feihu.hf
commited on
Commit
·
8728e66
1
Parent(s):
343ce47
remove q2_k;q3_k_m;q4_0
Browse files- README.md +1 -1
- qwq-32b-q2_k.gguf +0 -3
- qwq-32b-q3_k_m.gguf +0 -3
- qwq-32b-q4_0.gguf +0 -3
README.md
CHANGED
|
@@ -32,7 +32,7 @@ QwQ is the reasoning model of the Qwen series. Compared with conventional instru
|
|
| 32 |
- Number of Layers: 64
|
| 33 |
- Number of Attention Heads (GQA): 40 for Q and 8 for KV
|
| 34 |
- Context Length: Full 131,072 tokens
|
| 35 |
-
- Quantization:
|
| 36 |
|
| 37 |
**Note:** For the best experience, please review the [usage guidelines](#usage-guidelines) before deploying QwQ models.
|
| 38 |
|
|
|
|
| 32 |
- Number of Layers: 64
|
| 33 |
- Number of Attention Heads (GQA): 40 for Q and 8 for KV
|
| 34 |
- Context Length: Full 131,072 tokens
|
| 35 |
+
- Quantization: q4_K_M, q5_0, q5_K_M, q6_K, q8_0
|
| 36 |
|
| 37 |
**Note:** For the best experience, please review the [usage guidelines](#usage-guidelines) before deploying QwQ models.
|
| 38 |
|
qwq-32b-q2_k.gguf
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:4146aaf6dabff8452c4c02323098898b3b59af78c0bb41c90827342ca29dcd3d
|
| 3 |
-
size 12313098400
|
|
|
|
|
|
|
|
|
|
|
|
qwq-32b-q3_k_m.gguf
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:5c8abb3b760e67374f22d099f7631b16cc1c109961795fb2329a7b3b72171e54
|
| 3 |
-
size 15935047840
|
|
|
|
|
|
|
|
|
|
|
|
qwq-32b-q4_0.gguf
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:8e3a6c38a4a54a60493cc1f501722bd6fb07e758d370b9b34c22d0181c7e31d9
|
| 3 |
-
size 18640230560
|
|
|
|
|
|
|
|
|
|
|
|