Upload folder using huggingface_hub
Browse files- .gitattributes +1 -0
- additional_chat_templates/tool_use.jinja +152 -0
- chat_template.jinja +6 -0
- config.json +15 -0
- model.safetensors +3 -0
- model.safetensors.index.json +116 -0
- special_tokens_map.json +6 -0
- tokenizer.json +3 -0
- tokenizer_config.json +8 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
additional_chat_templates/tool_use.jinja
ADDED
|
@@ -0,0 +1,152 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{%- macro json_to_python_type(json_spec) %}
|
| 2 |
+
{%- set basic_type_map = {
|
| 3 |
+
"string": "str",
|
| 4 |
+
"number": "float",
|
| 5 |
+
"integer": "int",
|
| 6 |
+
"boolean": "bool"
|
| 7 |
+
} %}
|
| 8 |
+
|
| 9 |
+
{%- if basic_type_map[json_spec.type] is defined %}
|
| 10 |
+
{{- basic_type_map[json_spec.type] }}
|
| 11 |
+
{%- elif json_spec.type == "array" %}
|
| 12 |
+
{{- "list[" + json_to_python_type(json_spec|items) + "]"}}
|
| 13 |
+
{%- elif json_spec.type == "object" %}
|
| 14 |
+
{%- if json_spec.additionalProperties is defined %}
|
| 15 |
+
{{- "dict[str, " + json_to_python_type(json_spec.additionalProperties) + ']'}}
|
| 16 |
+
{%- else %}
|
| 17 |
+
{{- "dict" }}
|
| 18 |
+
{%- endif %}
|
| 19 |
+
{%- elif json_spec.type is iterable %}
|
| 20 |
+
{{- "Union[" }}
|
| 21 |
+
{%- for t in json_spec.type %}
|
| 22 |
+
{{- json_to_python_type({"type": t}) }}
|
| 23 |
+
{%- if not loop.last %}
|
| 24 |
+
{{- "," }}
|
| 25 |
+
{%- endif %}
|
| 26 |
+
{%- endfor %}
|
| 27 |
+
{{- "]" }}
|
| 28 |
+
{%- else %}
|
| 29 |
+
{{- "Any" }}
|
| 30 |
+
{%- endif %}
|
| 31 |
+
{%- endmacro %}
|
| 32 |
+
|
| 33 |
+
|
| 34 |
+
{{- bos_token }}
|
| 35 |
+
{{- '<|im_start|>system
|
| 36 |
+
' }}
|
| 37 |
+
{{- "You are a function calling AI model. You are provided with function signatures within <tools></tools> XML tags. You may call one or more functions to assist with the user query. Don't make assumptions about what values to plug into functions. Here are the available tools: <tools> " }}
|
| 38 |
+
{%- for tool in tools %}
|
| 39 |
+
{%- if tool.function is defined %}
|
| 40 |
+
{%- set tool = tool.function %}
|
| 41 |
+
{%- endif %}
|
| 42 |
+
{{- '{"type": "function", "function": ' }}
|
| 43 |
+
{{- '{"name": "' + tool.name + '", ' }}
|
| 44 |
+
{{- '"description": "' + tool.name + '(' }}
|
| 45 |
+
{%- for param_name, param_fields in tool.parameters.properties|items %}
|
| 46 |
+
{{- param_name + ": " + json_to_python_type(param_fields) }}
|
| 47 |
+
{%- if not loop.last %}
|
| 48 |
+
{{- ", " }}
|
| 49 |
+
{%- endif %}
|
| 50 |
+
{%- endfor %}
|
| 51 |
+
{{- ")" }}
|
| 52 |
+
{%- if tool.return is defined %}
|
| 53 |
+
{{- " -> " + json_to_python_type(tool.return) }}
|
| 54 |
+
{%- endif %}
|
| 55 |
+
{{- " - " + tool.description + "
|
| 56 |
+
|
| 57 |
+
" }}
|
| 58 |
+
{%- for param_name, param_fields in tool.parameters.properties|items %}
|
| 59 |
+
{%- if loop.first %}
|
| 60 |
+
{{- " Args:
|
| 61 |
+
" }}
|
| 62 |
+
{%- endif %}
|
| 63 |
+
