Upload folder using huggingface_hub
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- .gitattributes +1 -0
- added_tokens.json +28 -0
- chat_template.jinja +117 -0
- config.json +156 -0
- generation_config.json +13 -0
- merges.txt +0 -0
- model-00001-of-00098.safetensors +3 -0
- model-00002-of-00098.safetensors +3 -0
- model-00003-of-00098.safetensors +3 -0
- model-00004-of-00098.safetensors +3 -0
- model-00005-of-00098.safetensors +3 -0
- model-00006-of-00098.safetensors +3 -0
- model-00007-of-00098.safetensors +3 -0
- model-00008-of-00098.safetensors +3 -0
- model-00009-of-00098.safetensors +3 -0
- model-00010-of-00098.safetensors +3 -0
- model-00011-of-00098.safetensors +3 -0
- model-00012-of-00098.safetensors +3 -0
- model-00013-of-00098.safetensors +3 -0
- model-00014-of-00098.safetensors +3 -0
- model-00015-of-00098.safetensors +3 -0
- model-00016-of-00098.safetensors +3 -0
- model-00017-of-00098.safetensors +3 -0
- model-00018-of-00098.safetensors +3 -0
- model-00019-of-00098.safetensors +3 -0
- model-00020-of-00098.safetensors +3 -0
- model-00021-of-00098.safetensors +3 -0
- model-00022-of-00098.safetensors +3 -0
- model-00023-of-00098.safetensors +3 -0
- model-00024-of-00098.safetensors +3 -0
- model-00025-of-00098.safetensors +3 -0
- model-00026-of-00098.safetensors +3 -0
- model-00027-of-00098.safetensors +3 -0
- model-00028-of-00098.safetensors +3 -0
- model-00029-of-00098.safetensors +3 -0
- model-00030-of-00098.safetensors +3 -0
- model-00031-of-00098.safetensors +3 -0
- model-00032-of-00098.safetensors +3 -0
- model-00033-of-00098.safetensors +3 -0
- model-00034-of-00098.safetensors +3 -0
- model-00035-of-00098.safetensors +3 -0
- model-00036-of-00098.safetensors +3 -0
- model-00037-of-00098.safetensors +3 -0
- model-00038-of-00098.safetensors +3 -0
- model-00039-of-00098.safetensors +3 -0
- model-00040-of-00098.safetensors +3 -0
- model-00041-of-00098.safetensors +3 -0
- model-00042-of-00098.safetensors +3 -0
- model-00043-of-00098.safetensors +3 -0
- model-00044-of-00098.safetensors +3 -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
|
added_tokens.json
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"</think>": 151668,
|
| 3 |
+
"</tool_call>": 151658,
|
| 4 |
+
"</tool_response>": 151666,
|
| 5 |
+
"<think>": 151667,
|
| 6 |
+
"<tool_call>": 151657,
|
| 7 |
+
"<tool_response>": 151665,
|
| 8 |
+
"<|box_end|>": 151649,
|
| 9 |
+
"<|box_start|>": 151648,
|
| 10 |
+
"<|endoftext|>": 151643,
|
| 11 |
+
"<|file_sep|>": 151664,
|
| 12 |
+
"<|fim_middle|>": 151660,
|
| 13 |
+
"<|fim_pad|>": 151662,
|
| 14 |
+
"<|fim_prefix|>": 151659,
|
| 15 |
+
"<|fim_suffix|>": 151661,
|
| 16 |
+
"<|im_end|>": 151645,
|
| 17 |
+
"<|im_start|>": 151644,
|
| 18 |
+
"<|image_pad|>": 151655,
|
| 19 |
+
"<|object_ref_end|>": 151647,
|
| 20 |
+
"<|object_ref_start|>": 151646,
|
| 21 |
+
"<|quad_end|>": 151651,
|
| 22 |
+
"<|quad_start|>": 151650,
|
| 23 |
+
"<|repo_name|>": 151663,
|
| 24 |
+
"<|video_pad|>": 151656,
|
| 25 |
+
"<|vision_end|>": 151653,
|
| 26 |
+
"<|vision_pad|>": 151654,
|
| 27 |
+
"<|vision_start|>": 151652
|
| 28 |
+
}
|
chat_template.jinja
ADDED
|
