danielhanchen
commited on
Upload config
Browse files- config.json +5 -17
config.json
CHANGED
@@ -8,7 +8,10 @@
|
|
8 |
"attn_logit_softcapping": 50.0,
|
9 |
"bos_token_id": 2,
|
10 |
"cache_implementation": "hybrid",
|
11 |
-
"eos_token_id":
|
|
|
|
|
|
|
12 |
"final_logit_softcapping": 30.0,
|
13 |
"head_dim": 256,
|
14 |
"hidden_act": "gelu_pytorch_tanh",
|
@@ -22,27 +25,12 @@
|
|
22 |
"num_hidden_layers": 26,
|
23 |
"num_key_value_heads": 4,
|
24 |
"pad_token_id": 0,
|
25 |
-
"quantization_config": {
|
26 |
-
"_load_in_4bit": true,
|
27 |
-
"_load_in_8bit": false,
|
28 |
-
"bnb_4bit_compute_dtype": "bfloat16",
|
29 |
-
"bnb_4bit_quant_storage": "uint8",
|
30 |
-
"bnb_4bit_quant_type": "nf4",
|
31 |
-
"bnb_4bit_use_double_quant": true,
|
32 |
-
"llm_int8_enable_fp32_cpu_offload": false,
|
33 |
-
"llm_int8_has_fp16_weight": false,
|
34 |
-
"llm_int8_skip_modules": null,
|
35 |
-
"llm_int8_threshold": 6.0,
|
36 |
-
"load_in_4bit": true,
|
37 |
-
"load_in_8bit": false,
|
38 |
-
"quant_method": "bitsandbytes"
|
39 |
-
},
|
40 |
"query_pre_attn_scalar": 256,
|
41 |
"rms_norm_eps": 1e-06,
|
42 |
"rope_theta": 10000.0,
|
43 |
"sliding_window": 4096,
|
44 |
"torch_dtype": "bfloat16",
|
45 |
-
"transformers_version": "4.
|
46 |
"use_cache": true,
|
47 |
"vocab_size": 256000
|
48 |
}
|
|
|
8 |
"attn_logit_softcapping": 50.0,
|
9 |
"bos_token_id": 2,
|
10 |
"cache_implementation": "hybrid",
|
11 |
+
"eos_token_id": [
|
12 |
+
1,
|
13 |
+
107
|
14 |
+
],
|
15 |
"final_logit_softcapping": 30.0,
|
16 |
"head_dim": 256,
|
17 |
"hidden_act": "gelu_pytorch_tanh",
|
|
|
25 |
"num_hidden_layers": 26,
|
26 |
"num_key_value_heads": 4,
|
27 |
"pad_token_id": 0,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
28 |
"query_pre_attn_scalar": 256,
|
29 |
"rms_norm_eps": 1e-06,
|
30 |
"rope_theta": 10000.0,
|
31 |
"sliding_window": 4096,
|
32 |
"torch_dtype": "bfloat16",
|
33 |
+
"transformers_version": "4.44.0",
|
34 |
"use_cache": true,
|
35 |
"vocab_size": 256000
|
36 |
}
|