FastFlowLM commited on
Commit
4eb996f
·
verified ·
1 Parent(s): 5268fbf

feat: initial upload

Browse files
Files changed (9) hide show
  1. .gitattributes +6 -0
  2. attn.xclbin +3 -0
  3. config.json +151 -0
  4. dequant.xclbin +3 -0
  5. layer.xclbin +3 -0
  6. mm.xclbin +3 -0
  7. model.q4nx +3 -0
  8. tokenizer.json +3 -0
  9. tokenizer_config.json +116 -0
.gitattributes CHANGED
@@ -33,3 +33,9 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ attn.xclbin filter=lfs diff=lfs merge=lfs -text
37
+ dequant.xclbin filter=lfs diff=lfs merge=lfs -text
38
+ layer.xclbin filter=lfs diff=lfs merge=lfs -text
39
+ mm.xclbin filter=lfs diff=lfs merge=lfs -text
40
+ model.q4nx filter=lfs diff=lfs merge=lfs -text
41
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
attn.xclbin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a83098ca9a3392330e666c7fe2d1bc155d12b0226fa5fa75e973cf0c14ef558
3
+ size 527083
config.json ADDED
@@ -0,0 +1,151 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Phi-4-mini-instruct",
3
+ "architectures": [
4
+ "Phi3ForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "auto_map": {
9
+ "AutoConfig": "configuration_phi3.Phi3Config",
10
+ "AutoModelForCausalLM": "modeling_phi3.Phi3ForCausalLM",
11
+ "AutoTokenizer": "Xenova/gpt-4o"
12
+ },
13
+ "bos_token_id": 199999,
14
+ "embd_pdrop": 0.0,
15
+ "eos_token_id": 199999,
16
+ "full_attn_mod": 1,
17
+ "hidden_act": "silu",
18
+ "hidden_size": 3072,
19
+ "initializer_range": 0.02,
20
+ "intermediate_size": 8192,
21
+ "interpolate_factor": 1,
22
+ "lm_head_bias": false,
23
+ "max_position_embeddings": 131072,
24
+ "mlp_bias": false,
25
+ "model_type": "phi3",
26
+ "num_attention_heads": 24,
27
+ "num_hidden_layers": 32,
28
+ "num_key_value_heads": 8,
29
+ "head_dim": 128,
30
+ "original_max_position_embeddings": 4096,
31
+ "pad_token_id": 199999,
32
+ "partial_rotary_factor": 0.75,
33
+ "resid_pdrop": 0.0,
34
+ "rms_norm_eps": 1e-05,
35
+ "rope_scaling": {
36
+ "long_factor": [
37
+ 1,
38
+ 1.118320672,
39
+ 1.250641126,
40
+ 1.398617824,
41
+ 1.564103225,
42
+ 1.74916897,
43
+ 1.956131817,
44
+ 2.187582649,
45
+ 2.446418898,
46
+ 2.735880826,
47
+ 3.059592084,
48
+ 3.421605075,
49
+ 3.826451687,
50
+ 4.279200023,
51
+ 4.785517845,
52
+ 5.351743533,
53
+ 5.984965424,
54
+ 6.693110555,
55
+ 7.485043894,
56
+ 8.370679318,
57
+ 9.36110372,
58
+ 10.4687158,
59
+ 11.70738129,
60
+ 13.09260651,
61
+ 14.64173252,
62
+ 16.37415215,
63
+ 18.31155283,
64
+ 20.47818807,
65
+ 22.90118105,
66
+ 25.61086418,
67
+ 28.64115884,
68
+ 32.03,
69
+ 32.1,
70
+ 32.13,
71
+ 32.23,
72
+ 32.6,
73
+ 32.61,
74
+ 32.64,
75
+ 32.66,
76
+ 32.7,
77
+ 32.71,
78
+ 32.93,
79
+ 32.97,
80
+ 33.28,
81
+ 33.49,
82
+ 33.5,
83
+ 44.16,
84
+ 47.77
85
+ ],
86
+ "short_factor": [
87
+ 1.0,
88
+ 1.0,
89
+ 1.0,
90
+ 1.0,
91
+ 1.0,
92
+ 1.0,
93
+ 1.0,
94
+ 1.0,
95
+ 1.0,
96
+ 1.0,
97
+ 1.0,
98
+ 1.0,
99
+ 1.0,
100
+ 1.0,
101
+ 1.0,
102
+ 1.0,
103
+ 1.0,
104
+ 1.0,
105
+ 1.0,
106
+ 1.0,
107
+ 1.0,
108
+ 1.0,
109
+ 1.0,
110
+ 1.0,
111
+ 1.0,
112
+ 1.0,
113
+ 1.0,
114
+ 1.0,
115
+ 1.0,
116
+ 1.0,
117
+ 1.0,
118
+ 1.0,
119
+ 1.0,
120
+ 1.0,
121
+ 1.0,
122
+ 1.0,
123
+ 1.0,
124
+ 1.0,
125
+ 1.0,
126
+ 1.0,
127
+ 1.0,
128
+ 1.0,
129
+ 1.0,
130
+ 1.0,
131
+ 1.0,
132
+ 1.0,
133
+ 1.0,
134
+ 1.0
135
+ ],
136
+ "type": "longrope"
137
+ },
138
+ "rope_theta": 10000.0,
139
+ "sliding_window": 262144,
140
+ "tie_word_embeddings": true,
141
+ "torch_dtype": "bfloat16",
142
+ "transformers_version": "4.45.0",
143
+ "use_cache": true,
144
+ "vocab_size": 200064,
145
+ "addr_qk": 9216,
146
+ "addr_kv": 34304,
147
+ "addr_l_begin_mha": 54016,
