MLX
Safetensors
llama
8-bit precision
Goekdeniz-Guelmez commited on
Commit
d3effb6
1 Parent(s): 59bc657

2aa3de8aad3e49a4a7c7197795a825d1001220e29e15afac6e5f651c89694d0f

Browse files
README.md ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: amd/AMD-Llama-135m-code
3
+ datasets:
4
+ - cerebras/SlimPajama-627B
5
+ - manu/project_gutenberg
6
+ license: apache-2.0
7
+ tags:
8
+ - mlx
9
+ ---
10
+
11
+ # mlx-community/AMD-Llama-135m-code-8bit
12
+
13
+ The Model [mlx-community/AMD-Llama-135m-code-8bit](https://huggingface.co/mlx-community/AMD-Llama-135m-code-8bit) was converted to MLX format from [amd/AMD-Llama-135m-code](https://huggingface.co/amd/AMD-Llama-135m-code) using mlx-lm version **0.18.2**.
14
+
15
+ ## Use with mlx
16
+
17
+ ```bash
18
+ pip install mlx-lm
19
+ ```
20
+
21
+ ```python
22
+ from mlx_lm import load, generate
23
+
24
+ model, tokenizer = load("mlx-community/AMD-Llama-135m-code-8bit")
25
+
26
+ prompt="hello"
27
+
28
+ if hasattr(tokenizer, "apply_chat_template") and tokenizer.chat_template is not None:
29
+ messages = [{"role": "user", "content": prompt}]
30
+ prompt = tokenizer.apply_chat_template(
31
+ messages, tokenize=False, add_generation_prompt=True
32
+ )
33
+
34
+ response = generate(model, tokenizer, prompt=prompt, verbose=True)
35
+ ```
config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlamaForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 768,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 2048,
13
+ "max_position_embeddings": 2048,
14
+ "model_type": "llama",
15
+ "num_attention_heads": 12,
16
+ "num_hidden_layers": 12,
17
+ "num_key_value_heads": 12,
18
+ "pretraining_tp": 1,
19
+ "quantization": {
20
+ "group_size": 64,
21
+ "bits": 8
22
+ },
23
+ "quantization_config": {
24
+ "group_size": 64,
25
+ "bits": 8
26
+ },
27
+ "rms_norm_eps": 1e-05,
28
+ "rope_scaling": null,
29
+ "rope_theta": 10000.0,
30
+ "tie_word_embeddings": false,
31
+ "torch_dtype": "float32",
32
+ "transformers_version": "4.36.2",
33
+ "use_cache": true,
34
+ "vocab_size": 32000
35
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb8f45d8062d3f45d71f768c1b6cfd6f571ed5baf7dc412a23d70f1b1b822fc8
3
+ size 142536083
model.safetensors.index.json ADDED
@@ -0,0 +1,290 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 142505472
4
+ },
5
+ "weight_map": {
6
+ "lm_head.biases": "model.safetensors",
7
+ "lm_head.scales": "model.safetensors",
8
+ "lm_head.weight": "model.safetensors",
9
+ "model.embed_tokens.biases": "model.safetensors",
10
+ "model.embed_tokens.scales": "model.safetensors",
11
+ "model.embed_tokens.weight": "model.safetensors",
12
+ "model.layers.0.input_layernorm.weight": "model.safetensors",
13
+ "model.layers.0.mlp.down_proj.biases": "model.safetensors",
14
+ "model.layers.0.mlp.down_proj.scales": "model.safetensors",
15
+ "model.layers.0.mlp.down_proj.weight": "model.safetensors",
16
+ "model.layers.0.mlp.gate_proj.biases": "model.safetensors",
17
+ "model.layers.0.mlp.gate_proj.scales": "model.safetensors",
18
+ "model.layers.0.mlp.gate_proj.weight": "model.safetensors",
19
+ "model.layers.0.mlp.up_proj.biases": "model.safetensors",
20
