Hugging Face's logo

hybridaione
/
LFM2.5-1.2B-Text2SQL-MLX

Text Generation
MLX
Safetensors
English
lfm2
text2sql
sql
fine-tuned
lora
conversational
Model card Files
xet
Community
furukama commited on
Commit
1d4d4c2
·
verified ·
1 Parent(s): a89ac80

Upload folder using huggingface_hub

Browse files
Files changed (8) hide show
  1. README.md +42 -0
  2. chat_template.jinja +45 -0
  3. config.json +67 -0
  4. generation_config.json +7 -0
  5. model.safetensors +3 -0
  6. model.safetensors.index.json +342 -0
  7. tokenizer.json +0 -0
  8. tokenizer_config.json +20 -0
README.md ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: LiquidAI/LFM2.5-1.2B-Instruct
4
+ tags:
5
+ - text-to-sql
6
+ - sql
7
+ - mlx
8
+ - 4-bit
9
+ language:
10
+ - en
11
+ pipeline_tag: text-generation
12
+ library_name: mlx
13
+ ---
14
+
15
+ # LFM2.5-1.2B-Text2SQL (MLX 4-bit)
16
+
17
+ MLX-optimized 4-bit quantized version for Apple Silicon.
18
+
19
+ ## Usage
20
+
21
+ ```python
22
+ from mlx_lm import load, generate
23
+
24
+ model, tokenizer = load("hybridaione/LFM2.5-1.2B-Text2SQL-MLX")
25
+
26
+ prompt = '''<|im_start|>system
27
+ You are an expert SQL writer.<|im_end|>
28
+ <|im_start|>user
29
+ Schema:
30
+ CREATE TABLE users (id INTEGER, name TEXT);
31
+
32
+ Question: Count all users<|im_end|>
33
+ <|im_start|>assistant
34
+ '''
35
+
36
+ response = generate(model, tokenizer, prompt=prompt, max_tokens=256)
37
+ print(response)
38
+ ```
39
+
40
+ ## Other Formats
41
+ - **PyTorch/vLLM**: [hybridaione/LFM2.5-1.2B-Text2SQL](https://huggingface.co/hybridaione/LFM2.5-1.2B-Text2SQL)
42
+ - **GGUF**: [hybridaione/LFM2.5-1.2B-Text2SQL-GGUF](https://huggingface.co/hybridaione/LFM2.5-1.2B-Text2SQL-GGUF)
chat_template.jinja ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {{- bos_token -}}
2
+ {%- set keep_past_thinking = keep_past_thinking | default(false) -%}
3
+ {%- set ns = namespace(system_prompt="") -%}
4
+ {%- if messages[0]["role"] == "system" -%}
5
+ {%- set ns.system_prompt = messages[0]["content"] -%}
6
+ {%- set messages = messages[1:] -%}
7
+ {%- endif -%}
8
+ {%- if tools -%}
9
+ {%- set ns.system_prompt = ns.system_prompt + ("\n" if ns.system_prompt else "") + "List of tools: [" -%}
10
+ {%- for tool in tools -%}
11
+ {%- if tool is not string -%}
12
+ {%- set tool = tool | tojson -%}
13
+ {%- endif -%}
14
+ {%- set ns.system_prompt = ns.system_prompt + tool -%}
15
+ {%- if not loop.last -%}
16
+ {%- set ns.system_prompt = ns.system_prompt + ", " -%}
17
+ {%- endif -%}
18
+ {%- endfor -%}
19
+ {%- set ns.system_prompt = ns.system_prompt + "]" -%}
20
+ {%- endif -%}
21
+ {%- if ns.system_prompt -%}
22
+ {{- "<|im_start|>system\n" + ns.system_prompt + "<|im_end|>\n" -}}
23
+ {%- endif -%}
24
+ {%- set ns.last_assistant_index = -1 -%}
25
+ {%- for message in messages -%}
26
+ {%- if message["role"] == "assistant" -%}
27
+ {%- set ns.last_assistant_index = loop.index0 -%}
28
+ {%- endif -%}
29
+ {%- endfor -%}
30
+ {%- for message in messages -%}
31
+ {{- "<|im_start|>" + message["role"] + "\n" -}}
32
+ {%- set content = message["content"] -%}
33
+ {%- if content is not string -%}
34
+ {%- set content = content | tojson -%}
35
+ {%- endif -%}
36
+ {%- if message["role"] == "assistant" and not keep_past_thinking and loop.index0 != ns.last_assistant_index -%}
37
+ {%- if "</think>" in content -%}
38
+ {%- set content = content.split("</think>")[-1] | trim -%}
39
+ {%- endif -%}
40
+ {%- endif -%}
41
+ {{- content + "<|im_end|>\n" -}}
42
+ {%- endfor -%}
43
+ {%- if add_generation_prompt -%}
44
+ {{- "<|im_start|>assistant\n" -}}
45
+ {%- endif -%}
