Hugging Face's logo

gghfez
/
Mistral-Large-2407-LongCoT

Text Generation
Transformers
Safetensors
English
mistral
text-generation-inference
unsloth
trl
conversational
Inference Endpoints
Model card Files Community
gghfez commited on
Commit
312c779
·
verified ·
1 Parent(s): 235884f

Upload folder using huggingface_hub

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. config.json +30 -0
  2. generation_config.json +8 -0
  3. model-00001-of-00051.safetensors +3 -0
  4. model-00002-of-00051.safetensors +3 -0
  5. model-00003-of-00051.safetensors +3 -0
  6. model-00004-of-00051.safetensors +3 -0
  7. model-00005-of-00051.safetensors +3 -0
  8. model-00006-of-00051.safetensors +3 -0
  9. model-00007-of-00051.safetensors +3 -0
  10. model-00008-of-00051.safetensors +3 -0
  11. model-00009-of-00051.safetensors +3 -0
  12. model-00010-of-00051.safetensors +3 -0
  13. model-00011-of-00051.safetensors +3 -0
  14. model-00012-of-00051.safetensors +3 -0
  15. model-00013-of-00051.safetensors +3 -0
  16. model-00014-of-00051.safetensors +3 -0
  17. model-00015-of-00051.safetensors +3 -0
  18. model-00016-of-00051.safetensors +3 -0
  19. model-00017-of-00051.safetensors +3 -0
  20. model-00018-of-00051.safetensors +3 -0
  21. model-00019-of-00051.safetensors +3 -0
  22. model-00020-of-00051.safetensors +3 -0
  23. model-00021-of-00051.safetensors +3 -0
  24. model-00022-of-00051.safetensors +3 -0
  25. model-00023-of-00051.safetensors +3 -0
  26. model-00024-of-00051.safetensors +3 -0
  27. model-00025-of-00051.safetensors +3 -0
  28. model-00026-of-00051.safetensors +3 -0
  29. model-00027-of-00051.safetensors +3 -0
  30. model-00028-of-00051.safetensors +3 -0
  31. model-00029-of-00051.safetensors +3 -0
  32. model-00030-of-00051.safetensors +3 -0
  33. model-00031-of-00051.safetensors +3 -0
  34. model-00032-of-00051.safetensors +3 -0
  35. model-00033-of-00051.safetensors +3 -0
  36. model-00034-of-00051.safetensors +3 -0
  37. model-00035-of-00051.safetensors +3 -0
  38. model-00036-of-00051.safetensors +3 -0
  39. model-00037-of-00051.safetensors +3 -0
  40. model-00038-of-00051.safetensors +3 -0
  41. model-00039-of-00051.safetensors +3 -0
  42. model-00040-of-00051.safetensors +3 -0
  43. model-00041-of-00051.safetensors +3 -0
  44. model-00042-of-00051.safetensors +3 -0
  45. model-00043-of-00051.safetensors +3 -0
  46. model-00044-of-00051.safetensors +3 -0
  47. model-00045-of-00051.safetensors +3 -0
  48. model-00046-of-00051.safetensors +3 -0
  49. model-00047-of-00051.safetensors +3 -0
  50. model-00048-of-00051.safetensors +3 -0
config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "gghfez/Mistral-Large-2407-LongCoT",
3
+ "architectures": [
4
+ "MistralForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 2,
9
+ "head_dim": 128,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 12288,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 28672,
14
+ "max_position_embeddings": 131072,
15
+ "model_type": "mistral",
16
+ "num_attention_heads": 96,
17
+ "num_hidden_layers": 88,
18
+ "num_key_value_heads": 8,
19
+ "pad_token_id": 750,
20
+ "rms_norm_eps": 1e-05,
21
+ "rope_scaling": null,
22
+ "rope_theta": 1000000.0,
23
+ "sliding_window": null,
24
+ "tie_word_embeddings": false,
25
+ "torch_dtype": "bfloat16",
26
+ "transformers_version": "4.47.0",
27
+ "unsloth_version": "2024.12.4",
28
+ "use_cache": true,
29
+ "vocab_size": 32768
30
+ }
generation_config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "max_length": 131072,
6
+ "pad_token_id": 750,
7
+ "transformers_version": "4.47.0"
8
+ }
model-00001-of-00051.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76ae43e4fcc43649629ecc352df540ddc8bcde2ab583e2e6d8e4821fd51964c0
3
+ size 4932552432