+ "model.layers.0.mlp.up_proj.scales": "model.safetensors",
21
+ "model.layers.0.mlp.up_proj.weight": "model.safetensors",
22
+ "model.layers.0.post_attention_layernorm.weight": "model.safetensors",
23
+ "model.layers.0.self_attn.k_proj.biases": "model.safetensors",
24
+ "model.layers.0.self_attn.k_proj.scales": "model.safetensors",
25
+ "model.layers.0.self_attn.k_proj.weight": "model.safetensors",
26
+ "model.layers.0.self_attn.o_proj.biases": "model.safetensors",
27
+ "model.layers.0.self_attn.o_proj.scales": "model.safetensors",
28
+ "model.layers.0.self_attn.o_proj.weight": "model.safetensors",
29
+ "model.layers.0.self_attn.q_proj.biases": "model.safetensors",
30
+ "model.layers.0.self_attn.q_proj.scales": "model.safetensors",
31
+ "model.layers.0.self_attn.q_proj.weight": "model.safetensors",
32
+ "model.layers.0.self_attn.v_proj.biases": "model.safetensors",
33
+ "model.layers.0.self_attn.v_proj.scales": "model.safetensors",
34
+ "model.layers.0.self_attn.v_proj.weight": "model.safetensors",
35
+ "model.layers.1.input_layernorm.weight": "model.safetensors",
36
+ "model.layers.1.mlp.down_proj.biases": "model.safetensors",
37
+ "model.layers.1.mlp.down_proj.scales": "model.safetensors",
38
+ "model.layers.1.mlp.down_proj.weight": "model.safetensors",
39
+ "model.layers.1.mlp.gate_proj.biases": "model.safetensors",
40
+ "model.layers.1.mlp.gate_proj.scales": "model.safetensors",
41
+ "model.layers.1.mlp.gate_proj.weight": "model.safetensors",
42
+ "model.layers.1.mlp.up_proj.biases": "model.safetensors",
43
+ "model.layers.1.mlp.up_proj.scales": "model.safetensors",
44
+ "model.layers.1.mlp.up_proj.weight": "model.safetensors",
45
+ "model.layers.1.post_attention_layernorm.weight": "model.safetensors",
46
+ "model.layers.1.self_attn.k_proj.biases": "model.safetensors",
47
+ "model.layers.1.self_attn.k_proj.scales": "model.safetensors",
48
+ "model.layers.1.self_attn.k_proj.weight": "model.safetensors",
49
+ "model.layers.1.self_attn.o_proj.biases": "model.safetensors",
50
+ "model.layers.1.self_attn.o_proj.scales": "model.safetensors",
51
+ "model.layers.1.self_attn.o_proj.weight": "model.safetensors",
52
+ "model.layers.1.self_attn.q_proj.biases": "model.safetensors",
53
+ "model.layers.1.self_attn.q_proj.scales": "model.safetensors",
54
+ "model.layers.1.self_attn.q_proj.weight": "model.safetensors",
55
+ "model.layers.1.self_attn.v_proj.biases": "model.safetensors",
56
+ "model.layers.1.self_attn.v_proj.scales": "model.safetensors",
57
+ "model.layers.1.self_attn.v_proj.weight": "model.safetensors",
58
+ "model.layers.10.input_layernorm.weight": "model.safetensors",
59
+ "model.layers.10.mlp.down_proj.biases": "model.safetensors",
60
+ "model.layers.10.mlp.down_proj.scales": "model.safetensors",
61
+ "model.layers.10.mlp.down_proj.weight": "model.safetensors",
62
+ "model.layers.10.mlp.gate_proj.biases": "model.safetensors",
63
+ "model.layers.10.mlp.gate_proj.scales": "model.safetensors",
64
+ "model.layers.10.mlp.gate_proj.weight": "model.safetensors",
65
+ "model.layers.10.mlp.up_proj.biases": "model.safetensors",
66
+ "model.layers.10.mlp.up_proj.scales": "model.safetensors",
67
+ "model.layers.10.mlp.up_proj.weight": "model.safetensors",
