Hugging Face's logo

tacodevs
/
Behemoth-T1-v2-123B-FP8

Safetensors
mistral
compressed-tensors
Model card Files
xet
 Community
tacodevs commited on
Commit
9efdebc
·
verified ·
1 Parent(s): 3a7532b

Add files using upload-large-folder tool

Browse files
Files changed (35) hide show
  1. chat_template.jinja +1 -0
  2. config.json +76 -0
  3. generation_config.json +6 -0
  4. model-00001-of-00026.safetensors +3 -0
  5. model-00002-of-00026.safetensors +3 -0
  6. model-00003-of-00026.safetensors +3 -0
  7. model-00004-of-00026.safetensors +3 -0
  8. model-00005-of-00026.safetensors +3 -0
  9. model-00006-of-00026.safetensors +3 -0
  10. model-00007-of-00026.safetensors +3 -0
  11. model-00008-of-00026.safetensors +3 -0
  12. model-00009-of-00026.safetensors +3 -0
  13. model-00010-of-00026.safetensors +3 -0
  14. model-00011-of-00026.safetensors +3 -0
  15. model-00012-of-00026.safetensors +3 -0
  16. model-00013-of-00026.safetensors +3 -0
  17. model-00014-of-00026.safetensors +3 -0
  18. model-00015-of-00026.safetensors +3 -0
  19. model-00016-of-00026.safetensors +3 -0
  20. model-00017-of-00026.safetensors +3 -0
  21. model-00018-of-00026.safetensors +3 -0
  22. model-00019-of-00026.safetensors +3 -0
  23. model-00020-of-00026.safetensors +3 -0
  24. model-00021-of-00026.safetensors +3 -0
  25. model-00022-of-00026.safetensors +3 -0
  26. model-00023-of-00026.safetensors +3 -0
  27. model-00024-of-00026.safetensors +3 -0
  28. model-00025-of-00026.safetensors +3 -0
  29. model-00026-of-00026.safetensors +3 -0
  30. model.safetensors.index.json +0 -0
  31. recipe.yaml +7 -0
  32. special_tokens_map.json +23 -0
  33. tokenizer.json +0 -0
  34. tokenizer.model +3 -0
  35. tokenizer_config.json +0 -0
chat_template.jinja ADDED
@@ -0,0 +1 @@
 
