mstyslavity commited on
Commit
03ef5dc
·
verified ·
1 Parent(s): 5757595

Add files using upload-large-folder tool

Browse files
README.md ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language: en
3
+ library_name: mlx
4
+ tags:
5
+ - mlx
6
+ pipeline_tag: text-generation
7
+ ---
8
+
9
+ # mstyslavity/granite-finetuned-prisma-mergeshard2
10
+
11
+ ## Use with mlx
12
+
13
+ ```bash
14
+ pip install mlx-lm
15
+ ```
16
+
17
+ ```python
18
+ from mlx_lm import load, generate
19
+
20
+ model, tokenizer = load("mstyslavity/granite-finetuned-prisma-mergeshard2")
21
+
22
+ prompt = "hello"
23
+
24
+ if tokenizer.chat_template is not None:
25
+ messages = [{"role": "user", "content": prompt}]
26
+ prompt = tokenizer.apply_chat_template(
27
+ messages, add_generation_prompt=True
28
+ )
29
+
30
+ response = generate(model, tokenizer, prompt=prompt, verbose=True)
31
+ ```
chat_template.jinja ADDED
@@ -0,0 +1,118 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- set tools_system_message_prefix = 'You are a helpful assistant with access to the following tools. You may call one or more tools to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>' %}
2
+ {%- set tools_system_message_suffix = '\n</tools>\n\nFor each tool call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>. If a tool does not exist in the provided list of tools, notify the user that you do not have the ability to fulfill the request.' %}
3
+ {%- set documents_system_message_prefix = 'You are a helpful assistant with access to the following documents. You may use one or more documents to assist with the user query.\n\nYou are given a list of documents within <documents></documents> XML tags:\n<documents>' %}
4
+ {%- set documents_system_message_suffix = '\n</documents>\n\nWrite the response to the user\'s input by strictly aligning with the facts in the provided documents. If the information needed to answer the question is not available in the documents, inform the user that the question cannot be answered based on the available data.' %}
5
+ {%- set g4_default_system_message = 'You are a helpful assistant. Please ensure responses are professional, accurate, and safe.' %}
6
+ {%- if available_tools is defined and available_tools %}
7
+ {%- set tools = available_tools %}
8
+ {%- endif %}
9
+ {%- set ns = namespace(tools_system_message=tools_system_message_prefix,
10
+ documents_system_message=documents_system_message_prefix,
11
+ default_system_message=g4_default_system_message,
12
+ system_message=''
13
+ ) %}
14
+ {%- if tools %}
15
+ {%- for tool in tools %}
16
+ {%- set ns.tools_system_message = ns.tools_system_message + '\n' + (tool | tojson) %}
17
+ {%- endfor %}
18
+ {%- set ns.tools_system_message = ns.tools_system_message + tools_system_message_suffix %}
19
+ {%- else %}
20
+ {%- set ns.tools_system_message = '' %}
21
+ {%- endif %}
22
+ {%- if documents %}
23
+ {%- for document in documents %}
24
+ {%- set ns.documents_system_message = ns.documents_system_message + '\n' + (document | tojson) %}
25
+ {%- endfor %}
26
+ {%- set ns.documents_system_message = ns.documents_system_message + documents_system_message_suffix %}
27
+ {%- else %}
28
+ {%- set ns.documents_system_message = '' %}
29
+ {%- endif %}
30
+ {%- if messages[0].role == 'system' %}
31
+ {%- if messages[0].content is string %}
32
+ {%- set ns.system_message = messages[0].content %}
33
+ {%- elif messages[0].content is iterable %}
34
+ {%- for entry in messages[0].content %}
35
+ {%- if entry.type== 'text' %}
36
+ {%- if ns.system_message != '' %}
37
+ {%- set ns.system_message = ns.system_message + '\n' %}
38
+ {%- endif %}
39
+ {%- set ns.system_message = ns.system_message + entry.text %}
40
+ {%- endif %}
41
+ {%- endfor %}
42
+ {%- endif %}
43
+ {%- if tools and documents %}
44
+ {%- set ns.system_message = ns.system_message + '\n\n' + ns.tools_system_message + '\n\n' + ns.documents_system_message %}
45
+ {%- elif tools %}
46
+ {%- set ns.system_message = ns.system_message + '\n\n' + ns.tools_system_message %}
47
+ {%- elif documents %}
48
+ {%- set ns.system_message = ns.system_message + '\n\n' + ns.documents_system_message %}
49
+ {%- endif %}
50
+ {%- else %}
51
+ {%- if tools and documents %}
52
+ {%- set ns.system_message = ns.tools_system_message + '\n\n' + ns.documents_system_message %}
53
+ {%- elif tools %}
54
+ {%- set ns.system_message = ns.tools_system_message %}
55
+ {%- elif documents %}
56
+ {%- set ns.system_message = ns.documents_system_message %}
57
+ {%- endif %}
58
+ {%- endif %}
59
+ {%- if ns.system_message %}
60
+ {{- '<|start_of_role|>system<|end_of_role|>' + ns.system_message + '<|end_of_text|>\n' }}
61
+ {%- else %}
62
+ {{- '<|start_of_role|>system<|end_of_role|>' + ns.default_system_message + '<|end_of_text|>\n' }}
63
+ {%- endif %}
64
+ {%- for message in messages %}
65
+ {%- set content = namespace(val='') %}
66
+ {%- if message.content is string %}
67
+ {%- set content.val = message.content %}
68
+ {%- else %}
69
+ {%- if message.content is iterable %}
70
+ {%- for entry in message.content %}
71
+ {%- if entry.type== 'text' %}
72
+ {%- if content.val != '' %}
73
+ {%- set content.val = content.val + '\n' %}
74
+ {%- endif %}
75
+ {%- set content.val = content.val + entry.text %}
76
+ {%- endif %}
77
+ {%- endfor %}
78
+ {%- endif %}
79
+ {%- endif %}
80
+ {%- if (message.role == 'user') or (message.role == 'system' and not loop.first) %}
81
+ {{- '<|start_of_role|>' + message.role + '<|end_of_role|>' + content.val + '<|end_of_text|>\n' }}
82