@@ -0,0 +1,117 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{% macro render_extra_keys(json_dict, handled_keys) %}
|
| 2 |
+
{%- if json_dict is mapping %}
|
| 3 |
+
{%- for json_key in json_dict if json_key not in handled_keys %}
|
| 4 |
+
{%- if json_dict[json_key] is mapping or (json_dict[json_key] is sequence and json_dict[json_key] is not string) %}
|
| 5 |
+
{{- '\n<' ~ json_key ~ '>' ~ (json_dict[json_key] | tojson | safe) ~ '</' ~ json_key ~ '>' }}
|
| 6 |
+
{%- else %}
|
| 7 |
+
{{-'\n<' ~ json_key ~ '>' ~ (json_dict[json_key] | string) ~ '</' ~ json_key ~ '>' }}
|
| 8 |
+
{%- endif %}
|
| 9 |
+
{%- endfor %}
|
| 10 |
+
{%- endif %}
|
| 11 |
+
{% endmacro %}
|
| 12 |
+
|
| 13 |
+
{%- if messages[0]["role"] == "system" %}
|
| 14 |
+
{%- set system_message = messages[0]["content"] %}
|
| 15 |
+
{%- set loop_messages = messages[1:] %}
|
| 16 |
+
{%- else %}
|
| 17 |
+
{%- set loop_messages = messages %}
|
| 18 |
+
{%- endif %}
|
| 19 |
+
|
| 20 |
+
{%- if not tools is defined %}
|
| 21 |
+
{%- set tools = [] %}
|
| 22 |
+
{%- endif %}
|
| 23 |
+
|
| 24 |
+
{%- if system_message is defined %}
|
| 25 |
+
{{- "<|im_start|>system\n" + system_message }}
|
| 26 |
+
{%- else %}
|
| 27 |
+
{%- if tools is iterable and tools | length > 0 %}
|
| 28 |
+
{{- "<|im_start|>system\nYou are Qwen, a helpful AI assistant that can interact with a computer to solve tasks." }}
|
| 29 |
+
{%- endif %}
|
| 30 |
+
{%- endif %}
|
| 31 |
+
{%- if tools is iterable and tools | length > 0 %}
|
| 32 |
+
{{- "\n\n# Tools\n\nYou have access to the following functions:\n\n" }}
|
| 33 |
+
{{- "<tools>" }}
|
| 34 |
+
{%- for tool in tools %}
|
| 35 |
+
{%- if tool.function is defined %}
|
| 36 |
+
{%- set tool = tool.function %}
|
| 37 |
+
{%- endif %}
|
| 38 |
+
{{- "\n<function>\n<name>" ~ tool.name ~ "</name>" }}
|
| 39 |
+
{%- if tool.description is defined %}
|
| 40 |
+
{{- '\n<description>' ~ (tool.description | trim) ~ '</description>' }}
|
| 41 |
+
{%- endif %}
|
| 42 |
+
{{- '\n<parameters>' }}
|
| 43 |
+
{%- if tool.parameters is defined and tool.parameters is mapping and tool.parameters.properties is defined and tool.parameters.properties is mapping %}
|
| 44 |
+
{%- for param_name, param_fields in tool.parameters.properties|items %}
|
| 45 |
+
{{- '\n<parameter>' }}
|
| 46 |
+
{{- '\n<name>' ~ param_name ~ '</name>' }}
|
| 47 |
+
{%- if param_fields.type is defined %}
|
| 48 |
+
{{- '\n<type>' ~ (param_fields.type | string) ~ '</type>' }}
|
| 49 |
+
{%- endif %}
|
| 50 |
+
{%- if param_fields.description is defined %}
|
| 51 |
+
{{- '\n<description>' ~ (param_fields.description | trim) ~ '</description>' }}
|
| 52 |
+
{%- endif %}
|
| 53 |
+
{%- set handled_keys = ['name', 'type', 'description'] %}
|
| 54 |
+
{{- render_extra_keys(param_fields, handled_keys) }}
|
| 55 |
+
{{- '\n</parameter>' }}
|
| 56 |
+
{%- endfor %}
|
| 57 |
+
{%- endif %}
|
| 58 |
+
{% set handled_keys = ['type', 'properties'] %}
|
| 59 |
+
{{- render_extra_keys(tool.parameters, handled_keys) }}
|
| 60 |
+
{{- '\n</parameters>' }}
|
| 61 |
+
{%- set handled_keys = ['type', 'name', 'description', 'parameters'] %}
|
| 62 |
+
{{- render_extra_keys(tool, handled_keys) }}