68
+ "model.layers.10.post_attention_layernorm.weight": "model.safetensors",
69
+ "model.layers.10.self_attn.k_proj.biases": "model.safetensors",
70
+ "model.layers.10.self_attn.k_proj.scales": "model.safetensors",
71
+ "model.layers.10.self_attn.k_proj.weight": "model.safetensors",
72
+ "model.layers.10.self_attn.o_proj.biases": "model.safetensors",
73
+ "model.layers.10.self_attn.o_proj.scales": "model.safetensors",
74
+ "model.layers.10.self_attn.o_proj.weight": "model.safetensors",
75
+ "model.layers.10.self_attn.q_proj.biases": "model.safetensors",
76
+ "model.layers.10.self_attn.q_proj.scales": "model.safetensors",
77
+ "model.layers.10.self_attn.q_proj.weight": "model.safetensors",
78
+ "model.layers.10.self_attn.v_proj.biases": "model.safetensors",
79
+ "model.layers.10.self_attn.v_proj.scales": "model.safetensors",
80
+ "model.layers.10.self_attn.v_proj.weight": "model.safetensors",
81
+ "model.layers.11.input_layernorm.weight": "model.safetensors",
82
+ "model.layers.11.mlp.down_proj.biases": "model.safetensors",
83
+ "model.layers.11.mlp.down_proj.scales": "model.safetensors",
84
+ "model.layers.11.mlp.down_proj.weight": "model.safetensors",
85
+ "model.layers.11.mlp.gate_proj.biases": "model.safetensors",
86
+ "model.layers.11.mlp.gate_proj.scales": "model.safetensors",
87
+ "model.layers.11.mlp.gate_proj.weight": "model.safetensors",
88
+ "model.layers.11.mlp.up_proj.biases": "model.safetensors",
89
+ "model.layers.11.mlp.up_proj.scales": "model.safetensors",
90
+ "model.layers.11.mlp.up_proj.weight": "model.safetensors",
91
+ "model.layers.11.post_attention_layernorm.weight": "model.safetensors",
92
+ "model.layers.11.self_attn.k_proj.biases": "model.safetensors",
93
+ "model.layers.11.self_attn.k_proj.scales": "model.safetensors",
94
+ "model.layers.11.self_attn.k_proj.weight": "model.safetensors",
95
+ "model.layers.11.self_attn.o_proj.biases": "model.safetensors",
96
+ "model.layers.11.self_attn.o_proj.scales": "model.safetensors",
97
+ "model.layers.11.self_attn.o_proj.weight": "model.safetensors",
98
+ "model.layers.11.self_attn.q_proj.biases": "model.safetensors",
99
+ "model.layers.11.self_attn.q_proj.scales": "model.safetensors",
100
+ "model.layers.11.self_attn.q_proj.weight": "model.safetensors",
101
+ "model.layers.11.self_attn.v_proj.biases": "model.safetensors",
102
+ "model.layers.11.self_attn.v_proj.scales": "model.safetensors",
103
+ "model.layers.11.self_attn.v_proj.weight": "model.safetensors",
104
+ "model.layers.2.input_layernorm.weight": "model.safetensors",
105
+ "model.layers.2.mlp.down_proj.biases": "model.safetensors",
106
+ "model.layers.2.mlp.down_proj.scales": "model.safetensors",
107
+ "model.layers.2.mlp.down_proj.weight": "model.safetensors",
108
+ "model.layers.2.mlp.gate_proj.biases": "model.safetensors",
109
+ "model.layers.2.mlp.gate_proj.scales": "model.safetensors",
110
+ "model.layers.2.mlp.gate_proj.weight": "model.safetensors",
111
+ "model.layers.2.mlp.up_proj.biases": "model.safetensors",
112
+ "model.layers.2.mlp.up_proj.scales": "model.safetensors",
113
+ "model.layers.2.mlp.up_proj.weight": "model.safetensors",
114
