ssdataanalysis commited on
Commit
6d6124f
·
verified ·
1 Parent(s): 020f811

Clear repo before clean re-upload

Browse files
README.md DELETED
@@ -1,8 +0,0 @@
1
- ---
2
- license: apache-2.0
3
- pipeline_tag: text-generation
4
- library_name: mlx
5
- base_model: ai21labs/AI21-Jamba2-3B
6
- tags:
7
- - mlx
8
- ---
 
 
 
 
 
 
 
 
 
chat_template.jinja DELETED
@@ -1,66 +0,0 @@
1
- {%- if bos_token is defined and bos_token is not none %}{{- bos_token -}}{%- endif %}
2
- {%- if tools %}
3
- {{- '<|im_start|>system\n' }}
4
- {%- if messages|length > 0 and messages[0].role == 'system' %}
5
- {{- messages[0].content + '\n\n' }}
6
- {%- endif %}
7
- {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
8
- {%- for tool in tools %}
9
- {{- "\n" }}
10
- {{- tool | tojson }}
11
- {%- endfor %}
12
- {{- "\n</tools>\n\nFor each function 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><|im_end|>\n" }}
13
- {%- else %}
14
- {%- if messages|length > 0 and messages[0].role == 'system' %}
15
- {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
16
- {%- endif %}
17
- {%- endif %}
18
- {%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
19
- {%- for message in messages[::-1] %}
20
- {%- set index = (messages|length - 1) - loop.index0 %}
21
- {%- if ns.multi_step_tool and message.role == "user" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
22
- {%- set ns.multi_step_tool = false %}
23
- {%- set ns.last_query_index = index %}
24
- {%- endif %}
25
- {%- endfor %}
26
- {%- for message in messages %}
27
- {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
28
- {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
29
- {%- elif message.role == "assistant" %}
30
- {%- set content = message.content %}
31
- {{- '<|im_start|>' + message.role + '\n' + content }}
32
- {%- if message.tool_calls %}
33
- {%- for tool_call in message.tool_calls %}
34
- {%- if (loop.first and content) or (not loop.first) %}
35
- {{- '\n' }}
36
- {%- endif %}
37
- {%- if tool_call.function %}
38
- {%- set tool_call = tool_call.function %}
39
- {%- endif %}
40
- {{- '<tool_call>\n{"name": "' }}
41
- {{- tool_call.name }}
42
- {{- '", "arguments": ' }}
43
- {%- if tool_call.arguments is string %}
44
- {{- tool_call.arguments }}
45
- {%- else %}
46
- {{- tool_call.arguments | tojson }}
47
- {%- endif %}
48
- {{- '}\n</tool_call>' }}
49
- {%- endfor %}
50
- {%- endif %}
51
- {{- '<|im_end|>\n' }}
52
- {%- elif message.role == "tool" %}
53
- {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
54
- {{- '<|im_start|>user' }}
55
- {%- endif %}
56
- {{- '\n<tool_response>\n' }}
57
- {{- message.content }}
58
- {{- '\n</tool_response>' }}
59
- {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
60
- {{- '<|im_end|>\n' }}
61
- {%- endif %}
62
- {%- endif %}
63
- {%- endfor %}
64
- {%- if add_generation_prompt %}
65
- {{- '<|im_start|>assistant\n' }}
66
- {%- endif -%}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
config.json DELETED
@@ -1,41 +0,0 @@
1
- {
2
- "architectures": [
3
- "JambaForCausalLM"
4
- ],
5
- "attention_dropout": 0.0,
6
- "attn_layer_offset": 7,
7
- "attn_layer_period": 14,
8
- "bos_token_id": 1,
9
- "dtype": "bfloat16",
10
- "eos_token_id": 2,
11
- "expert_layer_offset": 1,
12
- "expert_layer_period": 2,
13
- "hidden_act": "silu",
14
- "hidden_size": 2560,
15
- "initializer_range": 0.02,
16
- "intermediate_size": 8192,
17
- "mamba_conv_bias": true,
18
- "mamba_d_conv": 4,
19
- "mamba_d_state": 16,
20
- "mamba_dt_rank": 160,
21
- "mamba_expand": 2,
22
- "mamba_proj_bias": false,
23
- "max_position_embeddings": 262144,
24
- "model_type": "jamba",
25
- "num_attention_heads": 20,
26
- "num_experts": 1,
27
- "num_experts_per_tok": 1,
28
- "num_hidden_layers": 28,
29
- "num_key_value_heads": 1,
30
- "num_logits_to_keep": 1,
31
- "output_router_logits": false,
32
- "pad_token_id": 0,
33
- "rms_norm_eps": 1e-06,
34
- "router_aux_loss_coef": 0.001,
35
- "sliding_window": null,
36
- "tie_word_embeddings": true,
37
- "transformers_version": "4.56.1",
38
- "use_cache": true,
39
- "use_mamba_kernels": true,
40
- "vocab_size": 65536
41
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
generation_config.json DELETED
@@ -1,7 +0,0 @@
1
- {
2
- "_from_model_config": true,
3
- "bos_token_id": 1,
4
- "eos_token_id": 2,
5
- "pad_token_id": 0,
6
- "transformers_version": "4.56.1"
7
- }
 
 
 
 
 
 
 
 
model-00001-of-00002.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:3fda780efaeb2f8250805b1239bf18316ee09a9b8c842e4a48c897377bbb0648
3
- size 5349850299
 
