Upload 3 files
Browse files- config.json +4 -3
- generation_config.json +1 -1
- model.safetensors +2 -2
config.json
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "deepseek-
|
| 3 |
"architectures": [
|
| 4 |
"DeepseekV3ForCausalLM"
|
| 5 |
],
|
|
@@ -32,6 +32,7 @@
|
|
| 32 |
"num_experts_per_tok": 6,
|
| 33 |
"num_hidden_layers": 2,
|
| 34 |
"num_key_value_heads": 2,
|
|
|
|
| 35 |
"pretraining_tp": 1,
|
| 36 |
"q_lora_rank": 2,
|
| 37 |
"qk_nope_head_dim": 2,
|
|
@@ -53,8 +54,8 @@
|
|
| 53 |
"tie_word_embeddings": false,
|
| 54 |
"topk_group": 3,
|
| 55 |
"topk_method": "noaux_tc",
|
| 56 |
-
"torch_dtype": "
|
| 57 |
-
"transformers_version": "4.
|
| 58 |
"use_cache": true,
|
| 59 |
"v_head_dim": 2,
|
| 60 |
"vocab_size": 102400
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "katuni4ka/tiny-random-deepseek-v3",
|
| 3 |
"architectures": [
|
| 4 |
"DeepseekV3ForCausalLM"
|
| 5 |
],
|
|
|
|
| 32 |
"num_experts_per_tok": 6,
|
| 33 |
"num_hidden_layers": 2,
|
| 34 |
"num_key_value_heads": 2,
|
| 35 |
+
"num_nextn_predict_layers": 1,
|
| 36 |
"pretraining_tp": 1,
|
| 37 |
"q_lora_rank": 2,
|
| 38 |
"qk_nope_head_dim": 2,
|
|
|
|
| 54 |
"tie_word_embeddings": false,
|
| 55 |
"topk_group": 3,
|
| 56 |
"topk_method": "noaux_tc",
|
| 57 |
+
"torch_dtype": "float32",
|
| 58 |
+
"transformers_version": "4.48.3",
|
| 59 |
"use_cache": true,
|
| 60 |
"v_head_dim": 2,
|
| 61 |
"vocab_size": 102400
|
generation_config.json
CHANGED
|
@@ -5,5 +5,5 @@
|
|
| 5 |
"eos_token_id": 100001,
|
| 6 |
"temperature": 0.3,
|
| 7 |
"top_p": 0.95,
|
| 8 |
-
"transformers_version": "4.
|
| 9 |
}
|
|
|
|
| 5 |
"eos_token_id": 100001,
|
| 6 |
"temperature": 0.3,
|
| 7 |
"top_p": 0.95,
|
| 8 |
+
"transformers_version": "4.48.3"
|
| 9 |
}
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cfbdbe3b14fae3948138aae5b254c9981826f84bd4069e5d688d8079ce437fc3
|
| 3 |
+
size 6680880
|