+ "model.layers.2.post_attention_layernorm.weight": "model.safetensors",
115
+ "model.layers.2.self_attn.k_proj.biases": "model.safetensors",
116
+ "model.layers.2.self_attn.k_proj.scales": "model.safetensors",
117
+ "model.layers.2.self_attn.k_proj.weight": "model.safetensors",
118
+ "model.layers.2.self_attn.o_proj.biases": "model.safetensors",
119
+ "model.layers.2.self_attn.o_proj.scales": "model.safetensors",
120
+ "model.layers.2.self_attn.o_proj.weight": "model.safetensors",
121
+ "model.layers.2.self_attn.q_proj.biases": "model.safetensors",
122
+ "model.layers.2.self_attn.q_proj.scales": "model.safetensors",
123
+ "model.layers.2.self_attn.q_proj.weight": "model.safetensors",
124
+ "model.layers.2.self_attn.v_proj.biases": "model.safetensors",
125
+ "model.layers.2.self_attn.v_proj.scales": "model.safetensors",
126
+ "model.layers.2.self_attn.v_proj.weight": "model.safetensors",
127
+ "model.layers.3.input_layernorm.weight": "model.safetensors",
128
+ "model.layers.3.mlp.down_proj.biases": "model.safetensors",
129
+ "model.layers.3.mlp.down_proj.scales": "model.safetensors",
130
+ "model.layers.3.mlp.down_proj.weight": "model.safetensors",
131
+ "model.layers.3.mlp.gate_proj.biases": "model.safetensors",
132
+ "model.layers.3.mlp.gate_proj.scales": "model.safetensors",
133
+ "model.layers.3.mlp.gate_proj.weight": "model.safetensors",
134
+ "model.layers.3.mlp.up_proj.biases": "model.safetensors",
135
+ "model.layers.3.mlp.up_proj.scales": "model.safetensors",
136
+ "model.layers.3.mlp.up_proj.weight": "model.safetensors",
137
+ "model.layers.3.post_attention_layernorm.weight": "model.safetensors",
138
+ "model.layers.3.self_attn.k_proj.biases": "model.safetensors",
139
+ "model.layers.3.self_attn.k_proj.scales": "model.safetensors",
140
+ "model.layers.3.self_attn.k_proj.weight": "model.safetensors",
141
+ "model.layers.3.self_attn.o_proj.biases": "model.safetensors",
142
+ "model.layers.3.self_attn.o_proj.scales": "model.safetensors",
143
+ "model.layers.3.self_attn.o_proj.weight": "model.safetensors",
144
+ "model.layers.3.self_attn.q_proj.biases": "model.safetensors",
145
+ "model.layers.3.self_attn.q_proj.scales": "model.safetensors",
146
+ "model.layers.3.self_attn.q_proj.weight": "model.safetensors",
147
+ "model.layers.3.self_attn.v_proj.biases": "model.safetensors",
148
+ "model.layers.3.self_attn.v_proj.scales": "model.safetensors",
149
+ "model.layers.3.self_attn.v_proj.weight": "model.safetensors",
150
+ "model.layers.4.input_layernorm.weight": "model.safetensors",
151
+ "model.layers.4.mlp.down_proj.biases": "model.safetensors",
152
+ "model.layers.4.mlp.down_proj.scales": "model.safetensors",
153
+ "model.layers.4.mlp.down_proj.weight": "model.safetensors",
154
+ "model.layers.4.mlp.gate_proj.biases": "model.safetensors",
155
+ "model.layers.4.mlp.gate_proj.scales": "model.safetensors",
156
+ "model.layers.4.mlp.gate_proj.weight": "model.safetensors",
157
+ "model.layers.4.mlp.up_proj.biases": "model.safetensors",
158
+ "model.layers.4.mlp.up_proj.scales": "model.safetensors",
159
+ "model.layers.4.mlp.up_proj.weight": "model.safetensors",
160
+ "model.layers.4.post_attention_layernorm.weight": "model.safetensors",
161