{{- " " + param_name + "(" + json_to_python_type(param_fields) + "): " + param_fields.description|trim }}
|
| 64 |
+
{%- endfor %}
|
| 65 |
+
{%- if tool.return is defined and tool.return.description is defined %}
|
| 66 |
+
{{- "
|
| 67 |
+
Returns:
|
| 68 |
+
" + tool.return.description }}
|
| 69 |
+
{%- endif %}
|
| 70 |
+
{{- '"' }}
|
| 71 |
+
{{- ', "parameters": ' }}
|
| 72 |
+
{%- if tool.parameters.properties | length == 0 %}
|
| 73 |
+
{{- "{}" }}
|
| 74 |
+
{%- else %}
|
| 75 |
+
{{- tool.parameters|tojson }}
|
| 76 |
+
{%- endif %}
|
| 77 |
+
{{- "}" }}
|
| 78 |
+
{%- if not loop.last %}
|
| 79 |
+
{{- "
|
| 80 |
+
" }}
|
| 81 |
+
{%- endif %}
|
| 82 |
+
{%- endfor %}
|
| 83 |
+
{{- " </tools>" }}
|
| 84 |
+
{{- 'Use the following pydantic model json schema for each tool call you will make: {"properties": {"name": {"title": "Name", "type": "string"}, "arguments": {"title": "Arguments", "type": "object"}}, "required": ["name", "arguments"], "title": "FunctionCall", "type": "object"}}
|
| 85 |
+
' }}
|
| 86 |
+
{{- "For each function call return a json object with function name and arguments within <tool_call></tool_call> XML tags as follows:
|
| 87 |
+
" }}
|
| 88 |
+
{{- "<tool_call>
|
| 89 |
+
" }}
|
| 90 |
+
{{- '{"name": <function-name>, "arguments": <args-dict>}
|
| 91 |
+
' }}
|
| 92 |
+
{{- '</tool_call><|im_end|>
|
| 93 |
+
' }}
|
| 94 |
+
{%- for message in messages %}
|
| 95 |
+
{%- if message.role == "user" or message.role == "system" or (message.role == "assistant" and message.tool_calls is not defined) %}
|
| 96 |
+
{{- '<|im_start|>' + message.role + '
|
| 97 |
+
' + message.content + '<|im_end|>' + '
|
| 98 |
+
' }}
|
| 99 |
+
{%- elif message.role == "assistant" %}
|
| 100 |
+
{{- '<|im_start|>' + message.role }}
|
| 101 |
+
{%- for tool_call in message.tool_calls %}
|
| 102 |
+
{{- '
|
| 103 |
+
<tool_call>
|
| 104 |
+
' }} {%- if tool_call.function is defined %}
|
| 105 |
+
{%- set tool_call = tool_call.function %}
|
| 106 |
+
{%- endif %}
|
| 107 |
+
{{- '{' }}
|
| 108 |
+
{{- '"name": "' }}
|
| 109 |
+
{{- tool_call.name }}
|
| 110 |
+
{{- '"' }}
|
| 111 |
+
{{- ', '}}
|
| 112 |
+
{%- if tool_call.arguments is defined %}
|
| 113 |
+
{{- '"arguments": ' }}
|
| 114 |
+
{%- if tool_call.arguments is string %}
|
| 115 |
+
{{- tool_call.arguments }}
|
| 116 |
+
{%- else %}
|
| 117 |
+
{{- tool_call.arguments|tojson }}
|
| 118 |
+
{%- endif %}
|
| 119 |
+
{%- endif %}
|
| 120 |
+
{{- '}' }}
|
| 121 |
+
{{- '
|
| 122 |
+
</tool_call>' }}
|
| 123 |
+
{%- endfor %}
|
| 124 |
+
{{- '<|im_end|>
|
| 125 |
+
' }}
|
| 126 |
+
{%- elif message.role == "tool" %}
|
| 127 |
+
{%- if loop.previtem and loop.previtem.role != "tool" %}
|
| 128 |
+
{{- '<|im_start|>tool
|
| 129 |
+
' }}
|
| 130 |
+
{%- endif %}
|
| 131 |
+
{{- '<tool_response>
|
| 132 |
+
' }}
|
| 133 |
+
{{- message.content }}
|
| 134 |
+
{%- if not loop.last %}
|
| 135 |
+
{{- '
|
| 136 |
+
</tool_response>
|
| 137 |
+
' }}
|
| 138 |
+
{%- else %}
|
| 139 |
+
{{- '
|
| 140 |
+
</tool_response>' }}
|
| 141 |
+
{%- endif %}
|
| 142 |
+
