apepkuss79
commited on
Commit
•
080f73d
1
Parent(s):
41f42ba
Update models
Browse files- .gitattributes +8 -0
- Qwen2.5-Coder-3B-Instruct-Q4_K_M.gguf +3 -0
- Qwen2.5-Coder-3B-Instruct-Q4_K_S.gguf +3 -0
- Qwen2.5-Coder-3B-Instruct-Q5_0.gguf +3 -0
- Qwen2.5-Coder-3B-Instruct-Q5_K_M.gguf +3 -0
- Qwen2.5-Coder-3B-Instruct-Q5_K_S.gguf +3 -0
- Qwen2.5-Coder-3B-Instruct-Q6_K.gguf +3 -0
- Qwen2.5-Coder-3B-Instruct-Q8_0.gguf +3 -0
- Qwen2.5-Coder-3B-Instruct-f16.gguf +3 -0
- config.json +27 -0
.gitattributes
CHANGED
@@ -38,3 +38,11 @@ Qwen2.5-Coder-3B-Instruct-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
|
38 |
Qwen2.5-Coder-3B-Instruct-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
39 |
Qwen2.5-Coder-3B-Instruct-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
40 |
Qwen2.5-Coder-3B-Instruct-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
38 |
Qwen2.5-Coder-3B-Instruct-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
39 |
Qwen2.5-Coder-3B-Instruct-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
40 |
Qwen2.5-Coder-3B-Instruct-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
|
41 |
+
Qwen2.5-Coder-3B-Instruct-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
42 |
+
Qwen2.5-Coder-3B-Instruct-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
43 |
+
Qwen2.5-Coder-3B-Instruct-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
|
44 |
+
Qwen2.5-Coder-3B-Instruct-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
45 |
+
Qwen2.5-Coder-3B-Instruct-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
46 |
+
Qwen2.5-Coder-3B-Instruct-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
|
47 |
+
Qwen2.5-Coder-3B-Instruct-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
48 |
+
Qwen2.5-Coder-3B-Instruct-f16.gguf filter=lfs diff=lfs merge=lfs -text
|
Qwen2.5-Coder-3B-Instruct-Q4_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1c78358fd2c8f8981e8165e54a4cbdb58335a659f5c8da67942fd488398cdb7e
|
3 |
+
size 1929903072
|
Qwen2.5-Coder-3B-Instruct-Q4_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:09620b8c4e99b70e16bc3c41e28e1196abbd71a14ad1c7240e09374b8e246c23
|
3 |
+
size 1834384352
|
Qwen2.5-Coder-3B-Instruct-Q5_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:752f9c98c8a4317be7150044ff15a348460990de75081cc8f1f8ade576459753
|
3 |
+
size 2169666528
|
Qwen2.5-Coder-3B-Instruct-Q5_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e768628dbaecf89b2542eb5701254a8f25d630b1e5201dda7619ba75ae6fda04
|
3 |
+
size 2224815072
|
Qwen2.5-Coder-3B-Instruct-Q5_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e4cd989dacfa79fd8a48e302dad8ce109ce83e18a5f0e70716eb02dfd608f2fa
|
3 |
+
size 2169666528
|
Qwen2.5-Coder-3B-Instruct-Q6_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c2ebac167f40fefc6a8e66afa1bd8cfad48f9f47f6ff2efa00a2f2e18543999d
|
3 |
+
size 2538159072
|
Qwen2.5-Coder-3B-Instruct-Q8_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5bc087d5cc14a83a1cb2d6f90a92e2fd29ebab7e32d6535740dc5d53a07089af
|
3 |
+
size 3285476320
|
Qwen2.5-Coder-3B-Instruct-f16.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:eabc7451ec218462534bf34939ce43f06b5ead6a733f87e0b3b94599e062aa13
|
3 |
+
size 6178317280
|
config.json
ADDED
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": 2048,
|
10 |
+
"initializer_range": 0.02,
|
11 |
+
"intermediate_size": 11008,
|
12 |
+
"max_position_embeddings": 32768,
|
13 |
+
"max_window_layers": 70,
|
14 |
+
"model_type": "qwen2",
|
15 |
+
"num_attention_heads": 16,
|
16 |
+
"num_hidden_layers": 36,
|
17 |
+
"num_key_value_heads": 2,
|
18 |
+
"rms_norm_eps": 1e-06,
|
19 |
+
"rope_theta": 1000000.0,
|
20 |
+
"sliding_window": 32768,
|
21 |
+
"tie_word_embeddings": true,
|
22 |
+
"torch_dtype": "bfloat16",
|
23 |
+
"transformers_version": "4.43.1",
|
24 |
+
"use_cache": true,
|
25 |
+
"use_sliding_window": false,
|
26 |
+
"vocab_size": 151936
|
27 |
+
}
|