 
 
 
model-00002-of-00002.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:3a0dd2e948be8e63780f65a1eb77e3c0429fd97a8bb64a1292b4d4d35f34bee7
3
- size 708876485
 
 
 
 
model.safetensors.index.json DELETED
@@ -1,470 +0,0 @@
1
- {
2
- "metadata": {
3
- "total_size": 6058674944,
4
- "total_parameters": 3027074432
5
- },
6
- "weight_map": {
7
- "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
8
- "model.final_layernorm.weight": "model-00002-of-00002.safetensors",
9
- "model.layers.0.feed_forward.down_proj.weight": "model-00001-of-00002.safetensors",
10
- "model.layers.0.feed_forward.gate_proj.weight": "model-00001-of-00002.safetensors",
11
- "model.layers.0.feed_forward.up_proj.weight": "model-00001-of-00002.safetensors",
12
- "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
13
- "model.layers.0.mamba.A_log": "model-00001-of-00002.safetensors",
14
- "model.layers.0.mamba.D": "model-00001-of-00002.safetensors",
15
- "model.layers.0.mamba.b_layernorm.weight": "model-00001-of-00002.safetensors",
16
- "model.layers.0.mamba.c_layernorm.weight": "model-00001-of-00002.safetensors",
17
- "model.layers.0.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
18
- "model.layers.0.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
19
- "model.layers.0.mamba.dt_layernorm.weight": "model-00001-of-00002.safetensors",
20
- "model.layers.0.mamba.dt_proj.bias": "model-00001-of-00002.safetensors",
21
- "model.layers.0.mamba.dt_proj.weight": "model-00001-of-00002.safetensors",
22
- "model.layers.0.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
23
- "model.layers.0.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
24
- "model.layers.0.mamba.x_proj.weight": "model-00001-of-00002.safetensors",
25
- "model.layers.0.pre_ff_layernorm.weight": "model-00001-of-00002.safetensors",
26
- "model.layers.1.feed_forward.down_proj.weight": "model-00001-of-00002.safetensors",
27
- "model.layers.1.feed_forward.gate_proj.weight": "model-00001-of-00002.safetensors",
28
- "model.layers.1.feed_forward.up_proj.weight": "model-00001-of-00002.safetensors",
29
- "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
30
- "model.layers.1.mamba.A_log": "model-00001-of-00002.safetensors",
31
- "model.layers.1.mamba.D": "model-00001-of-00002.safetensors",
32
- "model.layers.1.mamba.b_layernorm.weight": "model-00001-of-00002.safetensors",
33
- "model.layers.1.mamba.c_layernorm.weight": "model-00001-of-00002.safetensors",
34
- "model.layers.1.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
35
- "model.layers.1.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
36
- "model.layers.1.mamba.dt_layernorm.weight": "model-00001-of-00002.safetensors",
37
- "model.layers.1.mamba.dt_proj.bias": "model-00001-of-00002.safetensors",
38
- "model.layers.1.mamba.dt_proj.weight": "model-00001-of-00002.safetensors",
39
- "model.layers.1.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
40
- "model.layers.1.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
41
- "model.layers.1.mamba.x_proj.weight": "model-00001-of-00002.safetensors",
42
- "model.layers.1.pre_ff_layernorm.weight": "model-00001-of-00002.safetensors",
43
- "model.layers.10.feed_forward.down_proj.weight": "model-00001-of-00002.safetensors",
44
- "model.layers.10.feed_forward.gate_proj.weight": "model-00001-of-00002.safetensors",
45
- "model.layers.10.feed_forward.up_proj.weight": "model-00001-of-00002.safetensors",
46
- "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
47
- "model.layers.10.mamba.A_log": "model-00001-of-00002.safetensors",
48
- "model.layers.10.mamba.D": "model-00001-of-00002.safetensors",
49
- "model.layers.10.mamba.b_layernorm.weight": "model-00001-of-00002.safetensors",
50
- "model.layers.10.mamba.c_layernorm.weight": "model-00001-of-00002.safetensors",
51
- "model.layers.10.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
52
- "model.layers.10.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
53
- "model.layers.10.mamba.dt_layernorm.weight": "model-00001-of-00002.safetensors",
54
- "model.layers.10.mamba.dt_proj.bias": "model-00001-of-00002.safetensors",
55
- "model.layers.10.mamba.dt_proj.weight": "model-00001-of-00002.safetensors",
56
- "model.layers.10.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
57
- "model.layers.10.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
58
- "model.layers.10.mamba.x_proj.weight": "model-00001-of-00002.safetensors",
59
- "model.layers.10.pre_ff_layernorm.weight": "model-00001-of-00002.safetensors",
60
- "model.layers.11.feed_forward.down_proj.weight": "model-00001-of-00002.safetensors",
61
- "model.layers.11.feed_forward.gate_proj.weight": "model-00001-of-00002.safetensors",
62
- "model.layers.11.feed_forward.up_proj.weight": "model-00001-of-00002.safetensors",
63
- "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
64
- "model.layers.11.mamba.A_log": "model-00001-of-00002.safetensors",
65
- "model.layers.11.mamba.D": "model-00001-of-00002.safetensors",
66
- "model.layers.11.mamba.b_layernorm.weight": "model-00001-of-00002.safetensors",
67
- "model.layers.11.mamba.c_layernorm.weight": "model-00001-of-00002.safetensors",
68
- "model.layers.11.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
69
- "model.layers.11.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
70
- "model.layers.11.mamba.dt_layernorm.weight": "model-00001-of-00002.safetensors",
71
