Upload 6 files
Browse files- config.json +46 -0
- generation_config.json +13 -0
- params.json +11 -0
config.json
ADDED
|
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "LeroyDyer/_Spydaz_Web_AI_MistralStar_V2",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"MistralStarForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"auto_map": {
|
| 8 |
+
"AutoConfig": "LeroyDyer/_Spydaz_Web_AI_MistralStar_V2--modeling_mistral.MistralStarConfig",
|
| 9 |
+
"AutoModel": "LeroyDyer/_Spydaz_Web_AI_MistralStar_V2--modeling_mistral.MistralModel",
|
| 10 |
+
"AutoModelForCausalLM": "LeroyDyer/_Spydaz_Web_AI_MistralStar_V2--modeling_mistral.MistralStarForCausalLM"
|
| 11 |
+
},
|
| 12 |
+
"bos_token_id": 1,
|
| 13 |
+
"eos_token_id": 2,
|
| 14 |
+
"head_dim": 128,
|
| 15 |
+
"hidden_act": "silu",
|
| 16 |
+
"hidden_size": 4096,
|
| 17 |
+
"initializer_range": 0.02,
|
| 18 |
+
"intermediate_size": 14336,
|
| 19 |
+
"max_position_embeddings": 32768,
|
| 20 |
+
"max_thoughts": 13,
|
| 21 |
+
"merged_lm_and_talk_heads": false,
|
| 22 |
+
"merged_lm_and_think_heads": true,
|
| 23 |
+
"merged_talk_heads": true,
|
| 24 |
+
"model_type": "mistral",
|
| 25 |
+
"num_attention_heads": 32,
|
| 26 |
+
"num_hidden_layers": 32,
|
| 27 |
+
"num_key_value_heads": 8,
|
| 28 |
+
"pad_token_id": 0,
|
| 29 |
+
"rms_norm_eps": 1e-05,
|
| 30 |
+
"rope_scaling": null,
|
| 31 |
+
"rope_theta": 10000.0,
|
| 32 |
+
"sliding_window": 4096,
|
| 33 |
+
"thought_length": 10,
|
| 34 |
+
"tie_word_embeddings": false,
|
| 35 |
+
"torch_dtype": "bfloat16",
|
| 36 |
+
"transformers_version": "4.43.0.dev0",
|
| 37 |
+
"unsloth_version": "2024.7",
|
| 38 |
+
"use_cache": true,
|
| 39 |
+
"use_complex_talk_head": true,
|
| 40 |
+
"use_complex_think_head": false,
|
| 41 |
+
"use_concat_talk_head": true,
|
| 42 |
+
"use_shallow_talk": false,
|
| 43 |
+
"use_shallow_think": true,
|
| 44 |
+
"use_weighted_talk_head": true,
|
| 45 |
+
"vocab_size": 32002
|
| 46 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 1,
|
| 4 |
+
"do_sample": true,
|
| 5 |
+
"eos_token_id": 2,
|
| 6 |
+
"num_beams": 1,
|
| 7 |
+
"num_return_sequences": 2,
|
| 8 |
+
"temperature": 0.3,
|
| 9 |
+
"top_k": 100,
|
| 10 |
+
"top_p": 0.68,
|
| 11 |
+
"transformers_version": "4.43.0.dev0",
|
| 12 |
+
"use_cache": true
|
| 13 |
+
}
|
params.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"dim": 4096,
|
| 3 |
+
"n_layers": 32,
|
| 4 |
+
"head_dim": 128,
|
| 5 |
+
"hidden_dim": 14336,
|
| 6 |
+
"n_heads": 32,
|
| 7 |
+
"n_kv_heads": 8,
|
| 8 |
+
"norm_eps": 1e-05,
|
| 9 |
+
"vocab_size": 32768,
|
| 10 |
+
"rope_theta": 1000000.0
|
| 11 |
+
}
|