config.json ADDED
@@ -0,0 +1,67 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Lfm2ForCausalLM"
4
+ ],
5
+ "block_auto_adjust_ff_dim": true,
6
+ "block_dim": 2048,
7
+ "block_ff_dim": 12288,
8
+ "block_ffn_dim_multiplier": 1.0,
9
+ "block_mlp_init_scale": 1.0,
10
+ "block_multiple_of": 256,
11
+ "block_norm_eps": 1e-05,
12
+ "block_out_init_scale": 1.0,
13
+ "block_use_swiglu": true,
14
+ "block_use_xavier_init": true,
15
+ "bos_token_id": 1,
16
+ "conv_L_cache": 3,
17
+ "conv_bias": false,
18
+ "conv_dim": 2048,
19
+ "conv_use_xavier_init": true,
20
+ "dtype": "bfloat16",
21
+ "eos_token_id": 7,
22
+ "hidden_size": 2048,
23
+ "initializer_range": 0.02,
24
+ "intermediate_size": 12288,
25
+ "layer_types": [
26
+ "conv",
27
+ "conv",
28
+ "full_attention",
29
+ "conv",
30
+ "conv",
31
+ "full_attention",
32
+ "conv",
33
+ "conv",
34
+ "full_attention",
35
+ "conv",
36
+ "full_attention",
37
+ "conv",
38
+ "full_attention",
39
+ "conv",
40
+ "full_attention",
41
+ "conv"
42
+ ],
43
+ "max_position_embeddings": 128000,
44
+ "model_type": "lfm2",
45
+ "norm_eps": 1e-05,
46
+ "num_attention_heads": 32,
47
+ "num_heads": 32,
48
+ "num_hidden_layers": 16,
49
+ "num_key_value_heads": 8,
50
+ "pad_token_id": 0,
51
+ "quantization": {
52
+ "group_size": 64,
53
+ "bits": 4,
54
+ "mode": "affine"
55
+ },
56
+ "quantization_config": {
57
+ "group_size": 64,
58
+ "bits": 4,
59
+ "mode": "affine"
60
+ },
61
+ "rope_theta": 1000000.0,
62
+ "tie_embedding": true,
63
+ "transformers_version": "4.57.2",
64
+ "use_cache": true,
65
+ "use_pos_enc": true,
66
+ "vocab_size": 65536
67
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 7,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.57.2"
7
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa003939b5a7009c2095b03333ebdd6e5b1b12e515974b1d23df4fa08ab1957a
3
+ size 658540250
model.safetensors.index.json ADDED
@@ -0,0 +1,342 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 658503168,
4
+ "total_parameters": 1170340608
5
+ },
6
+ "weight_map": {
7
+ "model.embed_tokens.biases": "model.safetensors",
8
+ "model.embed_tokens.scales": "model.safetensors",
9
+ "model.embed_tokens.weight": "model.safetensors",
10
+ "model.embedding_norm.weight": "model.safetensors",
11
+ "model.layers.0.conv.conv.weight": "model.safetensors",
12
+ "model.layers.0.conv.in_proj.biases": "model.safetensors",
13
+ "model.layers.0.conv.in_proj.scales": "model.safetensors",
14
+ "model.layers.0.conv.in_proj.weight": "model.safetensors",
15
+ "model.layers.0.conv.out_proj.biases": "model.safetensors",
16
+ "model.layers.0.conv.out_proj.scales": "model.safetensors",
17
+ "model.layers.0.conv.out_proj.weight": "model.safetensors",
18
+ "model.layers.0.feed_forward.w1.biases": "model.safetensors",
19
+ "model.layers.0.feed_forward.w1.scales": "model.safetensors",
20
+ "model.layers.0.feed_forward.w1.weight": "model.safetensors",
21
+ "model.layers.0.feed_forward.w2.biases": "model.safetensors",
22
+ "model.layers.0.feed_forward.w2.scales": "model.safetensors",
23
+ "model.layers.0.feed_forward.w2.weight": "model.safetensors",
24
+ "model.layers.0.feed_forward.w3.biases": "model.safetensors",
25
+ "model.layers.0.feed_forward.w3.scales": "model.safetensors",
26
+ "model.layers.0.feed_forward.w3.weight": "model.safetensors",
27
+ "model.layers.0.ffn_norm.weight": "model.safetensors",
28
+ "model.layers.0.operator_norm.weight": "model.safetensors",
29
+ "model.layers.1.conv.conv.weight": "model.safetensors",
30
+ "model.layers.1.conv.in_proj.biases": "model.safetensors",
31
+ "model.layers.1.conv.in_proj.scales": "model.safetensors",