- "model.layers.11.mamba.dt_proj.bias": "model-00001-of-00002.safetensors",
72
- "model.layers.11.mamba.dt_proj.weight": "model-00001-of-00002.safetensors",
73
- "model.layers.11.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
74
- "model.layers.11.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
75
- "model.layers.11.mamba.x_proj.weight": "model-00001-of-00002.safetensors",
76
- "model.layers.11.pre_ff_layernorm.weight": "model-00001-of-00002.safetensors",
77
- "model.layers.12.feed_forward.down_proj.weight": "model-00001-of-00002.safetensors",
78
- "model.layers.12.feed_forward.gate_proj.weight": "model-00001-of-00002.safetensors",
79
- "model.layers.12.feed_forward.up_proj.weight": "model-00001-of-00002.safetensors",
80
- "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
81
- "model.layers.12.mamba.A_log": "model-00001-of-00002.safetensors",
82
- "model.layers.12.mamba.D": "model-00001-of-00002.safetensors",
83
- "model.layers.12.mamba.b_layernorm.weight": "model-00001-of-00002.safetensors",
84
- "model.layers.12.mamba.c_layernorm.weight": "model-00001-of-00002.safetensors",
85
- "model.layers.12.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
86
- "model.layers.12.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
87
- "model.layers.12.mamba.dt_layernorm.weight": "model-00001-of-00002.safetensors",
88
- "model.layers.12.mamba.dt_proj.bias": "model-00001-of-00002.safetensors",
89
- "model.layers.12.mamba.dt_proj.weight": "model-00001-of-00002.safetensors",
90
- "model.layers.12.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
91
- "model.layers.12.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
92
- "model.layers.12.mamba.x_proj.weight": "model-00001-of-00002.safetensors",
93
- "model.layers.12.pre_ff_layernorm.weight": "model-00001-of-00002.safetensors",
94
- "model.layers.13.feed_forward.down_proj.weight": "model-00001-of-00002.safetensors",
95
- "model.layers.13.feed_forward.gate_proj.weight": "model-00001-of-00002.safetensors",
96
- "model.layers.13.feed_forward.up_proj.weight": "model-00001-of-00002.safetensors",
97
- "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
98
- "model.layers.13.mamba.A_log": "model-00001-of-00002.safetensors",
99
- "model.layers.13.mamba.D": "model-00001-of-00002.safetensors",
100
- "model.layers.13.mamba.b_layernorm.weight": "model-00001-of-00002.safetensors",
101
- "model.layers.13.mamba.c_layernorm.weight": "model-00001-of-00002.safetensors",
102
- "model.layers.13.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
103
- "model.layers.13.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
104
- "model.layers.13.mamba.dt_layernorm.weight": "model-00001-of-00002.safetensors",
105
- "model.layers.13.mamba.dt_proj.bias": "model-00001-of-00002.safetensors",
106
- "model.layers.13.mamba.dt_proj.weight": "model-00001-of-00002.safetensors",
107
- "model.layers.13.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
108
- "model.layers.13.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
109
- "model.layers.13.mamba.x_proj.weight": "model-00001-of-00002.safetensors",
110
- "model.layers.13.pre_ff_layernorm.weight": "model-00001-of-00002.safetensors",
111
- "model.layers.14.feed_forward.down_proj.weight": "model-00001-of-00002.safetensors",
112
- "model.layers.14.feed_forward.gate_proj.weight": "model-00001-of-00002.safetensors",
113
- "model.layers.14.feed_forward.up_proj.weight": "model-00001-of-00002.safetensors",
114
- "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
115
- "model.layers.14.mamba.A_log": "model-00001-of-00002.safetensors",
116
- "model.layers.14.mamba.D": "model-00001-of-00002.safetensors",
117
- "model.layers.14.mamba.b_layernorm.weight": "model-00001-of-00002.safetensors",
118
- "model.layers.14.mamba.c_layernorm.weight": "model-00001-of-00002.safetensors",
119
- "model.layers.14.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
120
- "model.layers.14.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
121
- "model.layers.14.mamba.dt_layernorm.weight": "model-00001-of-00002.safetensors",
122
- "model.layers.14.mamba.dt_proj.bias": "model-00001-of-00002.safetensors",
123
- "model.layers.14.mamba.dt_proj.weight": "model-00001-of-00002.safetensors",
124
- "model.layers.14.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
125
- "model.layers.14.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
126
- "model.layers.14.mamba.x_proj.weight": "model-00001-of-00002.safetensors",
127
- "model.layers.14.pre_ff_layernorm.weight": "model-00001-of-00002.safetensors",
128
- "model.layers.15.feed_forward.down_proj.weight": "model-00001-of-00002.safetensors",
129
- "model.layers.15.feed_forward.gate_proj.weight": "model-00001-of-00002.safetensors",
130
- "model.layers.15.feed_forward.up_proj.weight": "model-00001-of-00002.safetensors",
131
- "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
132
- "model.layers.15.mamba.A_log": "model-00001-of-00002.safetensors",
133
- "model.layers.15.mamba.D": "model-00001-of-00002.safetensors",
134
- "model.layers.15.mamba.b_layernorm.weight": "model-00001-of-00002.safetensors",
135
- "model.layers.15.mamba.c_layernorm.weight": "model-00001-of-00002.safetensors",
136
- "model.layers.15.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
137
- "model.layers.15.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
138
- "model.layers.15.mamba.dt_layernorm.weight": "model-00001-of-00002.safetensors",
139
