2e4df4e7d0c7e786aa1e7bf2b8000ee85b7620
+size 14490105

delta_net-1.3B-100B/based_fda/ checkpoint_name____mnt__jfzn__msj__download_model__delta_net-1.3B-100B_based_fda.jsonl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21736891ba901ee13665d654ec200bddaf68ceb549143319ef2768b4988f0945
+size 14196557

delta_net-1.3B-100B/based_fda/results.json

@@ -0,0 +1,51 @@
+{
+  "results": {
+    "based_fda": {
+      "contains,none": 0.4250681198910082,
+      "contains_stderr,none": "N/A",
+      "alias": "based_fda"
+    }
+  },
+  "configs": {
+    "based_fda": {
+      "description": "",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "num_fewshot": 0,
+      "output_type": "generate_until",
+      "generation_kwargs": {
+        "until": [
+          "\n\n"
+        ],
+        "do_sample": false
+      },
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 0
+      }
+    }
+  },
+  "versions": {
+    "based_fda": 0
+  },
+  "n-shot": {
+    "based_fda": 0
+  },
+  "config": {
+    "model": "lm_eval_model",
+    "model_args": " checkpoint_name=/mnt/jfzn/msj/download_model/delta_net-1.3B-100B",
+    "batch_size": "8",
+    "batch_sizes": [],
+    "device": "cuda:0",
+    "use_cache": null,
+    "limit": null,
+    "bootstrap_iters": 100000,
+    "gen_kwargs": null
+  },
+  "git_hash": null,
+  "context_length": 2000,
+  "answer_length": 48,
+  "cutting_context": true,
+  "decode_mode": "default"
+}

delta_net-1.3B-100B/based_nq_2048/ checkpoint_name____mnt__jfzn__msj__delta_net-1.3B-100B_based_nq_2048.jsonl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2aa46583998ffa92fe9e454db0da7a3f4a22437e83e0959da3861aa95e1f80e
+size 41955055

delta_net-1.3B-100B/based_nq_2048/ checkpoint_name____mnt__jfzn__msj__download_model__delta_net-1.3B-100B_based_nq_2048.jsonl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e80805be830453ff52a403b20493742a76b3a4d2d2172d5d424c83c03988142
+size 41035265

delta_net-1.3B-100B/based_nq_2048/results.json

@@ -0,0 +1,51 @@
+{
+  "results": {
+    "based_nq_2048": {
+      "contains,none": 0.2454862210959772,
+      "contains_stderr,none": "N/A",
+      "alias": "based_nq_2048"
+    }
+  },
+  "configs": {
+    "based_nq_2048": {
+      "description": "",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "num_fewshot": 0,
+      "output_type": "generate_until",
+      "generation_kwargs": {
+        "until": [
+          "\n\n"
+        ],
+        "do_sample": false
+      },
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": "default"
+      }
+    }
+  },
+  "versions": {
+    "based_nq_2048": "default"
+  },
+  "n-shot": {
+    "based_nq_2048": 0
+  },
+  "config": {
+    "model": "lm_eval_model",
+    "model_args": " checkpoint_name=/mnt/jfzn/msj/download_model/delta_net-1.3B-100B",
+    "batch_size": "8",
+    "batch_sizes": [],
+    "device": "cuda:0",
+    "use_cache": null,
+    "limit": null,
+    "bootstrap_iters": 100000,
+    "gen_kwargs": null
+  },
+  "git_hash": null,
+  "context_length": 2000,
+  "answer_length": 48,
+  "cutting_context": true,
+  "decode_mode": "default"
+}

delta_net-1.3B-100B/based_squad/ checkpoint_name____mnt__jfzn__msj__delta_net-1.3B-100B_based_squad.jsonl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0539b8aed62ac4c7601069e37f0a4697d6600279a84e4365e752604fd33ce9e4
+size 14997314

delta_net-1.3B-100B/based_squad/ checkpoint_name____mnt__jfzn__msj__download_model__delta_net-1.3B-100B_based_squad.jsonl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc7950e0973468e7b536214c453ab275cdf5033b67dd513bba2c5cb4e9a6c6c4
+size 14995544