{%- if not loop.last and loop.nextitem.role != "tool" %}
|
| 143 |
+
{{- '<|im_end|>' }}
|
| 144 |
+
{%- elif loop.last %}
|
| 145 |
+
{{- '<|im_end|>' }}
|
| 146 |
+
{%- endif %}
|
| 147 |
+
{%- endif %}
|
| 148 |
+
{%- endfor %}
|
| 149 |
+
{%- if add_generation_prompt %}
|
| 150 |
+
{{- '<|im_start|>assistant
|
| 151 |
+
' }}
|
| 152 |
+
{%- endif %}
|
chat_template.jinja
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{{bos_token}}{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system
|
| 2 |
+
You are a helpful assistant.<|im_end|>
|
| 3 |
+
' }}{% endif %}{{'<|im_start|>' + message['role'] + '
|
| 4 |
+
' + message['content'] + '<|im_end|>' + '
|
| 5 |
+
'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
|
| 6 |
+
' }}{% endif %}
|
config.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"vocab_size": 128000,
|
| 3 |
+
"dim": 1024,
|
| 4 |
+
"num_layers": 6,
|
| 5 |
+
"num_heads": 16,
|
| 6 |
+
"max_recursion": 16,
|
| 7 |
+
"ffn_expansion": 4,
|
| 8 |
+
"max_position_embeddings": 1024,
|
| 9 |
+
"balancing_weight": 0.01,
|
| 10 |
+
"temperature": 1.0,
|
| 11 |
+
"window_size": 128,
|
| 12 |
+
"model_type": "MoR",
|
| 13 |
+
"architecture": "MixtureOfRecursions",
|
| 14 |
+
"hidden_act": "gelu"
|
| 15 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6c9e06a392ed6878be9c6529c2a8d803703bfe02144984bdffc33259d06a51fc
|
| 3 |
+
size 1361437728
|
model.safetensors.index.json
ADDED
|
@@ -0,0 +1,116 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 1361426496
|
| 4 |
+
},
|
| 5 |
+
"weight_map": {
|
| 6 |
+
"embed.weight": "model.safetensors",
|
| 7 |
+
"pos_embed.weight": "model.safetensors",
|
| 8 |
+
"first_layer.0.weight": "model.safetensors",
|
| 9 |
+
"first_layer.0.bias": "model.safetensors",
|
| 10 |
+
"first_layer.2.weight": "model.safetensors",
|
| 11 |
+
"first_layer.2.bias": "model.safetensors",
|
| 12 |
+
"recursive_layers.0.w_q.weight": "model.safetensors",
|
| 13 |
+
"recursive_layers.0.w_q.bias": "model.safetensors",
|
| 14 |
+
"recursive_layers.0.w_k.weight": "model.safetensors",
|
| 15 |
+
"recursive_layers.0.w_k.bias": "model.safetensors",
|
| 16 |
+
"recursive_layers.0.w_v.weight": "model.safetensors",
|
| 17 |
+
"recursive_layers.0.w_v.bias": "model.safetensors",
|
| 18 |
+
"recursive_layers.0.attn_out.weight": "model.safetensors",
|
| 19 |
+
"recursive_layers.0.attn_out.bias": "model.safetensors",
|
| 20 |
+
"recursive_layers.0.ffn.0.weight": "model.safetensors",
|
| 21 |
+
"recursive_layers.0.ffn.0.bias": "model.safetensors",
|
| 22 |
+
"recursive_layers.0.ffn.2.weight": "model.safetensors",
|
| 23 |
+
"recursive_layers.0.ffn.2.bias": "model.safetensors",
|
| 24 |
+
"recursive_layers.0.norm1.weight": "model.safetensors",
|
| 25 |
+
"recursive_layers.0.norm1.bias": "model.safetensors",
|
| 26 |
+
"recursive_layers.0.norm2.weight": "model.safetensors",
|
| 27 |
+
"recursive_layers.0.norm2.bias": "model.safetensors",
|
| 28 |
+
"recursive_layers.1.w_q.weight": "model.safetensors",
|
| 29 |
+
"recursive_layers.1.w_q.bias": "model.safetensors",
|
| 30 |
+
