Lets Make it Clear its a 2x3B MoE : Pretrained on Context Obedience, Python, Mermaids, Chain Of Thought
Browse files- config.json +35 -35
config.json
CHANGED
|
@@ -1,35 +1,35 @@
|
|
| 1 |
-
{
|
| 2 |
-
"_name_or_path": ".\\
|
| 3 |
-
"architectures": [
|
| 4 |
-
"MixtralForCausalLM"
|
| 5 |
-
],
|
| 6 |
-
"attention_bias": false,
|
| 7 |
-
"attention_dropout": 0.0,
|
| 8 |
-
"bos_token_id": 1,
|
| 9 |
-
"eos_token_id": 32000,
|
| 10 |
-
"hidden_act": "silu",
|
| 11 |
-
"hidden_size": 3072,
|
| 12 |
-
"initializer_range": 0.02,
|
| 13 |
-
"intermediate_size": 8192,
|
| 14 |
-
"max_position_embeddings": 16384,
|
| 15 |
-
"mlp_bias": false,
|
| 16 |
-
"model_type": "mixtral",
|
| 17 |
-
"num_attention_heads": 32,
|
| 18 |
-
"num_experts_per_tok": 1,
|
| 19 |
-
"num_hidden_layers": 30,
|
| 20 |
-
"num_key_value_heads": 32,
|
| 21 |
-
"num_local_experts": 2,
|
| 22 |
-
"output_router_logits": false,
|
| 23 |
-
"pretraining_tp": 1,
|
| 24 |
-
"rms_norm_eps": 1e-05,
|
| 25 |
-
"rope_scaling": null,
|
| 26 |
-
"rope_theta": 10000.0,
|
| 27 |
-
"router_aux_loss_coef": 0.001,
|
| 28 |
-
"router_jitter_noise": 0.0,
|
| 29 |
-
"sliding_window": null,
|
| 30 |
-
"tie_word_embeddings": false,
|
| 31 |
-
"torch_dtype": "bfloat16",
|
| 32 |
-
"transformers_version": "4.44.0",
|
| 33 |
-
"use_cache": false,
|
| 34 |
-
"vocab_size": 32064
|
| 35 |
-
}
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": ".\\TwinMoE-6B",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"MixtralForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_bias": false,
|
| 7 |
+
"attention_dropout": 0.0,
|
| 8 |
+
"bos_token_id": 1,
|
| 9 |
+
"eos_token_id": 32000,
|
| 10 |
+
"hidden_act": "silu",
|
| 11 |
+
"hidden_size": 3072,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 8192,
|
| 14 |
+
"max_position_embeddings": 16384,
|
| 15 |
+
"mlp_bias": false,
|
| 16 |
+
"model_type": "mixtral",
|
| 17 |
+
"num_attention_heads": 32,
|
| 18 |
+
"num_experts_per_tok": 1,
|
| 19 |
+
"num_hidden_layers": 30,
|
| 20 |
+
"num_key_value_heads": 32,
|
| 21 |
+
"num_local_experts": 2,
|
| 22 |
+
"output_router_logits": false,
|
| 23 |
+
"pretraining_tp": 1,
|
| 24 |
+
"rms_norm_eps": 1e-05,
|
| 25 |
+
"rope_scaling": null,
|
| 26 |
+
"rope_theta": 10000.0,
|
| 27 |
+
"router_aux_loss_coef": 0.001,
|
| 28 |
+
"router_jitter_noise": 0.0,
|
| 29 |
+
"sliding_window": null,
|
| 30 |
+
"tie_word_embeddings": false,
|
| 31 |
+
"torch_dtype": "bfloat16",
|
| 32 |
+
"transformers_version": "4.44.0",
|
| 33 |
+
"use_cache": false,
|
| 34 |
+
"vocab_size": 32064
|
| 35 |
+
}
|