+ "model.layers.4.self_attn.k_proj.biases": "model.safetensors",
162
+ "model.layers.4.self_attn.k_proj.scales": "model.safetensors",
163
+ "model.layers.4.self_attn.k_proj.weight": "model.safetensors",
164
+ "model.layers.4.self_attn.o_proj.biases": "model.safetensors",
165
+ "model.layers.4.self_attn.o_proj.scales": "model.safetensors",
166
+ "model.layers.4.self_attn.o_proj.weight": "model.safetensors",
167
+ "model.layers.4.self_attn.q_proj.biases": "model.safetensors",
168
+ "model.layers.4.self_attn.q_proj.scales": "model.safetensors",
169
+ "model.layers.4.self_attn.q_proj.weight": "model.safetensors",
170
+ "model.layers.4.self_attn.v_proj.biases": "model.safetensors",
171
+ "model.layers.4.self_attn.v_proj.scales": "model.safetensors",
172
+ "model.layers.4.self_attn.v_proj.weight": "model.safetensors",
173
+ "model.layers.5.input_layernorm.weight": "model.safetensors",
174
+ "model.layers.5.mlp.down_proj.biases": "model.safetensors",
175
+ "model.layers.5.mlp.down_proj.scales": "model.safetensors",
176
+ "model.layers.5.mlp.down_proj.weight": "model.safetensors",
177
+ "model.layers.5.mlp.gate_proj.biases": "model.safetensors",
178
+ "model.layers.5.mlp.gate_proj.scales": "model.safetensors",
179
+ "model.layers.5.mlp.gate_proj.weight": "model.safetensors",
180
+ "model.layers.5.mlp.up_proj.biases": "model.safetensors",
181
+ "model.layers.5.mlp.up_proj.scales": "model.safetensors",
182
+ "model.layers.5.mlp.up_proj.weight": "model.safetensors",
183
+ "model.layers.5.post_attention_layernorm.weight": "model.safetensors",
184
+ "model.layers.5.self_attn.k_proj.biases": "model.safetensors",
185
+ "model.layers.5.self_attn.k_proj.scales": "model.safetensors",
186
+ "model.layers.5.self_attn.k_proj.weight": "model.safetensors",
187
+ "model.layers.5.self_attn.o_proj.biases": "model.safetensors",
188
+ "model.layers.5.self_attn.o_proj.scales": "model.safetensors",
189
+ "model.layers.5.self_attn.o_proj.weight": "model.safetensors",
190
+ "model.layers.5.self_attn.q_proj.biases": "model.safetensors",
191
+ "model.layers.5.self_attn.q_proj.scales": "model.safetensors",
192
+ "model.layers.5.self_attn.q_proj.weight": "model.safetensors",
193
+ "model.layers.5.self_attn.v_proj.biases": "model.safetensors",
194
+ "model.layers.5.self_attn.v_proj.scales": "model.safetensors",
195
+ "model.layers.5.self_attn.v_proj.weight": "model.safetensors",
196
+ "model.layers.6.input_layernorm.weight": "model.safetensors",
197
+ "model.layers.6.mlp.down_proj.biases": "model.safetensors",
198
+ "model.layers.6.mlp.down_proj.scales": "model.safetensors",
199
+ "model.layers.6.mlp.down_proj.weight": "model.safetensors",
200
+ "model.layers.6.mlp.gate_proj.biases": "model.safetensors",
201
+ "model.layers.6.mlp.gate_proj.scales": "model.safetensors",
202
+ "model.layers.6.mlp.gate_proj.weight": "model.safetensors",
203
+ "model.layers.6.mlp.up_proj.biases": "model.safetensors",
204
+ "model.layers.6.mlp.up_proj.scales": "model.safetensors",
205
+ "model.layers.6.mlp.up_proj.weight": "model.safetensors",
206
+ "model.layers.6.post_attention_layernorm.weight": "model.safetensors",
207
+ "model.layers.6.self_attn.k_proj.biases": "model.safetensors",
