Updated compression_config to quantization_config
Browse files- config.json +25 -25
config.json
CHANGED
|
@@ -5,7 +5,30 @@
|
|
| 5 |
],
|
| 6 |
"attention_dropout": 0.0,
|
| 7 |
"bos_token_id": 1,
|
| 8 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 9 |
"config_groups": {
|
| 10 |
"group_0": {
|
| 11 |
"input_activations": {
|
|
@@ -44,28 +67,5 @@
|
|
| 44 |
"kv_cache_scheme": null,
|
| 45 |
"quant_method": "compressed-tensors",
|
| 46 |
"quantization_status": "frozen"
|
| 47 |
-
}
|
| 48 |
-
"eos_token_id": 2,
|
| 49 |
-
"hidden_act": "silu",
|
| 50 |
-
"hidden_size": 4096,
|
| 51 |
-
"initializer_range": 0.02,
|
| 52 |
-
"intermediate_size": 14336,
|
| 53 |
-
"max_position_embeddings": 32768,
|
| 54 |
-
"model_type": "mixtral",
|
| 55 |
-
"num_attention_heads": 32,
|
| 56 |
-
"num_experts_per_tok": 2,
|
| 57 |
-
"num_hidden_layers": 32,
|
| 58 |
-
"num_key_value_heads": 8,
|
| 59 |
-
"num_local_experts": 8,
|
| 60 |
-
"output_router_logits": false,
|
| 61 |
-
"rms_norm_eps": 1e-05,
|
| 62 |
-
"rope_theta": 1000000.0,
|
| 63 |
-
"router_aux_loss_coef": 0.02,
|
| 64 |
-
"router_jitter_noise": 0.0,
|
| 65 |
-
"sliding_window": null,
|
| 66 |
-
"tie_word_embeddings": false,
|
| 67 |
-
"torch_dtype": "float16",
|
| 68 |
-
"transformers_version": "4.43.4",
|
| 69 |
-
"use_cache": true,
|
| 70 |
-
"vocab_size": 32000
|
| 71 |
}
|
|
|
|
| 5 |
],
|
| 6 |
"attention_dropout": 0.0,
|
| 7 |
"bos_token_id": 1,
|
| 8 |
+
"eos_token_id": 2,
|
| 9 |
+
"hidden_act": "silu",
|
| 10 |
+
"hidden_size": 4096,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"intermediate_size": 14336,
|
| 13 |
+
"max_position_embeddings": 32768,
|
| 14 |
+
"model_type": "mixtral",
|
| 15 |
+
"num_attention_heads": 32,
|
| 16 |
+
"num_experts_per_tok": 2,
|
| 17 |
+
"num_hidden_layers": 32,
|
| 18 |
+
"num_key_value_heads": 8,
|
| 19 |
+
"num_local_experts": 8,
|
| 20 |
+
"output_router_logits": false,
|
| 21 |
+
"rms_norm_eps": 1e-05,
|
| 22 |
+
"rope_theta": 1000000.0,
|
| 23 |
+
"router_aux_loss_coef": 0.02,
|
| 24 |
+
"router_jitter_noise": 0.0,
|
| 25 |
+
"sliding_window": null,
|
| 26 |
+
"tie_word_embeddings": false,
|
| 27 |
+
"torch_dtype": "float16",
|
| 28 |
+
"transformers_version": "4.43.4",
|
| 29 |
+
"use_cache": true,
|
| 30 |
+
"vocab_size": 32000,
|
| 31 |
+
"quantization_config": {
|
| 32 |
"config_groups": {
|
| 33 |
"group_0": {
|
| 34 |
"input_activations": {
|
|
|
|
| 67 |
"kv_cache_scheme": null,
|
| 68 |
"quant_method": "compressed-tensors",
|
| 69 |
"quantization_status": "frozen"
|
| 70 |
+
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 71 |
}
|