prince-canuma commited on
Commit
e23f62c
·
verified ·
1 Parent(s): e96d1ee

Add files using upload-large-folder tool

Browse files
Files changed (50) hide show
  1. .ipynb_checkpoints/model-00001-of-00088-checkpoint.safetensors +0 -0
  2. README.md +37 -0
  3. config.json +66 -0
  4. generation_config.json +9 -0
  5. model-00002-of-00088.safetensors +3 -0
  6. model-00004-of-00088.safetensors +3 -0
  7. model-00005-of-00088.safetensors +3 -0
  8. model-00007-of-00088.safetensors +3 -0
  9. model-00010-of-00088.safetensors +3 -0
  10. model-00017-of-00088.safetensors +3 -0
  11. model-00018-of-00088.safetensors +3 -0
  12. model-00019-of-00088.safetensors +3 -0
  13. model-00023-of-00088.safetensors +3 -0
  14. model-00025-of-00088.safetensors +3 -0
  15. model-00028-of-00088.safetensors +3 -0
  16. model-00029-of-00088.safetensors +3 -0
  17. model-00030-of-00088.safetensors +3 -0
  18. model-00031-of-00088.safetensors +3 -0
  19. model-00037-of-00088.safetensors +3 -0
  20. model-00039-of-00088.safetensors +3 -0
  21. model-00041-of-00088.safetensors +3 -0
  22. model-00042-of-00088.safetensors +3 -0
  23. model-00044-of-00088.safetensors +3 -0
  24. model-00046-of-00088.safetensors +3 -0
  25. model-00048-of-00088.safetensors +3 -0
  26. model-00049-of-00088.safetensors +3 -0
  27. model-00050-of-00088.safetensors +3 -0
  28. model-00052-of-00088.safetensors +3 -0
  29. model-00054-of-00088.safetensors +3 -0
  30. model-00055-of-00088.safetensors +3 -0
  31. model-00058-of-00088.safetensors +3 -0
  32. model-00059-of-00088.safetensors +3 -0
  33. model-00060-of-00088.safetensors +3 -0
  34. model-00061-of-00088.safetensors +3 -0
  35. model-00063-of-00088.safetensors +3 -0
  36. model-00066-of-00088.safetensors +3 -0
  37. model-00069-of-00088.safetensors +3 -0
  38. model-00071-of-00088.safetensors +3 -0
  39. model-00073-of-00088.safetensors +3 -0
  40. model-00074-of-00088.safetensors +3 -0
  41. model-00075-of-00088.safetensors +3 -0
  42. model-00079-of-00088.safetensors +3 -0
  43. model-00084-of-00088.safetensors +3 -0
  44. model-00085-of-00088.safetensors +3 -0
  45. model-00086-of-00088.safetensors +3 -0
  46. model-00088-of-00088.safetensors +3 -0
  47. model.safetensors.index.json +0 -0
  48. special_tokens_map.json +23 -0
  49. tokenizer.json +0 -0
  50. tokenizer_config.json +0 -0
.ipynb_checkpoints/model-00001-of-00088-checkpoint.safetensors ADDED
File without changes
README.md ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ library_name: mlx
4
+ base_model: deepseek-ai/DeepSeek-V3.2-Speciale
5
+ base_model_relation: finetune
6
+ tags:
7
+ - mlx
8
+ pipeline_tag: text-generation
9
+ ---
10
+
11
+ # mlx-community/DeepSeek-V3.2-Speciale-4bit
12
+
13
+ This model [mlx-community/DeepSeek-V3.2-Speciale-4bit](https://huggingface.co/mlx-community/DeepSeek-V3.2-Speciale-4bit) was
14
+ converted to MLX format from [deepseek-ai/DeepSeek-V3.2-Speciale](https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Speciale)
15
+ using mlx-lm version **0.28.4**.
