Hugging Face's logo

mlx-community
/
LFM2-2.6B-Transcript-bf16

Text Generation
MLX
Safetensors
English
lfm2
liquid
edge
conversational
Model card Files
xet
Community
prince-canuma commited on
Commit
69e16e2
·
verified ·
1 Parent(s): ef53244

Add files using upload-large-folder tool

Browse files
Files changed (8) hide show
  1. README.md +43 -0
  2. chat_template.jinja +7 -0
  3. config.json +71 -0
  4. generation_config.json +7 -0
  5. model.safetensors +3 -0
  6. model.safetensors.index.json +274 -0
  7. tokenizer.json +0 -0
  8. tokenizer_config.json +21 -0
README.md ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: mlx
3
+ license: other
4
+ license_name: lfm1.0
5
+ license_link: LICENSE
6
+ language:
7
+ - en
8
+ pipeline_tag: text-generation
9
+ tags:
10
+ - liquid
11
+ - lfm2
12
+ - edge
13
+ - mlx
14
+ base_model: LiquidAI/LFM2-2.6B-Transcript
15
+ ---
16
+
17
+ # mlx-community/LFM2-2.6B-Transcript-bf16
18
+
19
+ This model [mlx-community/LFM2-2.6B-Transcript-bf16](https://huggingface.co/mlx-community/LFM2-2.6B-Transcript-bf16) was
20
+ converted to MLX format from [LiquidAI/LFM2-2.6B-Transcript](https://huggingface.co/LiquidAI/LFM2-2.6B-Transcript)
21
+ using mlx-lm version **0.30.2**.
22
+
23
+ ## Use with mlx
24
+
25
+ ```bash
26
+ pip install mlx-lm
27
+ ```
28
+
29
+ ```python
30
+ from mlx_lm import load, generate
31
+
32
+ model, tokenizer = load("mlx-community/LFM2-2.6B-Transcript-bf16")
33
+
34
+ prompt = "hello"
35
+
36
+ if tokenizer.chat_template is not None:
37
+ messages = [{"role": "user", "content": prompt}]
38
+ prompt = tokenizer.apply_chat_template(
39
+ messages, add_generation_prompt=True, return_dict=False,
40
+ )
41
+
42
+ response = generate(model, tokenizer, prompt=prompt, verbose=True)
43
+ ```
chat_template.jinja ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {{- bos_token -}}{%- set system_prompt = "" -%}{%- set ns = namespace(system_prompt="") -%}{%- if messages[0]["role"] == "system" -%} {%- set ns.system_prompt = messages[0]["content"] -%} {%- set messages = messages[1:] -%}{%- endif -%}{%- if tools -%} {%- set ns.system_prompt = ns.system_prompt + ("
2
+ " if ns.system_prompt else "") + "List of tools: <|tool_list_start|>[" -%} {%- for tool in tools -%} {%- if tool is not string -%} {%- set tool = tool | tojson -%} {%- endif -%} {%- set ns.system_prompt = ns.system_prompt + tool -%} {%- if not loop.last -%} {%- set ns.system_prompt = ns.system_prompt + ", " -%} {%- endif -%} {%- endfor -%} {%- set ns.system_prompt = ns.system_prompt + "]<|tool_list_end|>" -%}{%- endif -%}{%- if ns.system_prompt -%} {{- "<|im_start|>system
3
+ " + ns.system_prompt + "<|im_end|>
4
+ " -}}{%- endif -%}{%- for message in messages -%} {{- "<|im_start|>" + message["role"] + "
5
+ " -}} {%- set content = message["content"] -%} {%- if content is not string -%} {%- set content = content | tojson -%} {%- endif -%} {%- if message["role"] == "tool" -%} {%- set content = "<|tool_response_start|>" + content + "<|tool_response_end|>" -%} {%- endif -%} {{- content + "<|im_end|>
6
+ " -}}{%- endfor -%}{%- if add_generation_prompt -%} {{- "<|im_start|>assistant
7
+ " -}}{%- endif -%}
config.json ADDED
@@ -0,0 +1,71 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Lfm2ForCausalLM"
4
+ ],
5
+ "block_auto_adjust_ff_dim": false,
6
+ "block_dim": 2048,
7
+ "block_ff_dim": 10752,
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": 10752,
25
+ "layer_types": [
26
+ "conv",
27
+ "conv",
28
+ "full_attention",
29
+ "conv",
30
+ "conv",
31
+ "full_attention",
32
+ "conv",
33
+ "conv",
34
+ "conv",
35
+ "full_attention",
36
+ "conv",
37
+ "conv",
38
+ "conv",
39
+ "full_attention",
40
+ "conv",
41
+ "conv",
42
+ "conv",
43
+ "full_attention",
44
+ "conv",
45
+ "conv",
46
+ "conv",
47
+ "full_attention",
48
+ "conv",
49
+ "conv",
50
+ "full_attention",
51
+ "conv",
52
+ "conv",
53
+ "full_attention",
54
+ "conv",
55
+ "conv"
56
+ ],
57
+ "max_position_embeddings": 128000,
58
+ "model_type": "lfm2",
59
+ "norm_eps": 1e-05,
60
+ "num_attention_heads": 32,
61
+ "num_heads": 32,
62
+ "num_hidden_layers": 30,
63
+ "num_key_value_heads": 8,
64
+ "pad_token_id": 0,
65
+ "rope_theta": 1000000.0,
66
+ "tie_embedding": true,
67
+ "transformers_version": "4.57.2",
68
+ "use_cache": true,
69
+ "use_pos_enc": true,
70
+ "vocab_size": 65536
71
+ }
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 sha256:821593372bb9e5badb46488df2417dc37a7a75e5aadb3a72f64ad00d6c2fdaf5
3
+ size 5138574825
model.safetensors.index.json ADDED
@@ -0,0 +1,274 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 5138544640,
4
+ "total_parameters": 2569272320
5
+ },
6
+ "weight_map": {
7
+ "model.embed_tokens.weight": "model.safetensors",
8
+ "model.embedding_norm.weight": "model.safetensors",
9
+ "model.layers.0.conv.conv.weight": "model.safetensors",
10
+ "model.layers.0.conv.in_proj.weight": "model.safetensors",
11
+ "model.layers.0.conv.out_proj.weight": "model.safetensors",
12
+ "model.layers.0.feed_forward.w1.weight": "model.safetensors",
13
+ "model.layers.0.feed_forward.w2.weight": "model.safetensors",
14
+ "model.layers.0.feed_forward.w3.weight": "model.safetensors",
15
+ "model.layers.0.ffn_norm.weight": "model.safetensors",
16
+ "model.layers.0.operator_norm.weight": "model.safetensors",
17
+ "model.layers.1.conv.conv.weight": "model.safetensors",
18
+ "model.layers.1.conv.in_proj.weight": "model.safetensors",
19
+ "model.layers.1.conv.out_proj.weight": "model.safetensors",
20
+ "model.layers.1.feed_forward.w1.weight": "model.safetensors",
21
+ "model.layers.1.feed_forward.w2.weight": "model.safetensors",
22
+ "model.layers.1.feed_forward.w3.weight": "model.safetensors",
23
+ "model.layers.1.ffn_norm.weight": "model.safetensors",
24
+ "model.layers.1.operator_norm.weight": "model.safetensors",
25
+ "model.layers.10.conv.conv.weight": "model.safetensors",
26
+ "model.layers.10.conv.in_proj.weight": "model.safetensors",
27
+ "model.layers.10.conv.out_proj.weight": "model.safetensors",
28
+ "model.layers.10.feed_forward.w1.weight": "model.safetensors",
29
+ "model.layers.10.feed_forward.w2.weight": "model.safetensors",
30
+ "model.layers.10.feed_forward.w3.weight": "model.safetensors",
31
+ "model.layers.10.ffn_norm.weight": "model.safetensors",
32
+ "model.layers.10.operator_norm.weight": "model.safetensors",
33
+ "model.layers.11.conv.conv.weight": "model.safetensors",
34
+ "model.layers.11.conv.in_proj.weight": "model.safetensors",
35
+ "model.layers.11.conv.out_proj.weight": "model.safetensors",
36
+ "model.layers.11.feed_forward.w1.weight": "model.safetensors",
37
+ "model.layers.11.feed_forward.w2.weight": "model.safetensors",
38
+ "model.layers.11.feed_forward.w3.weight": "model.safetensors",
39
+ "model.layers.11.ffn_norm.weight": "model.safetensors",
40
+ "model.layers.11.operator_norm.weight": "model.safetensors",
41
+ "model.layers.12.conv.conv.weight": "model.safetensors",
42
+ "model.layers.12.conv.in_proj.weight": "model.safetensors",
43
+ "model.layers.12.conv.out_proj.weight": "model.safetensors",
44
+ "model.layers.12.feed_forward.w1.weight": "model.safetensors",
45
+ "model.layers.12.feed_forward.w2.weight": "model.safetensors",
46
+ "model.layers.12.feed_forward.w3.weight": "model.safetensors",
47
+ "model.layers.12.ffn_norm.weight": "model.safetensors",
48
+ "model.layers.12.operator_norm.weight": "model.safetensors",
49
+ "model.layers.13.feed_forward.w1.weight": "model.safetensors",
50
+ "model.layers.13.feed_forward.w2.weight": "model.safetensors",
51
+ "model.layers.13.feed_forward.w3.weight": "model.safetensors",
52
+ "model.layers.13.ffn_norm.weight": "model.safetensors",
53
+ "model.layers.13.operator_norm.weight": "model.safetensors",
54
+ "model.layers.13.self_attn.k_layernorm.weight": "model.safetensors",
55
+ "model.layers.13.self_attn.k_proj.weight": "model.safetensors",
56
+ "model.layers.13.self_attn.out_proj.weight": "model.safetensors",
57
+ "model.layers.13.self_attn.q_layernorm.weight": "model.safetensors",
58
+ "model.layers.13.self_attn.q_proj.weight": "model.safetensors",
59
+ "model.layers.13.self_attn.v_proj.weight": "model.safetensors",
60
+ "model.layers.14.conv.conv.weight": "model.safetensors",
61
+ "model.layers.14.conv.in_proj.weight": "model.safetensors",
62
+ "model.layers.14.conv.out_proj.weight": "model.safetensors",
63
+ "model.layers.14.feed_forward.w1.weight": "model.safetensors",
64
+ "model.layers.14.feed_forward.w2.weight": "model.safetensors",
65
+ "model.layers.14.feed_forward.w3.weight": "model.safetensors",
66
+ "model.layers.14.ffn_norm.weight": "model.safetensors",
67
+ "model.layers.14.operator_norm.weight": "model.safetensors",
68
+ "model.layers.15.conv.conv.weight": "model.safetensors",
69
+ "model.layers.15.conv.in_proj.weight": "model.safetensors",
70
+ "model.layers.15.conv.out_proj.weight": "model.safetensors",
71
+ "model.layers.15.feed_forward.w1.weight": "model.safetensors",
72
+ "model.layers.15.feed_forward.w2.weight": "model.safetensors",
73
+ "model.layers.15.feed_forward.w3.weight": "model.safetensors",
74
+ "model.layers.15.ffn_norm.weight": "model.safetensors",
75
+ "model.layers.15.operator_norm.weight": "model.safetensors",
76
+ "model.layers.16.conv.conv.weight": "model.safetensors",
77
+ "model.layers.16.conv.in_proj.weight": "model.safetensors",
78
+ "model.layers.16.conv.out_proj.weight": "model.safetensors",
79
+ "model.layers.16.feed_forward.w1.weight": "model.safetensors",
80
+ "model.layers.16.feed_forward.w2.weight": "model.safetensors",
81
+ "model.layers.16.feed_forward.w3.weight": "model.safetensors",
82
+ "model.layers.16.ffn_norm.weight": "model.safetensors",
83
+ "model.layers.16.operator_norm.weight": "model.safetensors",
84