+ {%- elif message.role == 'assistant' %}
83
+ {{- '<|start_of_role|>' + message.role + '<|end_of_role|>' + content.val }}
84
+ {%- if message.tool_calls %}
85
+ {%- for tool_call in message.tool_calls %}
86
+ {%- if (loop.first and content.val) or (not loop.first) %}
87
+ {{- '\n' }}
88
+ {%- endif %}
89
+ {%- if tool_call.function %}
90
+ {%- set tool_call = tool_call.function %}
91
+ {%- endif %}
92
+ {{- '<tool_call>\n{"name": "' }}
93
+ {{- tool_call.name }}
94
+ {{- '", "arguments": ' }}
95
+ {%- if tool_call.arguments is string %}
96
+ {{- tool_call.arguments }}
97
+ {%- else %}
98
+ {{- tool_call.arguments | tojson }}
99
+ {%- endif %}
100
+ {{- '}\n</tool_call>' }}
101
+ {%- endfor %}
102
+ {%- endif %}
103
+ {{- '<|end_of_text|>\n' }}
104
+ {%- elif message.role == 'tool' %}
105
+ {%- if loop.first or (messages[loop.index0 - 1].role != 'tool') %}
106
+ {{- '<|start_of_role|>user<|end_of_role|>' }}
107
+ {%- endif %}
108
+ {{- '\n<tool_response>\n' }}
109
+ {{- content.val }}
110
+ {{- '\n</tool_response>' }}
111
+ {%- if loop.last or (messages[loop.index0 + 1].role != 'tool') %}
112
+ {{- '<|end_of_text|>\n' }}
113
+ {%- endif %}
114
+ {%- endif %}
115
+ {%- endfor %}
116
+ {%- if add_generation_prompt %}
117
+ {{- '<|start_of_role|>assistant<|end_of_role|>' }}
118
+ {%- endif %}
config.json ADDED
@@ -0,0 +1,78 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "GraniteMoeHybridForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "attention_multiplier": 0.015625,
8
+ "bos_token_id": 100257,
9
+ "embedding_multiplier": 12,
10
+ "eos_token_id": 100257,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 1024,
13
+ "init_method": "mup",
14
+ "initializer_range": 0.1,
15
+ "intermediate_size": 2048,
16
+ "layer_types": [
17
+ "attention",
18
+ "attention",
19
+ "attention",
20
+ "attention",
21
+ "attention",
22
+ "attention",
23
+ "attention",
24
+ "attention",
25
+ "attention",
26
+ "attention",
27
+ "attention",
28
+ "attention",
29
+ "attention",
30
+ "attention",
31
+ "attention",
32
+ "attention",
33
+ "attention",
34
+ "attention",
35
+ "attention",
36
+ "attention",
37
+ "attention",
38
+ "attention",
39
+ "attention",
40
+ "attention",
41
+ "attention",
42
+ "attention",
43
+ "attention",
44
+ "attention"
45
+ ],
46
+ "logits_scaling": 4,
47
+ "mamba_chunk_size": 256,
48
+ "mamba_conv_bias": true,
49
+ "mamba_d_conv": 4,
50
+ "mamba_d_head": 16,
51
+ "mamba_d_state": 256,
52
+ "mamba_expand": 2,
53
+ "mamba_n_groups": 1,
54
+ "mamba_n_heads": 128,
55
+ "mamba_proj_bias": false,
56
+ "max_position_embeddings": 32768,
57
+ "model_type": "granitemoehybrid",
58
+ "normalization_function": "rmsnorm",
59
+ "num_attention_heads": 16,
60
+ "num_experts_per_tok": 0,
61
+ "num_hidden_layers": 28,
62
+ "num_key_value_heads": 4,
63
+ "num_local_experts": 0,
64
+ "output_router_logits": false,
65
+ "pad_token_id": 100256,
66
+ "position_embedding_type": "rope",
67
+ "residual_multiplier": 0.263,
68
+ "rms_norm_eps": 1e-05,
69
+ "rope_scaling": null,
70
+ "rope_theta": 10000000,
71
+ "router_aux_loss_coef": 0.01,
72
+ "shared_intermediate_size": 2048,
73
+ "tie_word_embeddings": true,
74
+ "torch_dtype": "bfloat16",
75
+ "transformers_version": "4.56.0",
76
+ "use_cache": true,
77
+ "vocab_size": 100352
78
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 100257,
4
+ "eos_token_id": 100257,
5
+ "pad_token_id": 100256,
6
+ "transformers_version": "4.56.0"
7
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f76cdaadcc1850a04f8030bba884a1434cf245ba466970b3d3ccf4ce0dc7aa61
3
+ size 883046526
model.safetensors.index.json ADDED
@@ -0,0 +1,262 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 883017728,
4
+ "total_parameters": 352379904
5
+ },
6
+ "weight_map": {
7
+ "model.embed_tokens.weight": "model.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model.safetensors",
13
+ "model.layers.0.self_attn.k_proj.weight": "model.safetensors",
14
+ "model.layers.0.self_attn.o_proj.weight": "model.safetensors",
15
+ "model.layers.0.self_attn.q_proj.weight": "model.safetensors",
16
+ "model.layers.0.self_attn.v_proj.weight": "model.safetensors",
17
+ "model.layers.1.input_layernorm.weight": "model.safetensors",
18
+ "model.layers.1.mlp.down_proj.weight": "model.safetensors",
19
+ "model.layers.1.mlp.gate_proj.weight": "model.safetensors",
20
+ "model.layers.1.mlp.up_proj.weight": "model.safetensors",
21
+ "model.layers.1.post_attention_layernorm.weight": "model.safetensors",
22
+ "model.layers.1.self_attn.k_proj.weight": "model.safetensors",
23
+ "model.layers.1.self_attn.o_proj.weight": "model.safetensors",
24
+ "model.layers.1.self_attn.q_proj.weight": "model.safetensors",
25
+ "model.layers.1.self_attn.v_proj.weight": "model.safetensors",
26
+ "model.layers.10.input_layernorm.weight": "model.safetensors",
27
+ "model.layers.10.mlp.down_proj.weight": "model.safetensors",
28
+ "model.layers.10.mlp.gate_proj.weight": "model.safetensors",
29
+ "model.layers.10.mlp.up_proj.weight": "model.safetensors",
30
+ "model.layers.10.post_attention_layernorm.weight": "model.safetensors",
31
+ "model.layers.10.self_attn.k_proj.weight": "model.safetensors",
32
+ "model.layers.10.self_attn.o_proj.weight": "model.safetensors",
33
+ "model.layers.10.self_attn.q_proj.weight": "model.safetensors",
34
+ "model.layers.10.self_attn.v_proj.weight": "model.safetensors",
35
+ "model.layers.11.input_layernorm.weight": "model.safetensors",
36
+ "model.layers.11.mlp.down_proj.weight": "model.safetensors",
37
