Add files using upload-large-folder tool
Browse files- .gitattributes +1 -0
- chat_template.jinja +86 -0
- config.json +59 -0
- generation_config.json +12 -0
- hf_quant_config.json +405 -0
- model.safetensors.index.json +0 -0
- mtp-bf16.safetensors +3 -0
- tokenizer.json +3 -0
- tokenizer_config.json +33 -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
|
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 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"GlmMoeDsaForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"dtype": "bfloat16",
|
| 8 |
+
"eos_token_id": [
|
| 9 |
+
154820,
|
| 10 |
+
154827,
|
| 11 |
+
154829
|
| 12 |
+
],
|
| 13 |
+
"ep_size": 1,
|
| 14 |
+
"first_k_dense_replace": 3,
|
| 15 |
+
"hidden_act": "silu",
|
| 16 |
+
"head_dim": 64,
|
| 17 |
+
"hidden_size": 6144,
|
| 18 |
+
"index_head_dim": 128,
|
| 19 |
+
"index_n_heads": 32,
|
| 20 |
+
"index_topk": 2048,
|
| 21 |
+
"indexer_rope_interleave": true,
|
| 22 |
+
"initializer_range": 0.02,
|
| 23 |
+
"intermediate_size": 12288,
|
| 24 |
+
"kv_lora_rank": 512,
|
| 25 |
+
"max_position_embeddings": 202752,
|
| 26 |
+
"moe_intermediate_size": 2048,
|
| 27 |
+
"moe_layer_freq": 1,
|
| 28 |
+
"model_type": "glm_moe_dsa",
|
| 29 |
+
"n_group": 1,
|
| 30 |
+
"n_routed_experts": 256,
|
| 31 |
+
"n_shared_experts": 1,
|
| 32 |
+
"norm_topk_prob": true,
|
| 33 |
+
"num_attention_heads": 64,
|
| 34 |
+
"num_experts_per_tok": 8,
|
| 35 |
+
"num_hidden_layers": 78,
|
| 36 |
+
"num_key_value_heads": 64,
|
| 37 |
+
"num_nextn_predict_layers": 1,
|
| 38 |
+
"pad_token_id": 154820,
|
| 39 |
+
"pretraining_tp": 1,
|
| 40 |
+
"q_lora_rank": 2048,
|
| 41 |
+
"qk_head_dim": 256,
|
| 42 |
+
"qk_nope_head_dim": 192,
|
| 43 |
+
"qk_rope_head_dim": 64,
|
| 44 |
+
"rms_norm_eps": 1e-05,
|
| 45 |
+
"rope_interleave": true,
|
| 46 |
+
"rope_parameters": {
|
| 47 |
+
"rope_theta": 1000000,
|
| 48 |
+
"rope_type": "default"
|
| 49 |
+
},
|
| 50 |
+
"routed_scaling_factor": 2.5,
|
| 51 |
+
"scoring_func": "sigmoid",
|
| 52 |
+
"tie_word_embeddings": false,
|
| 53 |
+
"topk_group": 1,
|
| 54 |
+
"topk_method": "noaux_tc",
|
| 55 |
+
"transformers_version": "5.0.2.dev0",
|
| 56 |
+
"use_cache": true,
|
| 57 |
+
"v_head_dim": 256,
|
| 58 |
+
"vocab_size": 154880
|
| 59 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"eos_token_id": [
|
| 4 |
+
154820,
|
| 5 |
+
154827,
|
| 6 |
+
154829
|
| 7 |
+
],
|
| 8 |
+
"pad_token_id": 154820,
|
| 9 |
+
"temperature": 1.0,
|
| 10 |
+
"top_p": 0.95,
|
| 11 |
+
"transformers_version": "5.0.2.dev0"
|
| 12 |
+
}
|
hf_quant_config.json
ADDED
|
@@ -0,0 +1,405 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"producer": {
|
| 3 |
+
"name": "modelopt",
|
| 4 |
+
"version": "0.42.0rc1.dev18+g418ee37f8.d20260219"
|
| 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.indexer*",
|
| 13 |
+
"model.layers.0.self_attn.kv_a_proj_with_mqa",
|
| 14 |
+
"model.layers.0.self_attn.kv_b_proj",
|
| 15 |
+
"model.layers.0.self_attn.q_a_proj",
|
| 16 |
+
"model.layers.0.self_attn.q_b_proj",
|
| 17 |
+
"model.layers.1.self_attn.indexer*",
|
| 18 |
+
"model.layers.1.self_attn.kv_a_proj_with_mqa",
|
| 19 |
+
"model.layers.1.self_attn.kv_b_proj",
|
| 20 |
+
"model.layers.1.self_attn.q_a_proj",
|
| 21 |
+
"model.layers.1.self_attn.q_b_proj",
|
| 22 |
+
"model.layers.10.self_attn.indexer*",
|
| 23 |
+
"model.layers.10.self_attn.kv_a_proj_with_mqa",
|
| 24 |
+
"model.layers.10.self_attn.kv_b_proj",
|
| 25 |
+
"model.layers.10.self_attn.q_a_proj",
|
| 26 |
+
"model.layers.10.self_attn.q_b_proj",
|
| 27 |
+
"model.layers.11.self_attn.indexer*",
|
| 28 |
+
"model.layers.11.self_attn.kv_a_proj_with_mqa",
|
| 29 |
+
"model.layers.11.self_attn.kv_b_proj",
|
| 30 |
+
"model.layers.11.self_attn.q_a_proj",
|
| 31 |
+
"model.layers.11.self_attn.q_b_proj",
|
| 32 |
+
"model.layers.12.self_attn.indexer*",
|
| 33 |
+
"model.layers.12.self_attn.kv_a_proj_with_mqa",
|
| 34 |
+
"model.layers.12.self_attn.kv_b_proj",
|
| 35 |
+
"model.layers.12.self_attn.q_a_proj",
|
| 36 |
+
"model.layers.12.self_attn.q_b_proj",
|
| 37 |
+
"model.layers.13.self_attn.indexer*",
|
| 38 |
+
"model.layers.13.self_attn.kv_a_proj_with_mqa",
|
| 39 |
+
"model.layers.13.self_attn.kv_b_proj",
|
| 40 |
+
"model.layers.13.self_attn.q_a_proj",
|
| 41 |
+
"model.layers.13.self_attn.q_b_proj",
|
| 42 |
+
"model.layers.14.self_attn.indexer*",
|
| 43 |
+
"model.layers.14.self_attn.kv_a_proj_with_mqa",
|
| 44 |
+
"model.layers.14.self_attn.kv_b_proj",
|
| 45 |
+
"model.layers.14.self_attn.q_a_proj",
|
| 46 |
+
"model.layers.14.self_attn.q_b_proj",
|
| 47 |
+
"model.layers.15.self_attn.indexer*",
|
| 48 |
+
"model.layers.15.self_attn.kv_a_proj_with_mqa",
|
| 49 |
+
"model.layers.15.self_attn.kv_b_proj",
|
| 50 |
+
"model.layers.15.self_attn.q_a_proj",
|
| 51 |
+
"model.layers.15.self_attn.q_b_proj",
|
| 52 |
+
"model.layers.16.self_attn.indexer*",
|
| 53 |
+
"model.layers.16.self_attn.kv_a_proj_with_mqa",
|
| 54 |
+
"model.layers.16.self_attn.kv_b_proj",
|
| 55 |
+
"model.layers.16.self_attn.q_a_proj",
|
| 56 |
+
"model.layers.16.self_attn.q_b_proj",
|
| 57 |
+
"model.layers.17.self_attn.indexer*",
|
| 58 |
+
"model.layers.17.self_attn.kv_a_proj_with_mqa",
|
| 59 |
+
"model.layers.17.self_attn.kv_b_proj",
|
| 60 |
+
"model.layers.17.self_attn.q_a_proj",
|
| 61 |
+
"model.layers.17.self_attn.q_b_proj",
|
| 62 |
+
"model.layers.18.self_attn.indexer*",
|
| 63 |
+
"model.layers.18.self_attn.kv_a_proj_with_mqa",
|
| 64 |
+
"model.layers.18.self_attn.kv_b_proj",
|
| 65 |
+
"model.layers.18.self_attn.q_a_proj",
|
| 66 |
+
"model.layers.18.self_attn.q_b_proj",
|
| 67 |
+
"model.layers.19.self_attn.indexer*",
|
| 68 |
+
"model.layers.19.self_attn.kv_a_proj_with_mqa",
|
| 69 |
+
"model.layers.19.self_attn.kv_b_proj",
|
| 70 |
+
"model.layers.19.self_attn.q_a_proj",
|
| 71 |
+
"model.layers.19.self_attn.q_b_proj",
|
| 72 |
+
"model.layers.2.self_attn.indexer*",
|
| 73 |
+
"model.layers.2.self_attn.kv_a_proj_with_mqa",
|
| 74 |
+
"model.layers.2.self_attn.kv_b_proj",
|
| 75 |
+
"model.layers.2.self_attn.q_a_proj",
|
| 76 |
+
"model.layers.2.self_attn.q_b_proj",
|
| 77 |
+
"model.layers.20.self_attn.indexer*",
|
| 78 |
+
"model.layers.20.self_attn.kv_a_proj_with_mqa",
|
| 79 |
+
"model.layers.20.self_attn.kv_b_proj",
|
| 80 |
+
"model.layers.20.self_attn.q_a_proj",
|
| 81 |
+
"model.layers.20.self_attn.q_b_proj",
|
| 82 |
+
"model.layers.21.self_attn.indexer*",
|
| 83 |
+
"model.layers.21.self_attn.kv_a_proj_with_mqa",
|
| 84 |
+
"model.layers.21.self_attn.kv_b_proj",
|
| 85 |
+
"model.layers.21.self_attn.q_a_proj",
|
| 86 |
+
"model.layers.21.self_attn.q_b_proj",
|
| 87 |
+
"model.layers.22.self_attn.indexer*",
|
| 88 |
+
"model.layers.22.self_attn.kv_a_proj_with_mqa",
|
| 89 |
+
"model.layers.22.self_attn.kv_b_proj",
|
| 90 |
+
"model.layers.22.self_attn.q_a_proj",
|
| 91 |
+
"model.layers.22.self_attn.q_b_proj",
|
| 92 |
+
"model.layers.23.self_attn.indexer*",
|
| 93 |
+
"model.layers.23.self_attn.kv_a_proj_with_mqa",
|
| 94 |
+
"model.layers.23.self_attn.kv_b_proj",
|
| 95 |
+
"model.layers.23.self_attn.q_a_proj",
|
| 96 |
+
"model.layers.23.self_attn.q_b_proj",
|
| 97 |
+
"model.layers.24.self_attn.indexer*",
|
| 98 |
+
"model.layers.24.self_attn.kv_a_proj_with_mqa",
|
| 99 |
+
"model.layers.24.self_attn.kv_b_proj",
|
| 100 |
+
"model.layers.24.self_attn.q_a_proj",
|
| 101 |
+
"model.layers.24.self_attn.q_b_proj",
|
| 102 |
+
"model.layers.25.self_attn.indexer*",
|
| 103 |
+
"model.layers.25.self_attn.kv_a_proj_with_mqa",
|
| 104 |
+
"model.layers.25.self_attn.kv_b_proj",
|
| 105 |
+
"model.layers.25.self_attn.q_a_proj",
|
| 106 |
+
"model.layers.25.self_attn.q_b_proj",
|
| 107 |
+
"model.layers.26.self_attn.indexer*",
|
| 108 |
+
"model.layers.26.self_attn.kv_a_proj_with_mqa",
|
| 109 |
+
"model.layers.26.self_attn.kv_b_proj",
|
| 110 |
+
"model.layers.26.self_attn.q_a_proj",
|
| 111 |
+
"model.layers.26.self_attn.q_b_proj",
|
| 112 |
+
"model.layers.27.self_attn.indexer*",
|
| 113 |
+
"model.layers.27.self_attn.kv_a_proj_with_mqa",
|
| 114 |
+
"model.layers.27.self_attn.kv_b_proj",
|
| 115 |
+
"model.layers.27.self_attn.q_a_proj",
|
| 116 |
+
"model.layers.27.self_attn.q_b_proj",
|
| 117 |
+
"model.layers.28.self_attn.indexer*",
|
| 118 |
+
"model.layers.28.self_attn.kv_a_proj_with_mqa",
|
| 119 |
+
"model.layers.28.self_attn.kv_b_proj",
|
| 120 |
+
"model.layers.28.self_attn.q_a_proj",
|
| 121 |
+
"model.layers.28.self_attn.q_b_proj",
|
| 122 |
+
"model.layers.29.self_attn.indexer*",
|
| 123 |
+
"model.layers.29.self_attn.kv_a_proj_with_mqa",
|
| 124 |
+
"model.layers.29.self_attn.kv_b_proj",
|
| 125 |
+
"model.layers.29.self_attn.q_a_proj",
|
| 126 |
+
"model.layers.29.self_attn.q_b_proj",
|
| 127 |
+
"model.layers.3.self_attn.indexer*",
|
| 128 |
+
"model.layers.3.self_attn.kv_a_proj_with_mqa",
|
| 129 |
+
"model.layers.3.self_attn.kv_b_proj",
|
| 130 |
+
"model.layers.3.self_attn.q_a_proj",
|
| 131 |
+
"model.layers.3.self_attn.q_b_proj",
|
| 132 |
+
"model.layers.30.self_attn.indexer*",
|
| 133 |
+
"model.layers.30.self_attn.kv_a_proj_with_mqa",
|
| 134 |
+
"model.layers.30.self_attn.kv_b_proj",
|
| 135 |
+
"model.layers.30.self_attn.q_a_proj",
|
| 136 |
+
"model.layers.30.self_attn.q_b_proj",
|
| 137 |
+
"model.layers.31.self_attn.indexer*",
|
| 138 |
+
"model.layers.31.self_attn.kv_a_proj_with_mqa",
|
| 139 |
+
"model.layers.31.self_attn.kv_b_proj",
|
| 140 |
+
"model.layers.31.self_attn.q_a_proj",
|
| 141 |
+
"model.layers.31.self_attn.q_b_proj",
|
| 142 |
+
"model.layers.32.self_attn.indexer*",
|
| 143 |
+
"model.layers.32.self_attn.kv_a_proj_with_mqa",
|
| 144 |
+
"model.layers.32.self_attn.kv_b_proj",
|
| 145 |
+
"model.layers.32.self_attn.q_a_proj",
|
| 146 |
+
"model.layers.32.self_attn.q_b_proj",
|
| 147 |
+
"model.layers.33.self_attn.indexer*",
|
| 148 |
+
"model.layers.33.self_attn.kv_a_proj_with_mqa",
|
| 149 |
+
"model.layers.33.self_attn.kv_b_proj",
|
| 150 |
+
"model.layers.33.self_attn.q_a_proj",
|
| 151 |
+
"model.layers.33.self_attn.q_b_proj",
|
| 152 |
+
"model.layers.34.self_attn.indexer*",
|
| 153 |
+
"model.layers.34.self_attn.kv_a_proj_with_mqa",
|
| 154 |
+
"model.layers.34.self_attn.kv_b_proj",
|
| 155 |
+
"model.layers.34.self_attn.q_a_proj",
|
| 156 |
+
"model.layers.34.self_attn.q_b_proj",
|
| 157 |
+
"model.layers.35.self_attn.indexer*",
|
| 158 |
+
"model.layers.35.self_attn.kv_a_proj_with_mqa",
|
| 159 |
+
"model.layers.35.self_attn.kv_b_proj",
|
| 160 |
+
"model.layers.35.self_attn.q_a_proj",
|
| 161 |
+
"model.layers.35.self_attn.q_b_proj",
|
| 162 |
+
"model.layers.36.self_attn.indexer*",
|
| 163 |
+
"model.layers.36.self_attn.kv_a_proj_with_mqa",
|
| 164 |
+
"model.layers.36.self_attn.kv_b_proj",
|
| 165 |
+
"model.layers.36.self_attn.q_a_proj",
|
| 166 |
+
"model.layers.36.self_attn.q_b_proj",
|
| 167 |
+
"model.layers.37.self_attn.indexer*",
|
| 168 |
+
"model.layers.37.self_attn.kv_a_proj_with_mqa",
|
| 169 |
+
"model.layers.37.self_attn.kv_b_proj",
|
| 170 |
+
"model.layers.37.self_attn.q_a_proj",
|
| 171 |
+
"model.layers.37.self_attn.q_b_proj",
|
| 172 |
+
"model.layers.38.self_attn.indexer*",
|
| 173 |
+
"model.layers.38.self_attn.kv_a_proj_with_mqa",
|
| 174 |
+
"model.layers.38.self_attn.kv_b_proj",
|
| 175 |
+
"model.layers.38.self_attn.q_a_proj",
|
| 176 |
+
"model.layers.38.self_attn.q_b_proj",
|
| 177 |
+
"model.layers.39.self_attn.indexer*",
|
| 178 |
+
"model.layers.39.self_attn.kv_a_proj_with_mqa",
|
| 179 |
+
"model.layers.39.self_attn.kv_b_proj",
|
| 180 |
+
"model.layers.39.self_attn.q_a_proj",
|
| 181 |
+
"model.layers.39.self_attn.q_b_proj",
|
| 182 |
+
"model.layers.4.self_attn.indexer*",
|
| 183 |
+
"model.layers.4.self_attn.kv_a_proj_with_mqa",
|
| 184 |
+
"model.layers.4.self_attn.kv_b_proj",
|
| 185 |
+
"model.layers.4.self_attn.q_a_proj",
|
| 186 |
+
"model.layers.4.self_attn.q_b_proj",
|
| 187 |
+
"model.layers.40.self_attn.indexer*",
|
| 188 |
+
"model.layers.40.self_attn.kv_a_proj_with_mqa",
|
| 189 |
+
"model.layers.40.self_attn.kv_b_proj",
|
| 190 |
+
"model.layers.40.self_attn.q_a_proj",
|
| 191 |
+
"model.layers.40.self_attn.q_b_proj",
|
| 192 |
+
"model.layers.41.self_attn.indexer*",
|
| 193 |
+
"model.layers.41.self_attn.kv_a_proj_with_mqa",
|
| 194 |
+
"model.layers.41.self_attn.kv_b_proj",
|
| 195 |
+
"model.layers.41.self_attn.q_a_proj",
|
| 196 |
+
"model.layers.41.self_attn.q_b_proj",
|
| 197 |
+
"model.layers.42.self_attn.indexer*",
|
| 198 |
+
"model.layers.42.self_attn.kv_a_proj_with_mqa",
|
| 199 |
+
"model.layers.42.self_attn.kv_b_proj",
|
| 200 |
+
"model.layers.42.self_attn.q_a_proj",
|
| 201 |
+
"model.layers.42.self_attn.q_b_proj",
|
| 202 |
+
"model.layers.43.self_attn.indexer*",
|
| 203 |
+
"model.layers.43.self_attn.kv_a_proj_with_mqa",
|
| 204 |
+
"model.layers.43.self_attn.kv_b_proj",
|
| 205 |
+
"model.layers.43.self_attn.q_a_proj",
|
| 206 |
+
"model.layers.43.self_attn.q_b_proj",
|
| 207 |
+
"model.layers.44.self_attn.indexer*",
|
| 208 |
+
"model.layers.44.self_attn.kv_a_proj_with_mqa",
|
| 209 |
+
"model.layers.44.self_attn.kv_b_proj",
|
| 210 |
+
"model.layers.44.self_attn.q_a_proj",
|
| 211 |
+
"model.layers.44.self_attn.q_b_proj",
|
| 212 |
+
"model.layers.45.self_attn.indexer*",
|
| 213 |
+
"model.layers.45.self_attn.kv_a_proj_with_mqa",
|
| 214 |
+
"model.layers.45.self_attn.kv_b_proj",
|
| 215 |
+
"model.layers.45.self_attn.q_a_proj",
|
| 216 |
+
"model.layers.45.self_attn.q_b_proj",
|
| 217 |
+
"model.layers.46.self_attn.indexer*",
|
| 218 |
+
"model.layers.46.self_attn.kv_a_proj_with_mqa",
|
| 219 |
+
"model.layers.46.self_attn.kv_b_proj",
|
| 220 |
+
"model.layers.46.self_attn.q_a_proj",
|
| 221 |
+
"model.layers.46.self_attn.q_b_proj",
|
| 222 |
+
"model.layers.47.self_attn.indexer*",
|
| 223 |
+
"model.layers.47.self_attn.kv_a_proj_with_mqa",
|
| 224 |
+
"model.layers.47.self_attn.kv_b_proj",
|
| 225 |
+
"model.layers.47.self_attn.q_a_proj",
|
| 226 |
+
"model.layers.47.self_attn.q_b_proj",
|
| 227 |
+
"model.layers.48.self_attn.indexer*",
|
| 228 |
+
"model.layers.48.self_attn.kv_a_proj_with_mqa",
|
| 229 |
+
"model.layers.48.self_attn.kv_b_proj",
|
| 230 |
+
"model.layers.48.self_attn.q_a_proj",
|
| 231 |
+
"model.layers.48.self_attn.q_b_proj",
|
| 232 |
+
"model.layers.49.self_attn.indexer*",
|
| 233 |
+
"model.layers.49.self_attn.kv_a_proj_with_mqa",
|
| 234 |
+
"model.layers.49.self_attn.kv_b_proj",
|
| 235 |
+
"model.layers.49.self_attn.q_a_proj",
|
| 236 |
+
"model.layers.49.self_attn.q_b_proj",
|
| 237 |
+
"model.layers.5.self_attn.indexer*",
|
| 238 |
+
"model.layers.5.self_attn.kv_a_proj_with_mqa",
|
| 239 |
+
"model.layers.5.self_attn.kv_b_proj",
|
| 240 |
+
"model.layers.5.self_attn.q_a_proj",
|
| 241 |
+
"model.layers.5.self_attn.q_b_proj",
|
| 242 |
+
"model.layers.50.self_attn.indexer*",
|
| 243 |
+
"model.layers.50.self_attn.kv_a_proj_with_mqa",
|
| 244 |
+
"model.layers.50.self_attn.kv_b_proj",
|
| 245 |
+
"model.layers.50.self_attn.q_a_proj",
|
| 246 |
+
"model.layers.50.self_attn.q_b_proj",
|
| 247 |
+
"model.layers.51.self_attn.indexer*",
|
| 248 |
+
"model.layers.51.self_attn.kv_a_proj_with_mqa",
|
| 249 |
+
"model.layers.51.self_attn.kv_b_proj",
|
| 250 |
+
"model.layers.51.self_attn.q_a_proj",
|
| 251 |
+
"model.layers.51.self_attn.q_b_proj",
|
| 252 |
+
"model.layers.52.self_attn.indexer*",
|
| 253 |
+
"model.layers.52.self_attn.kv_a_proj_with_mqa",
|
| 254 |
+
"model.layers.52.self_attn.kv_b_proj",
|
| 255 |
+
"model.layers.52.self_attn.q_a_proj",
|
| 256 |
+
"model.layers.52.self_attn.q_b_proj",
|
| 257 |
+
"model.layers.53.self_attn.indexer*",
|
| 258 |
+
"model.layers.53.self_attn.kv_a_proj_with_mqa",
|
| 259 |
+
"model.layers.53.self_attn.kv_b_proj",
|
| 260 |
+
"model.layers.53.self_attn.q_a_proj",
|
| 261 |
+
"model.layers.53.self_attn.q_b_proj",
|
| 262 |
+
"model.layers.54.self_attn.indexer*",
|
| 263 |
+
"model.layers.54.self_attn.kv_a_proj_with_mqa",
|
| 264 |
+
"model.layers.54.self_attn.kv_b_proj",
|
| 265 |
+
"model.layers.54.self_attn.q_a_proj",
|
| 266 |
+
"model.layers.54.self_attn.q_b_proj",
|
| 267 |
+
"model.layers.55.self_attn.indexer*",
|
| 268 |
+
"model.layers.55.self_attn.kv_a_proj_with_mqa",
|
| 269 |
+
"model.layers.55.self_attn.kv_b_proj",
|
| 270 |
+
"model.layers.55.self_attn.q_a_proj",
|
| 271 |
+
"model.layers.55.self_attn.q_b_proj",
|
| 272 |
+
"model.layers.56.self_attn.indexer*",
|
| 273 |
+
"model.layers.56.self_attn.kv_a_proj_with_mqa",
|
| 274 |
+
"model.layers.56.self_attn.kv_b_proj",
|
| 275 |
+
"model.layers.56.self_attn.q_a_proj",
|
| 276 |
+
"model.layers.56.self_attn.q_b_proj",
|
| 277 |
+
"model.layers.57.self_attn.indexer*",
|
| 278 |
+
"model.layers.57.self_attn.kv_a_proj_with_mqa",
|
| 279 |
+
"model.layers.57.self_attn.kv_b_proj",
|
| 280 |
+
"model.layers.57.self_attn.q_a_proj",
|
| 281 |
+
"model.layers.57.self_attn.q_b_proj",
|
| 282 |
+
"model.layers.58.self_attn.indexer*",
|
| 283 |
+
"model.layers.58.self_attn.kv_a_proj_with_mqa",
|
| 284 |
+
"model.layers.58.self_attn.kv_b_proj",
|
| 285 |
+
"model.layers.58.self_attn.q_a_proj",
|
| 286 |
+
"model.layers.58.self_attn.q_b_proj",
|
| 287 |
+
"model.layers.59.self_attn.indexer*",
|
| 288 |
+
"model.layers.59.self_attn.kv_a_proj_with_mqa",
|
| 289 |
+
"model.layers.59.self_attn.kv_b_proj",
|
| 290 |
+
"model.layers.59.self_attn.q_a_proj",
|
| 291 |
+
"model.layers.59.self_attn.q_b_proj",
|
| 292 |
+
"model.layers.6.self_attn.indexer*",
|
| 293 |
+
"model.layers.6.self_attn.kv_a_proj_with_mqa",
|
| 294 |
+
"model.layers.6.self_attn.kv_b_proj",
|
| 295 |
+
"model.layers.6.self_attn.q_a_proj",
|
| 296 |
+
"model.layers.6.self_attn.q_b_proj",
|
| 297 |
+
"model.layers.60.self_attn.indexer*",
|
| 298 |
+
"model.layers.60.self_attn.kv_a_proj_with_mqa",
|
| 299 |
+
"model.layers.60.self_attn.kv_b_proj",
|
| 300 |
+
"model.layers.60.self_attn.q_a_proj",
|
| 301 |
+
"model.layers.60.self_attn.q_b_proj",
|
| 302 |
+
"model.layers.61.self_attn.indexer*",
|
| 303 |
+
"model.layers.61.self_attn.kv_a_proj_with_mqa",
|
| 304 |
+
"model.layers.61.self_attn.kv_b_proj",
|
| 305 |
+
"model.layers.61.self_attn.q_a_proj",
|
| 306 |
+
"model.layers.61.self_attn.q_b_proj",
|
| 307 |
+
"model.layers.62.self_attn.indexer*",
|
| 308 |
+
"model.layers.62.self_attn.kv_a_proj_with_mqa",
|
| 309 |
+
"model.layers.62.self_attn.kv_b_proj",
|
| 310 |
+
"model.layers.62.self_attn.q_a_proj",
|
| 311 |
+
"model.layers.62.self_attn.q_b_proj",
|
| 312 |
+
"model.layers.63.self_attn.indexer*",
|
| 313 |
+
"model.layers.63.self_attn.kv_a_proj_with_mqa",
|
| 314 |
+
"model.layers.63.self_attn.kv_b_proj",
|
| 315 |
+
"model.layers.63.self_attn.q_a_proj",
|
| 316 |
+
"model.layers.63.self_attn.q_b_proj",
|
| 317 |
+
"model.layers.64.self_attn.indexer*",
|
| 318 |
+
"model.layers.64.self_attn.kv_a_proj_with_mqa",
|
| 319 |
+
"model.layers.64.self_attn.kv_b_proj",
|
| 320 |
+
"model.layers.64.self_attn.q_a_proj",
|
| 321 |
+
"model.layers.64.self_attn.q_b_proj",
|
| 322 |
+
"model.layers.65.self_attn.indexer*",
|
| 323 |
+
"model.layers.65.self_attn.kv_a_proj_with_mqa",
|
| 324 |
+
"model.layers.65.self_attn.kv_b_proj",
|
| 325 |
+
"model.layers.65.self_attn.q_a_proj",
|
| 326 |
+
"model.layers.65.self_attn.q_b_proj",
|
| 327 |
+
"model.layers.66.self_attn.indexer*",
|
| 328 |
+
"model.layers.66.self_attn.kv_a_proj_with_mqa",
|
| 329 |
+
"model.layers.66.self_attn.kv_b_proj",
|
| 330 |
+
"model.layers.66.self_attn.q_a_proj",
|
| 331 |
+
"model.layers.66.self_attn.q_b_proj",
|
| 332 |
+
"model.layers.67.self_attn.indexer*",
|
| 333 |
+
"model.layers.67.self_attn.kv_a_proj_with_mqa",
|
| 334 |
+
"model.layers.67.self_attn.kv_b_proj",
|
| 335 |
+
"model.layers.67.self_attn.q_a_proj",
|
| 336 |
+
"model.layers.67.self_attn.q_b_proj",
|
| 337 |
+
"model.layers.68.self_attn.indexer*",
|
| 338 |
+
"model.layers.68.self_attn.kv_a_proj_with_mqa",
|
| 339 |
+
"model.layers.68.self_attn.kv_b_proj",
|
| 340 |
+
"model.layers.68.self_attn.q_a_proj",
|
| 341 |
+
"model.layers.68.self_attn.q_b_proj",
|
| 342 |
+
"model.layers.69.self_attn.indexer*",
|
| 343 |
+
"model.layers.69.self_attn.kv_a_proj_with_mqa",
|
| 344 |
+
"model.layers.69.self_attn.kv_b_proj",
|
| 345 |
+
"model.layers.69.self_attn.q_a_proj",
|
| 346 |
+
"model.layers.69.self_attn.q_b_proj",
|
| 347 |
+
"model.layers.7.self_attn.indexer*",
|
| 348 |
+
"model.layers.7.self_attn.kv_a_proj_with_mqa",
|
| 349 |
+
"model.layers.7.self_attn.kv_b_proj",
|
| 350 |
+
"model.layers.7.self_attn.q_a_proj",
|
| 351 |
+
"model.layers.7.self_attn.q_b_proj",
|
| 352 |
+
"model.layers.70.self_attn.indexer*",
|
| 353 |
+
"model.layers.70.self_attn.kv_a_proj_with_mqa",
|
| 354 |
+
"model.layers.70.self_attn.kv_b_proj",
|
| 355 |
+
"model.layers.70.self_attn.q_a_proj",
|
| 356 |
+
"model.layers.70.self_attn.q_b_proj",
|
| 357 |
+
"model.layers.71.self_attn.indexer*",
|
| 358 |
+
"model.layers.71.self_attn.kv_a_proj_with_mqa",
|
| 359 |
+
"model.layers.71.self_attn.kv_b_proj",
|
| 360 |
+
"model.layers.71.self_attn.q_a_proj",
|
| 361 |
+
"model.layers.71.self_attn.q_b_proj",
|
| 362 |
+
"model.layers.72.self_attn.indexer*",
|
| 363 |
+
"model.layers.72.self_attn.kv_a_proj_with_mqa",
|
| 364 |
+
"model.layers.72.self_attn.kv_b_proj",
|
| 365 |
+
"model.layers.72.self_attn.q_a_proj",
|
| 366 |
+
"model.layers.72.self_attn.q_b_proj",
|
| 367 |
+
"model.layers.73.self_attn.indexer*",
|
| 368 |
+
"model.layers.73.self_attn.kv_a_proj_with_mqa",
|
| 369 |
+
"model.layers.73.self_attn.kv_b_proj",
|
| 370 |
+
"model.layers.73.self_attn.q_a_proj",
|
| 371 |
+
"model.layers.73.self_attn.q_b_proj",
|
| 372 |
+
"model.layers.74.self_attn.indexer*",
|
| 373 |
+
"model.layers.74.self_attn.kv_a_proj_with_mqa",
|
| 374 |
+
"model.layers.74.self_attn.kv_b_proj",
|
| 375 |
+
"model.layers.74.self_attn.q_a_proj",
|
| 376 |
+
"model.layers.74.self_attn.q_b_proj",
|
| 377 |
+
"model.layers.75.self_attn.indexer*",
|
| 378 |
+
"model.layers.75.self_attn.kv_a_proj_with_mqa",
|
| 379 |
+
"model.layers.75.self_attn.kv_b_proj",
|
| 380 |
+
"model.layers.75.self_attn.q_a_proj",
|
| 381 |
+
"model.layers.75.self_attn.q_b_proj",
|
| 382 |
+
"model.layers.76.self_attn.indexer*",
|
| 383 |
+
"model.layers.76.self_attn.kv_a_proj_with_mqa",
|
| 384 |
+
"model.layers.76.self_attn.kv_b_proj",
|
| 385 |
+
"model.layers.76.self_attn.q_a_proj",
|
| 386 |
+
"model.layers.76.self_attn.q_b_proj",
|
| 387 |
+
"model.layers.77.self_attn.indexer*",
|
| 388 |
+
"model.layers.77.self_attn.kv_a_proj_with_mqa",
|
| 389 |
+
"model.layers.77.self_attn.kv_b_proj",
|
| 390 |
+
"model.layers.77.self_attn.q_a_proj",
|
| 391 |
+
"model.layers.77.self_attn.q_b_proj",
|
| 392 |
+
"model.layers.8.self_attn.indexer*",
|
| 393 |
+
"model.layers.8.self_attn.kv_a_proj_with_mqa",
|
| 394 |
+
"model.layers.8.self_attn.kv_b_proj",
|
| 395 |
+
"model.layers.8.self_attn.q_a_proj",
|
| 396 |
+
"model.layers.8.self_attn.q_b_proj",
|
| 397 |
+
"model.layers.9.self_attn.indexer*",
|
| 398 |
+
"model.layers.9.self_attn.kv_a_proj_with_mqa",
|
| 399 |
+
"model.layers.9.self_attn.kv_b_proj",
|
| 400 |
+
"model.layers.9.self_attn.q_a_proj",
|
| 401 |
+
"model.layers.9.self_attn.q_b_proj",
|
| 402 |
+
"model.layers.78*"
|
| 403 |
+
]
|
| 404 |
+
}
|
| 405 |
+
}
|
model.safetensors.index.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
mtp-bf16.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:67844283f1213177823ac458f22bf10496bde275d2d8fc560a48c65fab952300
|
| 3 |
+
size 19905941808
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:19e773648cb4e65de8660ea6365e10acca112d42a854923df93db4a6f333a82d
|
| 3 |
+
size 20217442
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"backend": "tokenizers",
|
| 3 |
+
"clean_up_tokenization_spaces": false,
|
| 4 |
+
"do_lower_case": false,
|
| 5 |
+
"eos_token": "<|endoftext|>",
|
| 6 |
+
"extra_special_tokens": [
|
| 7 |
+
"<|endoftext|>",
|
| 8 |
+
"[MASK]",
|
| 9 |
+
"[gMASK]",
|
| 10 |
+
"[sMASK]",
|
| 11 |
+
"<sop>",
|
| 12 |
+
"<eop>",
|
| 13 |
+
"<|system|>",
|
| 14 |
+
"<|user|>",
|
| 15 |
+
"<|assistant|>",
|
| 16 |
+
"<|observation|>",
|
| 17 |
+
"<|begin_of_image|>",
|
| 18 |
+
"<|end_of_image|>",
|
| 19 |
+
"<|begin_of_video|>",
|
| 20 |
+
"<|end_of_video|>",
|
| 21 |
+
"<|begin_of_audio|>",
|
| 22 |
+
"<|end_of_audio|>",
|
| 23 |
+
"<|begin_of_transcription|>",
|
| 24 |
+
"<|end_of_transcription|>"
|
| 25 |
+
],
|
| 26 |
+
"is_local": true,
|
| 27 |
+
"model_max_length": 202752,
|
| 28 |
+
"model_specific_special_tokens": {},
|
| 29 |
+
"pad_token": "<|endoftext|>",
|
| 30 |
+
"padding_side": "left",
|
| 31 |
+
"remove_space": false,
|
| 32 |
+
"tokenizer_class": "TokenizersBackend"
|
| 33 |
+
}
|