Add GLM-4.7-PRISM AWQ (llmcompressor compressed-tensors) checkpoint
Browse files- .gitattributes +2 -0
- chat_template.jinja +86 -0
- config.json +347 -0
- generation_config.json +10 -0
- model-00001-of-00038.safetensors +3 -0
- model-00002-of-00038.safetensors +3 -0
- model-00003-of-00038.safetensors +3 -0
- model-00004-of-00038.safetensors +3 -0
- model-00005-of-00038.safetensors +3 -0
- model-00006-of-00038.safetensors +3 -0
- model-00007-of-00038.safetensors +3 -0
- model-00008-of-00038.safetensors +3 -0
- model-00009-of-00038.safetensors +3 -0
- model-00010-of-00038.safetensors +3 -0
- model-00011-of-00038.safetensors +3 -0
- model-00012-of-00038.safetensors +3 -0
- model-00013-of-00038.safetensors +3 -0
- model-00014-of-00038.safetensors +3 -0
- model-00015-of-00038.safetensors +3 -0
- model-00016-of-00038.safetensors +3 -0
- model-00017-of-00038.safetensors +3 -0
- model-00018-of-00038.safetensors +3 -0
- model-00019-of-00038.safetensors +3 -0
- model-00020-of-00038.safetensors +3 -0
- model-00021-of-00038.safetensors +3 -0
- model-00022-of-00038.safetensors +3 -0
- model-00023-of-00038.safetensors +3 -0
- model-00024-of-00038.safetensors +3 -0
- model-00025-of-00038.safetensors +3 -0
- model-00026-of-00038.safetensors +3 -0
- model-00027-of-00038.safetensors +3 -0
- model-00028-of-00038.safetensors +3 -0
- model-00029-of-00038.safetensors +3 -0
- model-00030-of-00038.safetensors +3 -0
- model-00031-of-00038.safetensors +3 -0
- model-00032-of-00038.safetensors +3 -0
- model-00033-of-00038.safetensors +3 -0
- model-00034-of-00038.safetensors +3 -0
- model-00035-of-00038.safetensors +3 -0
- model-00036-of-00038.safetensors +3 -0
- model-00037-of-00038.safetensors +3 -0
- model-00038-of-00038.safetensors +3 -0
- model.safetensors.index.json +3 -0
- recipe.yaml +17 -0
- special_tokens_map.json +40 -0
- tokenizer.json +3 -0
- tokenizer_config.json +326 -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 +1,347 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"quantization_config": {
|
| 34 |
+
"config_groups": {
|
| 35 |
+
"group_0": {
|
| 36 |
+
"format": "pack-quantized",
|
| 37 |
+
"input_activations": null,
|
| 38 |
+
"output_activations": null,
|
| 39 |
+
"targets": [
|
| 40 |
+
"Linear"
|
| 41 |
+
],
|
| 42 |
+
"weights": {
|
| 43 |
+
"actorder": null,
|
| 44 |
+
"block_structure": null,
|
| 45 |
+
"dynamic": false,
|
| 46 |
+
"group_size": 128,
|
| 47 |
+
"num_bits": 4,
|
| 48 |
+
"observer": "minmax",
|
| 49 |
+
"observer_kwargs": {},
|
| 50 |
+
"scale_dtype": null,
|
| 51 |
+
"strategy": "group",
|
| 52 |
+
"symmetric": false,
|
| 53 |
+
"type": "int",
|
| 54 |
+
"zp_dtype": "torch.int8"
|
| 55 |
+
}
|
| 56 |
+
}
|
| 57 |
+
},
|
| 58 |
+
"format": "pack-quantized",
|
| 59 |
+
"global_compression_ratio": null,
|
| 60 |
+
"ignore": [
|
| 61 |
+
"model.layers.3.mlp.shared_experts.gate_proj",
|
| 62 |
+
"model.layers.3.mlp.shared_experts.up_proj",
|
| 63 |
+
"model.layers.3.mlp.shared_experts.down_proj",
|
| 64 |
+
"model.layers.4.mlp.shared_experts.gate_proj",
|
| 65 |
+
"model.layers.4.mlp.shared_experts.up_proj",
|
| 66 |
+
"model.layers.4.mlp.shared_experts.down_proj",
|
| 67 |
+
"model.layers.5.mlp.shared_experts.gate_proj",
|
| 68 |
+
"model.layers.5.mlp.shared_experts.up_proj",
|
| 69 |
+
"model.layers.5.mlp.shared_experts.down_proj",
|
| 70 |
+
"model.layers.6.mlp.shared_experts.gate_proj",
|
| 71 |
+
"model.layers.6.mlp.shared_experts.up_proj",
|
| 72 |
+
"model.layers.6.mlp.shared_experts.down_proj",
|
| 73 |
+
"model.layers.7.mlp.shared_experts.gate_proj",
|
| 74 |
+
"model.layers.7.mlp.shared_experts.up_proj",
|
| 75 |
+
"model.layers.7.mlp.shared_experts.down_proj",
|
| 76 |
+
"model.layers.8.mlp.shared_experts.gate_proj",
|
| 77 |
+
"model.layers.8.mlp.shared_experts.up_proj",
|
| 78 |
+
"model.layers.8.mlp.shared_experts.down_proj",
|
| 79 |
+
"model.layers.9.mlp.shared_experts.gate_proj",
|
| 80 |
+
"model.layers.9.mlp.shared_experts.up_proj",
|
| 81 |
+
"model.layers.9.mlp.shared_experts.down_proj",
|
| 82 |
+
"model.layers.10.mlp.shared_experts.gate_proj",
|
| 83 |
+
"model.layers.10.mlp.shared_experts.up_proj",
|
| 84 |
+
"model.layers.10.mlp.shared_experts.down_proj",
|
| 85 |
+
"model.layers.11.mlp.shared_experts.gate_proj",
|
| 86 |
+
"model.layers.11.mlp.shared_experts.up_proj",
|
| 87 |
+
"model.layers.11.mlp.shared_experts.down_proj",
|
| 88 |
+
"model.layers.12.mlp.shared_experts.gate_proj",
|
| 89 |
+
"model.layers.12.mlp.shared_experts.up_proj",
|
| 90 |
+
"model.layers.12.mlp.shared_experts.down_proj",
|
| 91 |
+
"model.layers.13.mlp.shared_experts.gate_proj",
|
| 92 |
+
"model.layers.13.mlp.shared_experts.up_proj",
|
| 93 |
+
"model.layers.13.mlp.shared_experts.down_proj",
|
| 94 |
+
"model.layers.14.mlp.shared_experts.gate_proj",
|
| 95 |
+
"model.layers.14.mlp.shared_experts.up_proj",
|
| 96 |
+
"model.layers.14.mlp.shared_experts.down_proj",
|
| 97 |
+
"model.layers.15.mlp.shared_experts.gate_proj",
|
| 98 |
+
"model.layers.15.mlp.shared_experts.up_proj",
|
| 99 |
+
"model.layers.15.mlp.shared_experts.down_proj",
|
| 100 |
+
"model.layers.16.mlp.shared_experts.gate_proj",
|
| 101 |
+
"model.layers.16.mlp.shared_experts.up_proj",
|
| 102 |
+
"model.layers.16.mlp.shared_experts.down_proj",
|
| 103 |
+
"model.layers.17.mlp.shared_experts.gate_proj",
|
| 104 |
+
"model.layers.17.mlp.shared_experts.up_proj",
|
| 105 |
+
"model.layers.17.mlp.shared_experts.down_proj",
|
| 106 |
+
"model.layers.18.mlp.shared_experts.gate_proj",
|
| 107 |
+
"model.layers.18.mlp.shared_experts.up_proj",
|
| 108 |
+
"model.layers.18.mlp.shared_experts.down_proj",
|
| 109 |
+
"model.layers.19.mlp.shared_experts.gate_proj",
|
| 110 |
+
"model.layers.19.mlp.shared_experts.up_proj",
|
| 111 |
+
"model.layers.19.mlp.shared_experts.down_proj",
|
| 112 |
+
"model.layers.20.mlp.shared_experts.gate_proj",
|
| 113 |
+
"model.layers.20.mlp.shared_experts.up_proj",
|
| 114 |
+
"model.layers.20.mlp.shared_experts.down_proj",
|
| 115 |
+
"model.layers.21.mlp.shared_experts.gate_proj",
|
| 116 |
+
"model.layers.21.mlp.shared_experts.up_proj",
|
| 117 |
+
"model.layers.21.mlp.shared_experts.down_proj",
|
| 118 |
+
"model.layers.22.mlp.shared_experts.gate_proj",
|
| 119 |
+
"model.layers.22.mlp.shared_experts.up_proj",
|
| 120 |
+
"model.layers.22.mlp.shared_experts.down_proj",
|
| 121 |
+
"model.layers.23.mlp.shared_experts.gate_proj",
|
| 122 |
+
"model.layers.23.mlp.shared_experts.up_proj",
|
| 123 |
+
"model.layers.23.mlp.shared_experts.down_proj",
|
| 124 |
+
"model.layers.24.mlp.shared_experts.gate_proj",
|
| 125 |
+
"model.layers.24.mlp.shared_experts.up_proj",
|
| 126 |
+
"model.layers.24.mlp.shared_experts.down_proj",
|
| 127 |
+
"model.layers.25.mlp.shared_experts.gate_proj",
|
| 128 |
+
"model.layers.25.mlp.shared_experts.up_proj",
|
| 129 |
+
"model.layers.25.mlp.shared_experts.down_proj",
|
| 130 |
+
"model.layers.26.mlp.shared_experts.gate_proj",
|
| 131 |
+
"model.layers.26.mlp.shared_experts.up_proj",
|
| 132 |
+
"model.layers.26.mlp.shared_experts.down_proj",
|
| 133 |
+
"model.layers.27.mlp.shared_experts.gate_proj",
|
| 134 |
+
"model.layers.27.mlp.shared_experts.up_proj",
|
| 135 |
+
"model.layers.27.mlp.shared_experts.down_proj",
|
| 136 |
+
"model.layers.28.mlp.shared_experts.gate_proj",
|
| 137 |
+
"model.layers.28.mlp.shared_experts.up_proj",
|
| 138 |
+
"model.layers.28.mlp.shared_experts.down_proj",
|
| 139 |
+
"model.layers.29.mlp.shared_experts.gate_proj",
|
| 140 |
+
"model.layers.29.mlp.shared_experts.up_proj",
|
| 141 |
+
"model.layers.29.mlp.shared_experts.down_proj",
|
| 142 |
+
"model.layers.30.mlp.shared_experts.gate_proj",
|
| 143 |
+
"model.layers.30.mlp.shared_experts.up_proj",
|
| 144 |
+
"model.layers.30.mlp.shared_experts.down_proj",
|
| 145 |
+
"model.layers.31.mlp.shared_experts.gate_proj",
|
| 146 |
+
"model.layers.31.mlp.shared_experts.up_proj",
|
| 147 |
+
"model.layers.31.mlp.shared_experts.down_proj",
|
| 148 |
+
"model.layers.32.mlp.shared_experts.gate_proj",
|
| 149 |
+
"model.layers.32.mlp.shared_experts.up_proj",
|
| 150 |
+
"model.layers.32.mlp.shared_experts.down_proj",
|
| 151 |
+
"model.layers.33.mlp.shared_experts.gate_proj",
|
| 152 |
+
"model.layers.33.mlp.shared_experts.up_proj",
|
| 153 |
+
"model.layers.33.mlp.shared_experts.down_proj",
|
| 154 |
+
"model.layers.34.mlp.shared_experts.gate_proj",
|
| 155 |
+
"model.layers.34.mlp.shared_experts.up_proj",
|
| 156 |
+
"model.layers.34.mlp.shared_experts.down_proj",
|
| 157 |
+
"model.layers.35.mlp.shared_experts.gate_proj",
|
| 158 |
+
"model.layers.35.mlp.shared_experts.up_proj",
|
| 159 |
+
"model.layers.35.mlp.shared_experts.down_proj",
|
| 160 |
+
"model.layers.36.mlp.shared_experts.gate_proj",
|
| 161 |
+
"model.layers.36.mlp.shared_experts.up_proj",
|
| 162 |
+
"model.layers.36.mlp.shared_experts.down_proj",
|
| 163 |
+
"model.layers.37.mlp.shared_experts.gate_proj",
|
| 164 |
+
"model.layers.37.mlp.shared_experts.up_proj",
|
| 165 |
+
"model.layers.37.mlp.shared_experts.down_proj",
|
| 166 |
+
"model.layers.38.mlp.shared_experts.gate_proj",
|
| 167 |
+
"model.layers.38.mlp.shared_experts.up_proj",
|
| 168 |
+
"model.layers.38.mlp.shared_experts.down_proj",
|
| 169 |
+
"model.layers.39.mlp.shared_experts.gate_proj",
|
| 170 |
+