208
+ "model.layers.6.self_attn.k_proj.scales": "model.safetensors",
209
+ "model.layers.6.self_attn.k_proj.weight": "model.safetensors",
210
+ "model.layers.6.self_attn.o_proj.biases": "model.safetensors",
211
+ "model.layers.6.self_attn.o_proj.scales": "model.safetensors",
212
+ "model.layers.6.self_attn.o_proj.weight": "model.safetensors",
213
+ "model.layers.6.self_attn.q_proj.biases": "model.safetensors",
214
+ "model.layers.6.self_attn.q_proj.scales": "model.safetensors",
215
+ "model.layers.6.self_attn.q_proj.weight": "model.safetensors",
216
+ "model.layers.6.self_attn.v_proj.biases": "model.safetensors",
217
+ "model.layers.6.self_attn.v_proj.scales": "model.safetensors",
218
+ "model.layers.6.self_attn.v_proj.weight": "model.safetensors",
219
+ "model.layers.7.input_layernorm.weight": "model.safetensors",
220
+ "model.layers.7.mlp.down_proj.biases": "model.safetensors",
221
+ "model.layers.7.mlp.down_proj.scales": "model.safetensors",
222
+ "model.layers.7.mlp.down_proj.weight": "model.safetensors",
223
+ "model.layers.7.mlp.gate_proj.biases": "model.safetensors",
224
+ "model.layers.7.mlp.gate_proj.scales": "model.safetensors",
225
+ "model.layers.7.mlp.gate_proj.weight": "model.safetensors",
226
+ "model.layers.7.mlp.up_proj.biases": "model.safetensors",
227
+ "model.layers.7.mlp.up_proj.scales": "model.safetensors",
228
+ "model.layers.7.mlp.up_proj.weight": "model.safetensors",
229
+ "model.layers.7.post_attention_layernorm.weight": "model.safetensors",
230
+ "model.layers.7.self_attn.k_proj.biases": "model.safetensors",
231
+ "model.layers.7.self_attn.k_proj.scales": "model.safetensors",
232
+ "model.layers.7.self_attn.k_proj.weight": "model.safetensors",
233
+ "model.layers.7.self_attn.o_proj.biases": "model.safetensors",
234
+ "model.layers.7.self_attn.o_proj.scales": "model.safetensors",
235
+ "model.layers.7.self_attn.o_proj.weight": "model.safetensors",
236
+ "model.layers.7.self_attn.q_proj.biases": "model.safetensors",
237
+ "model.layers.7.self_attn.q_proj.scales": "model.safetensors",
238
+ "model.layers.7.self_attn.q_proj.weight": "model.safetensors",
239
+ "model.layers.7.self_attn.v_proj.biases": "model.safetensors",
240
+ "model.layers.7.self_attn.v_proj.scales": "model.safetensors",
241
+ "model.layers.7.self_attn.v_proj.weight": "model.safetensors",
242
+ "model.layers.8.input_layernorm.weight": "model.safetensors",
243
+ "model.layers.8.mlp.down_proj.biases": "model.safetensors",
244
+ "model.layers.8.mlp.down_proj.scales": "model.safetensors",
245
+ "model.layers.8.mlp.down_proj.weight": "model.safetensors",
246
+ "model.layers.8.mlp.gate_proj.biases": "model.safetensors",
247
+ "model.layers.8.mlp.gate_proj.scales": "model.safetensors",
248
+ "model.layers.8.mlp.gate_proj.weight": "model.safetensors",
249
+ "model.layers.8.mlp.up_proj.biases": "model.safetensors",
250
+ "model.layers.8.mlp.up_proj.scales": "model.safetensors",
251
+ "model.layers.8.mlp.up_proj.weight": "model.safetensors",
252
+ "model.layers.8.post_attention_layernorm.weight": "model.safetensors",
253
+ "model.layers.8.self_attn.k_proj.biases": "model.safetensors",
254