- "model.layers.15.mamba.dt_proj.bias": "model-00001-of-00002.safetensors",
140
- "model.layers.15.mamba.dt_proj.weight": "model-00001-of-00002.safetensors",
141
- "model.layers.15.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
142
- "model.layers.15.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
143
- "model.layers.15.mamba.x_proj.weight": "model-00001-of-00002.safetensors",
144
- "model.layers.15.pre_ff_layernorm.weight": "model-00001-of-00002.safetensors",
145
- "model.layers.16.feed_forward.down_proj.weight": "model-00001-of-00002.safetensors",
146
- "model.layers.16.feed_forward.gate_proj.weight": "model-00001-of-00002.safetensors",
147
- "model.layers.16.feed_forward.up_proj.weight": "model-00001-of-00002.safetensors",
148
- "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
149
- "model.layers.16.mamba.A_log": "model-00001-of-00002.safetensors",
150
- "model.layers.16.mamba.D": "model-00001-of-00002.safetensors",
151
- "model.layers.16.mamba.b_layernorm.weight": "model-00001-of-00002.safetensors",
152
- "model.layers.16.mamba.c_layernorm.weight": "model-00001-of-00002.safetensors",
153
- "model.layers.16.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
154
- "model.layers.16.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
155
- "model.layers.16.mamba.dt_layernorm.weight": "model-00001-of-00002.safetensors",
156
- "model.layers.16.mamba.dt_proj.bias": "model-00001-of-00002.safetensors",
157
- "model.layers.16.mamba.dt_proj.weight": "model-00001-of-00002.safetensors",
158
- "model.layers.16.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
159
- "model.layers.16.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
160
- "model.layers.16.mamba.x_proj.weight": "model-00001-of-00002.safetensors",
161
- "model.layers.16.pre_ff_layernorm.weight": "model-00001-of-00002.safetensors",
162
- "model.layers.17.feed_forward.down_proj.weight": "model-00001-of-00002.safetensors",
163
- "model.layers.17.feed_forward.gate_proj.weight": "model-00001-of-00002.safetensors",
164
- "model.layers.17.feed_forward.up_proj.weight": "model-00001-of-00002.safetensors",
165
- "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
166
- "model.layers.17.mamba.A_log": "model-00001-of-00002.safetensors",
167
- "model.layers.17.mamba.D": "model-00001-of-00002.safetensors",
168
- "model.layers.17.mamba.b_layernorm.weight": "model-00001-of-00002.safetensors",
169
- "model.layers.17.mamba.c_layernorm.weight": "model-00001-of-00002.safetensors",
170
- "model.layers.17.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
171
- "model.layers.17.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
172
- "model.layers.17.mamba.dt_layernorm.weight": "model-00001-of-00002.safetensors",
173
- "model.layers.17.mamba.dt_proj.bias": "model-00001-of-00002.safetensors",
174
- "model.layers.17.mamba.dt_proj.weight": "model-00001-of-00002.safetensors",
175
- "model.layers.17.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
176
- "model.layers.17.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
177
- "model.layers.17.mamba.x_proj.weight": "model-00001-of-00002.safetensors",
178
- "model.layers.17.pre_ff_layernorm.weight": "model-00001-of-00002.safetensors",
179
- "model.layers.18.feed_forward.down_proj.weight": "model-00001-of-00002.safetensors",
180
- "model.layers.18.feed_forward.gate_proj.weight": "model-00001-of-00002.safetensors",
181
- "model.layers.18.feed_forward.up_proj.weight": "model-00001-of-00002.safetensors",
182
- "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
183
- "model.layers.18.mamba.A_log": "model-00001-of-00002.safetensors",
184
- "model.layers.18.mamba.D": "model-00001-of-00002.safetensors",
185
- "model.layers.18.mamba.b_layernorm.weight": "model-00001-of-00002.safetensors",
186
- "model.layers.18.mamba.c_layernorm.weight": "model-00001-of-00002.safetensors",
187
- "model.layers.18.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
188
- "model.layers.18.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
189
- "model.layers.18.mamba.dt_layernorm.weight": "model-00001-of-00002.safetensors",
190
- "model.layers.18.mamba.dt_proj.bias": "model-00001-of-00002.safetensors",
191
- "model.layers.18.mamba.dt_proj.weight": "model-00001-of-00002.safetensors",
192
- "model.layers.18.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
193
- "model.layers.18.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
194
- "model.layers.18.mamba.x_proj.weight": "model-00001-of-00002.safetensors",
195
- "model.layers.18.pre_ff_layernorm.weight": "model-00001-of-00002.safetensors",
196
- "model.layers.19.feed_forward.down_proj.weight": "model-00001-of-00002.safetensors",
197
- "model.layers.19.feed_forward.gate_proj.weight": "model-00001-of-00002.safetensors",
198
- "model.layers.19.feed_forward.up_proj.weight": "model-00001-of-00002.safetensors",
199
- "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
200
- "model.layers.19.mamba.A_log": "model-00001-of-00002.safetensors",
201
- "model.layers.19.mamba.D": "model-00001-of-00002.safetensors",
202
- "model.layers.19.mamba.b_layernorm.weight": "model-00001-of-00002.safetensors",
203
- "model.layers.19.mamba.c_layernorm.weight": "model-00001-of-00002.safetensors",
204
- "model.layers.19.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
205
- "model.layers.19.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
206
- "model.layers.19.mamba.dt_layernorm.weight": "model-00001-of-00002.safetensors",
207
- "model.layers.19.mamba.dt_proj.bias": "model-00001-of-00002.safetensors",
208
- "model.layers.19.mamba.dt_proj.weight": "model-00001-of-00002.safetensors",
209
- "model.layers.19.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
210
- "model.layers.19.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
211
- "model.layers.19.mamba.x_proj.weight": "model-00001-of-00002.safetensors",
212
- "model.layers.19.pre_ff_layernorm.weight": "model-00001-of-00002.safetensors",
213
- "model.layers.2.feed_forward.down_proj.weight": "model-00001-of-00002.safetensors",
214
- "model.layers.2.feed_forward.gate_proj.weight": "model-00001-of-00002.safetensors",
215
- "model.layers.2.feed_forward.up_proj.weight": "model-00001-of-00002.safetensors",
216
- "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
217
- "model.layers.2.mamba.A_log": "model-00001-of-00002.safetensors",
218
- "model.layers.2.mamba.D": "model-00001-of-00002.safetensors",
219
- "model.layers.2.mamba.b_layernorm.weight": "model-00001-of-00002.safetensors",
220
- "model.layers.2.mamba.c_layernorm.weight": "model-00001-of-00002.safetensors",
221
- "model.layers.2.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
222
- "model.layers.2.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
223
- "model.layers.2.mamba.dt_layernorm.weight": "model-00001-of-00002.safetensors",
224
- "model.layers.2.mamba.dt_proj.bias": "model-00001-of-00002.safetensors",
225
- "model.layers.2.mamba.dt_proj.weight": "model-00001-of-00002.safetensors",
226
- "model.layers.2.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
227
- "model.layers.2.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
228
- "model.layers.2.mamba.x_proj.weight": "model-00001-of-00002.safetensors",
229
- "model.layers.2.pre_ff_layernorm.weight": "model-00001-of-00002.safetensors",
230
- "model.layers.20.feed_forward.down_proj.weight": "model-00001-of-00002.safetensors",
231
- "model.layers.20.feed_forward.gate_proj.weight": "model-00001-of-00002.safetensors",
232
- "model.layers.20.feed_forward.up_proj.weight": "model-00001-of-00002.safetensors",
233
- "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
234
- "model.layers.20.mamba.A_log": "model-00001-of-00002.safetensors",
235
- "model.layers.20.mamba.D": "model-00001-of-00002.safetensors",
236
- "model.layers.20.mamba.b_layernorm.weight": "model-00001-of-00002.safetensors",
237
- "model.layers.20.mamba.c_layernorm.weight": "model-00001-of-00002.safetensors",
238
- "model.layers.20.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
239
- "model.layers.20.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
240
- "model.layers.20.mamba.dt_layernorm.weight": "model-00001-of-00002.safetensors",
241
- "model.layers.20.mamba.dt_proj.bias": "model-00001-of-00002.safetensors",
242
- "model.layers.20.mamba.dt_proj.weight": "model-00001-of-00002.safetensors",
243
- "model.layers.20.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
244
- "model.layers.20.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
245
- "model.layers.20.mamba.x_proj.weight": "model-00001-of-00002.safetensors",
246
- "model.layers.20.pre_ff_layernorm.weight": "model-00001-of-00002.safetensors",
247
- "model.layers.21.feed_forward.down_proj.weight": "model-00001-of-00002.safetensors",
248
- "model.layers.21.feed_forward.gate_proj.weight": "model-00001-of-00002.safetensors",
249
- "model.layers.21.feed_forward.up_proj.weight": "model-00001-of-00002.safetensors",
250
- "model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
251
- "model.layers.21.pre_ff_layernorm.weight": "model-00001-of-00002.safetensors",
252
- "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
253
- "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
254
- "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
255
- "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
256
- "model.layers.22.feed_forward.down_proj.weight": "model-00001-of-00002.safetensors",
257
- "model.layers.22.feed_forward.gate_proj.weight": "model-00001-of-00002.safetensors",
258
- "model.layers.22.feed_forward.up_proj.weight": "model-00001-of-00002.safetensors",
259
- "model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
260
- "model.layers.22.mamba.A_log": "model-00001-of-00002.safetensors",
261
- "model.layers.22.mamba.D": "model-00001-of-00002.safetensors",
262
- "model.layers.22.mamba.b_layernorm.weight": "model-00001-of-00002.safetensors",
263
- "model.layers.22.mamba.c_layernorm.weight": "model-00001-of-00002.safetensors",
264
- "model.layers.22.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
265
- "model.layers.22.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
266
- "model.layers.22.mamba.dt_layernorm.weight": "model-00001-of-00002.safetensors",
267
- "model.layers.22.mamba.dt_proj.bias": "model-00001-of-00002.safetensors",
268
- "model.layers.22.mamba.dt_proj.weight": "model-00001-of-00002.safetensors",
269
- "model.layers.22.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
270
- "model.layers.22.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
271
- "model.layers.22.mamba.x_proj.weight": "model-00001-of-00002.safetensors",
272
- "model.layers.22.pre_ff_layernorm.weight": "model-00001-of-00002.safetensors",
273
- "model.layers.23.feed_forward.down_proj.weight": "model-00001-of-00002.safetensors",
274