"recursive_layers.1.w_k.weight": "model.safetensors",
|
| 31 |
+
"recursive_layers.1.w_k.bias": "model.safetensors",
|
| 32 |
+
"recursive_layers.1.w_v.weight": "model.safetensors",
|
| 33 |
+
"recursive_layers.1.w_v.bias": "model.safetensors",
|
| 34 |
+
"recursive_layers.1.attn_out.weight": "model.safetensors",
|
| 35 |
+
"recursive_layers.1.attn_out.bias": "model.safetensors",
|
| 36 |
+
"recursive_layers.1.ffn.0.weight": "model.safetensors",
|
| 37 |
+
"recursive_layers.1.ffn.0.bias": "model.safetensors",
|
| 38 |
+
"recursive_layers.1.ffn.2.weight": "model.safetensors",
|
| 39 |
+
"recursive_layers.1.ffn.2.bias": "model.safetensors",
|
| 40 |
+
"recursive_layers.1.norm1.weight": "model.safetensors",
|
| 41 |
+
"recursive_layers.1.norm1.bias": "model.safetensors",
|
| 42 |
+
"recursive_layers.1.norm2.weight": "model.safetensors",
|
| 43 |
+
"recursive_layers.1.norm2.bias": "model.safetensors",
|
| 44 |
+
"recursive_layers.2.w_q.weight": "model.safetensors",
|
| 45 |
+
"recursive_layers.2.w_q.bias": "model.safetensors",
|
| 46 |
+
"recursive_layers.2.w_k.weight": "model.safetensors",
|
| 47 |
+
"recursive_layers.2.w_k.bias": "model.safetensors",
|
| 48 |
+
"recursive_layers.2.w_v.weight": "model.safetensors",
|
| 49 |
+
"recursive_layers.2.w_v.bias": "model.safetensors",
|
| 50 |
+
"recursive_layers.2.attn_out.weight": "model.safetensors",
|
| 51 |
+
"recursive_layers.2.attn_out.bias": "model.safetensors",
|
| 52 |
+
"recursive_layers.2.ffn.0.weight": "model.safetensors",
|
| 53 |
+
"recursive_layers.2.ffn.0.bias": "model.safetensors",
|
| 54 |
+
"recursive_layers.2.ffn.2.weight": "model.safetensors",
|
| 55 |
+
"recursive_layers.2.ffn.2.bias": "model.safetensors",
|
| 56 |
+
"recursive_layers.2.norm1.weight": "model.safetensors",
|
| 57 |
+
"recursive_layers.2.norm1.bias": "model.safetensors",
|
| 58 |
+
"recursive_layers.2.norm2.weight": "model.safetensors",
|
| 59 |
+
"recursive_layers.2.norm2.bias": "model.safetensors",
|
| 60 |
+
"recursive_layers.3.w_q.weight": "model.safetensors",
|
| 61 |
+
"recursive_layers.3.w_q.bias": "model.safetensors",
|
| 62 |
+
"recursive_layers.3.w_k.weight": "model.safetensors",
|
| 63 |
+
"recursive_layers.3.w_k.bias": "model.safetensors",
|
| 64 |
+
"recursive_layers.3.w_v.weight": "model.safetensors",
|
| 65 |
+
"recursive_layers.3.w_v.bias": "model.safetensors",
|
| 66 |
+
"recursive_layers.3.attn_out.weight": "model.safetensors",
|
| 67 |
+
"recursive_layers.3.attn_out.bias": "model.safetensors",
|
| 68 |
+
"recursive_layers.3.ffn.0.weight": "model.safetensors",
|
| 69 |
+
"recursive_layers.3.ffn.0.bias": "model.safetensors",
|
| 70 |
+
"recursive_layers.3.ffn.2.weight": "model.safetensors",
|
| 71 |
+
"recursive_layers.3.ffn.2.bias": "model.safetensors",
|
| 72 |
+
"recursive_layers.3.norm1.weight": "model.safetensors",
|
| 73 |
+
"recursive_layers.3.norm1.bias": "model.safetensors",
|
| 74 |
+
"recursive_layers.3.norm2.weight": "model.safetensors",
|
| 75 |
+
"recursive_layers.3.norm2.bias": "model.safetensors",
|
| 76 |
+
"recursive_layers.4.w_q.weight": "model.safetensors",