delta_net-1.3B-100B/based_squad/results.json

@@ -0,0 +1,55 @@
+{
+  "results": {
+    "based_squad": {
+      "exact,none": 4.098085320792745,
+      "exact_stderr,none": "N/A",
+      "f1,none": 14.662322521108223,
+      "f1_stderr,none": "N/A",
+      "contains,none": 0.3432986227746053,
+      "contains_stderr,none": "N/A",
+      "alias": "based_squad"
+    }
+  },
+  "configs": {
+    "based_squad": {
+      "description": "",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "num_fewshot": 0,
+      "output_type": "generate_until",
+      "generation_kwargs": {
+        "until": [
+          "\n\n"
+        ],
+        "do_sample": false
+      },
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 0
+      }
+    }
+  },
+  "versions": {
+    "based_squad": 0
+  },
+  "n-shot": {
+    "based_squad": 0
+  },
+  "config": {
+    "model": "lm_eval_model",
+    "model_args": " checkpoint_name=/mnt/jfzn/msj/download_model/delta_net-1.3B-100B",
+    "batch_size": "8",
+    "batch_sizes": [],
+    "device": "cuda:0",
+    "use_cache": null,
+    "limit": null,
+    "bootstrap_iters": 100000,
+    "gen_kwargs": null
+  },
+  "git_hash": null,
+  "context_length": 2000,
+  "answer_length": 48,
+  "cutting_context": true,
+  "decode_mode": "default"
+}

delta_net-1.3B-100B/based_swde/results.json

@@ -0,0 +1,51 @@
+{
+  "results": {
+    "based_swde": {
+      "contains,none": 0.36363636363636365,
+      "contains_stderr,none": "N/A",
+      "alias": "based_swde"
+    }
+  },
+  "configs": {
+    "based_swde": {
+      "description": "",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "num_fewshot": 0,
+      "output_type": "generate_until",
+      "generation_kwargs": {
+        "until": [
+          "\n\n"
+        ],
+        "do_sample": false
+      },
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 0
+      }
+    }
+  },
+  "versions": {
+    "based_swde": 0
+  },
+  "n-shot": {
+    "based_swde": 0
+  },
+  "config": {
+    "model": "lm_eval_model",
+    "model_args": " checkpoint_name=/mnt/jfzn/msj/download_model/delta_net-1.3B-100B",
+    "batch_size": "8",
+    "batch_sizes": [],
+    "device": "cuda:0",
+    "use_cache": null,
+    "limit": null,
+    "bootstrap_iters": 100000,
+    "gen_kwargs": null
+  },
+  "git_hash": null,
+  "context_length": 2000,
+  "answer_length": 48,
+  "cutting_context": true,
+  "decode_mode": "default"
+}

delta_net-1.3B-100B/based_triviaqa/results.json

@@ -0,0 +1,55 @@
+{
+  "results": {
+    "based_triviaqa": {
+      "exact,none": 1.0071090047393365,
+      "exact_stderr,none": "N/A",
+      "f1,none": 7.6236297885650695,
+      "f1_stderr,none": "N/A",
+      "contains,none": 0.5687203791469194,
+      "contains_stderr,none": "N/A",
+      "alias": "based_triviaqa"
+    }
+  },
+  "configs": {
+    "based_triviaqa": {
+      "description": "",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "num_fewshot": 0,
+      "output_type": "generate_until",
+      "generation_kwargs": {
+        "until": [
+          "\n\n"
+        ],
+        "do_sample": false
+      },
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": "default"
+      }
+    }
+  },
+  "versions": {
+    "based_triviaqa": "default"
+  },
+  "n-shot": {
+    "based_triviaqa": 0
+  },
+  "config": {
+    "model": "lm_eval_model",
+    "model_args": " checkpoint_name=/mnt/jfzn/msj/download_model/delta_net-1.3B-100B",
+    "batch_size": "8",
+    "batch_sizes": [],
+    "device": "cuda:0",
+    "use_cache": null,
+    "limit": null,
+    "bootstrap_iters": 100000,
+    "gen_kwargs": null
+  },
+  "git_hash": null,
+  "context_length": 2000,
+  "answer_length": 48,
+  "cutting_context": true,
+  "decode_mode": "default"
+}