- "model.layers.23.feed_forward.gate_proj.weight": "model-00001-of-00002.safetensors",
275
- "model.layers.23.feed_forward.up_proj.weight": "model-00001-of-00002.safetensors",
276
- "model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
277
- "model.layers.23.mamba.A_log": "model-00001-of-00002.safetensors",
278
- "model.layers.23.mamba.D": "model-00001-of-00002.safetensors",
279
- "model.layers.23.mamba.b_layernorm.weight": "model-00001-of-00002.safetensors",
280
- "model.layers.23.mamba.c_layernorm.weight": "model-00001-of-00002.safetensors",
281
- "model.layers.23.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
282
- "model.layers.23.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
283
- "model.layers.23.mamba.dt_layernorm.weight": "model-00001-of-00002.safetensors",
284
- "model.layers.23.mamba.dt_proj.bias": "model-00001-of-00002.safetensors",
285
- "model.layers.23.mamba.dt_proj.weight": "model-00001-of-00002.safetensors",
286
- "model.layers.23.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
287
- "model.layers.23.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
288
- "model.layers.23.mamba.x_proj.weight": "model-00001-of-00002.safetensors",
289
- "model.layers.23.pre_ff_layernorm.weight": "model-00001-of-00002.safetensors",
290
- "model.layers.24.feed_forward.down_proj.weight": "model-00002-of-00002.safetensors",
291
- "model.layers.24.feed_forward.gate_proj.weight": "model-00001-of-00002.safetensors",
292
- "model.layers.24.feed_forward.up_proj.weight": "model-00002-of-00002.safetensors",
293
- "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
294
- "model.layers.24.mamba.A_log": "model-00001-of-00002.safetensors",
295
- "model.layers.24.mamba.D": "model-00001-of-00002.safetensors",
296
- "model.layers.24.mamba.b_layernorm.weight": "model-00001-of-00002.safetensors",
297
- "model.layers.24.mamba.c_layernorm.weight": "model-00001-of-00002.safetensors",
298
- "model.layers.24.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
299
- "model.layers.24.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
300
- "model.layers.24.mamba.dt_layernorm.weight": "model-00001-of-00002.safetensors",
301
- "model.layers.24.mamba.dt_proj.bias": "model-00001-of-00002.safetensors",
302
- "model.layers.24.mamba.dt_proj.weight": "model-00001-of-00002.safetensors",
303
- "model.layers.24.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
304
- "model.layers.24.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
305
- "model.layers.24.mamba.x_proj.weight": "model-00001-of-00002.safetensors",
306
- "model.layers.24.pre_ff_layernorm.weight": "model-00002-of-00002.safetensors",
307
- "model.layers.25.feed_forward.down_proj.weight": "model-00002-of-00002.safetensors",
308
- "model.layers.25.feed_forward.gate_proj.weight": "model-00002-of-00002.safetensors",
309
- "model.layers.25.feed_forward.up_proj.weight": "model-00002-of-00002.safetensors",
310
- "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
311
- "model.layers.25.mamba.A_log": "model-00002-of-00002.safetensors",
312
- "model.layers.25.mamba.D": "model-00002-of-00002.safetensors",
313
- "model.layers.25.mamba.b_layernorm.weight": "model-00002-of-00002.safetensors",
314
- "model.layers.25.mamba.c_layernorm.weight": "model-00002-of-00002.safetensors",
315
- "model.layers.25.mamba.conv1d.bias": "model-00002-of-00002.safetensors",
316
- "model.layers.25.mamba.conv1d.weight": "model-00002-of-00002.safetensors",
317
- "model.layers.25.mamba.dt_layernorm.weight": "model-00002-of-00002.safetensors",
318
- "model.layers.25.mamba.dt_proj.bias": "model-00002-of-00002.safetensors",
319
- "model.layers.25.mamba.dt_proj.weight": "model-00002-of-00002.safetensors",
320
- "model.layers.25.mamba.in_proj.weight": "model-00002-of-00002.safetensors",
321
- "model.layers.25.mamba.out_proj.weight": "model-00002-of-00002.safetensors",
322
- "model.layers.25.mamba.x_proj.weight": "model-00002-of-00002.safetensors",
323
- "model.layers.25.pre_ff_layernorm.weight": "model-00002-of-00002.safetensors",
324
- "model.layers.26.feed_forward.down_proj.weight": "model-00002-of-00002.safetensors",
325
- "model.layers.26.feed_forward.gate_proj.weight": "model-00002-of-00002.safetensors",
326
- "model.layers.26.feed_forward.up_proj.weight": "model-00002-of-00002.safetensors",
327
- "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
328
- "model.layers.26.mamba.A_log": "model-00002-of-00002.safetensors",
329
- "model.layers.26.mamba.D": "model-00002-of-00002.safetensors",
330
- "model.layers.26.mamba.b_layernorm.weight": "model-00002-of-00002.safetensors",
331
- "model.layers.26.mamba.c_layernorm.weight": "model-00002-of-00002.safetensors",
332
- "model.layers.26.mamba.conv1d.bias": "model-00002-of-00002.safetensors",
333
- "model.layers.26.mamba.conv1d.weight": "model-00002-of-00002.safetensors",
334
- "model.layers.26.mamba.dt_layernorm.weight": "model-00002-of-00002.safetensors",
335
- "model.layers.26.mamba.dt_proj.bias": "model-00002-of-00002.safetensors",
336
- "model.layers.26.mamba.dt_proj.weight": "model-00002-of-00002.safetensors",
337
- "model.layers.26.mamba.in_proj.weight": "model-00002-of-00002.safetensors",
338
- "model.layers.26.mamba.out_proj.weight": "model-00002-of-00002.safetensors",
339
- "model.layers.26.mamba.x_proj.weight": "model-00002-of-00002.safetensors",
340
- "model.layers.26.pre_ff_layernorm.weight": "model-00002-of-00002.safetensors",
341
