Upload Qwen2ForCausalLM
Browse files
config.json
CHANGED
|
@@ -1,5 +1,4 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "deepseek-ai/DeepSeek-R1-Distill-Qwen-14B",
|
| 3 |
"architectures": [
|
| 4 |
"Qwen2ForCausalLM"
|
| 5 |
],
|
|
@@ -17,11 +16,12 @@
|
|
| 17 |
"num_hidden_layers": 48,
|
| 18 |
"num_key_value_heads": 8,
|
| 19 |
"rms_norm_eps": 1e-05,
|
|
|
|
| 20 |
"rope_theta": 1000000.0,
|
| 21 |
-
"sliding_window":
|
| 22 |
"tie_word_embeddings": false,
|
| 23 |
"torch_dtype": "bfloat16",
|
| 24 |
-
"transformers_version": "4.
|
| 25 |
"use_cache": true,
|
| 26 |
"use_sliding_window": false,
|
| 27 |
"vocab_size": 152064
|
|
|
|
| 1 |
{
|
|
|
|
| 2 |
"architectures": [
|
| 3 |
"Qwen2ForCausalLM"
|
| 4 |
],
|
|
|
|
| 16 |
"num_hidden_layers": 48,
|
| 17 |
"num_key_value_heads": 8,
|
| 18 |
"rms_norm_eps": 1e-05,
|
| 19 |
+
"rope_scaling": null,
|
| 20 |
"rope_theta": 1000000.0,
|
| 21 |
+
"sliding_window": 131072,
|
| 22 |
"tie_word_embeddings": false,
|
| 23 |
"torch_dtype": "bfloat16",
|
| 24 |
+
"transformers_version": "4.52.3",
|
| 25 |
"use_cache": true,
|
| 26 |
"use_sliding_window": false,
|
| 27 |
"vocab_size": 152064
|
generation_config.json
CHANGED
|
@@ -5,5 +5,5 @@
|
|
| 5 |
"eos_token_id": 151643,
|
| 6 |
"temperature": 0.6,
|
| 7 |
"top_p": 0.95,
|
| 8 |
-
"transformers_version": "4.
|
| 9 |
}
|
|
|
|
| 5 |
"eos_token_id": 151643,
|
| 6 |
"temperature": 0.6,
|
| 7 |
"top_p": 0.95,
|
| 8 |
+
"transformers_version": "4.52.3"
|
| 9 |
}
|
model-00002-of-00006.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4954847344
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:909e9b1fca80ff912e5128b52b781e23f723152141826b24c8c9572b3e4767e0
|
| 3 |
size 4954847344
|
model-00003-of-00006.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4954847392
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ea2b7850f129b2cb38381a5c2839c0a2a4306a0aa478aa8f5a7345bf04b93e1e
|
| 3 |
size 4954847392
|
model-00004-of-00006.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4954847392
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9a95ddeb632a3ed804c179a3ea07e64a258990545da9e3b7778e6b194f9faee4
|
| 3 |
size 4954847392
|
model-00005-of-00006.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4954847392
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ad9606decf7f1abe3428e8bcec0776b0d6c18cf6f6b9b9e8aa9beb531ba8a919
|
| 3 |
size 4954847392
|
model-00006-of-00006.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4734533160
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:afb66af0f89f5536652fe3ede8be19c1f4749d27d74edf9f7e9a964115bc38b6
|
| 3 |
size 4734533160
|