Rename adapter_config.json to config.json
Browse files- adapter_config.json +0 -16
- config.json +68 -0
adapter_config.json
DELETED
|
@@ -1,16 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"base_model_name_or_path": "mosaicml/mpt-7b-chat",
|
| 3 |
-
"bias": "none",
|
| 4 |
-
"fan_in_fan_out": false,
|
| 5 |
-
"inference_mode": true,
|
| 6 |
-
"init_lora_weights": true,
|
| 7 |
-
"lora_alpha": 16,
|
| 8 |
-
"lora_dropout": 0.05,
|
| 9 |
-
"modules_to_save": null,
|
| 10 |
-
"peft_type": "LORA",
|
| 11 |
-
"r": 8,
|
| 12 |
-
"target_modules": [
|
| 13 |
-
"Wqkv"
|
| 14 |
-
],
|
| 15 |
-
"task_type": "CAUSAL_LM"
|
| 16 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
config.json
ADDED
|
@@ -0,0 +1,68 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"base_model_name_or_path": "mosaicml/mpt-7b-chat",
|
| 3 |
+
"bias": "none",
|
| 4 |
+
"fan_in_fan_out": false,
|
| 5 |
+
"inference_mode": true,
|
| 6 |
+
"init_lora_weights": true,
|
| 7 |
+
"lora_alpha": 16,
|
| 8 |
+
"lora_dropout": 0.05,
|
| 9 |
+
"modules_to_save": null,
|
| 10 |
+
"peft_type": "LORA",
|
| 11 |
+
"r": 8,
|
| 12 |
+
"target_modules": [
|
| 13 |
+
"Wqkv"
|
| 14 |
+
],
|
| 15 |
+
"task_type": "CAUSAL_LM",
|
| 16 |
+
|
| 17 |
+
|
| 18 |
+
"architectures": [
|
| 19 |
+
"MPTForCausalLM"
|
| 20 |
+
],
|
| 21 |
+
"attn_config": {
|
| 22 |
+
"alibi": true,
|
| 23 |
+
"alibi_bias_max": 8,
|
| 24 |
+
"attn_impl": "torch",
|
| 25 |
+
"attn_pdrop": 0,
|
| 26 |
+
"attn_type": "multihead_attention",
|
| 27 |
+
"attn_uses_sequence_id": false,
|
| 28 |
+
"clip_qkv": null,
|
| 29 |
+
"prefix_lm": false,
|
| 30 |
+
"qk_ln": false,
|
| 31 |
+
"softmax_scale": null
|
| 32 |
+
},
|
| 33 |
+
"auto_map": {
|
| 34 |
+
"AutoConfig": "configuration_mpt.MPTConfig",
|
| 35 |
+
"AutoModelForCausalLM": "modeling_mpt.MPTForCausalLM"
|
| 36 |
+
},
|
| 37 |
+
"d_model": 4096,
|
| 38 |
+
"emb_pdrop": 0,
|
| 39 |
+
"embedding_fraction": 1.0,
|
| 40 |
+
"expansion_ratio": 4,
|
| 41 |
+
"init_config": {
|
| 42 |
+
"emb_init_std": null,
|
| 43 |
+
"emb_init_uniform_lim": null,
|
| 44 |
+
"fan_mode": "fan_in",
|
| 45 |
+
"init_div_is_residual": true,
|
| 46 |
+
"init_gain": 0,
|
| 47 |
+
"init_nonlinearity": "relu",
|
| 48 |
+
"init_std": 0.02,
|
| 49 |
+
"name": "kaiming_normal_",
|
| 50 |
+
"verbose": 0
|
| 51 |
+
},
|
| 52 |
+
"init_device": "cpu",
|
| 53 |
+
"learned_pos_emb": true,
|
| 54 |
+
"logit_scale": null,
|
| 55 |
+
"max_seq_len": 2048,
|
| 56 |
+
"model_type": "mpt",
|
| 57 |
+
"n_heads": 32,
|
| 58 |
+
"n_layers": 32,
|
| 59 |
+
"no_bias": true,
|
| 60 |
+
"norm_type": "low_precision_layernorm",
|
| 61 |
+
"resid_pdrop": 0,
|
| 62 |
+
"tokenizer_name": "sam-mosaic/gpt-neox-20b-chatml",
|
| 63 |
+
"torch_dtype": "bfloat16",
|
| 64 |
+
"transformers_version": "4.28.1",
|
| 65 |
+
"use_cache": false,
|
| 66 |
+
"verbose": 0,
|
| 67 |
+
"vocab_size": 50432
|
| 68 |
+
}
|