- "model.layers.27.feed_forward.down_proj.weight": "model-00002-of-00002.safetensors",
342
- "model.layers.27.feed_forward.gate_proj.weight": "model-00002-of-00002.safetensors",
343
- "model.layers.27.feed_forward.up_proj.weight": "model-00002-of-00002.safetensors",
344
- "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
345
- "model.layers.27.mamba.A_log": "model-00002-of-00002.safetensors",
346
- "model.layers.27.mamba.D": "model-00002-of-00002.safetensors",
347
- "model.layers.27.mamba.b_layernorm.weight": "model-00002-of-00002.safetensors",
348
- "model.layers.27.mamba.c_layernorm.weight": "model-00002-of-00002.safetensors",
349
- "model.layers.27.mamba.conv1d.bias": "model-00002-of-00002.safetensors",
350
- "model.layers.27.mamba.conv1d.weight": "model-00002-of-00002.safetensors",
351
- "model.layers.27.mamba.dt_layernorm.weight": "model-00002-of-00002.safetensors",
352
- "model.layers.27.mamba.dt_proj.bias": "model-00002-of-00002.safetensors",
353
- "model.layers.27.mamba.dt_proj.weight": "model-00002-of-00002.safetensors",
354
- "model.layers.27.mamba.in_proj.weight": "model-00002-of-00002.safetensors",
355
- "model.layers.27.mamba.out_proj.weight": "model-00002-of-00002.safetensors",
356
- "model.layers.27.mamba.x_proj.weight": "model-00002-of-00002.safetensors",
357
- "model.layers.27.pre_ff_layernorm.weight": "model-00002-of-00002.safetensors",
358
- "model.layers.3.feed_forward.down_proj.weight": "model-00001-of-00002.safetensors",
359
- "model.layers.3.feed_forward.gate_proj.weight": "model-00001-of-00002.safetensors",
360
- "model.layers.3.feed_forward.up_proj.weight": "model-00001-of-00002.safetensors",
361
- "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
362
- "model.layers.3.mamba.A_log": "model-00001-of-00002.safetensors",
363
- "model.layers.3.mamba.D": "model-00001-of-00002.safetensors",
364
- "model.layers.3.mamba.b_layernorm.weight": "model-00001-of-00002.safetensors",
365
- "model.layers.3.mamba.c_layernorm.weight": "model-00001-of-00002.safetensors",
366
- "model.layers.3.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
367
- "model.layers.3.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
368
- "model.layers.3.mamba.dt_layernorm.weight": "model-00001-of-00002.safetensors",
369
- "model.layers.3.mamba.dt_proj.bias": "model-00001-of-00002.safetensors",
370
- "model.layers.3.mamba.dt_proj.weight": "model-00001-of-00002.safetensors",
371
- "model.layers.3.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
372
- "model.layers.3.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
373
- "model.layers.3.mamba.x_proj.weight": "model-00001-of-00002.safetensors",
374
- "model.layers.3.pre_ff_layernorm.weight": "model-00001-of-00002.safetensors",
375
- "model.layers.4.feed_forward.down_proj.weight": "model-00001-of-00002.safetensors",
376
- "model.layers.4.feed_forward.gate_proj.weight": "model-00001-of-00002.safetensors",
377
- "model.layers.4.feed_forward.up_proj.weight": "model-00001-of-00002.safetensors",
378
- "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
379
- "model.layers.4.mamba.A_log": "model-00001-of-00002.safetensors",
380
- "model.layers.4.mamba.D": "model-00001-of-00002.safetensors",
381
- "model.layers.4.mamba.b_layernorm.weight": "model-00001-of-00002.safetensors",
382
- "model.layers.4.mamba.c_layernorm.weight": "model-00001-of-00002.safetensors",
383
- "model.layers.4.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
384
- "model.layers.4.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
385
- "model.layers.4.mamba.dt_layernorm.weight": "model-00001-of-00002.safetensors",
386
- "model.layers.4.mamba.dt_proj.bias": "model-00001-of-00002.safetensors",
387
- "model.layers.4.mamba.dt_proj.weight": "model-00001-of-00002.safetensors",
388
- "model.layers.4.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
389
- "model.layers.4.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
390
- "model.layers.4.mamba.x_proj.weight": "model-00001-of-00002.safetensors",
391
- "model.layers.4.pre_ff_layernorm.weight": "model-00001-of-00002.safetensors",
392
- "model.layers.5.feed_forward.down_proj.weight": "model-00001-of-00002.safetensors",
393
- "model.layers.5.feed_forward.gate_proj.weight": "model-00001-of-00002.safetensors",
394
- "model.layers.5.feed_forward.up_proj.weight": "model-00001-of-00002.safetensors",
395
- "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
396
- "model.layers.5.mamba.A_log": "model-00001-of-00002.safetensors",
397
- "model.layers.5.mamba.D": "model-00001-of-00002.safetensors",
398
- "model.layers.5.mamba.b_layernorm.weight": "model-00001-of-00002.safetensors",
399
- "model.layers.5.mamba.c_layernorm.weight": "model-00001-of-00002.safetensors",
400
- "model.layers.5.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
401
- "model.layers.5.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
402
- "model.layers.5.mamba.dt_layernorm.weight": "model-00001-of-00002.safetensors",
403
- "model.layers.5.mamba.dt_proj.bias": "model-00001-of-00002.safetensors",
404
- "model.layers.5.mamba.dt_proj.weight": "model-00001-of-00002.safetensors",
405
- "model.layers.5.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
406
- "model.layers.5.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
407
- "model.layers.5.mamba.x_proj.weight": "model-00001-of-00002.safetensors",
408
- "model.layers.5.pre_ff_layernorm.weight": "model-00001-of-00002.safetensors",