+ "model.layers.8.self_attn.k_proj.scales": "model.safetensors",
255
+ "model.layers.8.self_attn.k_proj.weight": "model.safetensors",
256
+ "model.layers.8.self_attn.o_proj.biases": "model.safetensors",
257
+ "model.layers.8.self_attn.o_proj.scales": "model.safetensors",
258
+ "model.layers.8.self_attn.o_proj.weight": "model.safetensors",
259
+ "model.layers.8.self_attn.q_proj.biases": "model.safetensors",
260
+ "model.layers.8.self_attn.q_proj.scales": "model.safetensors",
261
+ "model.layers.8.self_attn.q_proj.weight": "model.safetensors",
262
+ "model.layers.8.self_attn.v_proj.biases": "model.safetensors",
263
+ "model.layers.8.self_attn.v_proj.scales": "model.safetensors",
264
+ "model.layers.8.self_attn.v_proj.weight": "model.safetensors",
265
+ "model.layers.9.input_layernorm.weight": "model.safetensors",
266
+ "model.layers.9.mlp.down_proj.biases": "model.safetensors",
267
+ "model.layers.9.mlp.down_proj.scales": "model.safetensors",
268
+ "model.layers.9.mlp.down_proj.weight": "model.safetensors",
269
+ "model.layers.9.mlp.gate_proj.biases": "model.safetensors",
270
+ "model.layers.9.mlp.gate_proj.scales": "model.safetensors",
271
+ "model.layers.9.mlp.gate_proj.weight": "model.safetensors",
272
+ "model.layers.9.mlp.up_proj.biases": "model.safetensors",
273
+ "model.layers.9.mlp.up_proj.scales": "model.safetensors",
274
+ "model.layers.9.mlp.up_proj.weight": "model.safetensors",
275
+ "model.layers.9.post_attention_layernorm.weight": "model.safetensors",
276
+ "model.layers.9.self_attn.k_proj.biases": "model.safetensors",
277
+ "model.layers.9.self_attn.k_proj.scales": "model.safetensors",
278
+ "model.layers.9.self_attn.k_proj.weight": "model.safetensors",
279
+ "model.layers.9.self_attn.o_proj.biases": "model.safetensors",
280
+ "model.layers.9.self_attn.o_proj.scales": "model.safetensors",
281
+ "model.layers.9.self_attn.o_proj.weight": "model.safetensors",
282
+ "model.layers.9.self_attn.q_proj.biases": "model.safetensors",
283
+ "model.layers.9.self_attn.q_proj.scales": "model.safetensors",
284
+ "model.layers.9.self_attn.q_proj.weight": "model.safetensors",
285
+ "model.layers.9.self_attn.v_proj.biases": "model.safetensors",
286
+ "model.layers.9.self_attn.v_proj.scales": "model.safetensors",
287
+ "model.layers.9.self_attn.v_proj.weight": "model.safetensors",
288
+ "model.norm.weight": "model.safetensors"
289
+ }
290
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "unk_token": {
17
+ "content": "<unk>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
tokenizer_config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": null,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<unk>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "2": {
23
+ "content": "</s>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": true
29
+ }
30
+ },
31
+ "bos_token": "<s>",
32
+ "clean_up_tokenization_spaces": false,
33
+ "eos_token": "</s>",
34
+ "legacy": true,
35
+ "model_max_length": 1000000000000000019884624838656,
36
+ "pad_token": null,
37
+ "sp_model_kwargs": {},
38
+ "spaces_between_special_tokens": false,
39
+ "tokenizer_class": "LlamaTokenizer",
40
+ "unk_token": "<unk>",
41
+ "use_default_system_prompt": true
42
+ }