Upload LlamaForCausalLM
Browse files- config.json +61 -0
- generation_config.json +9 -0
- pytorch_model.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"LlamaForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 128000,
|
| 8 |
+
"dtype": "bfloat16",
|
| 9 |
+
"eos_token_id": 128001,
|
| 10 |
+
"head_dim": 64,
|
| 11 |
+
"hidden_act": "silu",
|
| 12 |
+
"hidden_size": 2048,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 8192,
|
| 15 |
+
"max_position_embeddings": 131072,
|
| 16 |
+
"mlp_bias": false,
|
| 17 |
+
"model_type": "llama",
|
| 18 |
+
"num_attention_heads": 32,
|
| 19 |
+
"num_hidden_layers": 16,
|
| 20 |
+
"num_key_value_heads": 8,
|
| 21 |
+
"pretraining_tp": 1,
|
| 22 |
+
"quantization_config": {
|
| 23 |
+
"include_input_output_embeddings": false,
|
| 24 |
+
"modules_to_not_convert": null,
|
| 25 |
+
"quant_method": "torchao",
|
| 26 |
+
"quant_type": {
|
| 27 |
+
"default": {
|
| 28 |
+
"_data": {
|
| 29 |
+
"act_mapping_type": {
|
| 30 |
+
"_data": "SYMMETRIC",
|
| 31 |
+
"_type": "MappingType"
|
| 32 |
+
},
|
| 33 |
+
"layout": {
|
| 34 |
+
"_data": {},
|
| 35 |
+
"_type": "PlainLayout",
|
| 36 |
+
"_version": 1
|
| 37 |
+
},
|
| 38 |
+
"set_inductor_config": true,
|
| 39 |
+
"weight_only_decode": false
|
| 40 |
+
},
|
| 41 |
+
"_type": "Int8DynamicActivationInt8WeightConfig",
|
| 42 |
+
"_version": 1
|
| 43 |
+
}
|
| 44 |
+
},
|
| 45 |
+
"quant_type_kwargs": {},
|
| 46 |
+
"untie_embedding_weights": false
|
| 47 |
+
},
|
| 48 |
+
"rms_norm_eps": 1e-05,
|
| 49 |
+
"rope_scaling": {
|
| 50 |
+
"factor": 32.0,
|
| 51 |
+
"high_freq_factor": 4.0,
|
| 52 |
+
"low_freq_factor": 1.0,
|
| 53 |
+
"original_max_position_embeddings": 8192,
|
| 54 |
+
"rope_type": "llama3"
|
| 55 |
+
},
|
| 56 |
+
"rope_theta": 500000.0,
|
| 57 |
+
"tie_word_embeddings": true,
|
| 58 |
+
"transformers_version": "4.56.1",
|
| 59 |
+
"use_cache": true,
|
| 60 |
+
"vocab_size": 128256
|
| 61 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 128000,
|
| 4 |
+
"do_sample": true,
|
| 5 |
+
"eos_token_id": 128001,
|
| 6 |
+
"temperature": 0.6,
|
| 7 |
+
"top_p": 0.9,
|
| 8 |
+
"transformers_version": "4.56.1"
|
| 9 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:89262ec030b90f480da57b667e5fee099bba779c905e2d5ca1eba747c4f296ba
|
| 3 |
+
size 1499424299
|