Hugging Face's logo

Outlier-Ai
/
DeepSeek-R1-Distill-Qwen-32B-MLX-4bit

Text Generation
MLX
Safetensors
qwen2
4-bit precision
4bit
apple-silicon
chain-of-thought
chat
conversational
deepseek
deepseek-r1
deepseek-r1-distill
edge-ai
function-calling
instruct
local-llm
m1
m2
m3
m4
mac
mac-mini
mac-studio
macbook-air
macbook-pro
macos
metal
mlx-community
mlx-lm
no-cloud
offline
on-device
outlier
outlier-app
private
quantized
r1
r1-distill
reasoning
thinking
Model card Files
xet
 Community
ur-dad-matt commited on
Commit
2ce8065
·
verified ·
1 Parent(s): 998fd39

Initial upload: canonical-named twin of Outlier-Ai/Outlier-R1-Distill-32B-MLX-4bit

Browse files
Files changed (10) hide show
  1. .gitattributes +1 -0
  2. config.json +37 -0
  3. generation_config.json +9 -0
  4. model-00001-of-00004.safetensors +3 -0
  5. model-00002-of-00004.safetensors +3 -0
  6. model-00003-of-00004.safetensors +3 -0
  7. model-00004-of-00004.safetensors +3 -0
  8. model.safetensors.index.json +0 -0
  9. tokenizer.json +3 -0
  10. tokenizer_config.json +13 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ 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
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
config.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen2ForCausalLM"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "bos_token_id": 151643,
7
+ "eos_token_id": 151643,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 5120,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 27648,
12
+ "max_position_embeddings": 131072,
13
+ "max_window_layers": 64,
14
+ "model_type": "qwen2",
15
+ "num_attention_heads": 40,
16
+ "num_hidden_layers": 64,
17
+ "num_key_value_heads": 8,
18
+ "quantization": {
19
+ "group_size": 64,
20
+ "bits": 4,
21
+ "mode": "affine"
22
+ },
23
+ "quantization_config": {
24
+ "group_size": 64,
25
+ "bits": 4,
26
+ "mode": "affine"
27
+ },
28
+ "rms_norm_eps": 1e-05,
29
+ "rope_theta": 1000000.0,
30
+ "sliding_window": 131072,
31
+ "tie_word_embeddings": false,
32
+ "torch_dtype": "bfloat16",
33
+ "transformers_version": "4.43.1",
34
+ "use_cache": true,
35
+ "use_sliding_window": false,
36
+ "vocab_size": 152064
37
+ }
generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 151646,
4
+ "eos_token_id": 151643,
5
+ "do_sample": true,
6
+ "temperature": 0.6,
7
+ "top_p": 0.95,
8
+ "transformers_version": "4.39.3"
9
+ }
model-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8945fcfa6f506b8b62f949c76f58ceb5e99b79fd3e28c964c9e79fbadd98f9e
3
+ size 5366583057
model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2098646673c2329a65f6ca6efd7e4ec15d5fbd81be2a21b339d0ad39db583376
3
+ size 5335713350
model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66f3b77e78ee65912b4b35331d938c8c47dfd2c43eeafea1b35dc8aad347ad83
3
+ size 5366642308
model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aeb4f898ed6dad7dfe6bee89837107d06bbf10cafe267e4c9249050484fc5919
3
+ size 2362540963
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:322664cdc3082b6eba003af5228a77ca1d7936d402e584ecde8f15d3d98bdb72
3
+ size 11421911
tokenizer_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "backend": "tokenizers",
3
+ "bos_token": "<｜begin▁of▁sentence｜>",
4
+ "clean_up_tokenization_spaces": false,
5
+ "eos_token": "<｜end▁of▁sentence｜>",
6
+ "is_local": true,
7
+ "legacy": true,
8
+ "model_max_length": 16384,
9
+ "pad_token": "<｜end▁of▁sentence｜>",
10
+ "sp_model_kwargs": {},
11
+ "tokenizer_class": "TokenizersBackend",
12
+ "unk_token": null
13
+ }