409
- "model.layers.6.feed_forward.down_proj.weight": "model-00001-of-00002.safetensors",
410
- "model.layers.6.feed_forward.gate_proj.weight": "model-00001-of-00002.safetensors",
411
- "model.layers.6.feed_forward.up_proj.weight": "model-00001-of-00002.safetensors",
412
- "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
413
- "model.layers.6.mamba.A_log": "model-00001-of-00002.safetensors",
414
- "model.layers.6.mamba.D": "model-00001-of-00002.safetensors",
415
- "model.layers.6.mamba.b_layernorm.weight": "model-00001-of-00002.safetensors",
416
- "model.layers.6.mamba.c_layernorm.weight": "model-00001-of-00002.safetensors",
417
- "model.layers.6.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
418
- "model.layers.6.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
419
- "model.layers.6.mamba.dt_layernorm.weight": "model-00001-of-00002.safetensors",
420
- "model.layers.6.mamba.dt_proj.bias": "model-00001-of-00002.safetensors",
421
- "model.layers.6.mamba.dt_proj.weight": "model-00001-of-00002.safetensors",
422
- "model.layers.6.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
423
- "model.layers.6.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
424
- "model.layers.6.mamba.x_proj.weight": "model-00001-of-00002.safetensors",
425
- "model.layers.6.pre_ff_layernorm.weight": "model-00001-of-00002.safetensors",
426
- "model.layers.7.feed_forward.down_proj.weight": "model-00001-of-00002.safetensors",
427
- "model.layers.7.feed_forward.gate_proj.weight": "model-00001-of-00002.safetensors",
428
- "model.layers.7.feed_forward.up_proj.weight": "model-00001-of-00002.safetensors",
429
- "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
430
- "model.layers.7.pre_ff_layernorm.weight": "model-00001-of-00002.safetensors",
431
- "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
432
- "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
433
- "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
434
- "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
435
- "model.layers.8.feed_forward.down_proj.weight": "model-00001-of-00002.safetensors",
436
- "model.layers.8.feed_forward.gate_proj.weight": "model-00001-of-00002.safetensors",
437
- "model.layers.8.feed_forward.up_proj.weight": "model-00001-of-00002.safetensors",
438
- "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
439
- "model.layers.8.mamba.A_log": "model-00001-of-00002.safetensors",
440
- "model.layers.8.mamba.D": "model-00001-of-00002.safetensors",
441
- "model.layers.8.mamba.b_layernorm.weight": "model-00001-of-00002.safetensors",
442
- "model.layers.8.mamba.c_layernorm.weight": "model-00001-of-00002.safetensors",
443
- "model.layers.8.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
444
- "model.layers.8.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
445
- "model.layers.8.mamba.dt_layernorm.weight": "model-00001-of-00002.safetensors",
446
- "model.layers.8.mamba.dt_proj.bias": "model-00001-of-00002.safetensors",
447
- "model.layers.8.mamba.dt_proj.weight": "model-00001-of-00002.safetensors",
448
- "model.layers.8.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
449
- "model.layers.8.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
450
- "model.layers.8.mamba.x_proj.weight": "model-00001-of-00002.safetensors",
451
- "model.layers.8.pre_ff_layernorm.weight": "model-00001-of-00002.safetensors",
452
- "model.layers.9.feed_forward.down_proj.weight": "model-00001-of-00002.safetensors",
453
- "model.layers.9.feed_forward.gate_proj.weight": "model-00001-of-00002.safetensors",
454
- "model.layers.9.feed_forward.up_proj.weight": "model-00001-of-00002.safetensors",
455
- "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
456
- "model.layers.9.mamba.A_log": "model-00001-of-00002.safetensors",
457
- "model.layers.9.mamba.D": "model-00001-of-00002.safetensors",
458
- "model.layers.9.mamba.b_layernorm.weight": "model-00001-of-00002.safetensors",
459
- "model.layers.9.mamba.c_layernorm.weight": "model-00001-of-00002.safetensors",
460
- "model.layers.9.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
461
- "model.layers.9.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
462
- "model.layers.9.mamba.dt_layernorm.weight": "model-00001-of-00002.safetensors",
463
- "model.layers.9.mamba.dt_proj.bias": "model-00001-of-00002.safetensors",
464
- "model.layers.9.mamba.dt_proj.weight": "model-00001-of-00002.safetensors",
465
- "model.layers.9.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
466
- "model.layers.9.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
467
- "model.layers.9.mamba.x_proj.weight": "model-00001-of-00002.safetensors",
468
- "model.layers.9.pre_ff_layernorm.weight": "model-00001-of-00002.safetensors"
469
- }
470
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
tokenizer.json DELETED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json DELETED
@@ -1,16 +0,0 @@
1
- {
2
- "add_prefix_space": null,
3
- "backend": "tokenizers",
4
- "bos_token": "<|startoftext|>",
5
- "clean_up_tokenization_spaces": false,
6
- "eos_token": "<|im_end|>",
7
- "is_local": true,
8
- "legacy": true,
9
- "model_max_length": 1000000000000000019884624838656,
10
- "pad_token": "<|pad|>",
11
- "spaces_between_special_tokens": false,
12
- "tokenizer_class": "TokenizersBackend",
13
- "tool_parser_type": "json_tools",
14
- "unk_token": "<|unk|>",
15
- "use_default_system_prompt": false
16
- }