+ "model.layers.17.feed_forward.w1.weight": "model.safetensors",
85
+ "model.layers.17.feed_forward.w2.weight": "model.safetensors",
86
+ "model.layers.17.feed_forward.w3.weight": "model.safetensors",
87
+ "model.layers.17.ffn_norm.weight": "model.safetensors",
88
+ "model.layers.17.operator_norm.weight": "model.safetensors",
89
+ "model.layers.17.self_attn.k_layernorm.weight": "model.safetensors",
90
+ "model.layers.17.self_attn.k_proj.weight": "model.safetensors",
91
+ "model.layers.17.self_attn.out_proj.weight": "model.safetensors",
92
+ "model.layers.17.self_attn.q_layernorm.weight": "model.safetensors",
93
+ "model.layers.17.self_attn.q_proj.weight": "model.safetensors",
94
+ "model.layers.17.self_attn.v_proj.weight": "model.safetensors",
95
+ "model.layers.18.conv.conv.weight": "model.safetensors",
96
+ "model.layers.18.conv.in_proj.weight": "model.safetensors",
97
+ "model.layers.18.conv.out_proj.weight": "model.safetensors",
98
+ "model.layers.18.feed_forward.w1.weight": "model.safetensors",
99
+ "model.layers.18.feed_forward.w2.weight": "model.safetensors",
100
+ "model.layers.18.feed_forward.w3.weight": "model.safetensors",
101
+ "model.layers.18.ffn_norm.weight": "model.safetensors",
102
+ "model.layers.18.operator_norm.weight": "model.safetensors",
103
+ "model.layers.19.conv.conv.weight": "model.safetensors",
104
+ "model.layers.19.conv.in_proj.weight": "model.safetensors",
105
+ "model.layers.19.conv.out_proj.weight": "model.safetensors",
106
+ "model.layers.19.feed_forward.w1.weight": "model.safetensors",
107
+ "model.layers.19.feed_forward.w2.weight": "model.safetensors",
108
+ "model.layers.19.feed_forward.w3.weight": "model.safetensors",
109
+ "model.layers.19.ffn_norm.weight": "model.safetensors",
110
+ "model.layers.19.operator_norm.weight": "model.safetensors",
111
+ "model.layers.2.feed_forward.w1.weight": "model.safetensors",
112
+ "model.layers.2.feed_forward.w2.weight": "model.safetensors",
113
+ "model.layers.2.feed_forward.w3.weight": "model.safetensors",
114
+ "model.layers.2.ffn_norm.weight": "model.safetensors",
115
+ "model.layers.2.operator_norm.weight": "model.safetensors",
116
+ "model.layers.2.self_attn.k_layernorm.weight": "model.safetensors",
117
+ "model.layers.2.self_attn.k_proj.weight": "model.safetensors",
118
+ "model.layers.2.self_attn.out_proj.weight": "model.safetensors",
119
+ "model.layers.2.self_attn.q_layernorm.weight": "model.safetensors",
120
+ "model.layers.2.self_attn.q_proj.weight": "model.safetensors",
121
+ "model.layers.2.self_attn.v_proj.weight": "model.safetensors",
122
+ "model.layers.20.conv.conv.weight": "model.safetensors",
123
+ "model.layers.20.conv.in_proj.weight": "model.safetensors",
124
+ "model.layers.20.conv.out_proj.weight": "model.safetensors",
125
+ "model.layers.20.feed_forward.w1.weight": "model.safetensors",
126
+ "model.layers.20.feed_forward.w2.weight": "model.safetensors",
127
+ "model.layers.20.feed_forward.w3.weight": "model.safetensors",
128
+ "model.layers.20.ffn_norm.weight": "model.safetensors",
129
+ "model.layers.20.operator_norm.weight": "model.safetensors",
130
+ "model.layers.21.feed_forward.w1.weight": "model.safetensors",
131
+ "model.layers.21.feed_forward.w2.weight": "model.safetensors",
132
