Update config.json
Browse files- config.json +27 -38
config.json
CHANGED
|
@@ -1,39 +1,28 @@
|
|
| 1 |
-
{
|
| 2 |
-
"_name_or_path": "grimjim/llama-3-merge-virt-req-8B",
|
| 3 |
-
"architectures": [
|
| 4 |
-
"LlamaForCausalLM"
|
| 5 |
-
],
|
| 6 |
-
"attention_bias": false,
|
| 7 |
-
"attention_dropout": 0.0,
|
| 8 |
-
"bos_token_id": 128000,
|
| 9 |
-
"eos_token_id": 128009,
|
| 10 |
-
"hidden_act": "silu",
|
| 11 |
-
"hidden_size": 4096,
|
| 12 |
-
"initializer_range": 0.02,
|
| 13 |
-
"intermediate_size": 14336,
|
| 14 |
-
"max_position_embeddings": 8192,
|
| 15 |
-
"model_type": "llama",
|
| 16 |
-
"num_attention_heads": 32,
|
| 17 |
-
"num_hidden_layers": 32,
|
| 18 |
-
"num_key_value_heads": 8,
|
| 19 |
-
"pretraining_tp": 1,
|
| 20 |
-
"rms_norm_eps": 1e-05,
|
| 21 |
-
"rope_scaling": null,
|
| 22 |
-
"rope_theta": 500000.0,
|
| 23 |
-
"tie_word_embeddings": false,
|
| 24 |
-
"torch_dtype": "bfloat16",
|
| 25 |
-
"transformers_version": "4.40.1",
|
| 26 |
-
"use_cache": true,
|
| 27 |
-
"vocab_size": 128256
|
| 28 |
-
"quantization_config": {
|
| 29 |
-
"quant_method": "exl2",
|
| 30 |
-
"version": "0.0.20",
|
| 31 |
-
"bits": 6.5,
|
| 32 |
-
"head_bits": 8,
|
| 33 |
-
"calibration": {
|
| 34 |
-
"rows": 100,
|
| 35 |
-
"length": 2048,
|
| 36 |
-
"dataset": "(default)"
|
| 37 |
-
}
|
| 38 |
-
}
|
| 39 |
}
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "grimjim/llama-3-merge-virt-req-8B",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"LlamaForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_bias": false,
|
| 7 |
+
"attention_dropout": 0.0,
|
| 8 |
+
"bos_token_id": 128000,
|
| 9 |
+
"eos_token_id": 128009,
|
| 10 |
+
"hidden_act": "silu",
|
| 11 |
+
"hidden_size": 4096,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 14336,
|
| 14 |
+
"max_position_embeddings": 8192,
|
| 15 |
+
"model_type": "llama",
|
| 16 |
+
"num_attention_heads": 32,
|
| 17 |
+
"num_hidden_layers": 32,
|
| 18 |
+
"num_key_value_heads": 8,
|
| 19 |
+
"pretraining_tp": 1,
|
| 20 |
+
"rms_norm_eps": 1e-05,
|
| 21 |
+
"rope_scaling": null,
|
| 22 |
+
"rope_theta": 500000.0,
|
| 23 |
+
"tie_word_embeddings": false,
|
| 24 |
+
"torch_dtype": "bfloat16",
|
| 25 |
+
"transformers_version": "4.40.1",
|
| 26 |
+
"use_cache": true,
|
| 27 |
+
"vocab_size": 128256
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 28 |
}
|