初始化项目，由ModelHub XC社区提供模型

Model: kandivault/sprocket-500m
Source: Original Platform

chat/chat_template.jinja

@@ -0,0 +1 @@
+{% for m in messages %}{% if m['role'] == 'system' %}<|system|>{{ m['content'] }}<|end|>{% elif m['role'] == 'user' %}<|user|>{{ m['content'] }}<|end|>{% elif m['role'] == 'assistant' %}<|assistant|>{{ m['content'] }}<|end|>{% elif m['role'] == 'memory' %}<|memory_read|>{{ m['content'] }}<|end|>{% elif m['role'] == 'tool' %}<|tool_result|>{{ m['content'] }}<|end|>{% endif %}{% endfor %}{% if add_generation_prompt %}<|assistant|>{% endif %}

chat/config.json

@@ -0,0 +1,30 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "dtype": "bfloat16",
+  "eos_token_id": 5,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 1280,
+  "initializer_range": 0.02,
+  "intermediate_size": 3584,
+  "max_position_embeddings": 2048,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 20,
+  "num_hidden_layers": 26,
+  "num_key_value_heads": 4,
+  "pad_token_id": 1,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": true,
+  "transformers_version": "4.57.6",
+  "use_cache": true,
+  "vocab_size": 32000
+}

chat/export_provenance.json

@@ -0,0 +1,19 @@
+{
+  "source_ckpt": "checkpoints/500m_chat_final.pt",
+  "source_iter": 405,
+  "native_cfg": {
+    "vocab_size": 32000,
+    "dim": 1280,
+    "n_layers": 26,
+    "n_heads": 20,
+    "n_kv_heads": 4,
+    "max_seq_len": 2048,
+    "ffn_multiple_of": 256,
+    "ffn_dim_multiplier": null,
+    "rope_theta": 10000.0,
+    "dropout": 0.0,
+    "norm_eps": 1e-05,
+    "grad_checkpoint": false
+  },
+  "dtype": "bfloat16"
+}

chat/generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 5,
+  "pad_token_id": 1,
+  "transformers_version": "4.57.6"
+}

chat/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:551c6e262ec4561dda7c74c9ef7cb73bd1a555ad1e05e37e6600c84a5acefe97
+size 1002207984

chat/special_tokens_map.json

@@ -0,0 +1,17 @@
+{
+  "additional_special_tokens": [
+    "<|system|>",
+    "<|user|>",
+    "<|assistant|>",
+    "<|tool_call|>",
+    "<|tool_result|>",
+    "<think>",
+    "</think>",
+    "<|memory_read|>",
+    "<|memory_write|>"
+  ],
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|end|>",
+  "pad_token": "<|pad|>",
+  "unk_token": "<|endoftext|>"
+}

chat/tokenizer_config.json

@@ -0,0 +1,151 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<|pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<|system|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<|user|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<|assistant|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<|end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "<|tool_call|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": "<|tool_result|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "8": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "9": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "10": {
+      "content": "<|memory_read|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "11": {
+      "content": "<|memory_write|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "12": {
+      "content": "<|reserved_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "13": {
+      "content": "<|reserved_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "14": {
+      "content": "<|reserved_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "15": {
+      "content": "<|reserved_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|system|>",
+    "<|user|>",
+    "<|assistant|>",
+    "<|tool_call|>",
+    "<|tool_result|>",
+    "<think>",
+    "</think>",
+    "<|memory_read|>",
+    "<|memory_write|>"
+  ],
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|end|>",
+  "extra_special_tokens": {},
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|pad|>",
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "unk_token": "<|endoftext|>"
+}