Upload folder using huggingface_hub

chat_template.jinja

@@ -0,0 +1 @@
+{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ ' ' + message['content'] + eos_token }}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ ' ' }}{% endif %}

config.json

@@ -0,0 +1,36 @@
+{
+  "architectures": [
+    "HybridFourierLM"
+  ],
+  "auto_map": {
+    "AutoConfig": "model.HybridFourierConfig",
+    "AutoModelForCausalLM": "model.HybridFourierLM"
+  },
+  "bos_token_id": 1,
+  "dropout": 0.05,
+  "dtype": "bfloat16",
+  "eos_token_id": 2,
+  "latent_dim": 768,
+  "layer_types": [
+    "linear",
+    "linear",
+    "linear",
+    "softmax",
+    "linear",
+    "linear",
+    "linear",
+    "softmax",
+    "linear",
+    "linear",
+    "linear",
+    "softmax"
+  ],
+  "model_type": "hybrid_fourier_lm",
+  "num_layers": 12,
+  "num_modes": 64,
+  "pad_token_id": 2,
+  "time_scale": 128.0,
+  "transformers_version": "4.56.0",
+  "use_cache": false,
+  "vocab_size": 32768
+}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": [
+    2
+  ],
+  "pad_token_id": 2,
+  "transformers_version": "4.56.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2989225b566d339103b420ea4d3078d89b77f81c03349d3c7fbc4753166ec49d
+size 234681136

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3b73014300d86c2a2f52052dbdf1091e2258cb3d9789111c1779c6709dbfde3
+size 469516363

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f88e21bc7f577d6a08f1a19b17a9c2fed0f4dddc3a152748fb34da132e9f98ed
+size 14645

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33b1731f6f172e685db8110e11ac90faa1e42e5311e23a5ac694b5d79a258fbe
+size 1465

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "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
+  },
+  "pad_token": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37f00374dea48658ee8f5d0f21895b9bc55cb0103939607c8185bfd1c6ca1f89
+size 587404

trainer_state.json

@@ -0,0 +1,33 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 2,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [],
+  "logging_steps": 5,
+  "max_steps": 2,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1734111461376.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aac91bec2e12f16beb7db12d9d3c37fc06c2ba1193e5bd6365cb71cd8280232f
+size 5777