danielhanchen
commited on
Upload config
Browse files- config.json +14 -20
config.json
CHANGED
@@ -1,42 +1,36 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"architectures": [
|
4 |
-
"
|
5 |
],
|
|
|
6 |
"attention_dropout": 0.0,
|
|
|
|
|
|
|
|
|
7 |
"bos_token_id": 1,
|
|
|
8 |
"eos_token_id": 32000,
|
9 |
"hidden_act": "silu",
|
10 |
"hidden_size": 3072,
|
11 |
"initializer_range": 0.02,
|
12 |
"intermediate_size": 8192,
|
13 |
"max_position_embeddings": 4096,
|
14 |
-
"model_type": "
|
15 |
"num_attention_heads": 32,
|
16 |
"num_hidden_layers": 32,
|
17 |
"num_key_value_heads": 32,
|
|
|
18 |
"pad_token_id": 32000,
|
19 |
-
"
|
20 |
-
"_load_in_4bit": true,
|
21 |
-
"_load_in_8bit": false,
|
22 |
-
"bnb_4bit_compute_dtype": "bfloat16",
|
23 |
-
"bnb_4bit_quant_storage": "uint8",
|
24 |
-
"bnb_4bit_quant_type": "nf4",
|
25 |
-
"bnb_4bit_use_double_quant": true,
|
26 |
-
"llm_int8_enable_fp32_cpu_offload": false,
|
27 |
-
"llm_int8_has_fp16_weight": false,
|
28 |
-
"llm_int8_skip_modules": null,
|
29 |
-
"llm_int8_threshold": 6.0,
|
30 |
-
"load_in_4bit": true,
|
31 |
-
"load_in_8bit": false,
|
32 |
-
"quant_method": "bitsandbytes"
|
33 |
-
},
|
34 |
"rms_norm_eps": 1e-05,
|
|
|
35 |
"rope_theta": 10000.0,
|
36 |
-
"sliding_window":
|
37 |
"tie_word_embeddings": false,
|
38 |
"torch_dtype": "bfloat16",
|
39 |
-
"transformers_version": "4.
|
40 |
"use_cache": true,
|
41 |
"vocab_size": 32064
|
42 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "microsoft/Phi-3-mini-4k-instruct",
|
3 |
"architectures": [
|
4 |
+
"Phi3ForCausalLM"
|
5 |
],
|
6 |
+
"attention_bias": false,
|
7 |
"attention_dropout": 0.0,
|
8 |
+
"auto_map": {
|
9 |
+
"AutoConfig": "microsoft/Phi-3-mini-4k-instruct--configuration_phi3.Phi3Config",
|
10 |
+
"AutoModelForCausalLM": "microsoft/Phi-3-mini-4k-instruct--modeling_phi3.Phi3ForCausalLM"
|
11 |
+
},
|
12 |
"bos_token_id": 1,
|
13 |
+
"embd_pdrop": 0.0,
|
14 |
"eos_token_id": 32000,
|
15 |
"hidden_act": "silu",
|
16 |
"hidden_size": 3072,
|
17 |
"initializer_range": 0.02,
|
18 |
"intermediate_size": 8192,
|
19 |
"max_position_embeddings": 4096,
|
20 |
+
"model_type": "phi3",
|
21 |
"num_attention_heads": 32,
|
22 |
"num_hidden_layers": 32,
|
23 |
"num_key_value_heads": 32,
|
24 |
+
"original_max_position_embeddings": 4096,
|
25 |
"pad_token_id": 32000,
|
26 |
+
"resid_pdrop": 0.0,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
27 |
"rms_norm_eps": 1e-05,
|
28 |
+
"rope_scaling": null,
|
29 |
"rope_theta": 10000.0,
|
30 |
+
"sliding_window": 2047,
|
31 |
"tie_word_embeddings": false,
|
32 |
"torch_dtype": "bfloat16",
|
33 |
+
"transformers_version": "4.44.0",
|
34 |
"use_cache": true,
|
35 |
"vocab_size": 32064
|
36 |
}
|