gla-1.3B-100B/.hfd/last_download_command

@@ -0,0 +1 @@
+REPO_ID=fla-hub/gla-1.3B-100B TOOL=aria2c INCLUDE_PATTERNS= EXCLUDE_PATTERNS= DATASET=0 HF_USERNAME= HF_TOKEN= HF_TOKEN=https://huggingface.co REVISION=main

gla-1.3B-100B/.hfd/repo_metadata.json

@@ -0,0 +1 @@
+{"_id":"6608d28ec50f8393c5c2932f","id":"fla-hub/gla-1.3B-100B","private":false,"pipeline_tag":"text-generation","library_name":"transformers","tags":["transformers","safetensors","gla","text-generation","en","dataset:cerebras/SlimPajama-627B","arxiv:2312.06635","arxiv:2507.06457","license:mit","endpoints_compatible","region:us"],"downloads":3991,"likes":1,"modelId":"fla-hub/gla-1.3B-100B","author":"fla-hub","sha":"46b15820a4df269e99aed9d709e017677c15d24b","lastModified":"2025-09-09T10:26:33.000Z","gated":false,"disabled":false,"widgetData":[{"text":"My name is Julien and I like to"},{"text":"I like traveling by train because"},{"text":"Paris is an amazing place to visit,"},{"text":"Once upon a time,"}],"model-index":null,"config":{"architectures":["GLAForCausalLM"],"model_type":"gla","tokenizer_config":{"bos_token":"<s>","eos_token":"</s>","pad_token":null,"unk_token":"<unk>","use_default_system_prompt":false}},"cardData":{"datasets":["cerebras/SlimPajama-627B"],"language":["en"],"library_name":"transformers","license":"mit","pipeline_tag":"text-generation","tags":["text-generation","gla"]},"transformersInfo":{"auto_model":"AutoModelForCausalLM","pipeline_tag":"text-generation"},"siblings":[{"rfilename":".gitattributes"},{"rfilename":"README.md"},{"rfilename":"config.json"},{"rfilename":"generation_config.json"},{"rfilename":"model.safetensors"},{"rfilename":"special_tokens_map.json"},{"rfilename":"tokenizer.json"},{"rfilename":"tokenizer.model"},{"rfilename":"tokenizer_config.json"}],"spaces":[],"createdAt":"2024-03-31T03:03:42.000Z","safetensors":{"parameters":{"BF16":1365514240},"total":1365514240},"usedStorage":7725801115}

gla-1.3B-100B/based_drop/results.json

@@ -0,0 +1,51 @@
+{
+  "results": {
+    "based_drop": {
+      "contains,none": 0.19357930043124102,
+      "contains_stderr,none": "N/A",
+      "alias": "based_drop"
+    }
+  },
+  "configs": {
+    "based_drop": {
+      "description": "",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "num_fewshot": 0,
+      "output_type": "generate_until",
+      "generation_kwargs": {
+        "until": [
+          "\n\n"
+        ],
+        "do_sample": false
+      },
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": "default"
+      }
+    }
+  },
+  "versions": {
+    "based_drop": "default"
+  },
+  "n-shot": {
+    "based_drop": 0
+  },
+  "config": {
+    "model": "lm_eval_model",
+    "model_args": " checkpoint_name=/mnt/jfzn/msj/download_model/gla-1.3B-100B",
+    "batch_size": "8",
+    "batch_sizes": [],
+    "device": "cuda:0",
+    "use_cache": null,
+    "limit": null,
+    "bootstrap_iters": 100000,
+    "gen_kwargs": null
+  },
+  "git_hash": null,
+  "context_length": 2000,
+  "answer_length": 48,
+  "cutting_context": true,
+  "decode_mode": "default"
+}

gla-1.3B-100B/based_fda/ checkpoint_name____mnt__jfzn__msj__download_model__gla-1.3B-100B_based_fda.jsonl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a7b523167023d68fb8e5f1dda52b28b16efdbec9f1b92b7ced47e5700e51163
+size 14196379

gla-1.3B-100B/based_fda/ checkpoint_name____mnt__jfzn__msj__gla-1.3B-100B_based_fda.jsonl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aaa543c02364891c58079791e403b11f1523a98378102e45b6b3eafb329c92ac
+size 14492347

gla-1.3B-100B/based_fda/results.json

@@ -0,0 +1,51 @@
+{
+  "results": {
+    "based_fda": {
+      "contains,none": 0.27157129881925524,
+      "contains_stderr,none": "N/A",
+      "alias": "based_fda"
+    }
+  },
+  "configs": {
+    "based_fda": {
+      "description": "",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "num_fewshot": 0,
+      "output_type": "generate_until",
+      "generation_kwargs": {
+        "until": [
+          "\n\n"
+        ],
+        "do_sample": false
+      },
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 0
+      }
+    }
+  },
+  "versions": {
+    "based_fda": 0
+  },
+  "n-shot": {
+    "based_fda": 0
+  },
+  "config": {
+    "model": "lm_eval_model",
+    "model_args": " checkpoint_name=/mnt/jfzn/msj/download_model/gla-1.3B-100B",
+    "batch_size": "8",
+    "batch_sizes": [],
+    "device": "cuda:0",
+    "use_cache": null,
+    "limit": null,
+    "bootstrap_iters": 100000,
+    "gen_kwargs": null
+  },
+  "git_hash": null,
+  "context_length": 2000,
+  "answer_length": 48,
+  "cutting_context": true,
+  "decode_mode": "default"
+}

gla-1.3B-100B/based_nq_2048/ checkpoint_name____mnt__jfzn__msj__download_model__gla-1.3B-100B_based_nq_2048.jsonl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8ec94d98967baa6d1e274280f486787d8dc836e49d120a36bd3017de6102252
+size 41005103

gla-1.3B-100B/based_nq_2048/ checkpoint_name____mnt__jfzn__msj__gla-1.3B-100B_based_nq_2048.jsonl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f77e057a5310c128fa6ce85fc4f7793de2a6961f63a8cf4057a057c0c5efe9a9
+size 41926367

gla-1.3B-100B/based_nq_2048/results.json

@@ -0,0 +1,51 @@
+{
+  "results": {
+    "based_nq_2048": {
+      "contains,none": 0.22204624643649035,
+      "contains_stderr,none": "N/A",
+      "alias": "based_nq_2048"
+    }
+  },
+  "configs": {
+    "based_nq_2048": {
+      "description": "",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "num_fewshot": 0,
+      "output_type": "generate_until",
+      "generation_kwargs": {
+        "until": [
+          "\n\n"
+        ],
+        "do_sample": false
+      },
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": "default"
+      }
+    }
+  },
+  "versions": {
+    "based_nq_2048": "default"
+  },
+  "n-shot": {
+    "based_nq_2048": 0
+  },
+  "config": {
+    "model": "lm_eval_model",
+    "model_args": " checkpoint_name=/mnt/jfzn/msj/download_model/gla-1.3B-100B",
+    "batch_size": "8",
+    "batch_sizes": [],
+    "device": "cuda:0",
+    "use_cache": null,
+    "limit": null,
+    "bootstrap_iters": 100000,
+    "gen_kwargs": null
+  },
+  "git_hash": null,
+  "context_length": 2000,
+  "answer_length": 48,
+  "cutting_context": true,
+  "decode_mode": "default"
+}

gla-1.3B-100B/based_squad/ checkpoint_name____mnt__jfzn__msj__download_model__gla-1.3B-100B_based_squad.jsonl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:646834fc08075cd6ca756f7df597ed1a9a1bd899f781ec9bce71d3a13cf70a0c
+size 14983274

gla-1.3B-100B/based_squad/ checkpoint_name____mnt__jfzn__msj__gla-1.3B-100B_based_squad.jsonl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66a1ec7f9c455f30e00ddca4edfcd6cf8750fbcb405285f9a45b0c80abcf2acb
+size 14979950

