Upload folder using huggingface_hub
Browse files- config.json +16 -29
- pytorch_model.bin +3 -0
config.json
CHANGED
|
@@ -1,46 +1,33 @@
|
|
| 1 |
{
|
| 2 |
"architectures": [
|
| 3 |
-
"
|
| 4 |
],
|
| 5 |
"attention_bias": false,
|
| 6 |
"attention_dropout": 0.0,
|
| 7 |
-
"bos_token_id":
|
| 8 |
-
"draft_vocab_size":
|
| 9 |
-
"
|
| 10 |
-
|
| 11 |
-
0
|
| 12 |
-
],
|
| 13 |
-
"use_aux_hidden_state": true,
|
| 14 |
-
"use_input_layernorm_in_first_layer": true,
|
| 15 |
-
"use_last_layernorm": true,
|
| 16 |
-
"use_mtp_layernorm": false
|
| 17 |
-
},
|
| 18 |
-
"eos_token_id": null,
|
| 19 |
-
"head_dim": 4,
|
| 20 |
"hidden_act": "silu",
|
| 21 |
-
"hidden_size":
|
| 22 |
"initializer_range": 0.02,
|
| 23 |
-
"intermediate_size":
|
| 24 |
-
"max_position_embeddings":
|
|
|
|
| 25 |
"mlp_bias": false,
|
| 26 |
"model_type": "llama",
|
| 27 |
"num_attention_heads": 1,
|
| 28 |
"num_hidden_layers": 1,
|
| 29 |
"num_key_value_heads": 1,
|
| 30 |
-
"pad_token": null,
|
| 31 |
"pretraining_tp": 1,
|
| 32 |
-
"rms_norm_eps": 1e-
|
| 33 |
-
"rope_scaling":
|
| 34 |
-
|
| 35 |
-
|
| 36 |
-
"low_freq_factor": 1.0,
|
| 37 |
-
"original_max_position_embeddings": 8,
|
| 38 |
-
"rope_type": "llama3"
|
| 39 |
-
},
|
| 40 |
-
"rope_theta": 500000.0,
|
| 41 |
"tie_word_embeddings": false,
|
| 42 |
-
"torch_dtype": "
|
| 43 |
"transformers_version": "4.55.0",
|
| 44 |
"use_cache": true,
|
| 45 |
-
"
|
|
|
|
| 46 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"architectures": [
|
| 3 |
+
"LlamaForCausalLMEagle3"
|
| 4 |
],
|
| 5 |
"attention_bias": false,
|
| 6 |
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 151643,
|
| 8 |
+
"draft_vocab_size": 32000,
|
| 9 |
+
"eos_token_id": 151645,
|
| 10 |
+
"head_dim": 128,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11 |
"hidden_act": "silu",
|
| 12 |
+
"hidden_size": 40,
|
| 13 |
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 122,
|
| 15 |
+
"max_position_embeddings": 128,
|
| 16 |
+
"max_window_layers": 36,
|
| 17 |
"mlp_bias": false,
|
| 18 |
"model_type": "llama",
|
| 19 |
"num_attention_heads": 1,
|
| 20 |
"num_hidden_layers": 1,
|
| 21 |
"num_key_value_heads": 1,
|
|
|
|
| 22 |
"pretraining_tp": 1,
|
| 23 |
+
"rms_norm_eps": 1e-06,
|
| 24 |
+
"rope_scaling": null,
|
| 25 |
+
"rope_theta": 1000000,
|
| 26 |
+
"sliding_window": null,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 27 |
"tie_word_embeddings": false,
|
| 28 |
+
"torch_dtype": "bfloat16",
|
| 29 |
"transformers_version": "4.55.0",
|
| 30 |
"use_cache": true,
|
| 31 |
+
"use_sliding_window": false,
|
| 32 |
+
"vocab_size": 1519
|
| 33 |
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:19a1d5118edd68f6b4979c007c891917fe52099bfcb2a826ff62a8a43f147214
|
| 3 |
+
size 322472
|