Create config.json
Browse files- config.json +47 -0
config.json
ADDED
|
@@ -0,0 +1,47 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Cohere2ForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 5,
|
| 8 |
+
"cache_implementation": "hybrid",
|
| 9 |
+
"eos_token_id": 255001,
|
| 10 |
+
"head_dim": 128,
|
| 11 |
+
"hidden_act": "silu",
|
| 12 |
+
"hidden_size": 4096,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 14336,
|
| 15 |
+
"layer_norm_eps": 1e-05,
|
| 16 |
+
"layer_switch": 4,
|
| 17 |
+
"logit_scale": 0.25,
|
| 18 |
+
"max_position_embeddings": 8192,
|
| 19 |
+
"model_type": "cohere2",
|
| 20 |
+
"num_attention_heads": 32,
|
| 21 |
+
"num_hidden_layers": 32,
|
| 22 |
+
"num_key_value_heads": 8,
|
| 23 |
+
"order_of_interleaved_layers": "local_attn_first",
|
| 24 |
+
"pad_token_id": 0,
|
| 25 |
+
"position_embedding_type": "rope_gptj",
|
| 26 |
+
"quantization": {
|
| 27 |
+
"group_size": 64,
|
| 28 |
+
"bits": 4
|
| 29 |
+
},
|
| 30 |
+
"quantization_config": {
|
| 31 |
+
"group_size": 64,
|
| 32 |
+
"bits": 4
|
| 33 |
+
},
|
| 34 |
+
"rope_scaling": null,
|
| 35 |
+
"rope_theta": 50000,
|
| 36 |
+
"rotary_pct": 1.0,
|
| 37 |
+
"sliding_window": 4096,
|
| 38 |
+
"sliding_window_pattern": 4,
|
| 39 |
+
"torch_dtype": "bfloat16",
|
| 40 |
+
"transformers_version": "4.48.0.dev0",
|
| 41 |
+
"use_cache": true,
|
| 42 |
+
"use_embedding_sharing": true,
|
| 43 |
+
"use_gated_activation": true,
|
| 44 |
+
"use_parallel_block": true,
|
| 45 |
+
"use_parallel_embedding": true,
|
| 46 |
+
"vocab_size": 256000
|
| 47 |
+
}
|