gla-1.3B-100B/based_squad/results.json

@@ -0,0 +1,55 @@
+{
+  "results": {
+    "based_squad": {
+      "exact,none": 4.467584816929795,
+      "exact_stderr,none": "N/A",
+      "f1,none": 15.399587310201976,
+      "f1_stderr,none": "N/A",
+      "contains,none": 0.349009069533087,
+      "contains_stderr,none": "N/A",
+      "alias": "based_squad"
+    }
+  },
+  "configs": {
+    "based_squad": {
+      "description": "",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "num_fewshot": 0,
+      "output_type": "generate_until",
+      "generation_kwargs": {
+        "until": [
+          "\n\n"
+        ],
+        "do_sample": false
+      },
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 0
+      }
+    }
+  },
+  "versions": {
+    "based_squad": 0
+  },
+  "n-shot": {
+    "based_squad": 0
+  },
+  "config": {
+    "model": "lm_eval_model",
+    "model_args": " checkpoint_name=/mnt/jfzn/msj/download_model/gla-1.3B-100B",
+    "batch_size": "8",
+    "batch_sizes": [],
+    "device": "cuda:0",
+    "use_cache": null,
+    "limit": null,
+    "bootstrap_iters": 100000,
+    "gen_kwargs": null
+  },
+  "git_hash": null,
+  "context_length": 2000,
+  "answer_length": 48,
+  "cutting_context": true,
+  "decode_mode": "default"
+}

gla-1.3B-100B/based_swde/results.json

@@ -0,0 +1,51 @@
+{
+  "results": {
+    "based_swde": {
+      "contains,none": 0.3083411433926898,
+      "contains_stderr,none": "N/A",
+      "alias": "based_swde"
+    }
+  },
+  "configs": {
+    "based_swde": {
+      "description": "",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "num_fewshot": 0,
+      "output_type": "generate_until",
+      "generation_kwargs": {
+        "until": [
+          "\n\n"
+        ],
+        "do_sample": false
+      },
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 0
+      }
+    }
+  },
+  "versions": {
+    "based_swde": 0
+  },
+  "n-shot": {
+    "based_swde": 0
+  },
+  "config": {
+    "model": "lm_eval_model",
+    "model_args": " checkpoint_name=/mnt/jfzn/msj/download_model/gla-1.3B-100B",
+    "batch_size": "8",
+    "batch_sizes": [],
+    "device": "cuda:0",
+    "use_cache": null,
+    "limit": null,
+    "bootstrap_iters": 100000,
+    "gen_kwargs": null
+  },
+  "git_hash": null,
+  "context_length": 2000,
+  "answer_length": 48,
+  "cutting_context": true,
+  "decode_mode": "default"
+}

gla-1.3B-100B/based_triviaqa/results.json

@@ -0,0 +1,55 @@
+{
+  "results": {
+    "based_triviaqa": {
+      "exact,none": 1.3033175355450237,
+      "exact_stderr,none": "N/A",
+      "f1,none": 7.748952759132068,
+      "f1_stderr,none": "N/A",
+      "contains,none": 0.5574644549763034,
+      "contains_stderr,none": "N/A",
+      "alias": "based_triviaqa"
+    }
+  },
+  "configs": {
+    "based_triviaqa": {
+      "description": "",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "num_fewshot": 0,
+      "output_type": "generate_until",
+      "generation_kwargs": {
+        "until": [
+          "\n\n"
+        ],
+        "do_sample": false
+      },
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": "default"
+      }
+    }
+  },
+  "versions": {
+    "based_triviaqa": "default"
+  },
+  "n-shot": {
+    "based_triviaqa": 0
+  },
+  "config": {
+    "model": "lm_eval_model",
+    "model_args": " checkpoint_name=/mnt/jfzn/msj/download_model/gla-1.3B-100B",
+    "batch_size": "8",
+    "batch_sizes": [],
+    "device": "cuda:0",
+    "use_cache": null,
+    "limit": null,
+    "bootstrap_iters": 100000,
+    "gen_kwargs": null
+  },
+  "git_hash": null,
+  "context_length": 2000,
+  "answer_length": 48,
+  "cutting_context": true,
+  "decode_mode": "default"
+}

hgrn2-1.3B-100B/based_drop/results.json

@@ -0,0 +1,51 @@
+{
+  "results": {
+    "based_drop": {
+      "contains,none": 0.19262098706276953,
+      "contains_stderr,none": "N/A",
+      "alias": "based_drop"
+    }
+  },
+  "configs": {
+    "based_drop": {
+      "description": "",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "num_fewshot": 0,
+      "output_type": "generate_until",
+      "generation_kwargs": {
+        "until": [
+          "\n\n"
+        ],
+        "do_sample": false
+      },
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": "default"
+      }
+    }
+  },
+  "versions": {
+    "based_drop": "default"
+  },
+  "n-shot": {
+    "based_drop": 0
+  },
+  "config": {
+    "model": "lm_eval_model",
+    "model_args": " checkpoint_name=/mnt/jfzn/msj/download_model/hgrn2-1.3B-100B",
+    "batch_size": "8",
+    "batch_sizes": [],
+    "device": "cuda:0",
+    "use_cache": null,
+    "limit": null,
+    "bootstrap_iters": 100000,
+    "gen_kwargs": null
+  },
+  "git_hash": null,
+  "context_length": 2000,
+  "answer_length": 48,
+  "cutting_context": true,
+  "decode_mode": "default"
+}