+ "model.layers.21.feed_forward.w3.weight": "model.safetensors",
133
+ "model.layers.21.ffn_norm.weight": "model.safetensors",
134
+ "model.layers.21.operator_norm.weight": "model.safetensors",
135
+ "model.layers.21.self_attn.k_layernorm.weight": "model.safetensors",
136
+ "model.layers.21.self_attn.k_proj.weight": "model.safetensors",
137
+ "model.layers.21.self_attn.out_proj.weight": "model.safetensors",
138
+ "model.layers.21.self_attn.q_layernorm.weight": "model.safetensors",
139
+ "model.layers.21.self_attn.q_proj.weight": "model.safetensors",
140
+ "model.layers.21.self_attn.v_proj.weight": "model.safetensors",
141
+ "model.layers.22.conv.conv.weight": "model.safetensors",
142
+ "model.layers.22.conv.in_proj.weight": "model.safetensors",
143
+ "model.layers.22.conv.out_proj.weight": "model.safetensors",
144
+ "model.layers.22.feed_forward.w1.weight": "model.safetensors",
145
+ "model.layers.22.feed_forward.w2.weight": "model.safetensors",
146
+ "model.layers.22.feed_forward.w3.weight": "model.safetensors",
147
+ "model.layers.22.ffn_norm.weight": "model.safetensors",
148
+ "model.layers.22.operator_norm.weight": "model.safetensors",
149
+ "model.layers.23.conv.conv.weight": "model.safetensors",
150
+ "model.layers.23.conv.in_proj.weight": "model.safetensors",
151
+ "model.layers.23.conv.out_proj.weight": "model.safetensors",
152
+ "model.layers.23.feed_forward.w1.weight": "model.safetensors",
153
+ "model.layers.23.feed_forward.w2.weight": "model.safetensors",
154
+ "model.layers.23.feed_forward.w3.weight": "model.safetensors",
155
+ "model.layers.23.ffn_norm.weight": "model.safetensors",
156
+ "model.layers.23.operator_norm.weight": "model.safetensors",
157
+ "model.layers.24.feed_forward.w1.weight": "model.safetensors",
158
+ "model.layers.24.feed_forward.w2.weight": "model.safetensors",
159
+ "model.layers.24.feed_forward.w3.weight": "model.safetensors",
160
+ "model.layers.24.ffn_norm.weight": "model.safetensors",
161
+ "model.layers.24.operator_norm.weight": "model.safetensors",
162
+ "model.layers.24.self_attn.k_layernorm.weight": "model.safetensors",
163
+ "model.layers.24.self_attn.k_proj.weight": "model.safetensors",
164
+ "model.layers.24.self_attn.out_proj.weight": "model.safetensors",
165
+ "model.layers.24.self_attn.q_layernorm.weight": "model.safetensors",
166
+ "model.layers.24.self_attn.q_proj.weight": "model.safetensors",
167
+ "model.layers.24.self_attn.v_proj.weight": "model.safetensors",
168
+ "model.layers.25.conv.conv.weight": "model.safetensors",
169
+ "model.layers.25.conv.in_proj.weight": "model.safetensors",
170
+ "model.layers.25.conv.out_proj.weight": "model.safetensors",
171
+ "model.layers.25.feed_forward.w1.weight": "model.safetensors",
172
+ "model.layers.25.feed_forward.w2.weight": "model.safetensors",
173
+ "model.layers.25.feed_forward.w3.weight": "model.safetensors",
174
+ "model.layers.25.ffn_norm.weight": "model.safetensors",
175
+ "model.layers.25.operator_norm.weight": "model.safetensors",
176
+ "model.layers.26.conv.conv.weight": "model.safetensors",
177
+ "model.layers.26.conv.in_proj.weight": "model.safetensors",
178
+ "model.layers.26.conv.out_proj.weight": "model.safetensors",
179
+ "model.layers.26.feed_forward.w1.weight": "model.safetensors",
180
+ "model.layers.26.feed_forward.w2.weight": "model.safetensors",
181
+ "model.layers.26.feed_forward.w3.weight": "model.safetensors",
182
+ "model.layers.26.ffn_norm.weight": "model.safetensors",
183
+ "model.layers.26.operator_norm.weight": "model.safetensors",
184
+ "model.layers.27.feed_forward.w1.weight": "model.safetensors",
185
+ "model.layers.27.feed_forward.w2.weight": "model.safetensors",
186
+ "model.layers.27.feed_forward.w3.weight": "model.safetensors",
187
+ "model.layers.27.ffn_norm.weight": "model.safetensors",
188
+ "model.layers.27.operator_norm.weight": "model.safetensors",
189
+ "model.layers.27.self_attn.k_layernorm.weight": "model.safetensors",
190
+ "model.layers.27.self_attn.k_proj.weight": "model.safetensors",
191
+ "model.layers.27.self_attn.out_proj.weight": "model.safetensors",
192
+ "model.layers.27.self_attn.q_layernorm.weight": "model.safetensors",
193
+ "model.layers.27.self_attn.q_proj.weight": "model.safetensors",
194
+ "model.layers.27.self_attn.v_proj.weight": "model.safetensors",
195
+ "model.layers.28.conv.conv.weight": "model.safetensors",
196
+ "model.layers.28.conv.in_proj.weight": "model.safetensors",
197
+ "model.layers.28.conv.out_proj.weight": "model.safetensors",
198
+ "model.layers.28.feed_forward.w1.weight": "model.safetensors",
199
+ "model.layers.28.feed_forward.w2.weight": "model.safetensors",
200
+ "model.layers.28.feed_forward.w3.weight": "model.safetensors",
201
+ "model.layers.28.ffn_norm.weight": "model.safetensors",
202
+ "model.layers.28.operator_norm.weight": "model.safetensors",
203
+ "model.layers.29.conv.conv.weight": "model.safetensors",
204
+ "model.layers.29.conv.in_proj.weight": "model.safetensors",
205
+ "model.layers.29.conv.out_proj.weight": "model.safetensors",
206
+ "model.layers.29.feed_forward.w1.weight": "model.safetensors",
207
+ "model.layers.29.feed_forward.w2.weight": "model.safetensors",
208
+ "model.layers.29.feed_forward.w3.weight": "model.safetensors",
209
+ "model.layers.29.ffn_norm.weight": "model.safetensors",
210
+ "model.layers.29.operator_norm.weight": "model.safetensors",
211
+ "model.layers.3.conv.conv.weight": "model.safetensors",
212
+ "model.layers.3.conv.in_proj.weight": "model.safetensors",
213
+ "model.layers.3.conv.out_proj.weight": "model.safetensors",
214
+ "model.layers.3.feed_forward.w1.weight": "model.safetensors",
215
+ "model.layers.3.feed_forward.w2.weight": "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.weight": "model.safetensors",
221
+ "model.layers.4.conv.out_proj.weight": "model.safetensors",
222
+ "model.layers.4.feed_forward.w1.weight": "model.safetensors",
223
+ "model.layers.4.feed_forward.w2.weight": "model.safetensors",
224
+ "model.layers.4.feed_forward.w3.weight": "model.safetensors",
225
+ "model.layers.4.ffn_norm.weight": "model.safetensors",
226
+ "model.layers.4.operator_norm.weight": "model.safetensors",
227
+ "model.layers.5.feed_forward.w1.weight": "model.safetensors",
228
+ "model.layers.5.feed_forward.w2.weight": "model.safetensors",
229
+ "model.layers.5.feed_forward.w3.weight": "model.safetensors",
230
+ "model.layers.5.ffn_norm.weight": "model.safetensors",
231
+ "model.layers.5.operator_norm.weight": "model.safetensors",
232
