Update config.json
Browse files- config.json +14 -26
config.json
CHANGED
@@ -1,18 +1,17 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "tiiuae/falcon-7b",
|
3 |
"alibi": false,
|
4 |
"apply_residual_connection_post_layernorm": false,
|
5 |
"architectures": [
|
6 |
-
"
|
7 |
],
|
8 |
"attention_dropout": 0.0,
|
9 |
"auto_map": {
|
10 |
-
"AutoConfig": "
|
11 |
-
"AutoModel": "
|
12 |
-
"
|
13 |
-
"
|
14 |
-
"
|
15 |
-
"
|
16 |
},
|
17 |
"bias": false,
|
18 |
"bos_token_id": 11,
|
@@ -21,25 +20,14 @@
|
|
21 |
"hidden_size": 4544,
|
22 |
"initializer_range": 0.02,
|
23 |
"layer_norm_epsilon": 1e-05,
|
24 |
-
"model_type": "
|
25 |
"multi_query": true,
|
26 |
-
"
|
27 |
-
"
|
|
|
28 |
"parallel_attn": true,
|
29 |
-
"
|
30 |
-
|
31 |
-
"bnb_4bit_quant_type": "fp4",
|
32 |
-
"bnb_4bit_use_double_quant": false,
|
33 |
-
"llm_int8_enable_fp32_cpu_offload": false,
|
34 |
-
"llm_int8_has_fp16_weight": false,
|
35 |
-
"llm_int8_skip_modules": null,
|
36 |
-
"llm_int8_threshold": 6.0,
|
37 |
-
"load_in_4bit": false,
|
38 |
-
"load_in_8bit": true,
|
39 |
-
"quant_method": "bitsandbytes"
|
40 |
-
},
|
41 |
-
"torch_dtype": "float16",
|
42 |
-
"transformers_version": "4.34.0.dev0",
|
43 |
"use_cache": true,
|
44 |
"vocab_size": 65024
|
45 |
-
}
|
|
|
1 |
{
|
|
|
2 |
"alibi": false,
|
3 |
"apply_residual_connection_post_layernorm": false,
|
4 |
"architectures": [
|
5 |
+
"FalconForCausalLM"
|
6 |
],
|
7 |
"attention_dropout": 0.0,
|
8 |
"auto_map": {
|
9 |
+
"AutoConfig": "configuration_falcon.FalconConfig",
|
10 |
+
"AutoModel": "modeling_falcon.FalconModel",
|
11 |
+
"AutoModelForSequenceClassification": "modeling_falcon.FalconForSequenceClassification",
|
12 |
+
"AutoModelForTokenClassification": "modeling_falcon.FalconForTokenClassification",
|
13 |
+
"AutoModelForQuestionAnswering": "modeling_falcon.FalconForQuestionAnswering",
|
14 |
+
"AutoModelForCausalLM": "modeling_falcon.FalconForCausalLM"
|
15 |
},
|
16 |
"bias": false,
|
17 |
"bos_token_id": 11,
|
|
|
20 |
"hidden_size": 4544,
|
21 |
"initializer_range": 0.02,
|
22 |
"layer_norm_epsilon": 1e-05,
|
23 |
+
"model_type": "falcon",
|
24 |
"multi_query": true,
|
25 |
+
"new_decoder_architecture": false,
|
26 |
+
"num_attention_heads": 71,
|
27 |
+
"num_hidden_layers": 32,
|
28 |
"parallel_attn": true,
|
29 |
+
"torch_dtype": "bfloat16",
|
30 |
+
"transformers_version": "4.27.4",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
31 |
"use_cache": true,
|
32 |
"vocab_size": 65024
|
33 |
+
}
|