model-00002-of-00051.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed13c16428d2e59b2312e08f66582fbb2f2af163d43cf6a21a9577d9f236dcbf
3
+ size 4831938528
model-00003-of-00051.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b880e10b931bb64c50595e5e8d0e60a27e22fde2e7dc5f4fa9ac643e68490b25
3
+ size 4882269816
model-00004-of-00051.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7aaf1e5e5d294c42f71321bf055ec5991ad43ee328a12263ae70cba8162fe91e
3
+ size 4831889136
model-00005-of-00051.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a97adc5969773fcc22db6aa8326a77fc4155936abe13c886181b9d49ccde5b6f
3
+ size 4831938520
model-00006-of-00051.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8c3a1b4878d4e16c92aa48da597dde4b27ed2aea9d1c6446039a5acdb59e1db
3
+ size 4831938528
model-00007-of-00051.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9cc7e18bc4e625f62c0d9e9a1fca7bba103de528f7cc184404fd96210c4fe456
3
+ size 4882269832
model-00008-of-00051.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83e34d86e7b58c24a7b9351b13adb80bbe286947d62976518953605377ed7617
3
+ size 4831889152
model-00009-of-00051.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67241060f6335e1e24c6f87be5e53d52b8224737c232d43f2e29a264f3be9401
3
+ size 4831938536
model-00010-of-00051.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e51049a69c30bdf30f5a975baccddbd5e22a40a9785be2364811d7eba129d691
3
+ size 4831938544
model-00011-of-00051.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:833381f9ff97dc249a7c1c01f68d53868424fd85b8bfba9e0d23b28b65f38489
3
+ size 4882269832
model-00012-of-00051.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f45e7e53cc5d71a8ec7d2c67ac70aaa803614df9021ab971d9968f25e505814
3
+ size 4831889152
model-00013-of-00051.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4eca6a5d127d3e4eabd862365f927ab1806b4736995dcbb27ec0b1af6523de2
3
+ size 4831938536
model-00014-of-00051.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb07267f4254a128a45cd866b9c4480dc9ce64100b3cfb7d9bec9d6b4a479805
3
+ size 4831938544
model-00015-of-00051.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f48fa5704808ab3f72a29429c5d8e373ffe69886757c2ffcb7c4c4cc5e843fc6
3
+ size 4882269832
model-00016-of-00051.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:262bff060921b35b0820ee5d572b760ff7e6f23bfd8702dbe70715d0da708294
3
+ size 4831889152
model-00017-of-00051.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a3968093e7ff9b5c90a4a5fb104395031e686e81dfdd04ae58cfe62f1e04383
3
+ size 4831938536
model-00018-of-00051.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0359bc75d11f639cadab251dac3be46b92304685523d08fd4e4f806a4e5cdbf
3
+ size 4831938544
model-00019-of-00051.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c761559b345adc8940976b1ce243904e8803e72278c4e42f7733e980166bd95
3
+ size 4882269832
model-00020-of-00051.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:137bc0cae6e332f7b8dd567bfca84f5f48a0be60e38d41f5f307295ccbdcea23
3
+ size 4831889152
model-00021-of-00051.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b7731420f2e70b9ec7f50d99209485064e708becf4b579b975562ec0d7a622b6
3
+ size 4831938536
model-00022-of-00051.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:635d93495d23db26ee096c6744ebd6ec3845073ff73556245b5f511e7ce182f7
3
+ size 4831938544
model-00023-of-00051.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6242395f202b98dcf111c9e9e5e0708d8b353e1ad247af58215619643a8f7a83
3
+ size 4882269832
model-00024-of-00051.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78c26c3f57936a687c9e8a8fbfb20148e327ed25f911c908d9045cc93faabf8f
3
+ size 4831889152
model-00025-of-00051.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d705e4f0e5f2e4e2a603afd171d439e5b730198447724dafc483b7897ed0a86f