|
| 77 |
+
"recursive_layers.4.w_q.bias": "model.safetensors",
|
| 78 |
+
"recursive_layers.4.w_k.weight": "model.safetensors",
|
| 79 |
+
"recursive_layers.4.w_k.bias": "model.safetensors",
|
| 80 |
+
"recursive_layers.4.w_v.weight": "model.safetensors",
|
| 81 |
+
"recursive_layers.4.w_v.bias": "model.safetensors",
|
| 82 |
+
"recursive_layers.4.attn_out.weight": "model.safetensors",
|
| 83 |
+
"recursive_layers.4.attn_out.bias": "model.safetensors",
|
| 84 |
+
"recursive_layers.4.ffn.0.weight": "model.safetensors",
|
| 85 |
+
"recursive_layers.4.ffn.0.bias": "model.safetensors",
|
| 86 |
+
"recursive_layers.4.ffn.2.weight": "model.safetensors",
|
| 87 |
+
"recursive_layers.4.ffn.2.bias": "model.safetensors",
|
| 88 |
+
"recursive_layers.4.norm1.weight": "model.safetensors",
|
| 89 |
+
"recursive_layers.4.norm1.bias": "model.safetensors",
|
| 90 |
+
"recursive_layers.4.norm2.weight": "model.safetensors",
|
| 91 |
+
"recursive_layers.4.norm2.bias": "model.safetensors",
|
| 92 |
+
"recursive_layers.5.w_q.weight": "model.safetensors",
|
| 93 |
+
"recursive_layers.5.w_q.bias": "model.safetensors",
|
| 94 |
+
"recursive_layers.5.w_k.weight": "model.safetensors",
|
| 95 |
+
"recursive_layers.5.w_k.bias": "model.safetensors",
|
| 96 |
+
"recursive_layers.5.w_v.weight": "model.safetensors",
|
| 97 |
+
"recursive_layers.5.w_v.bias": "model.safetensors",
|
| 98 |
+
"recursive_layers.5.attn_out.weight": "model.safetensors",
|
| 99 |
+
"recursive_layers.5.attn_out.bias": "model.safetensors",
|
| 100 |
+
"recursive_layers.5.ffn.0.weight": "model.safetensors",
|
| 101 |
+
"recursive_layers.5.ffn.0.bias": "model.safetensors",
|
| 102 |
+
"recursive_layers.5.ffn.2.weight": "model.safetensors",
|
| 103 |
+
"recursive_layers.5.ffn.2.bias": "model.safetensors",
|
| 104 |
+
"recursive_layers.5.norm1.weight": "model.safetensors",
|
| 105 |
+
"recursive_layers.5.norm1.bias": "model.safetensors",
|
| 106 |
+
"recursive_layers.5.norm2.weight": "model.safetensors",
|
| 107 |
+
"recursive_layers.5.norm2.bias": "model.safetensors",
|
| 108 |
+
"router.linear.0.weight": "model.safetensors",
|
| 109 |
+
"router.linear.0.bias": "model.safetensors",
|
| 110 |
+
"router.linear.2.weight": "model.safetensors",
|
| 111 |
+
"router.linear.2.bias": "model.safetensors",
|
| 112 |
+
"final_norm.weight": "model.safetensors",
|
| 113 |
+
"final_norm.bias": "model.safetensors",
|
| 114 |
+
"head.weight": "model.safetensors"
|
| 115 |
+
}
|
| 116 |
+
}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<|begin_of_text|>",
|
| 3 |
+
"eos_token": "<|im_end|>",
|
| 4 |
+
"unk_token": null,
|
| 5 |
+
"pad_token": "<|im_end|>"
|
| 6 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:14b5e679cb69af62e14c3b98d346177bd4137d882a44f87dec9efec982b01a05
|
| 3 |
+
size 17209403
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 3 |
+
"bos_token": "<|begin_of_text|>",
|
| 4 |
+
"eos_token": "<|im_end|>",
|
| 5 |
+
"unk_token": null,
|
| 6 |
+
"pad_token": "<|im_end|>",
|
| 7 |
+
"model_max_length": 1024
|
| 8 |
+
}
|