Update models
Browse files- .gitattributes +13 -0
- Qwen3-4B-Q2_K.gguf +3 -0
- Qwen3-4B-Q3_K_L.gguf +3 -0
- Qwen3-4B-Q3_K_M.gguf +3 -0
- Qwen3-4B-Q3_K_S.gguf +3 -0
- Qwen3-4B-Q4_0.gguf +3 -0
- Qwen3-4B-Q4_K_M.gguf +3 -0
- Qwen3-4B-Q4_K_S.gguf +3 -0
- Qwen3-4B-Q5_0.gguf +3 -0
- Qwen3-4B-Q5_K_M.gguf +3 -0
- Qwen3-4B-Q5_K_S.gguf +3 -0
- Qwen3-4B-Q6_K.gguf +3 -0
- Qwen3-4B-Q8_0.gguf +3 -0
- Qwen3-4B-f16.gguf +3 -0
- config.json +30 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,16 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
Qwen3-4B-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
|
| 37 |
+
Qwen3-4B-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
| 38 |
+
Qwen3-4B-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
| 39 |
+
Qwen3-4B-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
| 40 |
+
Qwen3-4B-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
|
| 41 |
+
Qwen3-4B-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
| 42 |
+
Qwen3-4B-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
| 43 |
+
Qwen3-4B-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
|
| 44 |
+
Qwen3-4B-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
| 45 |
+
Qwen3-4B-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
| 46 |
+
Qwen3-4B-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
|
| 47 |
+
Qwen3-4B-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
| 48 |
+
Qwen3-4B-f16.gguf filter=lfs diff=lfs merge=lfs -text
|
Qwen3-4B-Q2_K.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4137b8e36be72a8fc23071a0d6ee074c139962f1766124e3b33b0f803cd8ea8a
|
| 3 |
+
size 1669499072
|
Qwen3-4B-Q3_K_L.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f2c8c8be9614857d606481f2b27a2ce1f03b466d3e7e3b289ad8777a3b75c717
|
| 3 |
+
size 2239785152
|
Qwen3-4B-Q3_K_M.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2ce9e04b4d275a36942656ce33e6e197be2fb501d70d935b3ecc85c47f36898b
|
| 3 |
+
size 2075617472
|
Qwen3-4B-Q3_K_S.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:48550febf50d478fedd3e719cb5b037eee3ac016c9bf7fd8cfaef62c08b37737
|
| 3 |
+
size 1886996672
|
Qwen3-4B-Q4_0.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:57e452384b46da669745e1b3c96d60766209d6ce7f8980b09d869cf8f471f340
|
| 3 |
+
size 2369546432
|
Qwen3-4B-Q4_K_M.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2d65a858f9d257bb930a37d460ec1d3d8e7d4330173cc601dfc2053a5379ee6c
|
| 3 |
+
size 2497280192
|
Qwen3-4B-Q4_K_S.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2e8d5cee60a9c23bd9f79ea8fc304b2edb9c6bd71e700604a53e76370577fcd2
|
| 3 |
+
size 2383308992
|
Qwen3-4B-Q5_0.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:eabdcf5d8879ba4598bd06064796b84c788aab87bd71e3f2d6b51b61bff25e4a
|
| 3 |
+
size 2823710912
|
Qwen3-4B-Q5_K_M.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cb0f6ab85a4244cc359d28190bf2718b2bbafc1fdc1a233a38c7aa01f2ab09ee
|
| 3 |
+
size 2889513152
|
Qwen3-4B-Q5_K_S.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9bbbfdb762bba9a2946036e8777c7e74fdd4648499e26cd76ed2d4003add08e9
|
| 3 |
+
size 2823710912
|
Qwen3-4B-Q6_K.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b20db9333940a1f59aeb84be20bf99fe5aab23124cd030f96c9db980cda3ef25
|
| 3 |
+
size 3306260672
|
Qwen3-4B-Q8_0.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:29a3c23ddd75ff5648f753549a71a75184fbf94cffe30feff2bd3c6ea673dc7d
|
| 3 |
+
size 4280404672
|
Qwen3-4B-f16.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:954dd741fedcd7ca7fb9ec1133fc610906ad7e554c8609c7b43f9ace5c6e452e
|
| 3 |
+
size 8051284672
|
config.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen3ForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 151643,
|
| 8 |
+
"eos_token_id": 151645,
|
| 9 |
+
"head_dim": 128,
|
| 10 |
+
"hidden_act": "silu",
|
| 11 |
+
"hidden_size": 2560,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 9728,
|
| 14 |
+
"max_position_embeddings": 40960,
|
| 15 |
+
"max_window_layers": 36,
|
| 16 |
+
"model_type": "qwen3",
|
| 17 |
+
"num_attention_heads": 32,
|
| 18 |
+
"num_hidden_layers": 36,
|
| 19 |
+
"num_key_value_heads": 8,
|
| 20 |
+
"rms_norm_eps": 1e-06,
|
| 21 |
+
"rope_scaling": null,
|
| 22 |
+
"rope_theta": 1000000,
|
| 23 |
+
"sliding_window": null,
|
| 24 |
+
"tie_word_embeddings": true,
|
| 25 |
+
"torch_dtype": "bfloat16",
|
| 26 |
+
"transformers_version": "4.51.0",
|
| 27 |
+
"use_cache": true,
|
| 28 |
+
"use_sliding_window": false,
|
| 29 |
+
"vocab_size": 151936
|
| 30 |
+
}
|