Upload 14 files

chat_template.jinja

@@ -0,0 +1,20 @@
+
+{%- if messages[0]['role'] == 'system' %}
+    {%- set system_message = messages[0]['content'] | trim + ' ' %}
+    {%- set messages = messages[1:] %}
+{%- else %}
+    {%- set system_message = 'A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user\'s questions. ' %}
+{%- endif %}
+
+{{- system_message }}
+{%- for message in messages %}
+    {%- if message['role'] == 'user' %}
+        {{- 'USER: ' + message['content'] | trim }}
+    {%- elif message['role'] == 'assistant' %}
+        {{- ' ASSISTANT: '  + message['content'] | trim + '</s>' }}
+    {%- endif %}
+{%- endfor %}
+
+{%- if add_generation_prompt %}
+    {{- ' ASSISTANT:' }}
+{%- endif %}

config.json

@@ -0,0 +1,40 @@
+{
+  "architectures": [
+    "Mamba2ForCausalLM"
+  ],
+  "bos_token_id": 1,
+  "chunk_size": 256,
+  "conv_kernel": 4,
+  "dtype": "bfloat16",
+  "eos_token_id": 2,
+  "expand": 2,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 1024,
+  "initializer_range": 0.1,
+  "layer_norm_epsilon": 1e-05,
+  "max_position_embeddings": 512,
+  "model_type": "mamba2",
+  "n_groups": 4,
+  "num_heads": 32,
+  "num_hidden_layers": 32,
+  "pad_token_id": 2,
+  "rescale_prenorm_residual": false,
+  "residual_in_fp32": true,
+  "rms_norm": true,
+  "state_size": 128,
+  "tie_word_embeddings": true,
+  "time_step_floor": 0.0001,
+  "time_step_limit": [
+    0.0,
+    Infinity
+  ],
+  "time_step_max": 0.1,
+  "time_step_min": 0.001,
+  "time_step_rank": 64,
+  "transformers_version": "4.57.0.dev0",
+  "use_bias": false,
+  "use_cache": false,
+  "use_conv_bias": true,
+  "vocab_size": 48000
+}

events.out.tfevents.1758125778.kurogane-B650-LiveMixer.154510.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f9fb45f4f0a972e59dd09c9d279ccd47fc609e80c7b865e021902d6664c1c55
+size 634117

generation_config.json

@@ -0,0 +1,10 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": [
+    2
+  ],
+  "pad_token_id": 2,
+  "transformers_version": "4.57.0.dev0",
+  "use_cache": false
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39d95a5dc952ddb436337b6153b9c1abc717e8a404f9130b23bf79795c25e3f1
+size 571381824

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28dcce2c2658c5357c1bbd878da23d80403a18f62733422dbf73ef1eefe8891c
+size 1142872651

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:716d83e48b4ef0ecc739db256420344d8764b568cd2fec53ea128d8653e43804
+size 14645

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77dba8276c2678293a057d183ecba01f3490cf9c10c3a39d159f1419432d7f0d
+size 1465

special_tokens_map.json

@@ -0,0 +1,35 @@
+{
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7978987401ef447724ded0544d048831954b7517a96555ce1593149e3678b6dc
+size 755169

tokenizer_config.json

@@ -0,0 +1,48 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:481ec7c68770023267e3d19662e403e5dc6037f9b855cd1e6fa740e3ca16b950
+size 6289