3
+ size 4831938536
model-00026-of-00051.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0918e7c18635aa9f85f1cc6eac17ed9ea3a90a9dd27c12539e31ce84bc2914e6
3
+ size 4831938544
model-00027-of-00051.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de469052d9c0c65adfec44acbc1ade859aab849b3d95e6b7ca5d2af04786669e
3
+ size 4882269832
model-00028-of-00051.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3783314d52062984ce6b845ca7df63e8ba8153e3bba41c1bf8356ee9351cc65e
3
+ size 4831889152
model-00029-of-00051.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c28a6cbc7aeb4df59f2d49effd9042afacb6a5d3968b2669723033872e024ad
3
+ size 4831938536
model-00030-of-00051.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a1289c730c0e003bc3e0543cf3d12c22564bcfa8f81b1af7440ac4b4c454915
3
+ size 4831938544
model-00031-of-00051.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b1523cce30578507cb8266482bfac41a7191802d96ba52b84041a89f9527a59
3
+ size 4882269832
model-00032-of-00051.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:74b01a09f54016cfa396b86aa0a7266f7fa350fabfadba90e191adc8ccbdd3f8
3
+ size 4831889152
model-00033-of-00051.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59d7e835ecf417cf0469df167129c67bb61c4075e698b88fd02d980549313f7e
3
+ size 4831938536
model-00034-of-00051.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f801b009a803205f74caf90b0ad49a35266cfeb35987b5896678d9582d3e9925
3
+ size 4831938544
model-00035-of-00051.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5795b4a3de96dff1b35211f9e4547d0ad6ede6c697199b187c5d0b5f2549bb9c
3
+ size 4882269832
model-00036-of-00051.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8871aebd98eddd4fb787298a76924914ea0e584988a2396cb1238a156b2a2125
3
+ size 4831889152
model-00037-of-00051.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:971ee95b65146c19041583487d42c13dc1b89a6a2b77d423d80b55b9354cf8e6
3
+ size 4831938536
model-00038-of-00051.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b0eb3aee633f3d54fd999981538842369116d2f71e1d742193ba31fa6bca6b17
3
+ size 4831938544
model-00039-of-00051.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:47872da5954585033e998812103ced9e5eeca01f23c91efb4e5fd8a4ee5f59b4
3
+ size 4882269832
model-00040-of-00051.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6563706e47199a9c9ec40db5a56cfe743157ed213e07b88da380388e4ce69fdc
3
+ size 4831889152
model-00041-of-00051.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eeb654ce5697cde9871ffd91f224a2f0a12a63f607082f18c627385caf039900
3
+ size 4831938536
model-00042-of-00051.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01c6fa3d6bf0386d119d2dd2f56325a5c89d96f8c19b06ba5c62d0a744a649cc
3
+ size 4831938544
model-00043-of-00051.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8bd9feeda42a2f2da07ce85665ebe3ab7a21c332a5889a6622bfbd2ed2b299f9
3
+ size 4882269832
model-00044-of-00051.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78ebd4af306b542d4f99fd197fdd60a8480e9b369ee00870d86025408b2ca89a
3
+ size 4831889152
model-00045-of-00051.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:196d71184c449d4af54f64ffc155300ad8ad0d11ea86da87ae65f330ee285784
3
+ size 4831938536
model-00046-of-00051.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2b2f34d5a70c5867bb0a808b5b70ca3433272c3a5cfb9053214e16ce1763004
3
+ size 4831938544
model-00047-of-00051.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8898b6e0ce61182d0da389e42a391b5ce0633eea1ff3f5985220a3576eea0f98
3
+ size 4882269832
model-00048-of-00051.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62959d69a67d6f6888263af19379a5abe9ac3b68a711117695974c5ef716e83e
3
+ size 4831889152