Upload model
Browse files- config.json +10 -5
- model.safetensors +3 -0
config.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
| 1 |
{
|
| 2 |
"architectures": [
|
| 3 |
-
"
|
| 4 |
],
|
| 5 |
"attention_bias": false,
|
| 6 |
"attention_dropout": 0.0,
|
|
@@ -13,6 +13,7 @@
|
|
| 13 |
"eos_token_id": 1,
|
| 14 |
"ep_size": 1,
|
| 15 |
"first_k_dense_replace": 3,
|
|
|
|
| 16 |
"hidden_act": "silu",
|
| 17 |
"hidden_size": 128,
|
| 18 |
"initializer_range": 0.02,
|
|
@@ -31,17 +32,21 @@
|
|
| 31 |
"num_hidden_layers": 3,
|
| 32 |
"num_key_value_heads": 128,
|
| 33 |
"num_nextn_predict_layers": 1,
|
|
|
|
| 34 |
"q_lora_rank": 1536,
|
|
|
|
| 35 |
"qk_nope_head_dim": 128,
|
| 36 |
"qk_rope_head_dim": 64,
|
| 37 |
"rms_norm_eps": 1e-06,
|
|
|
|
| 38 |
"rope_scaling": {
|
| 39 |
-
"beta_fast": 32,
|
| 40 |
-
"beta_slow": 1,
|
| 41 |
-
"factor": 40,
|
| 42 |
"mscale": 1.0,
|
| 43 |
"mscale_all_dim": 1.0,
|
| 44 |
"original_max_position_embeddings": 4096,
|
|
|
|
| 45 |
"type": "yarn"
|
| 46 |
},
|
| 47 |
"rope_theta": 10000,
|
|
@@ -51,7 +56,7 @@
|
|
| 51 |
"topk_group": 4,
|
| 52 |
"topk_method": "noaux_tc",
|
| 53 |
"torch_dtype": "bfloat16",
|
| 54 |
-
"transformers_version": "4.
|
| 55 |
"use_cache": true,
|
| 56 |
"v_head_dim": 128,
|
| 57 |
"vocab_size": 129280
|
|
|
|
| 1 |
{
|
| 2 |
"architectures": [
|
| 3 |
+
"DeepseekV3Model"
|
| 4 |
],
|
| 5 |
"attention_bias": false,
|
| 6 |
"attention_dropout": 0.0,
|
|
|
|
| 13 |
"eos_token_id": 1,
|
| 14 |
"ep_size": 1,
|
| 15 |
"first_k_dense_replace": 3,
|
| 16 |
+
"head_dim": 64,
|
| 17 |
"hidden_act": "silu",
|
| 18 |
"hidden_size": 128,
|
| 19 |
"initializer_range": 0.02,
|
|
|
|
| 32 |
"num_hidden_layers": 3,
|
| 33 |
"num_key_value_heads": 128,
|
| 34 |
"num_nextn_predict_layers": 1,
|
| 35 |
+
"pretraining_tp": 1,
|
| 36 |
"q_lora_rank": 1536,
|
| 37 |
+
"qk_head_dim": 192,
|
| 38 |
"qk_nope_head_dim": 128,
|
| 39 |
"qk_rope_head_dim": 64,
|
| 40 |
"rms_norm_eps": 1e-06,
|
| 41 |
+
"rope_interleave": true,
|
| 42 |
"rope_scaling": {
|
| 43 |
+
"beta_fast": 32.0,
|
| 44 |
+
"beta_slow": 1.0,
|
| 45 |
+
"factor": 40.0,
|
| 46 |
"mscale": 1.0,
|
| 47 |
"mscale_all_dim": 1.0,
|
| 48 |
"original_max_position_embeddings": 4096,
|
| 49 |
+
"rope_type": "yarn",
|
| 50 |
"type": "yarn"
|
| 51 |
},
|
| 52 |
"rope_theta": 10000,
|
|
|
|
| 56 |
"topk_group": 4,
|
| 57 |
"topk_method": "noaux_tc",
|
| 58 |
"torch_dtype": "bfloat16",
|
| 59 |
+
"transformers_version": "4.55.0",
|
| 60 |
"use_cache": true,
|
| 61 |
"v_head_dim": 128,
|
| 62 |
"vocab_size": 129280
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f46e95778e1e35bab985a28af36dd0f2e0822fbaa076f981913a35269c04cf6a
|
| 3 |
+
size 416941856
|