32
+ "model.layers.1.conv.in_proj.weight": "model.safetensors",
33
+ "model.layers.1.conv.out_proj.biases": "model.safetensors",
34
+ "model.layers.1.conv.out_proj.scales": "model.safetensors",
35
+ "model.layers.1.conv.out_proj.weight": "model.safetensors",
36
+ "model.layers.1.feed_forward.w1.biases": "model.safetensors",
37
+ "model.layers.1.feed_forward.w1.scales": "model.safetensors",
38
+ "model.layers.1.feed_forward.w1.weight": "model.safetensors",
39
+ "model.layers.1.feed_forward.w2.biases": "model.safetensors",
40
+ "model.layers.1.feed_forward.w2.scales": "model.safetensors",
41
+ "model.layers.1.feed_forward.w2.weight": "model.safetensors",
42
+ "model.layers.1.feed_forward.w3.biases": "model.safetensors",
43
+ "model.layers.1.feed_forward.w3.scales": "model.safetensors",
44
+ "model.layers.1.feed_forward.w3.weight": "model.safetensors",
45
+ "model.layers.1.ffn_norm.weight": "model.safetensors",
46
+ "model.layers.1.operator_norm.weight": "model.safetensors",
47
+ "model.layers.10.feed_forward.w1.biases": "model.safetensors",
48
+ "model.layers.10.feed_forward.w1.scales": "model.safetensors",
49
+ "model.layers.10.feed_forward.w1.weight": "model.safetensors",
50
+ "model.layers.10.feed_forward.w2.biases": "model.safetensors",
51
+ "model.layers.10.feed_forward.w2.scales": "model.safetensors",
52
+ "model.layers.10.feed_forward.w2.weight": "model.safetensors",
53
+ "model.layers.10.feed_forward.w3.biases": "model.safetensors",
54
+ "model.layers.10.feed_forward.w3.scales": "model.safetensors",
55
+ "model.layers.10.feed_forward.w3.weight": "model.safetensors",
56
+ "model.layers.10.ffn_norm.weight": "model.safetensors",
57
+ "model.layers.10.operator_norm.weight": "model.safetensors",
58
+ "model.layers.10.self_attn.k_layernorm.weight": "model.safetensors",
59
+ "model.layers.10.self_attn.k_proj.biases": "model.safetensors",
60
+ "model.layers.10.self_attn.k_proj.scales": "model.safetensors",
61
+ "model.layers.10.self_attn.k_proj.weight": "model.safetensors",
62
+ "model.layers.10.self_attn.out_proj.biases": "model.safetensors",
63
+ "model.layers.10.self_attn.out_proj.scales": "model.safetensors",
64
+ "model.layers.10.self_attn.out_proj.weight": "model.safetensors",
65
+ "model.layers.10.self_attn.q_layernorm.weight": "model.safetensors",
66
+ "model.layers.10.self_attn.q_proj.biases": "model.safetensors",
67
+ "model.layers.10.self_attn.q_proj.scales": "model.safetensors",
68
+ "model.layers.10.self_attn.q_proj.weight": "model.safetensors",
69
+ "model.layers.10.self_attn.v_proj.biases": "model.safetensors",
70
+ "model.layers.10.self_attn.v_proj.scales": "model.safetensors",
71
+ "model.layers.10.self_attn.v_proj.weight": "model.safetensors",
72
+ "model.layers.11.conv.conv.weight": "model.safetensors",
73
+ "model.layers.11.conv.in_proj.biases": "model.safetensors",
74
+ "model.layers.11.conv.in_proj.scales": "model.safetensors",
75
+ "model.layers.11.conv.in_proj.weight": "model.safetensors",
76
+ "model.layers.11.conv.out_proj.biases": "model.safetensors",
77
+ "model.layers.11.conv.out_proj.scales": "model.safetensors",
78
+ "model.layers.11.conv.out_proj.weight": "model.safetensors",
79
+ "model.layers.11.feed_forward.w1.biases": "model.safetensors",
80
+ "model.layers.11.feed_forward.w1.scales": "model.safetensors",
81
+ "model.layers.11.feed_forward.w1.weight": "model.safetensors",
82
+ "model.layers.11.feed_forward.w2.biases": "model.safetensors",
83
+ "model.layers.11.feed_forward.w2.scales": "model.safetensors",
84
+ "model.layers.11.feed_forward.w2.weight": "model.safetensors",
85