 
1
+ {{ bos_token }}{% for message in messages %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + '[/INST]' }}{% elif message['role'] == 'system' %}{{ '[SYSTEM_PROMPT] ' + message['content'] + '[/SYSTEM_PROMPT]' }}{% elif message['role'] == 'assistant' %}{{ ' ' + message['content'] + eos_token }}{% else %}{{ raise_exception('Only user, system and assistant roles are supported!') }}{% endif %}{% endfor %}
config.json ADDED
@@ -0,0 +1,76 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "MistralForCausalLM"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "bos_token_id": 1,
7
+ "dtype": "bfloat16",
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
+ "quantization_config": {
20
+ "config_groups": {
21
+ "group_0": {
22
+ "format": "float-quantized",
23
+ "input_activations": {
24
+ "actorder": null,
25
+ "block_structure": null,
26
+ "dynamic": true,
27
+ "group_size": null,
28
+ "num_bits": 8,
29
+ "observer": null,
30
+ "observer_kwargs": {},
31
+ "scale_dtype": null,
32
+ "strategy": "token",
33
+ "symmetric": true,
34
+ "type": "float",
35
+ "zp_dtype": null
36
+ },
37
+ "output_activations": null,
38
+ "targets": [
39
+ "Linear"
40
+ ],
41
+ "weights": {
42
+ "actorder": null,
43
+ "block_structure": null,
44
+ "dynamic": false,
45
+ "group_size": null,
46
+ "num_bits": 8,
47
+ "observer": "memoryless_minmax",
48
+ "observer_kwargs": {},
49
+ "scale_dtype": null,
50
+ "strategy": "channel",
51
+ "symmetric": true,
52
+ "type": "float",
53
+ "zp_dtype": null
54
+ }
55
+ }
56
+ },
57
+ "format": "float-quantized",
58
+ "global_compression_ratio": null,
59
+ "ignore": [
60
+ "lm_head"
61
+ ],
62
+ "kv_cache_scheme": null,
63
+ "quant_method": "compressed-tensors",
64
+ "quantization_status": "compressed",
65
+ "sparsity_config": {},
66
+ "transform_config": {},
67
+ "version": "0.14.0.1"
68
+ },
69
+ "rms_norm_eps": 1e-05,
70
+ "rope_theta": 1000000.0,
71
+ "sliding_window": null,
72
+ "tie_word_embeddings": false,
73
+ "transformers_version": "4.57.6",
74
+ "use_cache": true,
75
+ "vocab_size": 32768
76
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "transformers_version": "4.57.6"
6
+ }
model-00001-of-00026.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1074a968d79d6f15d49a182506daff38f27f9dc5755f0db1c6eeed23213b9e1a
3
+ size 4958398128
model-00002-of-00026.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:53598a53b2b328116bb206ee146f68d2fdb619ec1abcb282fe16a8891ab30aa6
3
+ size 4832680488
model-00003-of-00026.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:25bcedb5602a78e66195bcba0aa96d92706cfdf7b9df23c6658edb3293d1f9ee
3
+ size 4857866304
model-00004-of-00026.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16ac15536954438c36de90c8e1d1e91189a72434fc8041b77f021d2fdbf2c5f0
3
+ size 4832680552
model-00005-of-00026.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5acc8d5d190094a7c925d4ff8ab126d4279063c037c39b4fc05a41e8b43dabb7
3
+ size 4857866352
model-00006-of-00026.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:447344374002a789c2fb5fb65e6d73b615b1d5f1a955b9045fc5513274f66eba
3
+ size 4832680552
model-00007-of-00026.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1137e680cbd2b8b9a016d045c0da3be84190ba6405007b63a4d625ae90845e94
3
+ size 4857866352
model-00008-of-00026.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c51fb9fcfb94bef10ddba1e18126c8d6be75e306b1cc69e2b024142ae52f8e6e
3
+ size 4832680552
model-00009-of-00026.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:04ae7572e27187172ef7be2ebb13b272c25b2d4ec99e2ab92a305dee0144c66f
3
+ size 4857866352
model-00010-of-00026.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f8ba463114bf473cce07ac268292cf8acf73c51f3d1170642ab66dd71e63a17
3
+ size 4832680552
model-00011-of-00026.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05f2002ffb387af84224e46589fd8e688c0fcf5f2480151aafa8dfc9299f2033
3
+ size 4857866352
model-00012-of-00026.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0313a475c60c0d14caae33c06a8f0f3893f142609ae7ede28614104e35344c4
3
+ size 4832680552
model-00013-of-00026.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4fc1b19aca4354766bff3756aaaad7fac78093dfcf3e04511a451ca2ac627649
3
+ size 4857866352
model-00014-of-00026.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a6d7ac5e54cfca871d2f5b84ed165653ac8f9b7a14f7ff54f47312db5e1f5854
3
+ size 4832680552
model-00015-of-00026.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7eafe26afa6cdbd141c360cc51f721aec4938a7eef09651227ec981375adf54d
3
+ size 4857866352
model-00016-of-00026.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54e8704c42b164dac5ea6fe1b0548f06ff2b002596cb5bcf1a1b521288f1bde9
3
+ size 4832680552
model-00017-of-00026.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea88cf67186c9432931c5af839524eaf97c1239d0595ebbf19c6947e1c48eeca
3
+ size 4857866352
model-00018-of-00026.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:072e496ab3cf749b39831defd23146b59566c291201df9d0ce8cd44727cbe45d
3
+ size 4832680552
model-00019-of-00026.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:678e5ff314a9376d5a6d6993a175779092dae53c8e66bfdabbb57ac1ec13f3d0
3
+ size 4857866352
model-00020-of-00026.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ddf291f88c67f35c999d1c34d8e35c09f86ca1affc7c8bca13931bccbe4bb2b
3
+ size 4832680552
model-00021-of-00026.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d3ec4ca9901347d3e4f3cf58e4f8e8bbf588f7f7bb949a970ecb2dedc94be259
3
+ size 4857866352
model-00022-of-00026.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d698f4ebf97dc3b182d331d9d43790481c76ac58e34df625b7be6a98423715c
3
+ size 4832680552
model-00023-of-00026.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e83c5277fe831f7007293abc533f4fdd6ae5117de083e433e38e47bbd14e15d1
3
+ size 4857866352
model-00024-of-00026.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a12a96e112ea5d06d2cf5e8b2bb4c71cbd0a0cb2732d9c9a9d823e88be80898f
3
+ size 4832680552
model-00025-of-00026.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:33d336dbec7e8f91008c7c06cab34a2f0095f1b7152fac0dc4f20057df127837
3
+ size 4857866352
model-00026-of-00026.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd906308cd8dab55e067dc25912a8b957bd22992ed629e3103eae894a9ad0f83
3
+ size 2189695048
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
recipe.yaml ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ default_stage:
2
+ default_modifiers:
3
+ QuantizationModifier:
4
+ targets: [Linear]
5
+ ignore: [lm_head]
6
+ scheme: FP8_DYNAMIC
7
+ bypass_divisibility_checks: false
special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "unk_token": {
17
+ "content": "<unk>",
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.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b968b8dc352f42192367337c78ccc61e1eaddc6d641a579372d4f20694beb7a
3
+ size 587562
tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff