Upload MPTForCausalLM
Browse files- config.json +56 -0
- generation_config.json +5 -0
- pytorch_model.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "aisingapore/sea-lion-3b",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"MPTForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"attn_config": {
|
| 7 |
+
"alibi": false,
|
| 8 |
+
"alibi_bias_max": 8,
|
| 9 |
+
"attn_impl": "torch",
|
| 10 |
+
"attn_pdrop": 0.0,
|
| 11 |
+
"attn_type": "multihead_attention",
|
| 12 |
+
"attn_uses_sequence_id": false,
|
| 13 |
+
"clip_qkv": null,
|
| 14 |
+
"prefix_lm": false,
|
| 15 |
+
"qk_ln": false,
|
| 16 |
+
"softmax_scale": null
|
| 17 |
+
},
|
| 18 |
+
"auto_map": {
|
| 19 |
+
"AutoConfig": "aisingapore/sea-lion-3b--configuration_mpt.MPTConfig",
|
| 20 |
+
"AutoModelForCausalLM": "aisingapore/sea-lion-3b--modeling_mpt.MPTForCausalLM"
|
| 21 |
+
},
|
| 22 |
+
"d_model": 2560,
|
| 23 |
+
"emb_pdrop": 0.0,
|
| 24 |
+
"embedding_fraction": 1.0,
|
| 25 |
+
"expansion_ratio": 4,
|
| 26 |
+
"fc_type": "torch",
|
| 27 |
+
"ffn_config": {
|
| 28 |
+
"fc_type": "torch",
|
| 29 |
+
"ffn_type": "mptmlp"
|
| 30 |
+
},
|
| 31 |
+
"init_config": {
|
| 32 |
+
"emb_init_std": null,
|
| 33 |
+
"emb_init_uniform_lim": null,
|
| 34 |
+
"fan_mode": "fan_in",
|
| 35 |
+
"init_div_is_residual": true,
|
| 36 |
+
"init_gain": 0.0,
|
| 37 |
+
"init_nonlinearity": "relu",
|
| 38 |
+
"init_std": null,
|
| 39 |
+
"name": "kaiming_normal_",
|
| 40 |
+
"verbose": 0
|
| 41 |
+
},
|
| 42 |
+
"init_device": "cpu",
|
| 43 |
+
"learned_pos_emb": true,
|
| 44 |
+
"logit_scale": null,
|
| 45 |
+
"max_seq_len": 2048,
|
| 46 |
+
"model_type": "mpt",
|
| 47 |
+
"n_heads": 20,
|
| 48 |
+
"n_layers": 32,
|
| 49 |
+
"no_bias": false,
|
| 50 |
+
"norm_type": "low_precision_layernorm",
|
| 51 |
+
"resid_pdrop": 0.0,
|
| 52 |
+
"torch_dtype": "float16",
|
| 53 |
+
"transformers_version": "4.31.0",
|
| 54 |
+
"use_cache": false,
|
| 55 |
+
"vocab_size": 256000
|
| 56 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"transformers_version": "4.31.0",
|
| 4 |
+
"use_cache": false
|
| 5 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:94f797268f33e793ca9465a5d42b209cd98fe62afce54eecc38daf9025182601
|
| 3 |
+
size 6356642258
|