"model.layers.39.mlp.shared_experts.up_proj",
|
| 171 |
+
"model.layers.39.mlp.shared_experts.down_proj",
|
| 172 |
+
"model.layers.40.mlp.shared_experts.gate_proj",
|
| 173 |
+
"model.layers.40.mlp.shared_experts.up_proj",
|
| 174 |
+
"model.layers.40.mlp.shared_experts.down_proj",
|
| 175 |
+
"model.layers.41.mlp.shared_experts.gate_proj",
|
| 176 |
+
"model.layers.41.mlp.shared_experts.up_proj",
|
| 177 |
+
"model.layers.41.mlp.shared_experts.down_proj",
|
| 178 |
+
"model.layers.42.mlp.shared_experts.gate_proj",
|
| 179 |
+
"model.layers.42.mlp.shared_experts.up_proj",
|
| 180 |
+
"model.layers.42.mlp.shared_experts.down_proj",
|
| 181 |
+
"model.layers.43.mlp.shared_experts.gate_proj",
|
| 182 |
+
"model.layers.43.mlp.shared_experts.up_proj",
|
| 183 |
+
"model.layers.43.mlp.shared_experts.down_proj",
|
| 184 |
+
"model.layers.44.mlp.shared_experts.gate_proj",
|
| 185 |
+
"model.layers.44.mlp.shared_experts.up_proj",
|
| 186 |
+
"model.layers.44.mlp.shared_experts.down_proj",
|
| 187 |
+
"model.layers.45.mlp.shared_experts.gate_proj",
|
| 188 |
+
"model.layers.45.mlp.shared_experts.up_proj",
|
| 189 |
+
"model.layers.45.mlp.shared_experts.down_proj",
|
| 190 |
+
"model.layers.46.mlp.shared_experts.gate_proj",
|
| 191 |
+
"model.layers.46.mlp.shared_experts.up_proj",
|
| 192 |
+
"model.layers.46.mlp.shared_experts.down_proj",
|
| 193 |
+
"model.layers.47.mlp.shared_experts.gate_proj",
|
| 194 |
+
"model.layers.47.mlp.shared_experts.up_proj",
|
| 195 |
+
"model.layers.47.mlp.shared_experts.down_proj",
|
| 196 |
+
"model.layers.48.mlp.shared_experts.gate_proj",
|
| 197 |
+
"model.layers.48.mlp.shared_experts.up_proj",
|
| 198 |
+
"model.layers.48.mlp.shared_experts.down_proj",
|
| 199 |
+
"model.layers.49.mlp.shared_experts.gate_proj",
|
| 200 |
+
"model.layers.49.mlp.shared_experts.up_proj",
|
| 201 |
+
"model.layers.49.mlp.shared_experts.down_proj",
|
| 202 |
+
"model.layers.50.mlp.shared_experts.gate_proj",
|
| 203 |
+
"model.layers.50.mlp.shared_experts.up_proj",
|
| 204 |
+
"model.layers.50.mlp.shared_experts.down_proj",
|
| 205 |
+
"model.layers.51.mlp.shared_experts.gate_proj",
|
| 206 |
+
"model.layers.51.mlp.shared_experts.up_proj",
|
| 207 |
+
"model.layers.51.mlp.shared_experts.down_proj",
|
| 208 |
+
"model.layers.52.mlp.shared_experts.gate_proj",
|
| 209 |
+
"model.layers.52.mlp.shared_experts.up_proj",
|
| 210 |
+
"model.layers.52.mlp.shared_experts.down_proj",
|
| 211 |
+
"model.layers.53.mlp.shared_experts.gate_proj",
|
| 212 |
+
"model.layers.53.mlp.shared_experts.up_proj",
|
| 213 |
+
"model.layers.53.mlp.shared_experts.down_proj",
|
| 214 |
+
"model.layers.54.mlp.shared_experts.gate_proj",
|
| 215 |
+
"model.layers.54.mlp.shared_experts.up_proj",
|
| 216 |
+
"model.layers.54.mlp.shared_experts.down_proj",
|
| 217 |
+
"model.layers.55.mlp.shared_experts.gate_proj",
|
| 218 |
+
"model.layers.55.mlp.shared_experts.up_proj",
|
| 219 |
+
"model.layers.55.mlp.shared_experts.down_proj",
|
| 220 |
+
"model.layers.56.mlp.shared_experts.gate_proj",
|
| 221 |
+
"model.layers.56.mlp.shared_experts.up_proj",
|
| 222 |
+
"model.layers.56.mlp.shared_experts.down_proj",
|
| 223 |
+
"model.layers.57.mlp.shared_experts.gate_proj",
|
| 224 |
+
"model.layers.57.mlp.shared_experts.up_proj",
|
| 225 |
+
"model.layers.57.mlp.shared_experts.down_proj",
|
| 226 |
+
"model.layers.58.mlp.shared_experts.gate_proj",
|
| 227 |
+
"model.layers.58.mlp.shared_experts.up_proj",
|
| 228 |
+
"model.layers.58.mlp.shared_experts.down_proj",
|
| 229 |
+
"model.layers.59.mlp.shared_experts.gate_proj",
|
| 230 |
+
"model.layers.59.mlp.shared_experts.up_proj",
|
| 231 |
+
"model.layers.59.mlp.shared_experts.down_proj",
|
| 232 |
+
"model.layers.60.mlp.shared_experts.gate_proj",
|
| 233 |
+
"model.layers.60.mlp.shared_experts.up_proj",
|
| 234 |
+
"model.layers.60.mlp.shared_experts.down_proj",
|
| 235 |
+
"model.layers.61.mlp.shared_experts.gate_proj",
|
| 236 |
+
"model.layers.61.mlp.shared_experts.up_proj",
|
| 237 |
+
"model.layers.61.mlp.shared_experts.down_proj",
|
| 238 |
+
"model.layers.62.mlp.shared_experts.gate_proj",
|
| 239 |
+
"model.layers.62.mlp.shared_experts.up_proj",
|
| 240 |
+
"model.layers.62.mlp.shared_experts.down_proj",
|
| 241 |
+
"model.layers.63.mlp.shared_experts.gate_proj",
|
| 242 |
+
"model.layers.63.mlp.shared_experts.up_proj",
|
| 243 |
+
"model.layers.63.mlp.shared_experts.down_proj",
|
| 244 |
+
"model.layers.64.mlp.shared_experts.gate_proj",
|
| 245 |
+
"model.layers.64.mlp.shared_experts.up_proj",
|
| 246 |
+
"model.layers.64.mlp.shared_experts.down_proj",
|
| 247 |
+
"model.layers.65.mlp.shared_experts.gate_proj",
|
| 248 |
+