16
+
17
+ ## Use with mlx
18
+
19
+ ```bash
20
+ pip install mlx-lm
21
+ ```
22
+
23
+ ```python
24
+ from mlx_lm import load, generate
25
+
26
+ model, tokenizer = load("mlx-community/DeepSeek-V3.2-Speciale-4bit")
27
+
28
+ prompt = "hello"
29
+
30
+ if tokenizer.chat_template is not None:
31
+ messages = [{"role": "user", "content": prompt}]
32
+ prompt = tokenizer.apply_chat_template(
33
+ messages, add_generation_prompt=True
34
+ )
35
+
36
+ response = generate(model, tokenizer, prompt=prompt, verbose=True)
37
+ ```
config.json ADDED
@@ -0,0 +1,66 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "DeepseekV32ForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 0,
8
+ "eos_token_id": 1,
9
+ "ep_size": 1,
10
+ "first_k_dense_replace": 3,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 7168,
13
+ "index_head_dim": 128,
14
+ "index_n_heads": 64,
15
+ "index_topk": 2048,
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 18432,
18
+ "kv_lora_rank": 512,
19
+ "max_position_embeddings": 163840,
20
+ "model_type": "deepseek_v32",
21
+ "moe_intermediate_size": 2048,
22
+ "moe_layer_freq": 1,
23
+ "n_group": 8,
24
+ "n_routed_experts": 256,
25
+ "n_shared_experts": 1,
26
+ "norm_topk_prob": true,
27
+ "num_attention_heads": 128,
28
+ "num_experts_per_tok": 8,
29
+ "num_hidden_layers": 61,
30
+ "num_key_value_heads": 128,
31
+ "num_nextn_predict_layers": 1,
32
+ "q_lora_rank": 1536,
33
+ "qk_nope_head_dim": 128,
34
+ "qk_rope_head_dim": 64,
35
+ "quantization": {
36
+ "group_size": 64,
37
+ "bits": 4,
38
+ "mode": "affine"
39
+ },
40
+ "quantization_config": {
41
+ "group_size": 64,
42
+ "bits": 4,
43
+ "mode": "affine"
44
+ },
45
+ "rms_norm_eps": 1e-06,
46
+ "rope_scaling": {
47
+ "beta_fast": 32,
48
+ "beta_slow": 1,
49
+ "factor": 40,
50
+ "mscale": 1.0,
51
+ "mscale_all_dim": 1.0,
52
+ "original_max_position_embeddings": 4096,
53
+ "type": "yarn"
54
+ },
55
+ "rope_theta": 10000,
56
+ "routed_scaling_factor": 2.5,
57
+ "scoring_func": "sigmoid",
58
+ "tie_word_embeddings": false,
59
+ "topk_group": 4,
60
+ "topk_method": "noaux_tc",
61
+ "torch_dtype": "bfloat16",
62
+ "transformers_version": "4.44.2",
63
+ "use_cache": true,
64
+ "v_head_dim": 128,
65
+ "vocab_size": 129280
66
+ }
generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "eos_token_id": 1,
5
+ "do_sample": true,
6
+ "temperature": 1.0,
7
+ "top_p": 0.95,
8
+ "transformers_version": "4.46.3"
9
+ }
model-00002-of-00088.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00d8f7aff25936babcf1fab91bcc1e8259188c756c028f557f46a0e37eb6d1ab
3
+ size 4369439770
model-00004-of-00088.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:694a996a8971023792317e4be0d0ebb78b158d62d62766691dbcae9197925622
3
+ size 4369439870
model-00005-of-00088.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e0971a2406b2c3cbe0f1f77ed0bf07f8e642229c0b95dac36e33a97c90bf128
3
+ size 4369439740
model-00007-of-00088.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a0f0075c7a8f30f6fa664555f6d4ef20d00af05c5686a9621dcb8de61dbe8b6
3
+ size 4369439872
model-00010-of-00088.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cec7bc58fa56c2f2d67edcec05e1eb708961bb43a025b460a37173bc361c0585
3
+ size 4369439868
model-00017-of-00088.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2673a42db743a24deb66012e725a8bb3215d908e7fb646ef2f28d047dec70c28
3
+ size 4369439797
model-00018-of-00088.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:592e01b4022dea2df6201b60ebe1b105ec00534c9a78ff730e9f9a40314b1b4f
3
+ size 4227859226
model-00019-of-00088.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b43597be24a5e5f3ce9f5921a6452baac4cfbdfa79c2eed10b92b64c47875c38
3
+ size 4369439865
model-00023-of-00088.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d58d45bf972b162fc04def89b0e51a2a72a84dba489be6a7ec13105e572daa88
3
+ size 4369439783
model-00025-of-00088.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:70b36eedae247f72b91d7b37b15dfdb5989fa66865dca2bd889dc12b953a479c
3
+ size 4369439913
model-00028-of-00088.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b92bd0efabd3a7d31d52f520768f746426be55cab7b5f2320936f0019bd6c39
3
+ size 4369439905
model-00029-of-00088.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c1d357b5d4d051ee6e18ca6602ef6ccdd330ea8c37885d9c65daa5d4343d61d5
3
+ size 4369439833
model-00030-of-00088.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a78e9ebdeef306cff83e3016f23ee027b4234c735bb291ea77489bf922cb99f
3
+ size 4227859226
model-00031-of-00088.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eced75e79da28acb1830e6f3dd0b31e12705d1161b6cd6f7e95c1e8154efd448
3
+ size 4369439915
model-00037-of-00088.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:166cf91c467fab82fdfbaf57154a3a46767f9655c76308f60d66954d0a023248
3
+ size 4369439919
model-00039-of-00088.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab6c0f98a17b07fba936f8df79b6cdab8f64cbb482771798f060999f10bf8beb
3
+ size 4227859222
model-00041-of-00088.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:74bff4f3a8fbca038e027e8f3ef177661ed884dc31fd956d763835cdd1c43e03
3
+ size 4369439803
model-00042-of-00088.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d39b332079da9219dcbc27ead21056ffc8156f4b5938a1f67420372c39c1745b
3
+ size 4227859228
model-00044-of-00088.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59ace1c264bbef69cb6106aaa94e8ec56acb06763b1f180bb2f6527b94cb6b6c
3
+ size 4369439827
model-00046-of-00088.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8dbd70edd4a5ac34bdde5575496ddda0405e57eb8be44e99c2ddf097d84889f
3
+ size 4369439889
model-00048-of-00088.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:afa24b6d8739b2bc52b7ac6e5f41ef9088bcacda26c98d9652e5e049f1ab8cf8
3
+ size 4227859224
model-00049-of-00088.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09936c92e572e2f685650bf92d0601c48985c73467d1476f3ede860929d85a03
3
+ size 4369439919
model-00050-of-00088.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea3b31d9bbdc3af9fc9eaf9351ec2b6d28f8327fe19cfbcfd12ca34460b28c60
3
+ size 4369439799
model-00052-of-00088.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:15ebf171cf21448d912ecaf5c7f0f4e93dd8b22687bd958a2109d2e93d9cf2f5
3
+ size 4369439915
model-00054-of-00088.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b8d07714983e971583bd232c0680fda6e9aa28af22149ff6893993b5c256a77
3
+ size 4227859222
model-00055-of-00088.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2df146a970b208ec8dfe46659117f1f27b329da708a36a18446f6bb39985671
3
+ size 4369439869
model-00058-of-00088.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26f479cfa2155712637ffbf43188f5f8ff1da6a6f5f40c9715e2489339074bc4
3
+ size 4369439915
model-00059-of-00088.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ceb62b944b98c80588c6adf36a0f0eee8cf3b6ced0fa514b55924b60a5798ae1
3
+ size 4369439833
model-00060-of-00088.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f17a441afde0ace704f227b7ae84bbf9dd73af587ed62541514d1d3dd510efae
3
+ size 4227859226
model-00061-of-00088.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b10156084e969421f7733098550d8964d997443f23180f34122e5da6c9c6f877
3
+ size 4369439883
model-00063-of-00088.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a076c4a7232d7c6f31185ea8ad17b4fbd7bf73fca5f83750693e9e3d4f74021
3
+ size 4227859228
model-00066-of-00088.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4217a3dc95a1d32b767d105b156e9cc0bc54c3da081582573f7c105193822dee
3
+ size 4227859226
model-00069-of-00088.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:88fc5c5ead9dc29664e488213e2e6fbfb5f9649b81478bf182183806e8840483
3
+ size 4227859228
model-00071-of-00088.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e8c05412016af6a2b95fba7e0b17b734375eaa5f5c5bdc2f0552051ca8e8a24
3
+ size 4369439821
model-00073-of-00088.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb2a5a667d86a5a64ac90ec8a759706defa2c54bd6a59d8a8588e1ecdbbf9e5f
3
+ size 4369439903
model-00074-of-00088.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:779a6bf40756dd4db7a1ed07d41e256ccc70113880f89b12971d1557ea148b61
3
+ size 4369439801
model-00075-of-00088.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:25f7ff591acf8b48687173fc6d8da5c5cc785edd9838c7eb83023d2665eae279
3
+ size 4227859222
model-00079-of-00088.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c60adaa29f00fd164484ef7ff3855b92a5fb1363303facf52d084892dee672c5
3
+ size 4369439917
model-00084-of-00088.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9da6d8b17f958435a25e7a8642825e256b89af8ca58179085bb72cdaf8cfb1c9
3
+ size 4227859226
model-00085-of-00088.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c34627c7a79cdd2b9699f7bb579b6d8907f533d752e231db33d97bcfbdde0b98
3
+ size 4369439919
model-00086-of-00088.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:225682eb33348e007739dda5ae726a0540cdab155f6ee91f01fedeef5a0062ae
3
+ size 4369439785
model-00088-of-00088.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ee88b2e20d7c0e03811e428b369a09f9168f0e67caf6b2fb97b830393e508cc
3
+ size 2663675220
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|begin▁of▁sentence|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|end▁of▁sentence|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|end▁of▁sentence|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff