Upload folder using huggingface_hub

chat_template.jinja

@@ -0,0 +1,34 @@
+
+{{- '<|bos|>' }}
+{%- set ns = namespace(first_system='', injected=false) %}
+{%- if messages and messages[0].role == 'system' %}
+    {%- set ns.first_system = messages[0].content %}
+{%- endif %}
+
+{%- for message in messages %}
+    {%- if message.content is string %}
+        {%- set content = message.content %}
+    {%- else %}
+        {%- set content = '' %}
+    {%- endif %}
+    {%- if message.role == "user" %}
+        {%- if ns.first_system and not ns.injected %}
+            {{- '<|user_start|>' + ns.first_system + '\n\n' + content + '<|user_end|>' }}
+            {%- set ns.injected = true %}
+        {% else %}
+            {{- '<|user_start|>' + content + '<|user_end|>' }}
+        {% endif %}
+    {%- elif message.role == "assistant" %}
+        {{- '<|assistant_start|>' }}
+        {% generation %}
+        {{- content + '<|assistant_end|>' }}
+        {% endgeneration %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|assistant_start|>' }}
+{%- else %}
+    {% generation %}
+    {{- '<|endoftext|>' }}
+    {% endgeneration %}
+{%- endif %}

config.json

@@ -0,0 +1,34 @@
+{
+  "_rope_scaling": null,
+  "architectures": [
+    "Imu1ForCausalLM"
+  ],
+  "attn_gating": "per-head",
+  "attn_qknorm": true,
+  "attn_val_residual": true,
+  "bos_token_id": null,
+  "dtype": "float32",
+  "eos_token_id": 256,
+  "hidden_act": "silu",
+  "hidden_size": 1280,
+  "initializer_range": 0.02,
+  "intermediate_size": 3392,
+  "layernorm_scaling": true,
+  "max_position_embeddings": 8192,
+  "model_type": "imu_1",
+  "num_attention_heads": 20,
+  "num_hidden_layers": 18,
+  "num_key_value_heads": 20,
+  "pad_token_id": null,
+  "rms_norm_eps": 1e-05,
+  "rope_parameters": {
+    "rope_theta": 10000,
+    "rope_type": "default"
+  },
+  "rope_theta": 10000,
+  "tie_word_embeddings": false,
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "transformers_version": "5.0.0.dev0",
+  "use_cache": true,
+  "vocab_size": 65536
+}

generation_config.json

@@ -0,0 +1,5 @@
+{
+  "_from_model_config": true,
+  "eos_token_id": 256,
+  "transformers_version": "5.0.0.dev0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1099c3b75bab6a10b69589beae13483feb9e02551208ccbbfa33879735dbd57f
+size 2082823184

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1,176 @@
+{
+  "added_tokens_decoder": {
+    "256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "65536": {
+      "content": "<|reserved_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "65537": {
+      "content": "<|reserved_1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "65538": {
+      "content": "<|reserved_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "65539": {
+      "content": "<|reserved_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "65540": {
+      "content": "<|reserved_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "65541": {
+      "content": "<|reserved_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "65542": {
+      "content": "<|reserved_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "65543": {
+      "content": "<|reserved_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "65544": {
+      "content": "<|reserved_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "65545": {
+      "content": "<|reserved_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "65546": {
+      "content": "<|reserved_10|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "65547": {
+      "content": "<|reserved_11|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "65548": {
+      "content": "<|reserved_12|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "65549": {
+      "content": "<|reserved_13|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "65550": {
+      "content": "<|reserved_14|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "65551": {
+      "content": "<|reserved_15|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "65552": {
+      "content": "<|reserved_16|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "65553": {
+      "content": "<|reserved_17|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "65554": {
+      "content": "<|reserved_18|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "65555": {
+      "content": "<|reserved_19|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": false,
+  "extra_special_tokens": {},
+  "model_max_length": 1000000000000000019884624838656,
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}