+ "model.layers.11.mlp.gate_proj.weight": "model.safetensors",
38
+ "model.layers.11.mlp.up_proj.weight": "model.safetensors",
39
+ "model.layers.11.post_attention_layernorm.weight": "model.safetensors",
40
+ "model.layers.11.self_attn.k_proj.weight": "model.safetensors",
41
+ "model.layers.11.self_attn.o_proj.weight": "model.safetensors",
42
+ "model.layers.11.self_attn.q_proj.weight": "model.safetensors",
43
+ "model.layers.11.self_attn.v_proj.weight": "model.safetensors",
44
+ "model.layers.12.input_layernorm.weight": "model.safetensors",
45
+ "model.layers.12.mlp.down_proj.weight": "model.safetensors",
46
+ "model.layers.12.mlp.gate_proj.weight": "model.safetensors",
47
+ "model.layers.12.mlp.up_proj.weight": "model.safetensors",
48
+ "model.layers.12.post_attention_layernorm.weight": "model.safetensors",
49
+ "model.layers.12.self_attn.k_proj.weight": "model.safetensors",
50
+ "model.layers.12.self_attn.o_proj.weight": "model.safetensors",
51
+ "model.layers.12.self_attn.q_proj.weight": "model.safetensors",
52
+ "model.layers.12.self_attn.v_proj.weight": "model.safetensors",
53
+ "model.layers.13.input_layernorm.weight": "model.safetensors",
54
+ "model.layers.13.mlp.down_proj.weight": "model.safetensors",
55
+ "model.layers.13.mlp.gate_proj.weight": "model.safetensors",
56
+ "model.layers.13.mlp.up_proj.weight": "model.safetensors",
57
+ "model.layers.13.post_attention_layernorm.weight": "model.safetensors",
58
+ "model.layers.13.self_attn.k_proj.weight": "model.safetensors",
59
+ "model.layers.13.self_attn.o_proj.weight": "model.safetensors",
60
+ "model.layers.13.self_attn.q_proj.weight": "model.safetensors",
61
+ "model.layers.13.self_attn.v_proj.weight": "model.safetensors",
62
+ "model.layers.14.input_layernorm.weight": "model.safetensors",
63
+ "model.layers.14.mlp.down_proj.weight": "model.safetensors",
64
+ "model.layers.14.mlp.gate_proj.weight": "model.safetensors",
65
+ "model.layers.14.mlp.up_proj.weight": "model.safetensors",
66
+ "model.layers.14.post_attention_layernorm.weight": "model.safetensors",
67
+ "model.layers.14.self_attn.k_proj.weight": "model.safetensors",
68
+ "model.layers.14.self_attn.o_proj.weight": "model.safetensors",
69
+ "model.layers.14.self_attn.q_proj.weight": "model.safetensors",
70
+ "model.layers.14.self_attn.v_proj.weight": "model.safetensors",
71
+ "model.layers.15.input_layernorm.weight": "model.safetensors",
72
+ "model.layers.15.mlp.down_proj.weight": "model.safetensors",
73
+ "model.layers.15.mlp.gate_proj.weight": "model.safetensors",
74
+ "model.layers.15.mlp.up_proj.weight": "model.safetensors",
75
+ "model.layers.15.post_attention_layernorm.weight": "model.safetensors",
76
+ "model.layers.15.self_attn.k_proj.weight": "model.safetensors",
77
+ "model.layers.15.self_attn.o_proj.weight": "model.safetensors",
78
+ "model.layers.15.self_attn.q_proj.weight": "model.safetensors",
79
+ "model.layers.15.self_attn.v_proj.weight": "model.safetensors",
80
+ "model.layers.16.input_layernorm.weight": "model.safetensors",
81
+ "model.layers.16.mlp.down_proj.weight": "model.safetensors",
82
+ "model.layers.16.mlp.gate_proj.weight": "model.safetensors",
83
+ "model.layers.16.mlp.up_proj.weight": "model.safetensors",
84
+ "model.layers.16.post_attention_layernorm.weight": "model.safetensors",
85
+ "model.layers.16.self_attn.k_proj.weight": "model.safetensors",
86
+ "model.layers.16.self_attn.o_proj.weight": "model.safetensors",
87
+ "model.layers.16.self_attn.q_proj.weight": "model.safetensors",
88
+ "model.layers.16.self_attn.v_proj.weight": "model.safetensors",
89
+ "model.layers.17.input_layernorm.weight": "model.safetensors",
90
+ "model.layers.17.mlp.down_proj.weight": "model.safetensors",
91
+ "model.layers.17.mlp.gate_proj.weight": "model.safetensors",
92
+ "model.layers.17.mlp.up_proj.weight": "model.safetensors",
93
+ "model.layers.17.post_attention_layernorm.weight": "model.safetensors",
94
+ "model.layers.17.self_attn.k_proj.weight": "model.safetensors",
95
+ "model.layers.17.self_attn.o_proj.weight": "model.safetensors",
96
+ "model.layers.17.self_attn.q_proj.weight": "model.safetensors",
97
+ "model.layers.17.self_attn.v_proj.weight": "model.safetensors",
98
+ "model.layers.18.input_layernorm.weight": "model.safetensors",
99
+ "model.layers.18.mlp.down_proj.weight": "model.safetensors",
100
+ "model.layers.18.mlp.gate_proj.weight": "model.safetensors",
101
+ "model.layers.18.mlp.up_proj.weight": "model.safetensors",
102
+ "model.layers.18.post_attention_layernorm.weight": "model.safetensors",
103
+ "model.layers.18.self_attn.k_proj.weight": "model.safetensors",
104
+ "model.layers.18.self_attn.o_proj.weight": "model.safetensors",
105
+ "model.layers.18.self_attn.q_proj.weight": "model.safetensors",
106
+ "model.layers.18.self_attn.v_proj.weight": "model.safetensors",
107
+ "model.layers.19.input_layernorm.weight": "model.safetensors",
108
+ "model.layers.19.mlp.down_proj.weight": "model.safetensors",
109
+ "model.layers.19.mlp.gate_proj.weight": "model.safetensors",
110
+ "model.layers.19.mlp.up_proj.weight": "model.safetensors",
111
+ "model.layers.19.post_attention_layernorm.weight": "model.safetensors",
112
+ "model.layers.19.self_attn.k_proj.weight": "model.safetensors",
113
+ "model.layers.19.self_attn.o_proj.weight": "model.safetensors",
114
+ "model.layers.19.self_attn.q_proj.weight": "model.safetensors",
115
+ "model.layers.19.self_attn.v_proj.weight": "model.safetensors",
116
+ "model.layers.2.input_layernorm.weight": "model.safetensors",
117
+ "model.layers.2.mlp.down_proj.weight": "model.safetensors",