hgrn2-1.3B-100B/based_fda/ checkpoint_name____mnt__jfzn__msj__download_model__hgrn2-1.3B-100B_based_fda.jsonl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5ba7eb94d0e3b885116fc2cf3b54d79acfb12a040b87ae3cdccd8144fc21253
+size 14188153

hgrn2-1.3B-100B/based_fda/results.json

@@ -0,0 +1,51 @@
+{
+  "results": {
+    "based_fda": {
+      "contains,none": 0.1362397820163488,
+      "contains_stderr,none": "N/A",
+      "alias": "based_fda"
+    }
+  },
+  "configs": {
+    "based_fda": {
+      "description": "",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "num_fewshot": 0,
+      "output_type": "generate_until",
+      "generation_kwargs": {
+        "until": [
+          "\n\n"
+        ],
+        "do_sample": false
+      },
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 0
+      }
+    }
+  },
+  "versions": {
+    "based_fda": 0
+  },
+  "n-shot": {
+    "based_fda": 0
+  },
+  "config": {
+    "model": "lm_eval_model",
+    "model_args": " checkpoint_name=/mnt/jfzn/msj/download_model/hgrn2-1.3B-100B",
+    "batch_size": "8",
+    "batch_sizes": [],
+    "device": "cuda:0",
+    "use_cache": null,
+    "limit": null,
+    "bootstrap_iters": 100000,
+    "gen_kwargs": null
+  },
+  "git_hash": null,
+  "context_length": 2000,
+  "answer_length": 48,
+  "cutting_context": true,
+  "decode_mode": "default"
+}

hgrn2-1.3B-100B/based_nq_2048/ checkpoint_name____mnt__jfzn__msj__download_model__hgrn2-1.3B-100B_based_nq_2048.jsonl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3046421ad0497413cf63c3c4bd2ab6efac858886b16bd1496609b467a99964ba
+size 40978363

hgrn2-1.3B-100B/based_nq_2048/results.json

@@ -0,0 +1,51 @@
+{
+  "results": {
+    "based_nq_2048": {
+      "contains,none": 0.1954387076338296,
+      "contains_stderr,none": "N/A",
+      "alias": "based_nq_2048"
+    }
+  },
+  "configs": {
+    "based_nq_2048": {
+      "description": "",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "num_fewshot": 0,
+      "output_type": "generate_until",
+      "generation_kwargs": {
+        "until": [
+          "\n\n"
+        ],
+        "do_sample": false
+      },
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": "default"
+      }
+    }
+  },
+  "versions": {
+    "based_nq_2048": "default"
+  },
+  "n-shot": {
+    "based_nq_2048": 0
+  },
+  "config": {
+    "model": "lm_eval_model",
+    "model_args": " checkpoint_name=/mnt/jfzn/msj/download_model/hgrn2-1.3B-100B",
+    "batch_size": "8",
+    "batch_sizes": [],
+    "device": "cuda:0",
+    "use_cache": null,
+    "limit": null,
+    "bootstrap_iters": 100000,
+    "gen_kwargs": null
+  },
+  "git_hash": null,
+  "context_length": 2000,
+  "answer_length": 48,
+  "cutting_context": true,
+  "decode_mode": "default"
+}

hgrn2-1.3B-100B/based_squad/ checkpoint_name____mnt__jfzn__msj__download_model__hgrn2-1.3B-100B_based_squad.jsonl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:362e6d9731e716c5c66cbe12143f687d9df9fce1bcc464f5d5daa984bd65ab5b
+size 15095350

