Update models
Browse files- .gitattributes +13 -0
- Qwen2.5-14B-Instruct-1M-Q2_K.gguf +3 -0
- Qwen2.5-14B-Instruct-1M-Q3_K_L.gguf +3 -0
- Qwen2.5-14B-Instruct-1M-Q3_K_M.gguf +3 -0
- Qwen2.5-14B-Instruct-1M-Q3_K_S.gguf +3 -0
- Qwen2.5-14B-Instruct-1M-Q4_0.gguf +3 -0
- Qwen2.5-14B-Instruct-1M-Q4_K_M.gguf +3 -0
- Qwen2.5-14B-Instruct-1M-Q4_K_S.gguf +3 -0
- Qwen2.5-14B-Instruct-1M-Q5_0.gguf +3 -0
- Qwen2.5-14B-Instruct-1M-Q5_K_M.gguf +3 -0
- Qwen2.5-14B-Instruct-1M-Q5_K_S.gguf +3 -0
- Qwen2.5-14B-Instruct-1M-Q6_K.gguf +3 -0
- Qwen2.5-14B-Instruct-1M-Q8_0.gguf +3 -0
- Qwen2.5-14B-Instruct-1M-f16.gguf +3 -0
- config.json +33 -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 |
+
Qwen2.5-14B-Instruct-1M-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
|
37 |
+
Qwen2.5-14B-Instruct-1M-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
38 |
+
Qwen2.5-14B-Instruct-1M-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
39 |
+
Qwen2.5-14B-Instruct-1M-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
40 |
+
Qwen2.5-14B-Instruct-1M-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
|
41 |
+
Qwen2.5-14B-Instruct-1M-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
42 |
+
Qwen2.5-14B-Instruct-1M-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
43 |
+
Qwen2.5-14B-Instruct-1M-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
|
44 |
+
Qwen2.5-14B-Instruct-1M-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
45 |
+
Qwen2.5-14B-Instruct-1M-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
46 |
+
Qwen2.5-14B-Instruct-1M-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
|
47 |
+
Qwen2.5-14B-Instruct-1M-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
48 |
+
Qwen2.5-14B-Instruct-1M-f16.gguf filter=lfs diff=lfs merge=lfs -text
|
Qwen2.5-14B-Instruct-1M-Q2_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1ecb0f51445c2a92d2857d166b894ceb96f779be394c907be47788ebb4afded7
|
3 |
+
size 5770497824
|
Qwen2.5-14B-Instruct-1M-Q3_K_L.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6a19dbdbbbece500f620ae0c0bd94aabc3247608233a9f8e3015044eff2d0b89
|
3 |
+
size 7924768544
|
Qwen2.5-14B-Instruct-1M-Q3_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3d52bced57c5c252b917aac1de083939a32ece2b391cdbdf2441738e83379a40
|
3 |
+
size 7339204384
|
Qwen2.5-14B-Instruct-1M-Q3_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1d5988708812e690353cc37019ef3b9cd9c28cec5bde948acc7677e8819af615
|
3 |
+
size 6659596064
|
Qwen2.5-14B-Instruct-1M-Q4_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d7d336999c544ebecc0494145bc5b04ebc6740fc6c9013bf7512dfca5c7b05ed
|
3 |
+
size 8517725984
|
Qwen2.5-14B-Instruct-1M-Q4_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:246ce41732d3a6f242bba466b37eff8c011b19b26ff6d6e4c4e997b87f551ab0
|
3 |
+
size 8988110624
|
Qwen2.5-14B-Instruct-1M-Q4_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:45ad3e1d470d287b064a509535c6f60241887db66cd792c38e74096c2c8fc978
|
3 |
+
size 8573431584
|
Qwen2.5-14B-Instruct-1M-Q5_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6fff6fd41569527fa7b260b6434b5622bbaef06d132e36be8a4d4083fc7c777f
|
3 |
+
size 10266554144
|
Qwen2.5-14B-Instruct-1M-Q5_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b882d8fbe72559c42bc452273bdcd551f564463227a6d87dc84c1f0017aa18de
|
3 |
+
size 10508873504
|
Qwen2.5-14B-Instruct-1M-Q5_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2f7011372585fb13e450ec30a229cc2681a2955852ff4c1beb58d97115e825fe
|
3 |
+
size 10266554144
|
Qwen2.5-14B-Instruct-1M-Q6_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:df3ede3de849f4482580f124582d784a789fa375d000c63c23d8da7f63cc6dda
|
3 |
+
size 12124684064
|
Qwen2.5-14B-Instruct-1M-Q8_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ea3e3b82f5fd9305a98e325da2522a4e4e2fc9d2128a26b65b7bb9a130a71229
|
3 |
+
size 15701597984
|
Qwen2.5-14B-Instruct-1M-f16.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:00517c6fabea6f9f19bdf59af62f3884127c80f7e03bb78b5e96bf060d8e6eb4
|
3 |
+
size 29547716384
|
config.json
ADDED
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"Qwen2ForCausalLM"
|
4 |
+
],
|
5 |
+
"attention_dropout": 0.0,
|
6 |
+
"bos_token_id": 151643,
|
7 |
+
"eos_token_id": 151645,
|
8 |
+
"hidden_act": "silu",
|
9 |
+
"hidden_size": 5120,
|
10 |
+
"initializer_range": 0.02,
|
11 |
+
"intermediate_size": 13824,
|
12 |
+
"max_position_embeddings": 1010000,
|
13 |
+
"max_window_layers": 48,
|
14 |
+
"model_type": "qwen2",
|
15 |
+
"num_attention_heads": 40,
|
16 |
+
"num_hidden_layers": 48,
|
17 |
+
"num_key_value_heads": 8,
|
18 |
+
"rms_norm_eps": 1e-05,
|
19 |
+
"rope_scaling": null,
|
20 |
+
"rope_theta": 10000000.0,
|
21 |
+
"sliding_window": 1010000,
|
22 |
+
"tie_word_embeddings": false,
|
23 |
+
"torch_dtype": "bfloat16",
|
24 |
+
"transformers_version": "4.45.2",
|
25 |
+
"use_cache": true,
|
26 |
+
"use_sliding_window": false,
|
27 |
+
"vocab_size": 152064,
|
28 |
+
"dual_chunk_attention_config": {
|
29 |
+
"chunk_size": 262144,
|
30 |
+
"local_size": 8192,
|
31 |
+
"original_max_position_embeddings": 262144
|
32 |
+
}
|
33 |
+
}
|