118
+ "model.layers.2.mlp.gate_proj.weight": "model.safetensors",
119
+ "model.layers.2.mlp.up_proj.weight": "model.safetensors",
120
+ "model.layers.2.post_attention_layernorm.weight": "model.safetensors",
121
+ "model.layers.2.self_attn.k_proj.weight": "model.safetensors",
122
+ "model.layers.2.self_attn.o_proj.weight": "model.safetensors",
123
+ "model.layers.2.self_attn.q_proj.weight": "model.safetensors",
124
+ "model.layers.2.self_attn.v_proj.weight": "model.safetensors",
125
+ "model.layers.20.input_layernorm.weight": "model.safetensors",
126
+ "model.layers.20.mlp.down_proj.weight": "model.safetensors",
127
+ "model.layers.20.mlp.gate_proj.weight": "model.safetensors",
128
+ "model.layers.20.mlp.up_proj.weight": "model.safetensors",
129
+ "model.layers.20.post_attention_layernorm.weight": "model.safetensors",
130
+ "model.layers.20.self_attn.k_proj.weight": "model.safetensors",
131
+ "model.layers.20.self_attn.o_proj.weight": "model.safetensors",
132
+ "model.layers.20.self_attn.q_proj.weight": "model.safetensors",
133
+ "model.layers.20.self_attn.v_proj.weight": "model.safetensors",
134
+ "model.layers.21.input_layernorm.weight": "model.safetensors",
135
+ "model.layers.21.mlp.down_proj.weight": "model.safetensors",
136
+ "model.layers.21.mlp.gate_proj.weight": "model.safetensors",
137
+ "model.layers.21.mlp.up_proj.weight": "model.safetensors",
138
+ "model.layers.21.post_attention_layernorm.weight": "model.safetensors",
139
+ "model.layers.21.self_attn.k_proj.weight": "model.safetensors",
140
+ "model.layers.21.self_attn.o_proj.weight": "model.safetensors",
141
+ "model.layers.21.self_attn.q_proj.weight": "model.safetensors",
142
+ "model.layers.21.self_attn.v_proj.weight": "model.safetensors",
143
+ "model.layers.22.input_layernorm.weight": "model.safetensors",
144
+ "model.layers.22.mlp.down_proj.weight": "model.safetensors",
145
+ "model.layers.22.mlp.gate_proj.weight": "model.safetensors",
146
+ "model.layers.22.mlp.up_proj.weight": "model.safetensors",
147
+ "model.layers.22.post_attention_layernorm.weight": "model.safetensors",
148
+ "model.layers.22.self_attn.k_proj.weight": "model.safetensors",
149
+ "model.layers.22.self_attn.o_proj.weight": "model.safetensors",
150
+ "model.layers.22.self_attn.q_proj.weight": "model.safetensors",
151
+ "model.layers.22.self_attn.v_proj.weight": "model.safetensors",
152
+ "model.layers.23.input_layernorm.weight": "model.safetensors",
153
+ "model.layers.23.mlp.down_proj.weight": "model.safetensors",
154
+ "model.layers.23.mlp.gate_proj.weight": "model.safetensors",
155
+ "model.layers.23.mlp.up_proj.weight": "model.safetensors",
156
+ "model.layers.23.post_attention_layernorm.weight": "model.safetensors",
157
+ "model.layers.23.self_attn.k_proj.weight": "model.safetensors",
158
+ "model.layers.23.self_attn.o_proj.weight": "model.safetensors",
159
+ "model.layers.23.self_attn.q_proj.weight": "model.safetensors",
160
+ "model.layers.23.self_attn.v_proj.weight": "model.safetensors",
161
+ "model.layers.24.input_layernorm.weight": "model.safetensors",
162
+ "model.layers.24.mlp.down_proj.weight": "model.safetensors",
163
+ "model.layers.24.mlp.gate_proj.weight": "model.safetensors",
164
+ "model.layers.24.mlp.up_proj.weight": "model.safetensors",
165
+ "model.layers.24.post_attention_layernorm.weight": "model.safetensors",
166
+ "model.layers.24.self_attn.k_proj.weight": "model.safetensors",
167
+ "model.layers.24.self_attn.o_proj.weight": "model.safetensors",
168
+ "model.layers.24.self_attn.q_proj.weight": "model.safetensors",
169
+ "model.layers.24.self_attn.v_proj.weight": "model.safetensors",
170
+ "model.layers.25.input_layernorm.weight": "model.safetensors",
171
+ "model.layers.25.mlp.down_proj.weight": "model.safetensors",
172
+ "model.layers.25.mlp.gate_proj.weight": "model.safetensors",
173
+ "model.layers.25.mlp.up_proj.weight": "model.safetensors",
174
+ "model.layers.25.post_attention_layernorm.weight": "model.safetensors",
175
+ "model.layers.25.self_attn.k_proj.weight": "model.safetensors",
176
+ "model.layers.25.self_attn.o_proj.weight": "model.safetensors",
177
+ "model.layers.25.self_attn.q_proj.weight": "model.safetensors",
178
+ "model.layers.25.self_attn.v_proj.weight": "model.safetensors",
179
+ "model.layers.26.input_layernorm.weight": "model.safetensors",
180
+ "model.layers.26.mlp.down_proj.weight": "model.safetensors",
181
+ "model.layers.26.mlp.gate_proj.weight": "model.safetensors",
182
+ "model.layers.26.mlp.up_proj.weight": "model.safetensors",
183
+ "model.layers.26.post_attention_layernorm.weight": "model.safetensors",
184
+ "model.layers.26.self_attn.k_proj.weight": "model.safetensors",
185
+ "model.layers.26.self_attn.o_proj.weight": "model.safetensors",
186
+ "model.layers.26.self_attn.q_proj.weight": "model.safetensors",
187
+ "model.layers.26.self_attn.v_proj.weight": "model.safetensors",
188
+ "model.layers.27.input_layernorm.weight": "model.safetensors",
189
+ "model.layers.27.mlp.down_proj.weight": "model.safetensors",
190
+ "model.layers.27.mlp.gate_proj.weight": "model.safetensors",
191
+ "model.layers.27.mlp.up_proj.weight": "model.safetensors",
192
+ "model.layers.27.post_attention_layernorm.weight": "model.safetensors",
193
+ "model.layers.27.self_attn.k_proj.weight": "model.safetensors",
194
+ "model.layers.27.self_attn.o_proj.weight": "model.safetensors",
195
+ "model.layers.27.self_attn.q_proj.weight": "model.safetensors",
196
+ "model.layers.27.self_attn.v_proj.weight": "model.safetensors",
197