+ "model.layers.11.feed_forward.w3.biases": "model.safetensors",
86
+ "model.layers.11.feed_forward.w3.scales": "model.safetensors",
87
+ "model.layers.11.feed_forward.w3.weight": "model.safetensors",
88
+ "model.layers.11.ffn_norm.weight": "model.safetensors",
89
+ "model.layers.11.operator_norm.weight": "model.safetensors",
90
+ "model.layers.12.feed_forward.w1.biases": "model.safetensors",
91
+ "model.layers.12.feed_forward.w1.scales": "model.safetensors",
92
+ "model.layers.12.feed_forward.w1.weight": "model.safetensors",
93
+ "model.layers.12.feed_forward.w2.biases": "model.safetensors",
94
+ "model.layers.12.feed_forward.w2.scales": "model.safetensors",
95
+ "model.layers.12.feed_forward.w2.weight": "model.safetensors",
96
+ "model.layers.12.feed_forward.w3.biases": "model.safetensors",
97
+ "model.layers.12.feed_forward.w3.scales": "model.safetensors",
98
+ "model.layers.12.feed_forward.w3.weight": "model.safetensors",
99
+ "model.layers.12.ffn_norm.weight": "model.safetensors",
100
+ "model.layers.12.operator_norm.weight": "model.safetensors",
101
+ "model.layers.12.self_attn.k_layernorm.weight": "model.safetensors",
102
+ "model.layers.12.self_attn.k_proj.biases": "model.safetensors",
103
+ "model.layers.12.self_attn.k_proj.scales": "model.safetensors",
104
+ "model.layers.12.self_attn.k_proj.weight": "model.safetensors",
105
+ "model.layers.12.self_attn.out_proj.biases": "model.safetensors",
106
+ "model.layers.12.self_attn.out_proj.scales": "model.safetensors",
107
+ "model.layers.12.self_attn.out_proj.weight": "model.safetensors",
108
+ "model.layers.12.self_attn.q_layernorm.weight": "model.safetensors",
109
+ "model.layers.12.self_attn.q_proj.biases": "model.safetensors",
110
+ "model.layers.12.self_attn.q_proj.scales": "model.safetensors",
111
+ "model.layers.12.self_attn.q_proj.weight": "model.safetensors",
112
+ "model.layers.12.self_attn.v_proj.biases": "model.safetensors",
113
+ "model.layers.12.self_attn.v_proj.scales": "model.safetensors",
114
+ "model.layers.12.self_attn.v_proj.weight": "model.safetensors",
115
+ "model.layers.13.conv.conv.weight": "model.safetensors",
116
+ "model.layers.13.conv.in_proj.biases": "model.safetensors",
117
+ "model.layers.13.conv.in_proj.scales": "model.safetensors",
118
+ "model.layers.13.conv.in_proj.weight": "model.safetensors",
119
+ "model.layers.13.conv.out_proj.biases": "model.safetensors",
120
+ "model.layers.13.conv.out_proj.scales": "model.safetensors",
121
+ "model.layers.13.conv.out_proj.weight": "model.safetensors",
122
+ "model.layers.13.feed_forward.w1.biases": "model.safetensors",
123
+ "model.layers.13.feed_forward.w1.scales": "model.safetensors",
124
+ "model.layers.13.feed_forward.w1.weight": "model.safetensors",
125
+ "model.layers.13.feed_forward.w2.biases": "model.safetensors",
126
+ "model.layers.13.feed_forward.w2.scales": "model.safetensors",
127
+ "model.layers.13.feed_forward.w2.weight": "model.safetensors",
128
+ "model.layers.13.feed_forward.w3.biases": "model.safetensors",
129
+ "model.layers.13.feed_forward.w3.scales": "model.safetensors",
130
+ "model.layers.13.feed_forward.w3.weight": "model.safetensors",
131
+ "model.layers.13.ffn_norm.weight": "model.safetensors",
132
+ "model.layers.13.operator_norm.weight": "model.safetensors",
133
+ "model.layers.14.feed_forward.w1.biases": "model.safetensors",
134
+ "model.layers.14.feed_forward.w1.scales": "model.safetensors",
135
+ "model.layers.14.feed_forward.w1.weight": "model.safetensors",
136
+ "model.layers.14.feed_forward.w2.biases": "model.safetensors",
137
+ "model.layers.14.feed_forward.w2.scales": "model.safetensors",
138
+ "model.layers.14.feed_forward.w2.weight": "model.safetensors",
139
+ "model.layers.14.feed_forward.w3.biases": "model.safetensors",
140
+ "model.layers.14.feed_forward.w3.scales": "model.safetensors",
141
+ "model.layers.14.feed_forward.w3.weight": "model.safetensors",
142
+ "model.layers.14.ffn_norm.weight": "model.safetensors",
143
+ "model.layers.14.operator_norm.weight": "model.safetensors",
144
+ "model.layers.14.self_attn.k_layernorm.weight": "model.safetensors",
145
+ "model.layers.14.self_attn.k_proj.biases": "model.safetensors",
146
+ "model.layers.14.self_attn.k_proj.scales": "model.safetensors",
147
+ "model.layers.14.self_attn.k_proj.weight": "model.safetensors",
148
+ "model.layers.14.self_attn.out_proj.biases": "model.safetensors",
149
+ "model.layers.14.self_attn.out_proj.scales": "model.safetensors",
150
+ "model.layers.14.self_attn.out_proj.weight": "model.safetensors",
151
+ "model.layers.14.self_attn.q_layernorm.weight": "model.safetensors",
152
+ "model.layers.14.self_attn.q_proj.biases": "model.safetensors",
153
+ "model.layers.14.self_attn.q_proj.scales": "model.safetensors",
154
+ "model.layers.14.self_attn.q_proj.weight": "model.safetensors",
155
+ "model.layers.14.self_attn.v_proj.biases": "model.safetensors",
156
+ "model.layers.14.self_attn.v_proj.scales": "model.safetensors",
157
+ "model.layers.14.self_attn.v_proj.weight": "model.safetensors",
158
+ "model.layers.15.conv.conv.weight": "model.safetensors",
159
+ "model.layers.15.conv.in_proj.biases": "model.safetensors",
160
+ "model.layers.15.conv.in_proj.scales": "model.safetensors",
161
+ "model.layers.15.conv.in_proj.weight": "model.safetensors",
162
+ "model.layers.15.conv.out_proj.biases": "model.safetensors",
163
+ "model.layers.15.conv.out_proj.scales": "model.safetensors",
164
+ "model.layers.15.conv.out_proj.weight": "model.safetensors",
165
+ "model.layers.15.feed_forward.w1.biases": "model.safetensors",
166
+ "model.layers.15.feed_forward.w1.scales": "model.safetensors",
167
+ "model.layers.15.feed_forward.w1.weight": "model.safetensors",
168
+ "model.layers.15.feed_forward.w2.biases": "model.safetensors",
169
+ "model.layers.15.feed_forward.w2.scales": "model.safetensors",
170
+ "model.layers.15.feed_forward.w2.weight": "model.safetensors",
171
+ "model.layers.15.feed_forward.w3.biases": "model.safetensors",
172
+ "model.layers.15.feed_forward.w3.scales": "model.safetensors",
173
+ "model.layers.15.feed_forward.w3.weight": "model.safetensors",
174
+ "model.layers.15.ffn_norm.weight": "model.safetensors",
175
+ "model.layers.15.operator_norm.weight": "model.safetensors",
176
+ "model.layers.2.feed_forward.w1.biases": "model.safetensors",
177
+ "model.layers.2.feed_forward.w1.scales": "model.safetensors",
178
+ "model.layers.2.feed_forward.w1.weight": "model.safetensors",
179
+ "model.layers.2.feed_forward.w2.biases": "model.safetensors",
180
+ "model.layers.2.feed_forward.w2.scales": "model.safetensors",
181
+ "model.layers.2.feed_forward.w2.weight": "model.safetensors",
182
+ "model.layers.2.feed_forward.w3.biases": "model.safetensors",
183
+ "model.layers.2.feed_forward.w3.scales": "model.safetensors",
184
+ "model.layers.2.feed_forward.w3.weight": "model.safetensors",
185
+ "model.layers.2.ffn_norm.weight": "model.safetensors",
186
+ "model.layers.2.operator_norm.weight": "model.safetensors",
187
+ "model.layers.2.self_attn.k_layernorm.weight": "model.safetensors",
188
+ "model.layers.2.self_attn.k_proj.biases": "model.safetensors",
189
+ "model.layers.2.self_attn.k_proj.scales": "model.safetensors",
190