"model.layers.65.mlp.shared_experts.up_proj",
|
| 249 |
+
"model.layers.65.mlp.shared_experts.down_proj",
|
| 250 |
+
"model.layers.66.mlp.shared_experts.gate_proj",
|
| 251 |
+
"model.layers.66.mlp.shared_experts.up_proj",
|
| 252 |
+
"model.layers.66.mlp.shared_experts.down_proj",
|
| 253 |
+
"model.layers.67.mlp.shared_experts.gate_proj",
|
| 254 |
+
"model.layers.67.mlp.shared_experts.up_proj",
|
| 255 |
+
"model.layers.67.mlp.shared_experts.down_proj",
|
| 256 |
+
"model.layers.68.mlp.shared_experts.gate_proj",
|
| 257 |
+
"model.layers.68.mlp.shared_experts.up_proj",
|
| 258 |
+
"model.layers.68.mlp.shared_experts.down_proj",
|
| 259 |
+
"model.layers.69.mlp.shared_experts.gate_proj",
|
| 260 |
+
"model.layers.69.mlp.shared_experts.up_proj",
|
| 261 |
+
"model.layers.69.mlp.shared_experts.down_proj",
|
| 262 |
+
"model.layers.70.mlp.shared_experts.gate_proj",
|
| 263 |
+
"model.layers.70.mlp.shared_experts.up_proj",
|
| 264 |
+
"model.layers.70.mlp.shared_experts.down_proj",
|
| 265 |
+
"model.layers.71.mlp.shared_experts.gate_proj",
|
| 266 |
+
"model.layers.71.mlp.shared_experts.up_proj",
|
| 267 |
+
"model.layers.71.mlp.shared_experts.down_proj",
|
| 268 |
+
"model.layers.72.mlp.shared_experts.gate_proj",
|
| 269 |
+
"model.layers.72.mlp.shared_experts.up_proj",
|
| 270 |
+
"model.layers.72.mlp.shared_experts.down_proj",
|
| 271 |
+
"model.layers.73.mlp.shared_experts.gate_proj",
|
| 272 |
+
"model.layers.73.mlp.shared_experts.up_proj",
|
| 273 |
+
"model.layers.73.mlp.shared_experts.down_proj",
|
| 274 |
+
"model.layers.74.mlp.shared_experts.gate_proj",
|
| 275 |
+
"model.layers.74.mlp.shared_experts.up_proj",
|
| 276 |
+
"model.layers.74.mlp.shared_experts.down_proj",
|
| 277 |
+
"model.layers.75.mlp.shared_experts.gate_proj",
|
| 278 |
+
"model.layers.75.mlp.shared_experts.up_proj",
|
| 279 |
+
"model.layers.75.mlp.shared_experts.down_proj",
|
| 280 |
+
"model.layers.76.mlp.shared_experts.gate_proj",
|
| 281 |
+
"model.layers.76.mlp.shared_experts.up_proj",
|
| 282 |
+
"model.layers.76.mlp.shared_experts.down_proj",
|
| 283 |
+
"model.layers.77.mlp.shared_experts.gate_proj",
|
| 284 |
+
"model.layers.77.mlp.shared_experts.up_proj",
|
| 285 |
+
"model.layers.77.mlp.shared_experts.down_proj",
|
| 286 |
+
"model.layers.78.mlp.shared_experts.gate_proj",
|
| 287 |
+
"model.layers.78.mlp.shared_experts.up_proj",
|
| 288 |
+
"model.layers.78.mlp.shared_experts.down_proj",
|
| 289 |
+
"model.layers.79.mlp.shared_experts.gate_proj",
|
| 290 |
+
"model.layers.79.mlp.shared_experts.up_proj",
|
| 291 |
+
"model.layers.79.mlp.shared_experts.down_proj",
|
| 292 |
+
"model.layers.80.mlp.shared_experts.gate_proj",
|
| 293 |
+
"model.layers.80.mlp.shared_experts.up_proj",
|
| 294 |
+
"model.layers.80.mlp.shared_experts.down_proj",
|
| 295 |
+
"model.layers.81.mlp.shared_experts.gate_proj",
|
| 296 |
+
"model.layers.81.mlp.shared_experts.up_proj",
|
| 297 |
+
"model.layers.81.mlp.shared_experts.down_proj",
|
| 298 |
+
"model.layers.82.mlp.shared_experts.gate_proj",
|
| 299 |
+
"model.layers.82.mlp.shared_experts.up_proj",
|
| 300 |
+
"model.layers.82.mlp.shared_experts.down_proj",
|
| 301 |
+
"model.layers.83.mlp.shared_experts.gate_proj",
|
| 302 |
+
"model.layers.83.mlp.shared_experts.up_proj",
|
| 303 |
+
"model.layers.83.mlp.shared_experts.down_proj",
|
| 304 |
+
"model.layers.84.mlp.shared_experts.gate_proj",
|
| 305 |
+
"model.layers.84.mlp.shared_experts.up_proj",
|
| 306 |
+
"model.layers.84.mlp.shared_experts.down_proj",
|
| 307 |
+
"model.layers.85.mlp.shared_experts.gate_proj",
|
| 308 |
+
"model.layers.85.mlp.shared_experts.up_proj",
|
| 309 |
+
"model.layers.85.mlp.shared_experts.down_proj",
|
| 310 |
+
"model.layers.86.mlp.shared_experts.gate_proj",
|
| 311 |
+
"model.layers.86.mlp.shared_experts.up_proj",
|
| 312 |
+
"model.layers.86.mlp.shared_experts.down_proj",
|
| 313 |
+
"model.layers.87.mlp.shared_experts.gate_proj",
|
| 314 |
+
"model.layers.87.mlp.shared_experts.up_proj",
|
| 315 |
+
"model.layers.87.mlp.shared_experts.down_proj",
|
| 316 |
+
"model.layers.88.mlp.shared_experts.gate_proj",
|
| 317 |
+
"model.layers.88.mlp.shared_experts.up_proj",
|
| 318 |
+
"model.layers.88.mlp.shared_experts.down_proj",
|
| 319 |
+
"model.layers.89.mlp.shared_experts.gate_proj",
|
| 320 |
+
"model.layers.89.mlp.shared_experts.up_proj",
|
| 321 |
+
"model.layers.89.mlp.shared_experts.down_proj",
|
| 322 |
+
"model.layers.90.mlp.shared_experts.gate_proj",
|
| 323 |
+
"model.layers.90.mlp.shared_experts.up_proj",
|
| 324 |
+
"model.layers.90.mlp.shared_experts.down_proj",
|
| 325 |
+
"model.layers.91.mlp.shared_experts.gate_proj",