+ "model.layers.3.input_layernorm.weight": "model.safetensors",
198
+ "model.layers.3.mlp.down_proj.weight": "model.safetensors",
199
+ "model.layers.3.mlp.gate_proj.weight": "model.safetensors",
200
+ "model.layers.3.mlp.up_proj.weight": "model.safetensors",
201
+ "model.layers.3.post_attention_layernorm.weight": "model.safetensors",
202
+ "model.layers.3.self_attn.k_proj.weight": "model.safetensors",
203
+ "model.layers.3.self_attn.o_proj.weight": "model.safetensors",
204
+ "model.layers.3.self_attn.q_proj.weight": "model.safetensors",
205
+ "model.layers.3.self_attn.v_proj.weight": "model.safetensors",
206
+ "model.layers.4.input_layernorm.weight": "model.safetensors",
207
+ "model.layers.4.mlp.down_proj.weight": "model.safetensors",
208
+ "model.layers.4.mlp.gate_proj.weight": "model.safetensors",
209
+ "model.layers.4.mlp.up_proj.weight": "model.safetensors",
210
+ "model.layers.4.post_attention_layernorm.weight": "model.safetensors",
211
+ "model.layers.4.self_attn.k_proj.weight": "model.safetensors",
212
+ "model.layers.4.self_attn.o_proj.weight": "model.safetensors",
213
+ "model.layers.4.self_attn.q_proj.weight": "model.safetensors",
214
+ "model.layers.4.self_attn.v_proj.weight": "model.safetensors",
215
+ "model.layers.5.input_layernorm.weight": "model.safetensors",
216
+ "model.layers.5.mlp.down_proj.weight": "model.safetensors",
217
+ "model.layers.5.mlp.gate_proj.weight": "model.safetensors",
218
+ "model.layers.5.mlp.up_proj.weight": "model.safetensors",
219
+ "model.layers.5.post_attention_layernorm.weight": "model.safetensors",
220
+ "model.layers.5.self_attn.k_proj.weight": "model.safetensors",
221
+ "model.layers.5.self_attn.o_proj.weight": "model.safetensors",
222
+ "model.layers.5.self_attn.q_proj.weight": "model.safetensors",
223
+ "model.layers.5.self_attn.v_proj.weight": "model.safetensors",
224
+ "model.layers.6.input_layernorm.weight": "model.safetensors",
225
+ "model.layers.6.mlp.down_proj.weight": "model.safetensors",
226
+ "model.layers.6.mlp.gate_proj.weight": "model.safetensors",
227
+ "model.layers.6.mlp.up_proj.weight": "model.safetensors",
228
+ "model.layers.6.post_attention_layernorm.weight": "model.safetensors",
229
+ "model.layers.6.self_attn.k_proj.weight": "model.safetensors",
230
+ "model.layers.6.self_attn.o_proj.weight": "model.safetensors",
231
+ "model.layers.6.self_attn.q_proj.weight": "model.safetensors",
232
+ "model.layers.6.self_attn.v_proj.weight": "model.safetensors",
233
+ "model.layers.7.input_layernorm.weight": "model.safetensors",
234
+ "model.layers.7.mlp.down_proj.weight": "model.safetensors",
235
+ "model.layers.7.mlp.gate_proj.weight": "model.safetensors",
236
+ "model.layers.7.mlp.up_proj.weight": "model.safetensors",
237
+ "model.layers.7.post_attention_layernorm.weight": "model.safetensors",
238
+ "model.layers.7.self_attn.k_proj.weight": "model.safetensors",
239
+ "model.layers.7.self_attn.o_proj.weight": "model.safetensors",
240
+ "model.layers.7.self_attn.q_proj.weight": "model.safetensors",
241
+ "model.layers.7.self_attn.v_proj.weight": "model.safetensors",
242
+ "model.layers.8.input_layernorm.weight": "model.safetensors",
243
+ "model.layers.8.mlp.down_proj.weight": "model.safetensors",
244
+ "model.layers.8.mlp.gate_proj.weight": "model.safetensors",
245
+ "model.layers.8.mlp.up_proj.weight": "model.safetensors",
246
+ "model.layers.8.post_attention_layernorm.weight": "model.safetensors",
247
+ "model.layers.8.self_attn.k_proj.weight": "model.safetensors",
248
+ "model.layers.8.self_attn.o_proj.weight": "model.safetensors",
249
+ "model.layers.8.self_attn.q_proj.weight": "model.safetensors",
250
+ "model.layers.8.self_attn.v_proj.weight": "model.safetensors",
251
+ "model.layers.9.input_layernorm.weight": "model.safetensors",
252
+ "model.layers.9.mlp.down_proj.weight": "model.safetensors",
253
+ "model.layers.9.mlp.gate_proj.weight": "model.safetensors",
254
+ "model.layers.9.mlp.up_proj.weight": "model.safetensors",
255
+ "model.layers.9.post_attention_layernorm.weight": "model.safetensors",
256
+ "model.layers.9.self_attn.k_proj.weight": "model.safetensors",
257
+ "model.layers.9.self_attn.o_proj.weight": "model.safetensors",
258
+ "model.layers.9.self_attn.q_proj.weight": "model.safetensors",
259
+ "model.layers.9.self_attn.v_proj.weight": "model.safetensors",
260
+ "model.norm.weight": "model.safetensors"
261
+ }
262
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|end_of_text|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|end_of_text|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|pad|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<|unk|>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,788 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "100256": {
5
+ "content": "<|pad|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "100257": {
13
+ "content": "<|end_of_text|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "100258": {
21
+ "content": "<|fim_prefix|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "100259": {
29
+ "content": "<|fim_middle|>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "100260": {
37
+ "content": "<|fim_suffix|>",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "100261": {
45
+ "content": "<|fim_pad|>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "100262": {
53
+ "content": "<|filename|>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "100263": {
61
+ "content": "<|reponame|>",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "100264": {
69
+ "content": "<|start_of_role|>",