+ "model.layers.2.self_attn.k_proj.weight": "model.safetensors",
191
+ "model.layers.2.self_attn.out_proj.biases": "model.safetensors",
192
+ "model.layers.2.self_attn.out_proj.scales": "model.safetensors",
193
+ "model.layers.2.self_attn.out_proj.weight": "model.safetensors",
194
+ "model.layers.2.self_attn.q_layernorm.weight": "model.safetensors",
195
+ "model.layers.2.self_attn.q_proj.biases": "model.safetensors",
196
+ "model.layers.2.self_attn.q_proj.scales": "model.safetensors",
197
+ "model.layers.2.self_attn.q_proj.weight": "model.safetensors",
198
+ "model.layers.2.self_attn.v_proj.biases": "model.safetensors",
199
+ "model.layers.2.self_attn.v_proj.scales": "model.safetensors",
200
+ "model.layers.2.self_attn.v_proj.weight": "model.safetensors",
201
+ "model.layers.3.conv.conv.weight": "model.safetensors",
202
+ "model.layers.3.conv.in_proj.biases": "model.safetensors",
203
+ "model.layers.3.conv.in_proj.scales": "model.safetensors",
204
+ "model.layers.3.conv.in_proj.weight": "model.safetensors",
205
+ "model.layers.3.conv.out_proj.biases": "model.safetensors",
206
+ "model.layers.3.conv.out_proj.scales": "model.safetensors",
207
+ "model.layers.3.conv.out_proj.weight": "model.safetensors",
208
+ "model.layers.3.feed_forward.w1.biases": "model.safetensors",
209
+ "model.layers.3.feed_forward.w1.scales": "model.safetensors",
210
+ "model.layers.3.feed_forward.w1.weight": "model.safetensors",
211
+ "model.layers.3.feed_forward.w2.biases": "model.safetensors",
212
+ "model.layers.3.feed_forward.w2.scales": "model.safetensors",
213
+ "model.layers.3.feed_forward.w2.weight": "model.safetensors",
214
+ "model.layers.3.feed_forward.w3.biases": "model.safetensors",
215
+ "model.layers.3.feed_forward.w3.scales": "model.safetensors",
216
+ "model.layers.3.feed_forward.w3.weight": "model.safetensors",
217
+ "model.layers.3.ffn_norm.weight": "model.safetensors",
218
+ "model.layers.3.operator_norm.weight": "model.safetensors",
219
+ "model.layers.4.conv.conv.weight": "model.safetensors",
220
+ "model.layers.4.conv.in_proj.biases": "model.safetensors",
221
+ "model.layers.4.conv.in_proj.scales": "model.safetensors",
222
+ "model.layers.4.conv.in_proj.weight": "model.safetensors",
223
+ "model.layers.4.conv.out_proj.biases": "model.safetensors",
224
+ "model.layers.4.conv.out_proj.scales": "model.safetensors",
225
+ "model.layers.4.conv.out_proj.weight": "model.safetensors",
226
+ "model.layers.4.feed_forward.w1.biases": "model.safetensors",
227
+ "model.layers.4.feed_forward.w1.scales": "model.safetensors",
228
+ "model.layers.4.feed_forward.w1.weight": "model.safetensors",
229
+ "model.layers.4.feed_forward.w2.biases": "model.safetensors",
230
+ "model.layers.4.feed_forward.w2.scales": "model.safetensors",
231
+ "model.layers.4.feed_forward.w2.weight": "model.safetensors",
232
+ "model.layers.4.feed_forward.w3.biases": "model.safetensors",
233
+ "model.layers.4.feed_forward.w3.scales": "model.safetensors",
234
+ "model.layers.4.feed_forward.w3.weight": "model.safetensors",
235
+ "model.layers.4.ffn_norm.weight": "model.safetensors",
236
+ "model.layers.4.operator_norm.weight": "model.safetensors",
237
+ "model.layers.5.feed_forward.w1.biases": "model.safetensors",
238
+ "model.layers.5.feed_forward.w1.scales": "model.safetensors",
239
+ "model.layers.5.feed_forward.w1.weight": "model.safetensors",
240
+ "model.layers.5.feed_forward.w2.biases": "model.safetensors",
241
+ "model.layers.5.feed_forward.w2.scales": "model.safetensors",
242
+ "model.layers.5.feed_forward.w2.weight": "model.safetensors",
243
+ "model.layers.5.feed_forward.w3.biases": "model.safetensors",
244
+ "model.layers.5.feed_forward.w3.scales": "model.safetensors",
245
+ "model.layers.5.feed_forward.w3.weight": "model.safetensors",
246
+ "model.layers.5.ffn_norm.weight": "model.safetensors",
247
+ "model.layers.5.operator_norm.weight": "model.safetensors",
248
+ "model.layers.5.self_attn.k_layernorm.weight": "model.safetensors",
249
+ "model.layers.5.self_attn.k_proj.biases": "model.safetensors",
250
+ "model.layers.5.self_attn.k_proj.scales": "model.safetensors",
251
+ "model.layers.5.self_attn.k_proj.weight": "model.safetensors",
252
+ "model.layers.5.self_attn.out_proj.biases": "model.safetensors",
253
+ "model.layers.5.self_attn.out_proj.scales": "model.safetensors",
254
+ "model.layers.5.self_attn.out_proj.weight": "model.safetensors",
255
+ "model.layers.5.self_attn.q_layernorm.weight": "model.safetensors",
256
+ "model.layers.5.self_attn.q_proj.biases": "model.safetensors",
257
+ "model.layers.5.self_attn.q_proj.scales": "model.safetensors",
258
+ "model.layers.5.self_attn.q_proj.weight": "model.safetensors",
259
+ "model.layers.5.self_attn.v_proj.biases": "model.safetensors",
260
+ "model.layers.5.self_attn.v_proj.scales": "model.safetensors",
261
+ "model.layers.5.self_attn.v_proj.weight": "model.safetensors",
262
+ "model.layers.6.conv.conv.weight": "model.safetensors",
263
+ "model.layers.6.conv.in_proj.biases": "model.safetensors",
264
+ "model.layers.6.conv.in_proj.scales": "model.safetensors",
265
+ "model.layers.6.conv.in_proj.weight": "model.safetensors",
266
+ "model.layers.6.conv.out_proj.biases": "model.safetensors",
267
+ "model.layers.6.conv.out_proj.scales": "model.safetensors",
268
+ "model.layers.6.conv.out_proj.weight": "model.safetensors",
269
+ "model.layers.6.feed_forward.w1.biases": "model.safetensors",
270
+ "model.layers.6.feed_forward.w1.scales": "model.safetensors",
271
+ "model.layers.6.feed_forward.w1.weight": "model.safetensors",
272
+ "model.layers.6.feed_forward.w2.biases": "model.safetensors",
273
+ "model.layers.6.feed_forward.w2.scales": "model.safetensors",
274
+ "model.layers.6.feed_forward.w2.weight": "model.safetensors",
275
+ "model.layers.6.feed_forward.w3.biases": "model.safetensors",
276
+ "model.layers.6.feed_forward.w3.scales": "model.safetensors",
277
+ "model.layers.6.feed_forward.w3.weight": "model.safetensors",
278
+ "model.layers.6.ffn_norm.weight": "model.safetensors",
279
+ "model.layers.6.operator_norm.weight": "model.safetensors",
280
+ "model.layers.7.conv.conv.weight": "model.safetensors",
281
+ "model.layers.7.conv.in_proj.biases": "model.safetensors",
282
+ "model.layers.7.conv.in_proj.scales": "model.safetensors",
283
+ "model.layers.7.conv.in_proj.weight": "model.safetensors",
284
+ "model.layers.7.conv.out_proj.biases": "model.safetensors",
285
+ "model.layers.7.conv.out_proj.scales": "model.safetensors",
286
+ "model.layers.7.conv.out_proj.weight": "model.safetensors",
287
+ "model.layers.7.feed_forward.w1.biases": "model.safetensors",
288
+ "model.layers.7.feed_forward.w1.scales": "model.safetensors",
289
+ "model.layers.7.feed_forward.w1.weight": "model.safetensors",
290
+ "model.layers.7.feed_forward.w2.biases": "model.safetensors",
291
+ "model.layers.7.feed_forward.w2.scales": "model.safetensors",
292
+ "model.layers.7.feed_forward.w2.weight": "model.safetensors",
293
+ "model.layers.7.feed_forward.w3.biases": "model.safetensors",
294
+ "model.layers.7.feed_forward.w3.scales": "model.safetensors",
295
+ "model.layers.7.feed_forward.w3.weight": "model.safetensors",
296
+ "model.layers.7.ffn_norm.weight": "model.safetensors",
297