|
| 63 |
+
{{- '\n</function>' }}
|
| 64 |
+
{%- endfor %}
|
| 65 |
+
{{- "\n</tools>" }}
|
| 66 |
+
{{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
|
| 67 |
+
{%- endif %}
|
| 68 |
+
{%- if system_message is defined %}
|
| 69 |
+
{{- '<|im_end|>\n' }}
|
| 70 |
+
{%- else %}
|
| 71 |
+
{%- if tools is iterable and tools | length > 0 %}
|
| 72 |
+
{{- '<|im_end|>\n' }}
|
| 73 |
+
{%- endif %}
|
| 74 |
+
{%- endif %}
|
| 75 |
+
{%- for message in loop_messages %}
|
| 76 |
+
{%- if message.role == "assistant" and message.tool_calls is defined and message.tool_calls is iterable and message.tool_calls | length > 0 %}
|
| 77 |
+
{{- '<|im_start|>' + message.role }}
|
| 78 |
+
{%- if message.content is defined and message.content is string and message.content | trim | length > 0 %}
|
| 79 |
+
{{- '\n' + message.content | trim + '\n' }}
|
| 80 |
+
{%- endif %}
|
| 81 |
+
{%- for tool_call in message.tool_calls %}
|
| 82 |
+
{%- if tool_call.function is defined %}
|
| 83 |
+
{%- set tool_call = tool_call.function %}
|
| 84 |
+
{%- endif %}
|
| 85 |
+
{{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
|
| 86 |
+
{%- if tool_call.arguments is defined %}
|
| 87 |
+
{%- for args_name, args_value in tool_call.arguments|items %}
|
| 88 |
+
{{- '<parameter=' + args_name + '>\n' }}
|
| 89 |
+
{%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}
|
| 90 |
+
{{- args_value }}
|
| 91 |
+
{{- '\n</parameter>\n' }}
|
| 92 |
+
{%- endfor %}
|
| 93 |
+
{%- endif %}
|
| 94 |
+
{{- '</function>\n</tool_call>' }}
|
| 95 |
+
{%- endfor %}
|
| 96 |
+
{{- '<|im_end|>\n' }}
|
| 97 |
+
{%- elif message.role == "user" or message.role == "system" or message.role == "assistant" %}
|
| 98 |
+
{{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
|
| 99 |
+
{%- elif message.role == "tool" %}
|
| 100 |
+
{%- if loop.previtem and loop.previtem.role != "tool" %}
|
| 101 |
+
{{- '<|im_start|>user\n' }}
|
| 102 |
+
{%- endif %}
|
| 103 |
+
{{- '<tool_response>\n' }}
|
| 104 |
+
{{- message.content }}
|
| 105 |
+
{{- '\n</tool_response>\n' }}
|
| 106 |
+
{%- if not loop.last and loop.nextitem.role != "tool" %}
|
| 107 |
+
{{- '<|im_end|>\n' }}
|
| 108 |
+
{%- elif loop.last %}
|
| 109 |
+
{{- '<|im_end|>\n' }}
|
| 110 |
+
{%- endif %}
|
| 111 |
+
{%- else %}
|
| 112 |
+
{{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>\n' }}
|
| 113 |
+
{%- endif %}
|
| 114 |
+
{%- endfor %}
|
| 115 |
+
{%- if add_generation_prompt %}
|
| 116 |
+
{{- '<|im_start|>assistant\n' }}
|
| 117 |
+
{%- endif %}
|
config.json
ADDED
|
@@ -0,0 +1,156 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen3MoeForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"decoder_sparse_step": 1,
|
| 8 |
+
"eos_token_id": 151645,
|
| 9 |
+
"head_dim": 128,
|
| 10 |
+
"hidden_act": "silu",
|
| 11 |
+
"hidden_size": 6144,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 8192,
|
| 14 |
+
"max_position_embeddings": 262144,
|
| 15 |
+
"max_window_layers": 62,
|
| 16 |
+
"mlp_only_layers": [],
|
| 17 |
+
"model_type": "qwen3_moe",
|
| 18 |
+
"moe_intermediate_size": 2560,
|
| 19 |
+
"norm_topk_prob": true,
|
| 20 |
+
"num_attention_heads": 96,
|
| 21 |
+
"num_experts": 160,
|
| 22 |
+
"num_experts_per_tok": 8,
|
| 23 |
+
"num_hidden_layers": 62,
|
| 24 |
+
"num_key_value_heads": 8,
|
| 25 |
+
"output_router_logits": false,
|
| 26 |
+
"qkv_bias": false,
|
| 27 |
+
"quantization_config": {
|
| 28 |
+
"algo_config": null,
|
| 29 |
+
"exclude": [
|
| 30 |
+
"model.layers.0.mlp.gate",
|
| 31 |
+
"model.layers.1.mlp.gate",
|
| 32 |
+
"model.layers.2.mlp.gate",
|
| 33 |
+
"model.layers.3.mlp.gate",
|
| 34 |
+
"model.layers.4.mlp.gate",
|
| 35 |
+
"model.layers.5.mlp.gate",
|
| 36 |
+
"model.layers.6.mlp.gate",
|
| 37 |
+
"model.layers.7.mlp.gate",
|
| 38 |
+
"model.layers.8.mlp.gate",
|
| 39 |
+
"model.layers.9.mlp.gate",
|
| 40 |
+
"model.layers.10.mlp.gate",
|
| 41 |
+
"model.layers.11.mlp.gate",
|
| 42 |
+
"model.layers.12.mlp.gate",
|
| 43 |
+
"model.layers.13.mlp.gate",
|
| 44 |
+
"model.layers.14.mlp.gate",
|
| 45 |
+
"model.layers.15.mlp.gate",
|
| 46 |
+
"model.layers.16.mlp.gate",
|
| 47 |
+
"model.layers.17.mlp.gate",
|
| 48 |
+
"model.layers.18.mlp.gate",
|
| 49 |
+
"model.layers.19.mlp.gate",
|
| 50 |
+
"model.layers.20.mlp.gate",
|
| 51 |
+
"model.layers.21.mlp.gate",
|
| 52 |
+
"model.layers.22.mlp.gate",
|
| 53 |
+
"model.layers.23.mlp.gate",
|
| 54 |
+
"model.layers.24.mlp.gate",
|
| 55 |
+
"model.layers.25.mlp.gate",
|
| 56 |
+
"model.layers.26.mlp.gate",
|
| 57 |
+
"model.layers.27.mlp.gate",
|
| 58 |
+
"model.layers.28.mlp.gate",
|
| 59 |
+
"model.layers.29.mlp.gate",
|
| 60 |
+
"model.layers.30.mlp.gate",
|
| 61 |
+
"model.layers.31.mlp.gate",
|
| 62 |
+
"model.layers.32.mlp.gate",
|
| 63 |
+
"model.layers.33.mlp.gate",
|
| 64 |
+
"model.layers.34.mlp.gate",
|
| 65 |
+
"model.layers.35.mlp.gate",
|
| 66 |
+
"model.layers.36.mlp.gate",
|
| 67 |
+
"model.layers.37.mlp.gate",
|
| 68 |
+
"model.layers.38.mlp.gate",
|
| 69 |
+
"model.layers.39.mlp.gate",
|
| 70 |
+
"model.layers.40.mlp.gate",
|
| 71 |
+
"model.layers.41.mlp.gate",
|
| 72 |
+
"model.layers.42.mlp.gate",
|
| 73 |
+
"model.layers.43.mlp.gate",
|
| 74 |
+
"model.layers.44.mlp.gate",
|
| 75 |
+
"model.layers.45.mlp.gate",
|
| 76 |
+
"model.layers.46.mlp.gate",
|
| 77 |
+
"model.layers.47.mlp.gate",
|
| 78 |
+
"model.layers.48.mlp.gate",
|
| 79 |
+
"model.layers.49.mlp.gate",
|
| 80 |
+
"model.layers.50.mlp.gate",
|
| 81 |
+
"model.layers.51.mlp.gate",
|
| 82 |
+
"model.layers.52.mlp.gate",
|
| 83 |
+
"model.layers.53.mlp.gate",
|
| 84 |
+
"model.layers.54.mlp.gate",
|
| 85 |
+
"model.layers.55.mlp.gate",
|
| 86 |
+
"model.layers.56.mlp.gate",
|
| 87 |
+
"model.layers.57.mlp.gate",
|
| 88 |
+
"model.layers.58.mlp.gate",
|
| 89 |
+
"model.layers.59.mlp.gate",
|
| 90 |
+
"model.layers.60.mlp.gate",
|
| 91 |
+
"model.layers.61.mlp.gate",
|
| 92 |
+
"lm_head"
|
| 93 |
+
],
|
| 94 |
+
"export": {
|
| 95 |
+
"kv_cache_group": [],
|
| 96 |
+
"min_kv_scale": 0.0,
|
| 97 |
+
"pack_method": "reorder",
|
| 98 |
+
"weight_format": "real_quantized",
|
| 99 |
+
"weight_merge_groups": null
|
| 100 |
+
},
|
| 101 |
+
"global_quant_config": {
|
| 102 |
+
"bias": null,
|
| 103 |
+
"input_tensors": {
|
| 104 |
+
"ch_axis": 1,
|
| 105 |
+
"dtype": "fp8_e4m3",
|
| 106 |
+
"group_size": null,
|
| 107 |
+
"is_dynamic": true,
|
| 108 |
+
"is_scale_quant": false,
|
| 109 |
+
"mx_element_dtype": null,
|
| 110 |
+
"observer_cls": "PerChannelMinMaxObserver",
|
| 111 |
+
"qscheme": "per_channel",
|
| 112 |
+
"round_method": null,
|
| 113 |
+
"scale_calculation_mode": null,
|
| 114 |
+
"scale_format": null,
|
| 115 |
+
"scale_type": null,
|
| 116 |
+
"symmetric": null
|
| 117 |
+
},
|
| 118 |
+
"output_tensors": null,
|
| 119 |
+
"target_device": null,
|
| 120 |
+
"weight": {
|
| 121 |
+
"ch_axis": 0,
|
| 122 |
+
"dtype": "fp8_e4m3",
|
| 123 |
+
"group_size": null,
|
| 124 |
+
"is_dynamic": false,
|
| 125 |
+
"is_scale_quant": false,
|
| 126 |
+
"mx_element_dtype": null,
|
| 127 |
+
"observer_cls": "PerChannelMinMaxObserver",
|
| 128 |
+
"qscheme": "per_channel",
|
| 129 |
+
"round_method": null,
|
| 130 |
+
"scale_calculation_mode": null,
|
| 131 |
+
"scale_format": null,
|
| 132 |
+
"scale_type": null,
|
| 133 |
+
"symmetric": null
|
| 134 |
+
}
|
| 135 |
+
},
|
| 136 |
+
"layer_quant_config": {},
|
| 137 |
+
"layer_type_quant_config": {},
|
| 138 |
+
"quant_method": "quark",
|
| 139 |
+
"quant_mode": "eager_mode",
|
| 140 |
+
"softmax_quant_spec": null,
|
| 141 |
+
"version": "0.9"
|
| 142 |
+
},
|
| 143 |
+
"rms_norm_eps": 1e-06,
|
| 144 |
+
"rope_scaling": null,
|
| 145 |
+
"rope_theta": 10000000,
|
| 146 |
+
"router_aux_loss_coef": 0.0,
|
| 147 |
+
"shared_expert_intermediate_size": 0,
|
| 148 |
+
"sliding_window": null,
|
| 149 |
+
"tie_word_embeddings": false,
|
| 150 |
+
"torch_dtype": "float32",
|
| 151 |
+
"transformers_version": "4.55.4",
|
| 152 |
+
"use_cache": true,
|
| 153 |
+
"use_qk_norm": true,
|
| 154 |
+
"use_sliding_window": false,
|
| 155 |
+
"vocab_size": 151936
|
| 156 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_sample": true,
|
| 3 |
+
"eos_token_id": [
|
| 4 |
+
151645,
|
| 5 |
+
151643
|
| 6 |
+
],
|
| 7 |
+
"pad_token_id": 151643,
|
| 8 |
+
"repetition_penalty": 1.05,
|
| 9 |
+
"temperature": 0.7,
|
| 10 |
+
"top_k": 20,
|
| 11 |
+
"top_p": 0.8,
|
| 12 |
+
"transformers_version": "4.55.4"
|
| 13 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
model-00001-of-00098.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:99ea7441e91ce086ffa2fd944d9138bd77c13f755b9226f6d300dfd69330cc29
|
| 3 |
+
size 4987903264
|
model-00002-of-00098.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a4e942a1848c36b88f430e24bf8f98a23e0346f7d681db3aa77f6d13076663aa
|
| 3 |
+
size 4990808040
|
model-00003-of-00098.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:02abbbaaf6d2679744cdfbb59301f3ae5fc304cf69bef374e151337479b89bed
|
| 3 |
+
size 4985278176
|
model-00004-of-00098.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:194b1f014129964ce62ffa7028e55e1565b2b1579e8b50effe3c552e0856456e
|
| 3 |
+
size 4985278352
|
model-00005-of-00098.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2adc482c3d8f68b172f921ad9181fbbd38e4a9f54ff9a31d944725011fff481d
|
| 3 |
+
size 4990822320
|
model-00006-of-00098.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6e66240b50e38efbd918492bfe8db3cd7133670501480fc28923044eaa380537
|
| 3 |
+
size 4985278240
|