|
| 326 |
+
"model.layers.91.mlp.shared_experts.up_proj",
|
| 327 |
+
"model.layers.91.mlp.shared_experts.down_proj",
|
| 328 |
+
"lm_head"
|
| 329 |
+
],
|
| 330 |
+
"kv_cache_scheme": null,
|
| 331 |
+
"quant_method": "compressed-tensors",
|
| 332 |
+
"quantization_status": "compressed",
|
| 333 |
+
"sparsity_config": {},
|
| 334 |
+
"transform_config": {},
|
| 335 |
+
"version": "0.13.0"
|
| 336 |
+
},
|
| 337 |
+
"rms_norm_eps": 1e-05,
|
| 338 |
+
"rope_scaling": null,
|
| 339 |
+
"rope_theta": 1000000,
|
| 340 |
+
"routed_scaling_factor": 2.5,
|
| 341 |
+
"tie_word_embeddings": false,
|
| 342 |
+
"topk_group": 1,
|
| 343 |
+
"transformers_version": "4.57.3",
|
| 344 |
+
"use_cache": true,
|
| 345 |
+
"use_qk_norm": true,
|
| 346 |
+
"vocab_size": 151552
|
| 347 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"eos_token_id": [
|
| 4 |
+
151329,
|
| 5 |
+
151336,
|
| 6 |
+
151338
|
| 7 |
+
],
|
| 8 |
+
"pad_token_id": 151329,
|
| 9 |
+
"transformers_version": "4.57.3"
|
| 10 |
+
}
|
model-00001-of-00038.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:960f400e04450362fdca72ecd44c746fbe623d77632b63c141eabe07e9507726
|
| 3 |
+
size 4999300248
|
model-00002-of-00038.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:384889b86121b60025bb94ed73b0d1d8ab95e4178c602d923751842f8dfc8000
|
| 3 |
+
size 4999906656
|
model-00003-of-00038.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3793082a96f7d2df4fe0e0a10a63aa639a79be116ae61ce075dd823359e5d174
|
| 3 |
+
size 4997015992
|
model-00004-of-00038.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:54f76b9bb26b0b4714764348c439842c25eb0a2bb30a951c6eeffeb334007e84
|
| 3 |
+
size 4999909432
|
model-00005-of-00038.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ccd6924648477040badeb843d7c3107fb564ac7ee73d5487abd416a06e5111eb
|
| 3 |
+
size 4992937768
|
model-00006-of-00038.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:56a4888c5b6c155b7b2d995df0542b7150df8d03bc72cc3ced869453982aacad
|
| 3 |
+
size 4999907936
|
model-00007-of-00038.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e0d0808155c0bb7d4d8959168ec11068038823bb874ff9df0ebeb8cc90e9fdef
|
| 3 |
+
size 4999911392
|
model-00008-of-00038.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ef713138c92df9d083d1db11781ced5dded95ad56226328b61ac2b37428ff8de
|
| 3 |
+
size 4997020592
|
model-00009-of-00038.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d65edf9722309161ffdbfd6626483bdcd5a541c310e48bd8df7b1ac8a1772164
|
| 3 |
+
size 4999910992
|
model-00010-of-00038.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:df0fa9dec315e561ce230fb25ef5dbfeba0622950fafa81a1a13a58e68634031
|
| 3 |
+
size 4976592640
|
model-00011-of-00038.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c37511699f2602a9541535e6557a54fff2a8c4d3ec865a26f92054e3e377e554
|
| 3 |
+
size 4999907936
|
model-00012-of-00038.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bd9996b6014ca66b980289f68b7d70cb821aa1529b80467f23d2fddaf1c23e56
|
| 3 |
+
size 4999911392
|
model-00013-of-00038.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0f4393674e8a02eb3c508b911a6fb3f2d3a8d43e8ea547761d9d8a16ef868d69
|
| 3 |
+
size 4997020592
|
model-00014-of-00038.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2a0064b3a402575769fcf3f7d7247fe6dac384e14c0cd51b0d6243c80e51f69d
|
| 3 |
+
size 4999910992
|
model-00015-of-00038.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8be1ff37e8d1b74887049b3914e38113cc6f2e9e4af0560a970a1bcb5ff0b788
|
| 3 |
+
size 4976592640
|
model-00016-of-00038.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a6da0296d73f754d24cbc3faa4c912ae3f357034a7db67f890b66b0816358b74
|
| 3 |
+
size 4999907936
|
model-00017-of-00038.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:99993afe77bb03260628208eb9a8d2d34e10085177557b2700938a3d6ca88b95
|
| 3 |
+
size 4999911392
|
model-00018-of-00038.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5a5932d6c436f915d393f5dade618583cfa4a906cd8ef0c89122d278f66b7e62
|
| 3 |
+
size 4997020592
|
model-00019-of-00038.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4af0fcdc25669dc20eb80f8d73edb28d0de5a002bb530449be2b9ec43b068b69
|
| 3 |
+
size 4999910992
|
model-00020-of-00038.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:683182ba49bd18249f0c67ad9b748361559ca92664911bb3cf970232aea88c4c
|
| 3 |
+
size 4976592640
|
model-00021-of-00038.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7329a3f1a20742ad93b0ba4f9fa51b9a5dcb9973803b2e580dacb0979e423966
|
| 3 |
+
size 4999907936
|
model-00022-of-00038.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4a0288c8a0efd8def7e9baffe1f2d72e6d87120c999d6193c9892d09edd200dc