70
+ "lstrip": false,
71
+ "normalized": false,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "100265": {
77
+ "content": "<|end_of_role|>",
78
+ "lstrip": false,
79
+ "normalized": false,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "100266": {
85
+ "content": "<|unused_1|>",
86
+ "lstrip": false,
87
+ "normalized": false,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": true
91
+ },
92
+ "100267": {
93
+ "content": "<|start_of_plugin|>",
94
+ "lstrip": false,
95
+ "normalized": false,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": true
99
+ },
100
+ "100268": {
101
+ "content": "<|end_of_plugin|>",
102
+ "lstrip": false,
103
+ "normalized": false,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": true
107
+ },
108
+ "100269": {
109
+ "content": "<|unk|>",
110
+ "lstrip": false,
111
+ "normalized": false,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": true
115
+ },
116
+ "100270": {
117
+ "content": "<tool_call>",
118
+ "lstrip": false,
119
+ "normalized": false,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": true
123
+ },
124
+ "100271": {
125
+ "content": "</tool_call>",
126
+ "lstrip": false,
127
+ "normalized": false,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": true
131
+ },
132
+ "100272": {
133
+ "content": "<tool_response>",
134
+ "lstrip": false,
135
+ "normalized": false,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": true
139
+ },
140
+ "100273": {
141
+ "content": "</tool_response>",
142
+ "lstrip": false,
143
+ "normalized": false,
144
+ "rstrip": false,
145
+ "single_word": false,
146
+ "special": true
147
+ },
148
+ "100274": {
149
+ "content": "<think>",
150
+ "lstrip": false,
151
+ "normalized": false,
152
+ "rstrip": false,
153
+ "single_word": false,
154
+ "special": true
155
+ },
156
+ "100275": {
157
+ "content": "</think>",
158
+ "lstrip": false,
159
+ "normalized": false,
160
+ "rstrip": false,
161
+ "single_word": false,
162
+ "special": true
163
+ },
164
+ "100276": {
165
+ "content": "<think_on>",
166
+ "lstrip": false,
167
+ "normalized": false,
168
+ "rstrip": false,
169
+ "single_word": false,
170
+ "special": true
171
+ },
172
+ "100277": {
173
+ "content": "<think_off>",
174
+ "lstrip": false,
175
+ "normalized": false,
176
+ "rstrip": false,
177
+ "single_word": false,
178
+ "special": true
179
+ },
180
+ "100278": {
181
+ "content": "<schema>",
182
+ "lstrip": false,
183
+ "normalized": false,
184
+ "rstrip": false,
185
+ "single_word": false,
186
+ "special": true
187
+ },
188
+ "100279": {
189
+ "content": "</schema>",
190
+ "lstrip": false,
191
+ "normalized": false,
192
+ "rstrip": false,
193
+ "single_word": false,
194
+ "special": true
195
+ },
196
+ "100280": {
197
+ "content": "<tools>",
198
+ "lstrip": false,
199
+ "normalized": false,
200
+ "rstrip": false,
201
+ "single_word": false,
202
+ "special": true
203
+ },
204
+ "100281": {
205
+ "content": "</tools>",
206
+ "lstrip": false,
207
+ "normalized": false,
208
+ "rstrip": false,
209
+ "single_word": false,
210
+ "special": true
211
+ },
212
+ "100282": {
213
+ "content": "<documents>",
214
+ "lstrip": false,
215
+ "normalized": false,
216
+ "rstrip": false,
217
+ "single_word": false,
218
+ "special": true
219
+ },
220
+ "100283": {
221
+ "content": "</documents>",
222
+ "lstrip": false,
223
+ "normalized": false,
224
+ "rstrip": false,
225
+ "single_word": false,
226
+ "special": true
227
+ },
228
+ "100284": {
229
+ "content": "<|unused_15|>",
230
+ "lstrip": false,
231
+ "normalized": false,
232
+ "rstrip": false,
233
+ "single_word": false,
234
+ "special": true
235
+ },
236
+ "100285": {
237
+ "content": "<|unused_16|>",
238
+ "lstrip": false,
239
+ "normalized": false,
240
+ "rstrip": false,
241
+ "single_word": false,
242
+ "special": true
243
+ },
244
+ "100286": {
245
+ "content": "<|unused_17|>",
246
+ "lstrip": false,
247
+ "normalized": false,
248
+ "rstrip": false,
249
+ "single_word": false,
250
+ "special": true
251
+ },
252
+ "100287": {
253
+ "content": "<|unused_18|>",
254
+ "lstrip": false,
255
+ "normalized": false,
256
+ "rstrip": false,
257
+ "single_word": false,
258
+ "special": true
259
+ },
260
+ "100288": {
261
+ "content": "<|unused_19|>",
262
+ "lstrip": false,
263
+ "normalized": false,
264
+ "rstrip": false,
265
+ "single_word": false,
266
+ "special": true
267
+ },
268
+ "100289": {
269
+ "content": "<|unused_20|>",
270
+ "lstrip": false,
271
+ "normalized": false,
272
+ "rstrip": false,
273
+ "single_word": false,
274
+ "special": true
275
+ },
276
+ "100290": {
277
+ "content": "<|unused_21|>",
278
+ "lstrip": false,
279
+ "normalized": false,
280
+ "rstrip": false,
281
+ "single_word": false,
282
+ "special": true
283
+ },
284
+ "100291": {
285
+ "content": "<|unused_22|>",
286
+ "lstrip": false,
287
+ "normalized": false,
288
+ "rstrip": false,
289
+ "single_word": false,
290
+ "special": true
291
+ },
292
+ "100292": {
293
+ "content": "<|unused_23|>",
294
+ "lstrip": false,
295
+ "normalized": false,
296
+ "rstrip": false,
297
+ "single_word": false,
298
+ "special": true
299
+ },
300
+ "100293": {
301
+ "content": "<|unused_24|>",
302
+ "lstrip": false,
303
+ "normalized": false,
304
+ "rstrip": false,
305
+ "single_word": false,
306
+ "special": true
307
+ },
308
+ "100294": {
309
+ "content": "<|unused_25|>",
310
+ "lstrip": false,
311
+ "normalized": false,
312
+ "rstrip": false,
313
+ "single_word": false,
314
+ "special": true
315
+ },
316
+ "100295": {
317
+ "content": "<|unused_26|>",
318