model-00007-of-00098.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0fc8d9518518746788a3d0b91c8bc0233eeef2980dfdd60ccc3b9cd55e3863e2
|
| 3 |
+
size 4985278392
|
model-00008-of-00098.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2a9a28f780445219fb22679766de8cff24a12606a3217827e0caa89c897e28c6
|
| 3 |
+
size 4990822208
|
model-00009-of-00098.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:12ce3af9e6050917a29dec6b1468137e4401ce8850f22265f8d95d84592ad57d
|
| 3 |
+
size 4985278304
|
model-00010-of-00098.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7cb9416ef334b4f7a13243a755133250d09476d6e1bbb1750af50250cdfef4c4
|
| 3 |
+
size 4990808200
|
model-00011-of-00098.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7da89d23767e39703ba2d4593d8b217a3efbc8d3cb3ab36d2dca235a50ca8f78
|
| 3 |
+
size 4985278016
|
model-00012-of-00098.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5c7b18b0a95cdc4f2e20361a331c5b47d4843b9238d3228ff791bed611e797d2
|
| 3 |
+
size 4985278352
|
model-00013-of-00098.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0e3fea972e406699c588668500020f1093dea685bd9ea92a1f46447110c9676e
|
| 3 |
+
size 4990822480
|
model-00014-of-00098.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e6a8e8def7a4b304369ffbd7adedaba37d9f4b9b65a9d834252e6831b6352945
|
| 3 |
+
size 4985278080
|
model-00015-of-00098.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:076f8dc44b64a945cae96165107daacdfa19c3c19ad8e4c10d912eee27ec7957
|
| 3 |
+
size 4985278352
|
model-00016-of-00098.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f58d05d1e4109c511789759177c3909c889aea86db23dcd8dfad7a6798a4455c
|
| 3 |
+
size 4990822416
|
model-00017-of-00098.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:99a3e6007b2efe01a9b51277e1b6f42a8db377e8556735f6820dfb42903d9b88
|
| 3 |
+
size 4985278608
|
model-00018-of-00098.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:56a7d032f6e52a1d31e5e92884d641908ca9986deb34f6655c0624e4af86bb25
|
| 3 |
+
size 4985278976
|
model-00019-of-00098.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:38b6f287019ed5221fdec16aa5a30fea25a7fb4dbfca1290377e75b49cba31ae
|
| 3 |
+
size 4990808648
|
model-00020-of-00098.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3b4efdced69fca16951be29229b63b3a3cabc3b0e4c29d4ae2cbed39f16522c6
|
| 3 |
+
size 4985278824
|
model-00021-of-00098.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:70463f4bfb4c0c8ce79a311e064cfc85909ecb3ee293e3de6e3a3c7c75350dd9
|
| 3 |
+
size 4985278984
|
model-00022-of-00098.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1926ec4140aea2f49e7aaa4b071bf59f493daac72d0c444c3387fe3236ebb64e
|
| 3 |
+
size 4990822920
|
model-00023-of-00098.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6ca4694c0f8efae39d19368755ad0f003c4519c5ab8309d6e51bfe08ce1361c8
|
| 3 |
+
size 4985278888
|
model-00024-of-00098.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6fa5544a1978ce02ef3d35367ec4985569660d01329b2f39f46826d4cbee3cad
|
| 3 |
+
size 4984547560
|
model-00025-of-00098.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6a8558c3ad4afaebd1de8c80deda1cd0160acb61c3587e40c5443708ce3782c3
|
| 3 |
+
size 4991554272
|