hgrn2-1.3B-100B/based_swde/results.json

@@ -0,0 +1,51 @@
+{
+  "results": {
+    "based_swde": {
+      "contains,none": 0.2268041237113402,
+      "contains_stderr,none": "N/A",
+      "alias": "based_swde"
+    }
+  },
+  "configs": {
+    "based_swde": {
+      "description": "",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "num_fewshot": 0,
+      "output_type": "generate_until",
+      "generation_kwargs": {
+        "until": [
+          "\n\n"
+        ],
+        "do_sample": false
+      },
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 0
+      }
+    }
+  },
+  "versions": {
+    "based_swde": 0
+  },
+  "n-shot": {
+    "based_swde": 0
+  },
+  "config": {
+    "model": "lm_eval_model",
+    "model_args": " checkpoint_name=/mnt/jfzn/msj/download_model/hgrn2-1.3B-100B",
+    "batch_size": "8",
+    "batch_sizes": [],
+    "device": "cuda:0",
+    "use_cache": null,
+    "limit": null,
+    "bootstrap_iters": 100000,
+    "gen_kwargs": null
+  },
+  "git_hash": null,
+  "context_length": 2000,
+  "answer_length": 48,
+  "cutting_context": true,
+  "decode_mode": "default"
+}

retnet-1.3B-100B/based_fda/ checkpoint_name____mnt__jfzn__msj__download_model__retnet-1.3B-100B_based_fda.jsonl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3bc28d86e2f2ccf2ab55361cac74d5404697de31688a64623a3ab532fd56188
+size 14186601

transformer-1.3B-100B/config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "fla-hub/transformer-1.3B-100B",
+  "architectures": [
+    "TransformerForCausalLM"
+  ],
+  "attention_bias": false,
+  "bos_token_id": 1,
+  "elementwise_affine": true,
+  "eos_token_id": 2,
+  "fuse_cross_entropy": true,
+  "fuse_norm": true,
+  "fuse_swiglu": true,
+  "hidden_act": "swish",
+  "hidden_ratio": 4,
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": null,
+  "max_position_embeddings": 204800,
+  "model_type": "transformer",
+  "norm_eps": 1e-06,
+  "num_heads": 32,
+  "num_hidden_layers": 24,
+  "num_kv_heads": null,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.48.2",
+  "use_cache": true,
+  "vocab_size": 32000,
+  "window_size": null
+}

transformer-1.3B-100B/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.48.2"
+}

transformer-1.3B-100B/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:780b0295e9a6bd686c004e281bcec94130dc5a3e1d111ba440f2cd5f601fe790
+size 2728619696

transformer-1.3B-100B/results

@@ -0,0 +1,15 @@
+|----------------|------:|------|-----:|---------------|---|------:|---|------|
+|arc_challenge   |      1|none  |     0|acc            |↑  | 0.2372|±  |0.0124|
+|                |       |none  |     0|acc_norm       |↑  | 0.2782|±  |0.0131|
+|arc_easy        |      1|none  |     0|acc            |↑  | 0.5497|±  |0.0102|
+|                |       |none  |     0|acc_norm       |↑  | 0.4949|±  |0.0103|
+|hellaswag       |      1|none  |     0|acc            |↑  | 0.3864|±  |0.0049|
+|                |       |none  |     0|acc_norm       |↑  | 0.4917|±  |0.0050|
+|lambada_standard|      1|none  |     0|acc            |↑  | 0.4077|±  |0.0068|
+|                |       |none  |     0|perplexity     |↓  |19.3234|±  |0.6254|
+|piqa            |      1|none  |     0|acc            |↑  | 0.7029|±  |0.0107|
+|                |       |none  |     0|acc_norm       |↑  | 0.7040|±  |0.0107|
+|wikitext        |      2|none  |     0|bits_per_byte  |↓  | 0.7738|±  |   N/A|
+|                |       |none  |     0|byte_perplexity|↓  | 1.7097|±  |   N/A|
+|                |       |none  |     0|word_perplexity|↓  |17.6031|±  |   N/A|
+|winogrande      |      1|none  |     0|acc            |↑  | 0.5556|±  |0.0140|

transformer-1.3B-100B/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
+  }
+}

transformer-1.3B-100B/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

transformer-1.3B-100B/tokenizer_config.json

@@ -0,0 +1,42 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "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>",
+  "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
+}