+ "lstrip": false,
319
+ "normalized": false,
320
+ "rstrip": false,
321
+ "single_word": false,
322
+ "special": true
323
+ },
324
+ "100296": {
325
+ "content": "<|unused_27|>",
326
+ "lstrip": false,
327
+ "normalized": false,
328
+ "rstrip": false,
329
+ "single_word": false,
330
+ "special": true
331
+ },
332
+ "100297": {
333
+ "content": "<|unused_28|>",
334
+ "lstrip": false,
335
+ "normalized": false,
336
+ "rstrip": false,
337
+ "single_word": false,
338
+ "special": true
339
+ },
340
+ "100298": {
341
+ "content": "<|unused_29|>",
342
+ "lstrip": false,
343
+ "normalized": false,
344
+ "rstrip": false,
345
+ "single_word": false,
346
+ "special": true
347
+ },
348
+ "100299": {
349
+ "content": "<|unused_30|>",
350
+ "lstrip": false,
351
+ "normalized": false,
352
+ "rstrip": false,
353
+ "single_word": false,
354
+ "special": true
355
+ },
356
+ "100300": {
357
+ "content": "<|unused_31|>",
358
+ "lstrip": false,
359
+ "normalized": false,
360
+ "rstrip": false,
361
+ "single_word": false,
362
+ "special": true
363
+ },
364
+ "100301": {
365
+ "content": "<|unused_32|>",
366
+ "lstrip": false,
367
+ "normalized": false,
368
+ "rstrip": false,
369
+ "single_word": false,
370
+ "special": true
371
+ },
372
+ "100302": {
373
+ "content": "<|unused_33|>",
374
+ "lstrip": false,
375
+ "normalized": false,
376
+ "rstrip": false,
377
+ "single_word": false,
378
+ "special": true
379
+ },
380
+ "100303": {
381
+ "content": "<|unused_34|>",
382
+ "lstrip": false,
383
+ "normalized": false,
384
+ "rstrip": false,
385
+ "single_word": false,
386
+ "special": true
387
+ },
388
+ "100304": {
389
+ "content": "<|unused_35|>",
390
+ "lstrip": false,
391
+ "normalized": false,
392
+ "rstrip": false,
393
+ "single_word": false,
394
+ "special": true
395
+ },
396
+ "100305": {
397
+ "content": "<|unused_36|>",
398
+ "lstrip": false,
399
+ "normalized": false,
400
+ "rstrip": false,
401
+ "single_word": false,
402
+ "special": true
403
+ },
404
+ "100306": {
405
+ "content": "<|unused_37|>",
406
+ "lstrip": false,
407
+ "normalized": false,
408
+ "rstrip": false,
409
+ "single_word": false,
410
+ "special": true
411
+ },
412
+ "100307": {
413
+ "content": "<|unused_38|>",
414
+ "lstrip": false,
415
+ "normalized": false,
416
+ "rstrip": false,
417
+ "single_word": false,
418
+ "special": true
419
+ },
420
+ "100308": {
421
+ "content": "<|unused_39|>",
422
+ "lstrip": false,
423
+ "normalized": false,
424
+ "rstrip": false,
425
+ "single_word": false,
426
+ "special": true
427
+ },
428
+ "100309": {
429
+ "content": "<|unused_40|>",
430
+ "lstrip": false,
431
+ "normalized": false,
432
+ "rstrip": false,
433
+ "single_word": false,
434
+ "special": true
435
+ },
436
+ "100310": {
437
+ "content": "<|unused_41|>",
438
+ "lstrip": false,
439
+ "normalized": false,
440
+ "rstrip": false,
441
+ "single_word": false,
442
+ "special": true
443
+ },
444
+ "100311": {
445
+ "content": "<|unused_42|>",
446
+ "lstrip": false,
447
+ "normalized": false,
448
+ "rstrip": false,
449
+ "single_word": false,
450
+ "special": true
451
+ },
452
+ "100312": {
453
+ "content": "<|unused_43|>",
454
+ "lstrip": false,
455
+ "normalized": false,
456
+ "rstrip": false,
457
+ "single_word": false,
458
+ "special": true
459
+ },
460
+ "100313": {
461
+ "content": "<|unused_44|>",
462
+ "lstrip": false,
463
+ "normalized": false,
464
+ "rstrip": false,
465
+ "single_word": false,
466
+ "special": true
467
+ },
468
+ "100314": {
469
+ "content": "<|unused_45|>",
470
+ "lstrip": false,
471
+ "normalized": false,
472
+ "rstrip": false,
473
+ "single_word": false,
474
+ "special": true
475
+ },
476
+ "100315": {
477
+ "content": "<|unused_46|>",
478
+ "lstrip": false,
479
+ "normalized": false,
480
+ "rstrip": false,
481
+ "single_word": false,
482
+ "special": true
483
+ },
484
+ "100316": {
485
+ "content": "<|unused_47|>",
486
+ "lstrip": false,
487
+ "normalized": false,
488
+ "rstrip": false,
489
+ "single_word": false,
490
+ "special": true
491
+ },
492
+ "100317": {
493
+ "content": "<|unused_48|>",
494
+ "lstrip": false,
495
+ "normalized": false,
496
+ "rstrip": false,
497
+ "single_word": false,
498
+ "special": true
499
+ },
500
+ "100318": {
501
+ "content": "<|unused_49|>",
502
+ "lstrip": false,
503
+ "normalized": false,
504
+ "rstrip": false,
505
+ "single_word": false,
506
+ "special": true
507
+ },
508
+ "100319": {
509
+ "content": "<|unused_50|>",
510
+ "lstrip": false,
511
+ "normalized": false,
512
+ "rstrip": false,
513
+ "single_word": false,
514
+ "special": true
515
+ },
516
+ "100320": {
517
+ "content": "<|unused_51|>",
518
+ "lstrip": false,
519
+ "normalized": false,
520
+ "rstrip": false,
521
+ "single_word": false,
522
+ "special": true
523
+ },
524
+ "100321": {
525
+ "content": "<|unused_52|>",
526
+ "lstrip": false,
527
+ "normalized": false,
528
+ "rstrip": false,
529
+ "single_word": false,
530
+ "special": true
531
+ },
532
+ "100322": {
533
+ "content": "<|unused_53|>",
534
+ "lstrip": false,
535
+ "normalized": false,
536
+ "rstrip": false,
537
+ "single_word": false,
538
+ "special": true
539
+ },
540
+ "100323": {
541
+ "content": "<|unused_54|>",
542
+ "lstrip": false,
543
+ "normalized": false,
544
+ "rstrip": false,
545
+ "single_word": false,
546
+ "special": true
547
+ },
548
+ "100324": {
549
+ "content": "<|unused_55|>",
550
+ "lstrip": false,
551
+ "normalized": false,
552
+ "rstrip": false,
553
+ "single_word": false,
554
+ "special": true
555
+ },
556
+ "100325": {
557
+ "content": "<|unused_56|>",
558