+ "model.layers.5.self_attn.k_layernorm.weight": "model.safetensors",
233
+ "model.layers.5.self_attn.k_proj.weight": "model.safetensors",
234
+ "model.layers.5.self_attn.out_proj.weight": "model.safetensors",
235
+ "model.layers.5.self_attn.q_layernorm.weight": "model.safetensors",
236
+ "model.layers.5.self_attn.q_proj.weight": "model.safetensors",
237
+ "model.layers.5.self_attn.v_proj.weight": "model.safetensors",
238
+ "model.layers.6.conv.conv.weight": "model.safetensors",
239
+ "model.layers.6.conv.in_proj.weight": "model.safetensors",
240
+ "model.layers.6.conv.out_proj.weight": "model.safetensors",
241
+ "model.layers.6.feed_forward.w1.weight": "model.safetensors",
242
+ "model.layers.6.feed_forward.w2.weight": "model.safetensors",
243
+ "model.layers.6.feed_forward.w3.weight": "model.safetensors",
244
+ "model.layers.6.ffn_norm.weight": "model.safetensors",
245
+ "model.layers.6.operator_norm.weight": "model.safetensors",
246
+ "model.layers.7.conv.conv.weight": "model.safetensors",
247
+ "model.layers.7.conv.in_proj.weight": "model.safetensors",
248
+ "model.layers.7.conv.out_proj.weight": "model.safetensors",
249
+ "model.layers.7.feed_forward.w1.weight": "model.safetensors",
250
+ "model.layers.7.feed_forward.w2.weight": "model.safetensors",
251
+ "model.layers.7.feed_forward.w3.weight": "model.safetensors",
252
+ "model.layers.7.ffn_norm.weight": "model.safetensors",
253
+ "model.layers.7.operator_norm.weight": "model.safetensors",
254
+ "model.layers.8.conv.conv.weight": "model.safetensors",
255
+ "model.layers.8.conv.in_proj.weight": "model.safetensors",
256
+ "model.layers.8.conv.out_proj.weight": "model.safetensors",
257
+ "model.layers.8.feed_forward.w1.weight": "model.safetensors",
258
+ "model.layers.8.feed_forward.w2.weight": "model.safetensors",
259
+ "model.layers.8.feed_forward.w3.weight": "model.safetensors",
260
+ "model.layers.8.ffn_norm.weight": "model.safetensors",
261
+ "model.layers.8.operator_norm.weight": "model.safetensors",
262
+ "model.layers.9.feed_forward.w1.weight": "model.safetensors",
263
+ "model.layers.9.feed_forward.w2.weight": "model.safetensors",
264
+ "model.layers.9.feed_forward.w3.weight": "model.safetensors",
265
+ "model.layers.9.ffn_norm.weight": "model.safetensors",
266
+ "model.layers.9.operator_norm.weight": "model.safetensors",
267
+ "model.layers.9.self_attn.k_layernorm.weight": "model.safetensors",
268
+ "model.layers.9.self_attn.k_proj.weight": "model.safetensors",
269
+ "model.layers.9.self_attn.out_proj.weight": "model.safetensors",
270
+ "model.layers.9.self_attn.q_layernorm.weight": "model.safetensors",
271
+ "model.layers.9.self_attn.q_proj.weight": "model.safetensors",
272
+ "model.layers.9.self_attn.v_proj.weight": "model.safetensors"
273
+ }
274
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": 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": false,
9
+ "model_input_names": [
10
+ "input_ids",
11
+ "attention_mask"
12
+ ],
13
+ "model_max_length": 1000000000000000019884624838656,
14
+ "model_specific_special_tokens": {},
15
+ "pad_token": "<|pad|>",
16
+ "sp_model_kwargs": {},
17
+ "spaces_between_special_tokens": false,
18
+ "tokenizer_class": "TokenizersBackend",
19
+ "use_default_system_prompt": false,
20
+ "use_fast": true
21
+ }