model-00026-of-00098.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:06afb3e972d0828d764f4be96de08cec8d41d595113ec4f7c0485ef0284107c8
|
| 3 |
+
size 4985278952
|
model-00027-of-00098.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6f3e809ddbe40f06d5c8f64aba8b72413071db709cc6ea3433c3a76902ea961f
|
| 3 |
+
size 4990808808
|
model-00028-of-00098.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f83bf0b35e6d6b93fcb8ea2e884223d61a291301fd6834027918f698c636dfc4
|
| 3 |
+
size 4985278664
|
model-00029-of-00098.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7478adae7b4e09d61289dc711cad99e679d8908ae30e8b5456235eb445e17282
|
| 3 |
+
size 4985278976
|
model-00030-of-00098.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:891dccde8899121498375e4a75c959dfd726a8d508ec2c35838a9e58fa43c4cb
|
| 3 |
+
size 4990823088
|
model-00031-of-00098.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8f036bf877d94f2bd51e7f5d48334f62cecd21f765b94948e70f3154c634cf40
|
| 3 |
+
size 4985278728
|
model-00032-of-00098.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:06561f31a842d72c8df5ea5d22c7435163a8c2d565e6594b32031239cb936e0a
|
| 3 |
+
size 4985278976
|
model-00033-of-00098.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1de387201a79a39985a532b20f205eafa0ed76ecb8c51a024f8aed4e8780f7c3
|
| 3 |
+
size 4990823024
|
model-00034-of-00098.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b69055bc3c1ba2b7aa59f7a5ac966bca27356f1f20845473678aefe0ada608c9
|
| 3 |
+
size 4985278792
|
model-00035-of-00098.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4faf082b189e3b71e9581fe81bef6108634ff9a122ca65dd3588b4d797972bf7
|
| 3 |
+
size 4985278976
|
model-00036-of-00098.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:966f37bbdf1f45e26cbd0de15befd02c15a282b440d00be36bdf6f921a1f531c
|
| 3 |
+
size 4990808624
|
model-00037-of-00098.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0aa95ca3688777792e0611545be4ef24c055dbcff20f912ae791d1709e6fd161
|
| 3 |
+
size 4985278848
|
model-00038-of-00098.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5f98b980c26e42efd78ccf946d288b8293d1a518f66597cca7a8ce809f044f3a
|
| 3 |
+
size 4985279008
|
model-00039-of-00098.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:46c337186a43a7469864117cc891c0904000f4923a296ed6cd1ee722a133b2b6
|
| 3 |
+
size 4990822872
|
model-00040-of-00098.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6314e1d80ebb412e5869515f4c31ebdc14afaf85791e142a3a855a96a21f0b0f
|
| 3 |
+
size 4985278912
|
model-00041-of-00098.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9a9083807a0719f685b13790ffc1c2de6bd04a620847ad242259df7c98374c15
|
| 3 |
+
size 4990823184
|
model-00042-of-00098.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ab1a6753f57a0a1f6f3b10730d64536cd4fac8278b34fec086f34b13d1df46b5
|
| 3 |
+
size 4985278624
|
model-00043-of-00098.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2652504a54dcfab86f62e0aa966f3ae176becf41ff3e6cc9719c949caef53aa3
|
| 3 |
+
size 4985278976
|
model-00044-of-00098.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e0bc94c0af69314cbb39ff670795b771d2c9cb43ff198fb2dc2eede5b5eacb87
|
| 3 |
+
size 4990808784
|