148
+ "addr_l_end_mha": 25344,
149
+ "addr_kk": 45056,
150
+ "flm_version": "0.9.25"
151
+ }
dequant.xclbin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7a392a444613b0d281f4f2d05f1f7d1d34eb26a6824ac44dbe1f871209b505f
3
+ size 114059
layer.xclbin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:419d20a6d68475a9e4f47731eb2a6b0c8388630cb319fa4a1e57cabad25bc1e5
3
+ size 433995
mm.xclbin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aba4dbcb8b033dac2abe9a16ebf173296a7cc365c5bca6a09dee5c344ab82efe
3
+ size 507419
model.q4nx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:13b91962618b76f6ff205c1fe5afa20ce6a656df82ce877dcd3db1874ece21c8
3
+ size 3627014968
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:382cc235b56c725945e149cc25f191da667c836655efd0857b004320e90e91ea
3
+ size 15524095
tokenizer_config.json ADDED
@@ -0,0 +1,116 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": false,
5
+ "added_tokens_decoder": {
6
+ "199999": {
7
+ "content": "<|endoftext|>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "200018": {
15
+ "content": "<|endofprompt|>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "200019": {
23
+ "content": "<|assistant|>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": true,
27
+ "single_word": false,
28
+ "special": true
29
+ },
30
+ "200020": {
31
+ "content": "<|end|>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": true,
35
+ "single_word": false,
36
+ "special": true
37
+ },
38
+ "200021": {
39
+ "content": "<|user|>",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": true,
43
+ "single_word": false,
44
+ "special": true
45
+ },
46
+ "200022": {
47
+ "content": "<|system|>",
48
+ "lstrip": false,
49
+ "normalized": false,
50
+ "rstrip": true,
51
+ "single_word": false,
52
+ "special": true
53
+ },
54
+ "200023": {
55
+ "content": "<|tool|>",
56
+ "lstrip": false,
57
+ "normalized": false,
58
+ "rstrip": true,
59
+ "single_word": false,
60
+ "special": false
61
+ },
62
+ "200024": {
63
+ "content": "<|/tool|>",
64
+ "lstrip": false,
65
+ "normalized": false,
66
+ "rstrip": true,
67
+ "single_word": false,
68
+ "special": false
69
+ },
70
+ "200025": {
71
+ "content": "<|tool_call|>",
72
+ "lstrip": false,
73
+ "normalized": false,
74
+ "rstrip": true,
75
+ "single_word": false,
76
+ "special": false
77
+ },
78
+ "200026": {
79
+ "content": "<|/tool_call|>",
80
+ "lstrip": false,
81
+ "normalized": false,
82
+ "rstrip": true,
83
+ "single_word": false,
84
+ "special": false
85
+ },
86
+ "200027": {
87
+ "content": "<|tool_response|>",
88
+ "lstrip": false,
89
+ "normalized": false,
90
+ "rstrip": true,
91
+ "single_word": false,
92
+ "special": false
93
+ },
94
+ "200028": {
95
+ "content": "<|tag|>",
96
+ "lstrip": false,
97
+ "normalized": false,
98
+ "rstrip": true,
99
+ "single_word": false,
100
+ "special": true
101
+ }
102
+ },
103
+ "bos_token": "<|endoftext|>",
104
+ "chat_template": "{% for message in messages %}{% if message['role'] == 'system' and 'tools' in message and message['tools'] is not none %}{{ '<|' + message['role'] + '|>' + message['content'] + '<|tool|>' + message['tools'] + '<|/tool|>' + '<|end|>' }}{% else %}{{ '<|' + message['role'] + '|>' + message['content'] + '<|end|>' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>' }}{% else %}{{ eos_token }}{% endif %}",
105
+ "clean_up_tokenization_spaces": false,
106
+ "eos_token": "<|endoftext|>",
107
+ "model_max_length": 131072,
108
+ "pad_token": "<|endoftext|>",
109
+ "tokenizer_class": "GPT2Tokenizer",
110
+ "unk_token": "<|endoftext|>",
111
+ "eos_token_id": [
112
+ 199999,
113
+ 200020
114
+ ]
115
+
116
+ }