danielhanchen commited on
Commit
1507f89
·
verified ·
1 Parent(s): 28b5794

Add files using upload-large-folder tool

Browse files
.gitattributes CHANGED
@@ -33,3 +33,9 @@ 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
+ DeepSeek-R1-0528-Qwen3-8B-UD-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text
37
+ DeepSeek-R1-0528-Qwen3-8B-UD-Q2_K_XL.gguf filter=lfs diff=lfs merge=lfs -text
38
+ DeepSeek-R1-0528-Qwen3-8B-UD-Q3_K_XL.gguf filter=lfs diff=lfs merge=lfs -text
39
+ DeepSeek-R1-0528-Qwen3-8B-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
40
+ DeepSeek-R1-0528-Qwen3-8B-UD-Q4_K_XL.gguf filter=lfs diff=lfs merge=lfs -text
41
+ DeepSeek-R1-0528-Qwen3-8B-UD-Q5_K_XL.gguf filter=lfs diff=lfs merge=lfs -text
DeepSeek-R1-0528-Qwen3-8B-Q4_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3a2aa71266292d1eb44893958ed2910313592cfa1d6caf2b99f760231231f23
3
+ size 5027783456
DeepSeek-R1-0528-Qwen3-8B-UD-IQ1_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6624c26d68829e91cf49a5ab337c82d2888a9f2679605ee6b98d2cdb35b14c5e
3
+ size 2268693280
DeepSeek-R1-0528-Qwen3-8B-UD-Q2_K_XL.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ffda8235e192325a179c0fde93332c6b7bf8e0cdd9fca7b11937457da3ea302d
3
+ size 3501974304
DeepSeek-R1-0528-Qwen3-8B-UD-Q3_K_XL.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d558a00df16706eab1fd1f5ef2ef4ee7250fbe1b10f1c09052f3d2357071c292
3
+ size 4313735968
DeepSeek-R1-0528-Qwen3-8B-UD-Q4_K_XL.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e4809ef01a14bfb12383ed1e454ce63f54607a7ca3405389640b8805117a74a
3
+ size 5122745120
DeepSeek-R1-0528-Qwen3-8B-UD-Q5_K_XL.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:53030325085a99fc69922a9416122ee17d9933e240a7ba71d23c74432974fef7
3
+ size 5883585312
README.md CHANGED
@@ -1,12 +1,10 @@
1
  ---
2
  tags:
3
- - deepseek
4
  - unsloth
5
  base_model:
6
  - deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
7
  license: mit
8
  library_name: transformers
9
- base_model_relation: quantized
10
  ---
11
  <div>
12
  <p style="margin-top: 0;margin-bottom: 0;">
 
1
  ---
2
  tags:
 
3
  - unsloth
4
  base_model:
5
  - deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
6
  license: mit
7
  library_name: transformers
 
8
  ---
9
  <div>
10
  <p style="margin-top: 0;margin-bottom: 0;">
config.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 4096,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 12288,
14
+ "max_position_embeddings": 131072,
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
+ "pad_token_id": 151654,
21
+ "rms_norm_eps": 1e-06,
22
+ "rope_scaling": {
23
+ "attn_factor": 0.8782488562869419,
24
+ "factor": 4.0,
25
+ "original_max_position_embeddings": 32768,
26
+ "rope_type": "yarn"
27
+ },
28
+ "rope_theta": 1000000,
29
+ "sliding_window": null,
30
+ "tie_word_embeddings": false,
31
+ "torch_dtype": "bfloat16",
32
+ "transformers_version": "4.52.3",
33
+ "unsloth_fixed": true,
34
+ "use_cache": true,
35
+ "use_sliding_window": false,
36
+ "vocab_size": 151936
37
+ }