|
| 3 |
+
size 4999911392
|
model-00023-of-00038.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6299857763ecce436819056d20b7cc717848adcd8c983baf67d95a1d0b05d8a2
|
| 3 |
+
size 4997020592
|
model-00024-of-00038.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:05ae175293aa1345c957761dac67e24a8d15af552e50a946bbb7ec398692944a
|
| 3 |
+
size 4999910992
|
model-00025-of-00038.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:835753406c2fd681be16212cba49dd401277e098b9bb751fe5ff164760db85c9
|
| 3 |
+
size 4976592640
|
model-00026-of-00038.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:41a5b1219bbf901aa87e599551b9791870d2d46006d3690eb4cd2057b7e690ea
|
| 3 |
+
size 4999907936
|
model-00027-of-00038.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9a93505051a2cf28fd855c2ee0df0ae758ac11637e0e99b378c408e9b21673b7
|
| 3 |
+
size 4999911392
|
model-00028-of-00038.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:974219903eac70ac81ea5f956bd3772f5faa0bb5a4ff0014afccd6905f08165d
|
| 3 |
+
size 4997020592
|
model-00029-of-00038.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ca7010ee3329c51428c3e37db062de0c960fff54315d8e3a1c911e490adc4805
|
| 3 |
+
size 4999910992
|
model-00030-of-00038.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ea6e33e8c82148274233bc5a80245ec73f4c36d375a4c498fdd0bc4b7fc578bf
|
| 3 |
+
size 4976592640
|
model-00031-of-00038.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bcb4fdd37a210a056616978a292110fe62c4035ad3ecef724bb5e9cc5ca3cb68
|
| 3 |
+
size 4999907936
|
model-00032-of-00038.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e66b5f7e78bd311d459296a4c499e2d825252dcdf90ca0c9efe1258c839d047f
|
| 3 |
+
size 4999911392
|
model-00033-of-00038.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1c9790ef1a8c1beb3da6a68ee68b2f9b355ad2245cee74353a0df7377f3c7184
|
| 3 |
+
size 4997020592
|
model-00034-of-00038.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bb9c4614c532722313dbb05ac1427a096e169f366a6b3fb0086e7fa76855c18e
|
| 3 |
+
size 4999910992
|
model-00035-of-00038.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c7d4775a04c982b36806178ac592a2d6d327a5eb24c0881bb9b7ef17d9fcea4f
|
| 3 |
+
size 4976592640
|
model-00036-of-00038.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:434408e665b42817c05440623d087d8e7a0c0f5bd9c5a908615dd9549fa0fea7
|
| 3 |
+
size 4999907936
|
model-00037-of-00038.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:288d434501c61d2c991fea8a01168cd5c86e04cf95e05378808751cefbb137d5
|
| 3 |
+
size 4999911392
|
model-00038-of-00038.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cb8ab351a09936e6ce5b1ddd03efa6b78bd43763b7ca8b8ba99ccab90ad2762a
|
| 3 |
+
size 4000589880
|
model.safetensors.index.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:47434ee967203c5f9f62544ee4070de0283cf3fc8f5730ca71f45affdc0d5434
|
| 3 |
+
size 16987657
|
recipe.yaml
ADDED
|
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
default_stage:
|
| 2 |
+
default_modifiers:
|
| 3 |
+
AWQModifier:
|
| 4 |
+
targets: [Linear]
|
| 5 |
+
ignore: ['re:.*embed_tokens.*', 're:.*shared_experts.*', 're:.*shared_head.*', 're:.*lm_head.*']
|
| 6 |
+
scheme: W4A16_ASYM
|
| 7 |
+
mappings:
|
| 8 |
+
- smooth_layer: re:.*input_layernorm$
|
| 9 |
+
balance_layers: ['re:.*q_proj$', 're:.*k_proj$', 're:.*v_proj$']
|
| 10 |
+
- smooth_layer: re:.*v_proj$
|
| 11 |
+
balance_layers: ['re:.*o_proj$']
|
| 12 |
+
- smooth_layer: re:.*post_attention_layernorm$
|
| 13 |
+
balance_layers: ['re:.*gate_proj$', 're:.*up_proj$']
|
| 14 |
+
- smooth_layer: re:.*up_proj$
|
| 15 |
+
balance_layers: ['re:.*down_proj$']
|
| 16 |
+
duo_scaling: true
|
| 17 |
+
n_grid: 20
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|endoftext|>",
|
| 4 |
+
"[MASK]",
|
| 5 |
+
"[gMASK]",
|
| 6 |
+
"[sMASK]",
|
| 7 |
+
"<sop>",
|
| 8 |
+
"<eop>",
|
| 9 |
+
"<|system|>",
|
| 10 |
+
"<|user|>",
|
| 11 |
+
"<|assistant|>",
|
| 12 |
+
"<|observation|>",
|
| 13 |
+
"<|begin_of_image|>",
|
| 14 |
+
"<|end_of_image|>",
|
| 15 |
+
"<|begin_of_video|>",
|
| 16 |
+
"<|end_of_video|>",
|
| 17 |
+
"<|begin_of_audio|>",
|
| 18 |
+
"<|end_of_audio|>",
|
| 19 |
+
"<|begin_of_transcription|>",
|
| 20 |
+
"<|end_of_transcription|>",
|
| 21 |
+
"<|code_prefix|>",
|
| 22 |
+
"<|code_middle|>",
|
| 23 |
+
"<|code_suffix|>",
|
| 24 |
+
"/nothink"
|
| 25 |
+
],
|
| 26 |
+
"eos_token": {
|
| 27 |
+
"content": "<|endoftext|>",
|
| 28 |
+
"lstrip": false,
|
| 29 |
+
"normalized": false,
|
| 30 |
+
"rstrip": false,
|
| 31 |
+
"single_word": false
|
| 32 |
+
},
|
| 33 |
+
"pad_token": {
|
| 34 |
