Upload folder using huggingface_hub
Browse filesThis view is limited to 50 files because it contains too many changes. See raw diff
- .gitattributes +2 -0
- chat_template.jinja +86 -0
- config.json +171 -0
- generation_config.json +11 -0
- hf_quant_config.json +107 -0
- model-00001-of-00044.safetensors +3 -0
- model-00002-of-00044.safetensors +3 -0
- model-00003-of-00044.safetensors +3 -0
- model-00004-of-00044.safetensors +3 -0
- model-00005-of-00044.safetensors +3 -0
- model-00006-of-00044.safetensors +3 -0
- model-00007-of-00044.safetensors +3 -0
- model-00008-of-00044.safetensors +3 -0
- model-00009-of-00044.safetensors +3 -0
- model-00010-of-00044.safetensors +3 -0
- model-00011-of-00044.safetensors +3 -0
- model-00012-of-00044.safetensors +3 -0
- model-00013-of-00044.safetensors +3 -0
- model-00014-of-00044.safetensors +3 -0
- model-00015-of-00044.safetensors +3 -0
- model-00016-of-00044.safetensors +3 -0
- model-00017-of-00044.safetensors +3 -0
- model-00018-of-00044.safetensors +3 -0
- model-00019-of-00044.safetensors +3 -0
- model-00020-of-00044.safetensors +3 -0
- model-00021-of-00044.safetensors +3 -0
- model-00022-of-00044.safetensors +3 -0
- model-00023-of-00044.safetensors +3 -0
- model-00024-of-00044.safetensors +3 -0
- model-00025-of-00044.safetensors +3 -0
- model-00026-of-00044.safetensors +3 -0
- model-00027-of-00044.safetensors +3 -0
- model-00028-of-00044.safetensors +3 -0
- model-00029-of-00044.safetensors +3 -0
- model-00030-of-00044.safetensors +3 -0
- model-00031-of-00044.safetensors +3 -0
- model-00032-of-00044.safetensors +3 -0
- model-00033-of-00044.safetensors +3 -0
- model-00034-of-00044.safetensors +3 -0
- model-00035-of-00044.safetensors +3 -0
- model-00036-of-00044.safetensors +3 -0
- model-00037-of-00044.safetensors +3 -0
- model-00038-of-00044.safetensors +3 -0
- model-00039-of-00044.safetensors +3 -0
- model-00040-of-00044.safetensors +3 -0
- model-00041-of-00044.safetensors +3 -0
- model-00042-of-00044.safetensors +3 -0
- model-00043-of-00044.safetensors +3 -0
- model-00044-of-00044.safetensors +3 -0
- model.safetensors.index.json +3 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,5 @@ 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 |
+
model.safetensors.index.json filter=lfs diff=lfs merge=lfs -text
|
| 37 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
chat_template.jinja
ADDED
|
@@ -0,0 +1,86 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
[gMASK]<sop>
|
| 2 |
+
{%- if tools -%}
|
| 3 |
+
<|system|>
|
| 4 |
+
# Tools
|
| 5 |
+
|
| 6 |
+
You may call one or more functions to assist with the user query.
