Upload LlamaForSequenceClassification
Browse files- config.json +39 -1
- model.safetensors +2 -2
config.json
CHANGED
@@ -9,19 +9,57 @@
|
|
9 |
"eos_token_id": 2,
|
10 |
"hidden_act": "silu",
|
11 |
"hidden_size": 2048,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
12 |
"initializer_range": 0.02,
|
13 |
"intermediate_size": 5632,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
14 |
"max_position_embeddings": 2048,
|
15 |
"model_type": "llama",
|
16 |
"num_attention_heads": 32,
|
17 |
"num_hidden_layers": 22,
|
18 |
"num_key_value_heads": 4,
|
19 |
"pretraining_tp": 1,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
20 |
"rms_norm_eps": 1e-05,
|
21 |
"rope_scaling": null,
|
22 |
"rope_theta": 10000.0,
|
23 |
"tie_word_embeddings": false,
|
24 |
-
"torch_dtype": "
|
25 |
"transformers_version": "4.38.2",
|
26 |
"use_cache": true,
|
27 |
"vocab_size": 32000
|
|
|
9 |
"eos_token_id": 2,
|
10 |
"hidden_act": "silu",
|
11 |
"hidden_size": 2048,
|
12 |
+
"id2label": {
|
13 |
+
"0": "LABEL_0",
|
14 |
+
"1": "LABEL_1",
|
15 |
+
"2": "LABEL_2",
|
16 |
+
"3": "LABEL_3",
|
17 |
+
"4": "LABEL_4",
|
18 |
+
"5": "LABEL_5",
|
19 |
+
"6": "LABEL_6",
|
20 |
+
"7": "LABEL_7",
|
21 |
+
"8": "LABEL_8",
|
22 |
+
"9": "LABEL_9",
|
23 |
+
"10": "LABEL_10"
|
24 |
+
},
|
25 |
"initializer_range": 0.02,
|
26 |
"intermediate_size": 5632,
|
27 |
+
"label2id": {
|
28 |
+
"LABEL_0": 0,
|
29 |
+
"LABEL_1": 1,
|
30 |
+
"LABEL_10": 10,
|
31 |
+
"LABEL_2": 2,
|
32 |
+
"LABEL_3": 3,
|
33 |
+
"LABEL_4": 4,
|
34 |
+
"LABEL_5": 5,
|
35 |
+
"LABEL_6": 6,
|
36 |
+
"LABEL_7": 7,
|
37 |
+
"LABEL_8": 8,
|
38 |
+
"LABEL_9": 9
|
39 |
+
},
|
40 |
"max_position_embeddings": 2048,
|
41 |
"model_type": "llama",
|
42 |
"num_attention_heads": 32,
|
43 |
"num_hidden_layers": 22,
|
44 |
"num_key_value_heads": 4,
|
45 |
"pretraining_tp": 1,
|
46 |
+
"quantization_config": {
|
47 |
+
"backend": "autoawq",
|
48 |
+
"bits": 4,
|
49 |
+
"do_fuse": false,
|
50 |
+
"fuse_max_seq_len": null,
|
51 |
+
"group_size": 128,
|
52 |
+
"modules_to_fuse": null,
|
53 |
+
"modules_to_not_convert": null,
|
54 |
+
"quant_method": "awq",
|
55 |
+
"version": "gemm",
|
56 |
+
"zero_point": true
|
57 |
+
},
|
58 |
"rms_norm_eps": 1e-05,
|
59 |
"rope_scaling": null,
|
60 |
"rope_theta": 10000.0,
|
61 |
"tie_word_embeddings": false,
|
62 |
+
"torch_dtype": "float16",
|
63 |
"transformers_version": "4.38.2",
|
64 |
"use_cache": true,
|
65 |
"vocab_size": 32000
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bc26e079cb762ea92d2cb1018edfb1bc31556af142ac7c81307d4722a3a38476
|
3 |
+
size 634723464
|