+
"content": "<|endoftext|>",
|
| 35 |
+
"lstrip": false,
|
| 36 |
+
"normalized": false,
|
| 37 |
+
"rstrip": false,
|
| 38 |
+
"single_word": false
|
| 39 |
+
}
|
| 40 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:75c97372a63e519d5847c4293abb99aa5132f5c94b649e6deff61478e7f7909d
|
| 3 |
+
size 19970915
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,326 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"151329": {
|
| 4 |
+
"content": "<|endoftext|>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"151330": {
|
| 12 |
+
"content": "[MASK]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"151331": {
|
| 20 |
+
"content": "[gMASK]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"151332": {
|
| 28 |
+
"content": "[sMASK]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"151333": {
|
| 36 |
+
"content": "<sop>",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
},
|
| 43 |
+
"151334": {
|
| 44 |
+
"content": "<eop>",
|
| 45 |
+
"lstrip": false,
|
| 46 |
+
"normalized": false,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"single_word": false,
|
| 49 |
+
"special": true
|
| 50 |
+
},
|
| 51 |
+
"151335": {
|
| 52 |
+
"content": "<|system|>",
|
| 53 |
+
"lstrip": false,
|
| 54 |
+
"normalized": false,
|
| 55 |
+
"rstrip": false,
|
| 56 |
+
"single_word": false,
|
| 57 |
+
"special": true
|
| 58 |
+
},
|
| 59 |
+
"151336": {
|
| 60 |
+
"content": "<|user|>",
|
| 61 |
+
"lstrip": false,
|
| 62 |
+
"normalized": false,
|
| 63 |
+
"rstrip": false,
|
| 64 |
+
"single_word": false,
|
| 65 |
+
"special": true
|
| 66 |
+
},
|
| 67 |
+
"151337": {
|
| 68 |
+
"content": "<|assistant|>",
|
| 69 |
+
"lstrip": false,
|
| 70 |
+
"normalized": false,
|
| 71 |
+
"rstrip": false,
|
| 72 |
+
"single_word": false,
|
| 73 |
+
"special": true
|
| 74 |
+
},
|
| 75 |
+
"151338": {
|
| 76 |
+
"content": "<|observation|>",
|
| 77 |
+
"lstrip": false,
|
| 78 |
+
"normalized": false,
|
| 79 |
+
"rstrip": false,
|
| 80 |
+
"single_word": false,
|
| 81 |
+
"special": true
|
| 82 |
+
},
|
| 83 |
+
"151339": {
|
| 84 |
+
"content": "<|begin_of_image|>",
|
| 85 |
+
"lstrip": false,
|
| 86 |
+
"normalized": false,
|
| 87 |
+
"rstrip": false,
|
| 88 |
+
"single_word": false,
|
| 89 |
+
"special": true
|
| 90 |
+
},
|
| 91 |
+
"151340": {
|
| 92 |
+
"content": "<|end_of_image|>",
|
| 93 |
+
"lstrip": false,
|
| 94 |
+
"normalized": false,
|
| 95 |
+
"rstrip": false,
|
| 96 |
+
"single_word": false,
|
| 97 |
+
"special": true
|
| 98 |
+
},
|
| 99 |
+
"151341": {
|
| 100 |
+
"content": "<|begin_of_video|>",
|
| 101 |
+
"lstrip": false,
|
| 102 |
+
"normalized": false,
|
| 103 |
+
"rstrip": false,
|
| 104 |
+
"single_word": false,
|
| 105 |
+
"special": true
|
| 106 |
+
},
|
| 107 |
+
"151342": {
|
| 108 |
+
"content": "<|end_of_video|>",
|
| 109 |
+
"lstrip": false,
|
| 110 |
+
"normalized": false,
|
| 111 |
+
"rstrip": false,
|
| 112 |
+
"single_word": false,
|
| 113 |
+
"special": true
|
| 114 |
+
},
|
| 115 |
+
"151343": {
|
| 116 |
+
"content": "<|begin_of_audio|>",
|
| 117 |
+
"lstrip": false,
|
| 118 |
+
"normalized": false,
|
| 119 |
+
"rstrip": false,
|
| 120 |
+
"single_word": false,
|
| 121 |
+
"special": true
|
| 122 |
+
},
|
| 123 |
+
"151344": {
|
| 124 |
+
"content": "<|end_of_audio|>",
|
| 125 |
+
"lstrip": false,
|
| 126 |
+
"normalized": false,
|
| 127 |
+
"rstrip": false,
|
| 128 |
+
"single_word": false,
|
| 129 |
+
"special": true
|
| 130 |
+
},
|
| 131 |
+
"151345": {
|
| 132 |
+
"content": "<|begin_of_transcription|>",
|
| 133 |
+
"lstrip": false,
|
| 134 |
+
"normalized": false,
|
| 135 |
+
"rstrip": false,
|
| 136 |
+
"single_word": false,
|
| 137 |
+
"special": true
|
| 138 |
+
},
|
| 139 |
+
"151346": {
|
| 140 |
+
"content": "<|end_of_transcription|>",
|
| 141 |
+
"lstrip": false,
|
| 142 |
+
"normalized": false,
|
| 143 |
+
"rstrip": false,
|
| 144 |
+
"single_word": false,
|
| 145 |
+
"special": true
|
| 146 |
+
},
|
| 147 |
+
"151347": {
|
| 148 |
+
"content": "<|code_prefix|>",
|
| 149 |
+
"lstrip": false,
|
| 150 |
+
"normalized": false,
|
| 151 |
+
"rstrip": false,
|
| 152 |
+
"single_word": false,
|
| 153 |
+
"special": true
|
| 154 |
+
},
|
| 155 |
+
"151348": {
|
| 156 |
+
"content": "<|code_middle|>",
|
| 157 |
+
"lstrip": false,
|
| 158 |
+
"normalized": false,
|
| 159 |
+
"rstrip": false,
|
| 160 |
+
"single_word": false,
|
| 161 |
+
"special": true
|
| 162 |
+
},
|
| 163 |
+
"151349": {
|
| 164 |
+
"content": "<|code_suffix|>",
|
| 165 |
+
"lstrip": false,
|
| 166 |
+
"normalized": false,
|
| 167 |
+
"rstrip": false,
|
| 168 |
+
"single_word": false,
|
| 169 |
+
"special": true
|
| 170 |
+
},
|
| 171 |
+
"151350": {
|
| 172 |
+
"content": "<think>",
|
| 173 |
+
"lstrip": false,
|
| 174 |
+
"normalized": false,
|
| 175 |
+
"rstrip": false,
|
| 176 |
+
"single_word": false,
|
| 177 |
+
"special": false
|
| 178 |
+
},
|
| 179 |
+
"151351": {
|
| 180 |
+
"content": "</think>",
|
| 181 |
+
"lstrip": false,
|
| 182 |
+
"normalized": false,
|
| 183 |
+
"rstrip": false,
|
| 184 |
+
"single_word": false,
|
| 185 |
+
"special": false
|
| 186 |
+
},
|
| 187 |
+
"151352": {
|
| 188 |
+
"content": "<tool_call>",
|
| 189 |
+
"lstrip": false,
|
| 190 |
+
"normalized": false,
|
| 191 |
+
"rstrip": false,
|
| 192 |
+
"single_word": false,
|
| 193 |
+
"special": false
|
| 194 |
+
},
|
| 195 |
+
"151353": {
|
| 196 |
+
"content": "</tool_call>",
|
| 197 |
+
"lstrip": false,
|
| 198 |
+
"normalized": false,
|
| 199 |
+
"rstrip": false,
|
| 200 |
+
"single_word": false,
|
| 201 |
+
"special": false
|
| 202 |
+
},
|
| 203 |
+
"151354": {
|
| 204 |
+
"content": "<tool_response>",
|
| 205 |
+
"lstrip": false,
|
| 206 |
+
"normalized": false,
|
| 207 |
+
"rstrip": false,
|
| 208 |
+
"single_word": false,
|
| 209 |
+
"special": false
|
| 210 |
+
},
|
| 211 |
+
"151355": {
|
| 212 |
+
"content": "</tool_response>",
|
| 213 |
+
"lstrip": false,
|
| 214 |
+
"normalized": false,
|
| 215 |
+
"rstrip": false,
|
| 216 |
+
"single_word": false,
|
| 217 |
+
"special": false
|
| 218 |
+
},
|
| 219 |
+
"151356": {
|
| 220 |
+
"content": "<arg_key>",
|
| 221 |
+
"lstrip": false,
|
| 222 |
+
"normalized": false,
|
| 223 |
+
"rstrip": false,
|
| 224 |
+
"single_word": false,
|
| 225 |
+
"special": false
|
| 226 |
+
},
|
| 227 |
+
"151357": {
|
| 228 |
+
"content": "</arg_key>",
|
| 229 |
+
"lstrip": false,
|
| 230 |
+
"normalized": false,
|
| 231 |
+
"rstrip": false,
|
| 232 |
+
"single_word": false,
|
| 233 |
+
"special": false
|
| 234 |
+
},
|
| 235 |
+
"151358": {
|
| 236 |
+
"content": "<arg_value>",
|
| 237 |
+
"lstrip": false,
|
| 238 |
+
"normalized": false,
|
| 239 |
+
"rstrip": false,
|
| 240 |
+
"single_word": false,
|
| 241 |
+
"special": false
|
| 242 |
+
},
|
| 243 |
+
"151359": {
|
| 244 |
+
"content": "</arg_value>",
|
| 245 |
+
"lstrip": false,
|
| 246 |
+
"normalized": false,
|
| 247 |
+
"rstrip": false,
|
| 248 |
+
"single_word": false,
|
| 249 |
+
"special": false
|
| 250 |
+
},
|
| 251 |
+
"151360": {
|
| 252 |
+
"content": "/nothink",
|
| 253 |
+
"lstrip": false,
|
| 254 |
+
"normalized": false,
|
| 255 |
+
"rstrip": false,
|
| 256 |
+
"single_word": false,
|
| 257 |
+
"special": true
|
| 258 |
+
},
|
| 259 |
+
"151361": {
|
| 260 |
+
"content": "<|begin_of_box|>",
|
| 261 |
+
"lstrip": false,
|
| 262 |
+
"normalized": false,
|
| 263 |
+
"rstrip": false,
|
| 264 |
+
"single_word": false,
|
| 265 |
+
"special": false
|
| 266 |
+
},
|
| 267 |
+
"151362": {
|
| 268 |
+
"content": "<|end_of_box|>",
|
| 269 |
+
"lstrip": false,
|
| 270 |
+
"normalized": false,
|
| 271 |
+
"rstrip": false,
|
| 272 |
+
"single_word": false,
|
| 273 |
+
"special": false
|
| 274 |
+
},
|
| 275 |
+
"151363": {
|
| 276 |
+
"content": "<|image|>",
|
| 277 |
+
"lstrip": false,
|
| 278 |
+
"normalized": false,
|
| 279 |
+
"rstrip": false,
|
| 280 |
+
"single_word": false,
|
| 281 |
+
"special": false
|
| 282 |
+
},
|
| 283 |
+
"151364": {
|
| 284 |
+
"content": "<|video|>",
|
| 285 |
+
"lstrip": false,
|
| 286 |
+
"normalized": false,
|
| 287 |
+
"rstrip": false,
|
| 288 |
+
"single_word": false,
|
| 289 |
+
"special": false
|
| 290 |
+
}
|
| 291 |
+
},
|
| 292 |
+
"additional_special_tokens": [
|
| 293 |
+
"<|endoftext|>",
|
| 294 |
+
"[MASK]",
|
| 295 |
+
"[gMASK]",
|
| 296 |
+
"[sMASK]",
|
| 297 |
+
"<sop>",
|
| 298 |
+
"<eop>",
|
| 299 |
+
"<|system|>",
|
| 300 |
+
"<|user|>",
|
| 301 |
+
"<|assistant|>",
|
| 302 |
+
"<|observation|>",
|
| 303 |
+
"<|begin_of_image|>",
|
| 304 |
+
"<|end_of_image|>",
|
| 305 |
+
"<|begin_of_video|>",
|
| 306 |
+
"<|end_of_video|>",
|
| 307 |
+
"<|begin_of_audio|>",
|
| 308 |
+
"<|end_of_audio|>",
|
| 309 |
+
"<|begin_of_transcription|>",
|
| 310 |
+
"<|end_of_transcription|>",
|
| 311 |
+
"<|code_prefix|>",
|
| 312 |
+
"<|code_middle|>",
|
| 313 |
+
"<|code_suffix|>",
|
| 314 |
+
"/nothink"
|
| 315 |
+
],
|
| 316 |
+
"clean_up_tokenization_spaces": false,
|
| 317 |
+
"do_lower_case": false,
|
| 318 |
+
"eos_token": "<|endoftext|>",
|
| 319 |
+
"extra_special_tokens": {},
|
| 320 |
+
"fix_mistral_regex": true,
|
| 321 |
+
"model_max_length": 128000,
|
| 322 |
+
"pad_token": "<|endoftext|>",
|
| 323 |
+
"padding_side": "left",
|
| 324 |
+
"remove_space": false,
|
| 325 |
+
"tokenizer_class": "PreTrainedTokenizerFast"
|
| 326 |
+
}
|