|
| 7 |
+
|
| 8 |
+
You are provided with function signatures within <tools></tools> XML tags:
|
| 9 |
+
<tools>
|
| 10 |
+
{% for tool in tools %}
|
| 11 |
+
{{ tool | tojson(ensure_ascii=False) }}
|
| 12 |
+
{% endfor %}
|
| 13 |
+
</tools>
|
| 14 |
+
|
| 15 |
+
For each function call, output the function name and arguments within the following XML format:
|
| 16 |
+
<tool_call>{function-name}<arg_key>{arg-key-1}</arg_key><arg_value>{arg-value-1}</arg_value><arg_key>{arg-key-2}</arg_key><arg_value>{arg-value-2}</arg_value>...</tool_call>{%- endif -%}
|
| 17 |
+
{%- macro visible_text(content) -%}
|
| 18 |
+
{%- if content is string -%}
|
| 19 |
+
{{- content }}
|
| 20 |
+
{%- elif content is iterable and content is not mapping -%}
|
| 21 |
+
{%- for item in content -%}
|
| 22 |
+
{%- if item is mapping and item.type == 'text' -%}
|
| 23 |
+
{{- item.text }}
|
| 24 |
+
{%- elif item is string -%}
|
| 25 |
+
{{- item }}
|
| 26 |
+
{%- endif -%}
|
| 27 |
+
{%- endfor -%}
|
| 28 |
+
{%- else -%}
|
| 29 |
+
{{- content }}
|
| 30 |
+
{%- endif -%}
|
| 31 |
+
{%- endmacro -%}
|
| 32 |
+
{%- set ns = namespace(last_user_index=-1) %}
|
| 33 |
+
{%- for m in messages %}
|
| 34 |
+
{%- if m.role == 'user' %}
|
| 35 |
+
{% set ns.last_user_index = loop.index0 -%}
|
| 36 |
+
{%- endif %}
|
| 37 |
+
{%- endfor %}
|
| 38 |
+
{% for m in messages %}
|
| 39 |
+
{%- if m.role == 'user' -%}<|user|>{{ visible_text(m.content) }}
|
| 40 |
+
{%- elif m.role == 'assistant' -%}
|
| 41 |
+
<|assistant|>
|
| 42 |
+
{%- set reasoning_content = '' %}
|
| 43 |
+
{%- set content = visible_text(m.content) %}
|
| 44 |
+
{%- if m.reasoning_content is string %}
|
| 45 |
+
{%- set reasoning_content = m.reasoning_content %}
|
| 46 |
+
{%- else %}
|
| 47 |
+
{%- if '</think>' in content %}
|
| 48 |
+
{%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
|
| 49 |
+
{%- set content = content.split('</think>')[-1].lstrip('\n') %}
|
| 50 |
+
{%- endif %}
|
| 51 |
+
{%- endif %}
|
| 52 |
+
{%- if ((clear_thinking is defined and not clear_thinking) or loop.index0 > ns.last_user_index) and reasoning_content -%}
|
| 53 |
+
{{ '<think>' + reasoning_content.strip() + '</think>'}}
|
| 54 |
+
{%- else -%}
|
| 55 |
+
{{ '</think>' }}
|
| 56 |
+
{%- endif -%}
|
| 57 |
+
{%- if content.strip() -%}
|
| 58 |
+
{{ content.strip() }}
|
| 59 |
+
{%- endif -%}
|
| 60 |
+
{% if m.tool_calls %}
|
| 61 |
+
{% for tc in m.tool_calls %}
|
| 62 |
+
{%- if tc.function %}
|
| 63 |
+
{%- set tc = tc.function %}
|
| 64 |
+
{%- endif %}
|
| 65 |
+
{{- '<tool_call>' + tc.name -}}
|
| 66 |
+
{% set _args = tc.arguments %}{% for k, v in _args.items() %}<arg_key>{{ k }}</arg_key><arg_value>{{ v | tojson(ensure_ascii=False) if v is not string else v }}</arg_value>{% endfor %}</tool_call>{% endfor %}
|
| 67 |
+
{% endif %}
|
| 68 |
+
{%- elif m.role == 'tool' -%}
|
| 69 |
+
{%- if m.content is string -%}
|
| 70 |
+
{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
|
| 71 |
+
{{- '<|observation|>' }}
|
| 72 |
+
{%- endif %}
|
| 73 |
+
{{- '<tool_response>' }}
|
| 74 |
+
{{- m.content }}
|
| 75 |
+
{{- '</tool_response>' }}
|
| 76 |
+
{%- else -%}
|
| 77 |
+
<|observation|>{% for tr in m.content %}
|
| 78 |
+
<tool_response>{{ tr.output if tr.output is defined else tr }}</tool_response>{% endfor -%}
|
| 79 |
+
{% endif -%}
|
| 80 |
+
{%- elif m.role == 'system' -%}
|
| 81 |
+
<|system|>{{ visible_text(m.content) }}
|
| 82 |
+
{%- endif -%}
|
| 83 |
+
{%- endfor -%}
|
| 84 |
+
{%- if add_generation_prompt -%}
|
| 85 |
+
<|assistant|>{{- '</think>' if (enable_thinking is defined and not enable_thinking) else '<think>' -}}
|
| 86 |
+
{%- endif -%}
|
config.json
ADDED
|
@@ -0,0 +1,171 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Glm4MoeForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": true,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"dtype": "bfloat16",
|
| 8 |
+
"eos_token_id": [
|
| 9 |
+
151329,
|
| 10 |
+
151336,
|
| 11 |
+
151338
|
| 12 |
+
],
|
| 13 |
+
"first_k_dense_replace": 3,
|
| 14 |
+
"head_dim": 128,
|
| 15 |
+
"hidden_act": "silu",
|
| 16 |
+
"hidden_size": 5120,
|
| 17 |
+
"initializer_range": 0.02,
|
| 18 |
+
"intermediate_size": 12288,
|
| 19 |
+
"max_position_embeddings": 202752,
|
| 20 |
+
"model_type": "glm4_moe",
|
| 21 |
+
"moe_intermediate_size": 1536,
|
| 22 |
+
"n_group": 1,
|
| 23 |
+
"n_routed_experts": 160,
|
| 24 |
+
"n_shared_experts": 1,
|
| 25 |
+
"norm_topk_prob": true,
|
| 26 |
+
"num_attention_heads": 96,
|
| 27 |
+
"num_experts_per_tok": 8,
|
| 28 |
+
"num_hidden_layers": 92,
|
| 29 |
+
"num_key_value_heads": 8,
|
| 30 |
+
"num_nextn_predict_layers": 1,
|
| 31 |
+
"pad_token_id": 151329,
|
| 32 |
+
"partial_rotary_factor": 0.5,
|
| 33 |
+
"rms_norm_eps": 1e-05,
|
| 34 |
+
"rope_scaling": null,
|
| 35 |
+
"rope_theta": 1000000,
|
| 36 |
+
"routed_scaling_factor": 2.5,
|
| 37 |
+
"tie_word_embeddings": false,
|
| 38 |
+
"topk_group": 1,
|
| 39 |
+
"transformers_version": "4.57.1",
|
| 40 |
+
"use_cache": true,
|
| 41 |
+
"use_qk_norm": true,
|
| 42 |
+
"vocab_size": 151552,
|
| 43 |
+
"quantization_config": {
|
| 44 |
+
"config_groups": {
|
| 45 |
+
"group_0": {
|
| 46 |
+
"input_activations": {
|
| 47 |
+
"dynamic": false,
|
| 48 |
+
"num_bits": 4,
|
| 49 |
+
"type": "float",
|
| 50 |
+
"group_size": 16
|
| 51 |
+
},
|
| 52 |
+
"weights": {
|
| 53 |
+
"dynamic": false,
|
| 54 |
+
"num_bits": 4,
|
| 55 |
+
"type": "float",
|
| 56 |
+
"group_size": 16
|
| 57 |
+
},
|
| 58 |
+
"targets": [
|
| 59 |
+
"Linear"
|
| 60 |
+
]
|
| 61 |
+
}
|
| 62 |
+
},
|
| 63 |
+
"ignore": [
|
| 64 |
+
"lm_head",
|
| 65 |
+
"model.layers.0.self_attn*",
|
| 66 |
+
"model.layers.1.self_attn*",
|
| 67 |
+
"model.layers.10.self_attn*",
|
| 68 |
+
"model.layers.11.self_attn*",
|
| 69 |
+
"model.layers.12.self_attn*",
|
| 70 |
+
"model.layers.13.self_attn*",
|
| 71 |
+
"model.layers.14.self_attn*",
|
| 72 |
+
"model.layers.15.self_attn*",
|
| 73 |
+
"model.layers.16.self_attn*",
|
| 74 |
+
"model.layers.17.self_attn*",
|
| 75 |
+
"model.layers.18.self_attn*",
|
| 76 |
+
"model.layers.19.self_attn*",
|
| 77 |
+
"model.layers.2.self_attn*",
|
| 78 |
+
"model.layers.20.self_attn*",
|
| 79 |
+
"model.layers.21.self_attn*",
|
| 80 |
+
"model.layers.22.self_attn*",
|
| 81 |
+
"model.layers.23.self_attn*",
|
| 82 |
+
"model.layers.24.self_attn*",
|
| 83 |
+
"model.layers.25.self_attn*",
|
| 84 |
+
"model.layers.26.self_attn*",
|
| 85 |
+
"model.layers.27.self_attn*",
|
| 86 |
+
"model.layers.28.self_attn*",
|
| 87 |
+
"model.layers.29.self_attn*",
|
| 88 |
+
"model.layers.3.self_attn*",
|
| 89 |
+
"model.layers.30.self_attn*",
|
| 90 |
+
"model.layers.31.self_attn*",
|
| 91 |
+
"model.layers.32.self_attn*",
|
| 92 |
+
"model.layers.33.self_attn*",
|
| 93 |
+
"model.layers.34.self_attn*",
|
| 94 |
+
"model.layers.35.self_attn*",
|
| 95 |
+
"model.layers.36.self_attn*",
|
| 96 |
+
"model.layers.37.self_attn*",
|
| 97 |
+
"model.layers.38.self_attn*",
|
| 98 |
+
"model.layers.39.self_attn*",
|
| 99 |
+
"model.layers.4.self_attn*",
|
| 100 |
+
"model.layers.40.self_attn*",
|
| 101 |
+
"model.layers.41.self_attn*",
|
| 102 |
+
"model.layers.42.self_attn*",
|
| 103 |
+
"model.layers.43.self_attn*",
|
| 104 |
+
"model.layers.44.self_attn*",
|
| 105 |
+
"model.layers.45.self_attn*",
|
| 106 |
+
"model.layers.46.self_attn*",
|
| 107 |
+
"model.layers.47.self_attn*",
|
| 108 |
+
"model.layers.48.self_attn*",
|
| 109 |
+
"model.layers.49.self_attn*",
|
| 110 |
+
"model.layers.5.self_attn*",
|
| 111 |
+
"model.layers.50.self_attn*",
|
| 112 |
+
"model.layers.51.self_attn*",
|
| 113 |
+
"model.layers.52.self_attn*",
|
| 114 |
+
"model.layers.53.self_attn*",
|
| 115 |
+
"model.layers.54.self_attn*",
|
| 116 |
+
"model.layers.55.self_attn*",
|
| 117 |
+
"model.layers.56.self_attn*",
|
| 118 |
+
"model.layers.57.self_attn*",
|
| 119 |
+
"model.layers.58.self_attn*",
|
| 120 |
+
"model.layers.59.self_attn*",
|
| 121 |
+
"model.layers.6.self_attn*",
|
| 122 |
+
"model.layers.60.self_attn*",
|
| 123 |
+
"model.layers.61.self_attn*",
|
| 124 |
+
"model.layers.62.self_attn*",
|
| 125 |
+
"model.layers.63.self_attn*",
|
| 126 |
+
"model.layers.64.self_attn*",
|
| 127 |
+
"model.layers.65.self_attn*",
|
| 128 |
+
"model.layers.66.self_attn*",
|
| 129 |
+
"model.layers.67.self_attn*",
|
| 130 |
+
"model.layers.68.self_attn*",
|
| 131 |
+
"model.layers.69.self_attn*",
|
| 132 |
+
"model.layers.7.self_attn*",
|
| 133 |
+
"model.layers.70.self_attn*",
|
| 134 |
+
"model.layers.71.self_attn*",
|
| 135 |
+
"model.layers.72.self_attn*",
|
| 136 |
+
"model.layers.73.self_attn*",
|
| 137 |
+
"model.layers.74.self_attn*",
|
| 138 |
+
"model.layers.75.self_attn*",
|
| 139 |
+
"model.layers.76.self_attn*",
|
| 140 |
+
"model.layers.77.self_attn*",
|
| 141 |
+
"model.layers.78.self_attn*",
|
| 142 |
+
"model.layers.79.self_attn*",
|
| 143 |
+
"model.layers.8.self_attn*",
|
| 144 |
+
"model.layers.80.self_attn*",
|
| 145 |
+
"model.layers.81.self_attn*",
|
| 146 |
+
"model.layers.82.self_attn*",
|
| 147 |
+
"model.layers.83.self_attn*",
|
| 148 |
+
"model.layers.84.self_attn*",
|
| 149 |
+
"model.layers.85.self_attn*",
|
| 150 |
+
"model.layers.86.self_attn*",
|
| 151 |
+
"model.layers.87.self_attn*",
|
| 152 |
+
"model.layers.88.self_attn*",
|
| 153 |
+
"model.layers.89.self_attn*",
|
| 154 |
+
"model.layers.9.self_attn*",
|
| 155 |
+
"model.layers.90.self_attn*",
|
| 156 |
+
"model.layers.91.self_attn*",
|
| 157 |
+
"model.layers.92*"
|
| 158 |
+
],
|
| 159 |
+
"quant_algo": "NVFP4",
|
| 160 |
+
"kv_cache_scheme": {
|
| 161 |
+
"dynamic": false,
|
| 162 |
+
"num_bits": 8,
|
| 163 |
+
"type": "float"
|
| 164 |
+
},
|
| 165 |
+
"producer": {
|
| 166 |
+
"name": "modelopt",
|
| 167 |
+
"version": "0.41.0"
|
| 168 |
+
},
|
| 169 |
+
"quant_method": "modelopt"
|
| 170 |
+
}
|
| 171 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"eos_token_id": [
|
| 4 |
+
151329,
|
| 5 |
+
151336,
|
| 6 |
+
151338
|
| 7 |
+
],
|
| 8 |
+
"pad_token_id": 151329,
|
| 9 |
+
"temperature": 1.0,
|
| 10 |
+
"transformers_version": "4.56.2"
|
| 11 |
+
}
|
hf_quant_config.json
ADDED
|
@@ -0,0 +1,107 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"producer": {
|
| 3 |
+
"name": "modelopt",
|
| 4 |
+
"version": "0.41.0"
|
| 5 |
+
},
|
| 6 |
+
"quantization": {
|
| 7 |
+
"quant_algo": "NVFP4",
|
| 8 |
+
"kv_cache_quant_algo": "FP8",
|
| 9 |
+
"group_size": 16,
|
| 10 |
+
"exclude_modules": [
|
| 11 |
+
"lm_head",
|
| 12 |
+
"model.layers.0.self_attn*",
|
| 13 |
+
"model.layers.1.self_attn*",
|
| 14 |
+
"model.layers.10.self_attn*",
|
| 15 |
+
"model.layers.11.self_attn*",
|
| 16 |
+
"model.layers.12.self_attn*",
|
| 17 |
+
"model.layers.13.self_attn*",
|
| 18 |
+
"model.layers.14.self_attn*",
|
| 19 |
+
"model.layers.15.self_attn*",
|
| 20 |
+
"model.layers.16.self_attn*",
|
| 21 |
+
"model.layers.17.self_attn*",
|
| 22 |
+
"model.layers.18.self_attn*",
|
| 23 |
+
"model.layers.19.self_attn*",
|
| 24 |
+
"model.layers.2.self_attn*",
|
| 25 |
+
"model.layers.20.self_attn*",
|
| 26 |
+
"model.layers.21.self_attn*",
|
| 27 |
+
"model.layers.22.self_attn*",
|
| 28 |
+
"model.layers.23.self_attn*",
|
| 29 |
+
"model.layers.24.self_attn*",
|
| 30 |
+
"model.layers.25.self_attn*",
|
| 31 |
+
"model.layers.26.self_attn*",
|
| 32 |
+
"model.layers.27.self_attn*",
|
| 33 |
+
"model.layers.28.self_attn*",
|
| 34 |
+
"model.layers.29.self_attn*",
|
| 35 |
+
"model.layers.3.self_attn*",
|
| 36 |
+
"model.layers.30.self_attn*",
|
| 37 |
+
"model.layers.31.self_attn*",
|
| 38 |
+
"model.layers.32.self_attn*",
|
| 39 |
+
"model.layers.33.self_attn*",
|
| 40 |
+
"model.layers.34.self_attn*",
|
| 41 |
+
"model.layers.35.self_attn*",
|
| 42 |
+
"model.layers.36.self_attn*",
|
| 43 |
+
"model.layers.37.self_attn*",
|
| 44 |
+
"model.layers.38.self_attn*",
|
| 45 |
+
"model.layers.39.self_attn*",
|
| 46 |
+
"model.layers.4.self_attn*",
|
| 47 |
+
"model.layers.40.self_attn*",
|
| 48 |
+
"model.layers.41.self_attn*",
|
| 49 |
+
"model.layers.42.self_attn*",
|
| 50 |
+
"model.layers.43.self_attn*",
|
| 51 |
+
"model.layers.44.self_attn*",
|
| 52 |
+
"model.layers.45.self_attn*",
|
| 53 |
+
"model.layers.46.self_attn*",
|
| 54 |
+
"model.layers.47.self_attn*",
|
| 55 |
+
"model.layers.48.self_attn*",
|
| 56 |
+
"model.layers.49.self_attn*",
|
| 57 |
+
"model.layers.5.self_attn*",
|
| 58 |
+
"model.layers.50.self_attn*",
|
| 59 |
+
"model.layers.51.self_attn*",
|
| 60 |
+
"model.layers.52.self_attn*",
|
| 61 |
+
"model.layers.53.self_attn*",
|
| 62 |
+
"model.layers.54.self_attn*",
|
| 63 |
+
"model.layers.55.self_attn*",
|
| 64 |
+
"model.layers.56.self_attn*",
|
| 65 |
+
"model.layers.57.self_attn*",
|
| 66 |
+
"model.layers.58.self_attn*",
|
| 67 |
+
"model.layers.59.self_attn*",
|
| 68 |
+
"model.layers.6.self_attn*",
|
| 69 |
+
"model.layers.60.self_attn*",
|
| 70 |
+
"model.layers.61.self_attn*",
|
| 71 |
+
"model.layers.62.self_attn*",
|
| 72 |
+
"model.layers.63.self_attn*",
|
| 73 |
+
"model.layers.64.self_attn*",
|
| 74 |
+
"model.layers.65.self_attn*",
|
| 75 |
+
"model.layers.66.self_attn*",
|
| 76 |
+
"model.layers.67.self_attn*",
|
| 77 |
+
"model.layers.68.self_attn*",
|
| 78 |
+
"model.layers.69.self_attn*",
|
| 79 |
+
"model.layers.7.self_attn*",
|
| 80 |
+
"model.layers.70.self_attn*",
|
| 81 |
+
"model.layers.71.self_attn*",
|
| 82 |
+
"model.layers.72.self_attn*",
|
| 83 |
+
"model.layers.73.self_attn*",
|
| 84 |
+
"model.layers.74.self_attn*",
|
| 85 |
+
"model.layers.75.self_attn*",
|
| 86 |
+
"model.layers.76.self_attn*",
|
| 87 |
+
"model.layers.77.self_attn*",
|
| 88 |
+
"model.layers.78.self_attn*",
|
| 89 |
+
"model.layers.79.self_attn*",
|
| 90 |
+
"model.layers.8.self_attn*",
|
| 91 |
+
"model.layers.80.self_attn*",
|
| 92 |
+
"model.layers.81.self_attn*",
|
| 93 |
+
"model.layers.82.self_attn*",
|
| 94 |
+
"model.layers.83.self_attn*",
|
| 95 |
+
"model.layers.84.self_attn*",
|
| 96 |
+
"model.layers.85.self_attn*",
|
| 97 |
+
"model.layers.86.self_attn*",
|
| 98 |
+
"model.layers.87.self_attn*",
|
| 99 |
+
"model.layers.88.self_attn*",
|
| 100 |
+
"model.layers.89.self_attn*",
|
| 101 |
+
"model.layers.9.self_attn*",
|
| 102 |
+
"model.layers.90.self_attn*",
|
| 103 |
+
"model.layers.91.self_attn*",
|
| 104 |
+
"model.layers.92*"
|
| 105 |
+
]
|
| 106 |
+
}
|
| 107 |
+
}
|
model-00001-of-00044.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8c39f7efc803ccfa2f647875fffdd6fed8ed0365b614af4650e6b9773c10b320
|
| 3 |
+
size 5000150024
|
model-00002-of-00044.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c8e84c2ffeb814d3ff4bd6fa2b92f8ae8d64657a4b2affd2742a5137cb0d89b3
|
| 3 |
+
size 4921861160
|
model-00003-of-00044.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2d282fbf39cf62dbbea39e85a74a0971f43fddece9d21d703940818271b47974
|
| 3 |
+
size 4969207952
|
model-00004-of-00044.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:068a4483a887fbdc63a71a012456f582c804e701564fdefd0938c595c98570a1
|
| 3 |
+
size 4996873824
|
model-00005-of-00044.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:301c2d61e32958bbe8e86543984b560acd68ca37a48844a65467d3fdd61307e9
|
| 3 |
+
size 4999347728
|
model-00006-of-00044.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6a22253abc988074bccf81256d9043ed857d06b537c35306e785a0f8d9c6f909
|
| 3 |
+
size 4999347808
|
model-00007-of-00044.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ac1a835bb0309d72ccae04613cdac17e856a366f143e629b45856157c912fbd5
|
| 3 |
+
size 4999347800
|
model-00008-of-00044.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6dcf77b8273b1665d6801424bbfbc510e9d0632df68046856997d963823247f2
|
| 3 |
+
size 4999347808
|
model-00009-of-00044.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8bad915b1c9c1b10b018201638e23d30311b4477acc19ddda4b8988a0b453c98
|
| 3 |
+
size 4999347808
|
model-00010-of-00044.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2cc2731b43889d9a9823dd46c4e5dce2c1fe35bdba940b8eae7760294850d245
|
| 3 |
+
size 4999347800
|
model-00011-of-00044.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:edd5c2ec5d66baececa953acabcf2549e741a8abf61f97fdc73133fd46511a4d
|
| 3 |
+
size 4999347808
|
model-00012-of-00044.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d128aa164e063854b3814028c3a5704c42c29586b1d33ea10f9bde9624a850f3
|
| 3 |
+
size 4999347928
|
model-00013-of-00044.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:226113283ed63c1d8530344050ca4d5cf38a8168cf76659bbf5bc23cd94b9397
|
| 3 |
+
size 4999347960
|
model-00014-of-00044.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:10c4b6361fcdce16836b616e450b89ab87445d822d658b460e464693530f3ac4
|
| 3 |
+
size 4999348024
|
model-00015-of-00044.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:874ac3e7c39442f673167112e4165889a36d43784e5dc8084c5a51a31d66f4b0
|
| 3 |
+
size 4999348192
|
model-00016-of-00044.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e65a597176392b9032587a4e7ef34a7d65b0fa1dbbfefe44183149c70c14b1d0
|
| 3 |
+
size 4965614944
|
model-00017-of-00044.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e00c00604a5901ee25157c5776e043ed95e54978cabc9386f94fee73220c5faa
|
| 3 |
+
size 4969211856
|
model-00018-of-00044.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e89947bcc9d0b5e88abae04aeee6e88910f10c12fe266f2e070261e358651a8f
|
| 3 |
+
size 4996877712
|
model-00019-of-00044.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1ed602dc348768afd1aa68d4438f92a6fc92c7cfca0e18c5e5040e56329b0964
|
| 3 |
+
size 4999347728
|
model-00020-of-00044.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:26422eb5989fe86dc3cda8d8d6f93451c6699b0b8578198da7ba22bdeb25db08
|
| 3 |
+
size 4999347808
|
model-00021-of-00044.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8b98767c7869041f2b958e80508cebc9fc389ac5ec3b2af247e29231b01340e9
|
| 3 |
+
size 4999347800
|
model-00022-of-00044.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ae0eacc27afb4ae1b2e212a89e45c65c1aff0a5601c856679d6c25fba0729868
|
| 3 |
+
size 4999347808
|
model-00023-of-00044.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:325914f55b6e2cf3a367029e36099c022e740a2169ca9f83dfd02c33d109884d
|
| 3 |
+
size 4999347808
|
model-00024-of-00044.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1cefbf420e6b3d106e3d80686eb0dd156fd7b6ade8b0307272593b31c7977cc8
|
| 3 |
+
size 4999347800
|
model-00025-of-00044.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:33f42893a9a0b43b88ac65f25d3dfbf9d067a2b7be0d4ebd8ea73d6415d566bd
|
| 3 |
+
size 4999347808
|
model-00026-of-00044.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c0b6d3db0225511e9f28f62132b0c5cd624348eb2624c54b955b20c731162926
|
| 3 |
+
size 4999347928
|
model-00027-of-00044.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7e01ef81166589cd5ac604a577ff2197561f21da778a98b2bcd1519be161a950
|
| 3 |
+
size 4999347960
|
model-00028-of-00044.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fa2dcddfdefff92fa6ca4dd2c06b83bf2bb04d41faa9fc93251906b9b0a59b3d
|
| 3 |
+
size 4999348024
|
model-00029-of-00044.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c85b6b9961a65aeeb1e6158c0693db0dfe8775d162714ed21f30b9622a6af9fc
|
| 3 |
+
size 4999348192
|
model-00030-of-00044.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5dea0b184987260b031107e63c8478d899edd98cfa7c0c2262ef3c560a95a0b4
|
| 3 |
+
size 4965614944
|
model-00031-of-00044.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:959858266ed17686b4635b30b417e3939d49ea4afe85d98c7d195fbee953c213
|
| 3 |
+
size 4969211856
|
model-00032-of-00044.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:08b04b59da6879b1aaa3bcc60c6dfc56192342859d3f818ea6a0870c75559f3e
|
| 3 |
+
size 4996877712
|
model-00033-of-00044.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:25c61a2ef4b910109136d3319d900eeb158e7f61ad34ee7ba630d60ee3ee51c3
|
| 3 |
+
size 4999347728
|
model-00034-of-00044.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a2b864c46e32818810e13b03956baf304fd5cb0ae38e9fd17b81a3c316b878d1
|
| 3 |
+
size 4999347808
|
model-00035-of-00044.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:242c936229d08e9e8df91810c291fe29ec85f57edd505bd3bc641b4e2c0d2570
|
| 3 |
+
size 4999347800
|
model-00036-of-00044.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a179f3784b91b87e83eb66a6fa2b850e6edd623df8b601064e5fba8a9310db27
|
| 3 |
+
size 4999347808
|
model-00037-of-00044.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:796e3f3783088396453ea0d4f3768537734994d76f275b78786da789fcf97d23
|
| 3 |
+
size 4999347808
|
model-00038-of-00044.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d20e6b09a57371777ddf2b57278935b0ef7e0c8566eef8474056f9e7e456f093
|
| 3 |
+
size 4999347800
|
model-00039-of-00044.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ee800faa6c132d69c1270c6e60a778a4c08322b3d8ae244c0e1722ed69deca2c
|
| 3 |
+
size 4999347808
|
model-00040-of-00044.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b0dbbba1d224183fa2e76a94ad8b2b7cd615a5a8c8930275d1e82b7de21bb31c
|
| 3 |
+
size 4999347928
|
model-00041-of-00044.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:196df17946086145f36e302ce5c7fc36ad74ce1b316980f12b3088dd9aca1bcb
|
| 3 |
+
size 4999347960
|
model-00042-of-00044.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a687e235a38c2a4f45cace4a2e4cca3815610c3a285c911c55ac1c1572116e49
|
| 3 |
+
size 4999348024
|
model-00043-of-00044.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d0ff36e81a17536c9c0612d39281ad8d05e070fa1e142e013c088dfe83a5149b
|
| 3 |
+
size 4999348192
|
model-00044-of-00044.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fabd3e7e639765b857ec9004f23fe1322812d45b5efaeacbee164dc8b35096a7
|
| 3 |
+
size 4106327920
|
model.safetensors.index.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:46b6de452023890532d59e0ec6b8570b5ed9bc7a130c0f105debed443d576bfd
|
| 3 |
+
size 16547896
|