+ "model.layers.7.operator_norm.weight": "model.safetensors",
298
+ "model.layers.8.feed_forward.w1.biases": "model.safetensors",
299
+ "model.layers.8.feed_forward.w1.scales": "model.safetensors",
300
+ "model.layers.8.feed_forward.w1.weight": "model.safetensors",
301
+ "model.layers.8.feed_forward.w2.biases": "model.safetensors",
302
+ "model.layers.8.feed_forward.w2.scales": "model.safetensors",
303
+ "model.layers.8.feed_forward.w2.weight": "model.safetensors",
304
+ "model.layers.8.feed_forward.w3.biases": "model.safetensors",
305
+ "model.layers.8.feed_forward.w3.scales": "model.safetensors",
306
+ "model.layers.8.feed_forward.w3.weight": "model.safetensors",
307
+ "model.layers.8.ffn_norm.weight": "model.safetensors",
308
+ "model.layers.8.operator_norm.weight": "model.safetensors",
309
+ "model.layers.8.self_attn.k_layernorm.weight": "model.safetensors",
310
+ "model.layers.8.self_attn.k_proj.biases": "model.safetensors",
311
+ "model.layers.8.self_attn.k_proj.scales": "model.safetensors",
312
+ "model.layers.8.self_attn.k_proj.weight": "model.safetensors",
313
+ "model.layers.8.self_attn.out_proj.biases": "model.safetensors",
314
+ "model.layers.8.self_attn.out_proj.scales": "model.safetensors",
315
+ "model.layers.8.self_attn.out_proj.weight": "model.safetensors",
316
+ "model.layers.8.self_attn.q_layernorm.weight": "model.safetensors",
317
+ "model.layers.8.self_attn.q_proj.biases": "model.safetensors",
318
+ "model.layers.8.self_attn.q_proj.scales": "model.safetensors",
319
+ "model.layers.8.self_attn.q_proj.weight": "model.safetensors",
320
+ "model.layers.8.self_attn.v_proj.biases": "model.safetensors",
321
+ "model.layers.8.self_attn.v_proj.scales": "model.safetensors",
322
+ "model.layers.8.self_attn.v_proj.weight": "model.safetensors",
323
+ "model.layers.9.conv.conv.weight": "model.safetensors",
324
+ "model.layers.9.conv.in_proj.biases": "model.safetensors",
325
+ "model.layers.9.conv.in_proj.scales": "model.safetensors",
326
+ "model.layers.9.conv.in_proj.weight": "model.safetensors",
327
+ "model.layers.9.conv.out_proj.biases": "model.safetensors",
328
+ "model.layers.9.conv.out_proj.scales": "model.safetensors",
329
+ "model.layers.9.conv.out_proj.weight": "model.safetensors",
330
+ "model.layers.9.feed_forward.w1.biases": "model.safetensors",
331
+ "model.layers.9.feed_forward.w1.scales": "model.safetensors",
332
+ "model.layers.9.feed_forward.w1.weight": "model.safetensors",
333
+ "model.layers.9.feed_forward.w2.biases": "model.safetensors",
334
+ "model.layers.9.feed_forward.w2.scales": "model.safetensors",
335
+ "model.layers.9.feed_forward.w2.weight": "model.safetensors",
336
+ "model.layers.9.feed_forward.w3.biases": "model.safetensors",
337
+ "model.layers.9.feed_forward.w3.scales": "model.safetensors",
338
+ "model.layers.9.feed_forward.w3.weight": "model.safetensors",
339
+ "model.layers.9.ffn_norm.weight": "model.safetensors",
340
+ "model.layers.9.operator_norm.weight": "model.safetensors"
341
+ }
342
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "backend": "tokenizers",
3
+ "bos_token": "<|startoftext|>",
4
+ "clean_up_tokenization_spaces": false,
5
+ "eos_token": "<|im_end|>",
6
+ "is_local": true,
7
+ "legacy": false,
8
+ "model_input_names": [
9
+ "input_ids",
10
+ "attention_mask"
11
+ ],
12
+ "model_max_length": 1000000000000000019884624838656,
13
+ "model_specific_special_tokens": {},
14
+ "pad_token": "<|pad|>",
15
+ "sp_model_kwargs": {},
16
+ "spaces_between_special_tokens": false,
17
+ "tokenizer_class": "TokenizersBackend",
18
+ "use_default_system_prompt": false,
19
+ "use_fast": true
20
+ }