+ "lstrip": false,
559
+ "normalized": false,
560
+ "rstrip": false,
561
+ "single_word": false,
562
+ "special": true
563
+ },
564
+ "100326": {
565
+ "content": "<|unused_57|>",
566
+ "lstrip": false,
567
+ "normalized": false,
568
+ "rstrip": false,
569
+ "single_word": false,
570
+ "special": true
571
+ },
572
+ "100327": {
573
+ "content": "<|unused_58|>",
574
+ "lstrip": false,
575
+ "normalized": false,
576
+ "rstrip": false,
577
+ "single_word": false,
578
+ "special": true
579
+ },
580
+ "100328": {
581
+ "content": "<|unused_59|>",
582
+ "lstrip": false,
583
+ "normalized": false,
584
+ "rstrip": false,
585
+ "single_word": false,
586
+ "special": true
587
+ },
588
+ "100329": {
589
+ "content": "<|unused_60|>",
590
+ "lstrip": false,
591
+ "normalized": false,
592
+ "rstrip": false,
593
+ "single_word": false,
594
+ "special": true
595
+ },
596
+ "100330": {
597
+ "content": "<|unused_61|>",
598
+ "lstrip": false,
599
+ "normalized": false,
600
+ "rstrip": false,
601
+ "single_word": false,
602
+ "special": true
603
+ },
604
+ "100331": {
605
+ "content": "<|unused_62|>",
606
+ "lstrip": false,
607
+ "normalized": false,
608
+ "rstrip": false,
609
+ "single_word": false,
610
+ "special": true
611
+ },
612
+ "100332": {
613
+ "content": "<|unused_63|>",
614
+ "lstrip": false,
615
+ "normalized": false,
616
+ "rstrip": false,
617
+ "single_word": false,
618
+ "special": true
619
+ },
620
+ "100333": {
621
+ "content": "<|unused_64|>",
622
+ "lstrip": false,
623
+ "normalized": false,
624
+ "rstrip": false,
625
+ "single_word": false,
626
+ "special": true
627
+ },
628
+ "100334": {
629
+ "content": "<|unused_65|>",
630
+ "lstrip": false,
631
+ "normalized": false,
632
+ "rstrip": false,
633
+ "single_word": false,
634
+ "special": true
635
+ },
636
+ "100335": {
637
+ "content": "<|unused_66|>",
638
+ "lstrip": false,
639
+ "normalized": false,
640
+ "rstrip": false,
641
+ "single_word": false,
642
+ "special": true
643
+ },
644
+ "100336": {
645
+ "content": "<|unused_67|>",
646
+ "lstrip": false,
647
+ "normalized": false,
648
+ "rstrip": false,
649
+ "single_word": false,
650
+ "special": true
651
+ },
652
+ "100337": {
653
+ "content": "<|unused_68|>",
654
+ "lstrip": false,
655
+ "normalized": false,
656
+ "rstrip": false,
657
+ "single_word": false,
658
+ "special": true
659
+ },
660
+ "100338": {
661
+ "content": "<|unused_69|>",
662
+ "lstrip": false,
663
+ "normalized": false,
664
+ "rstrip": false,
665
+ "single_word": false,
666
+ "special": true
667
+ },
668
+ "100339": {
669
+ "content": "<|unused_70|>",
670
+ "lstrip": false,
671
+ "normalized": false,
672
+ "rstrip": false,
673
+ "single_word": false,
674
+ "special": true
675
+ },
676
+ "100340": {
677
+ "content": "<|unused_71|>",
678
+ "lstrip": false,
679
+ "normalized": false,
680
+ "rstrip": false,
681
+ "single_word": false,
682
+ "special": true
683
+ },
684
+ "100341": {
685
+ "content": "<|unused_72|>",
686
+ "lstrip": false,
687
+ "normalized": false,
688
+ "rstrip": false,
689
+ "single_word": false,
690
+ "special": true
691
+ },
692
+ "100342": {
693
+ "content": "<|unused_73|>",
694
+ "lstrip": false,
695
+ "normalized": false,
696
+ "rstrip": false,
697
+ "single_word": false,
698
+ "special": true
699
+ },
700
+ "100343": {
701
+ "content": "<|unused_74|>",
702
+ "lstrip": false,
703
+ "normalized": false,
704
+ "rstrip": false,
705
+ "single_word": false,
706
+ "special": true
707
+ },
708
+ "100344": {
709
+ "content": "<|unused_75|>",
710
+ "lstrip": false,
711
+ "normalized": false,
712
+ "rstrip": false,
713
+ "single_word": false,
714
+ "special": true
715
+ },
716
+ "100345": {
717
+ "content": "<|unused_76|>",
718
+ "lstrip": false,
719
+ "normalized": false,
720
+ "rstrip": false,
721
+ "single_word": false,
722
+ "special": true
723
+ },
724
+ "100346": {
725
+ "content": "<|unused_77|>",
726
+ "lstrip": false,
727
+ "normalized": false,
728
+ "rstrip": false,
729
+ "single_word": false,
730
+ "special": true
731
+ },
732
+ "100347": {
733
+ "content": "<|unused_78|>",
734
+ "lstrip": false,
735
+ "normalized": false,
736
+ "rstrip": false,
737
+ "single_word": false,
738
+ "special": true
739
+ },
740
+ "100348": {
741
+ "content": "<|unused_79|>",
742
+ "lstrip": false,
743
+ "normalized": false,
744
+ "rstrip": false,
745
+ "single_word": false,
746
+ "special": true
747
+ },
748
+ "100349": {
749
+ "content": "<|unused_80|>",
750
+ "lstrip": false,
751
+ "normalized": false,
752
+ "rstrip": false,
753
+ "single_word": false,
754
+ "special": true
755
+ },
756
+ "100350": {
757
+ "content": "<|unused_81|>",
758
+ "lstrip": false,
759
+ "normalized": false,
760
+ "rstrip": false,
761
+ "single_word": false,
762
+ "special": true
763
+ },
764
+ "100351": {
765
+ "content": "<|unused_82|>",
766
+ "lstrip": false,
767
+ "normalized": false,
768
+ "rstrip": false,
769
+ "single_word": false,
770
+ "special": true
771
+ }
772
+ },
773
+ "additional_special_tokens": [],
774
+ "backend": "tokenizers",
775
+ "bos_token": "<|end_of_text|>",
776
+ "clean_up_tokenization_spaces": false,
777
+ "eos_token": "<|end_of_text|>",
778
+ "errors": "replace",
779
+ "extra_special_tokens": {},
780
+ "fix_mistral_regex": true,
781
+ "is_local": true,
782
+ "model_max_length": 1000000000000000019884624838656,
783
+ "model_specific_special_tokens": {},
784
+ "pad_token": "<|pad|>",
785
+ "padding_side": "left",
786
+ "tokenizer_class": "GPT2Tokenizer",
787
+ "unk_token": "<|unk|>"
788
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff