sadkins65 commited on
Commit
9804e70
·
verified ·
1 Parent(s): e852317

Upload folder using huggingface_hub

Browse files
config.json ADDED
@@ -0,0 +1,71 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/home/sadkins/.cache/huggingface/hub/models--mistralai--Mixtral-8x7B-Instruct-v0.1/snapshots/67c3bf6b0aa8b6670f892629331d314f9af0b522",
3
+ "architectures": [
4
+ "MixtralForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "compression_config": {
9
+ "config_groups": {
10
+ "group_0": {
11
+ "input_activations": {
12
+ "block_structure": null,
13
+ "dynamic": false,
14
+ "group_size": null,
15
+ "num_bits": 8,
16
+ "observer": "minmax",
17
+ "observer_kwargs": {},
18
+ "strategy": "tensor",
19
+ "symmetric": true,
20
+ "type": "float"
21
+ },
22
+ "output_activations": null,
23
+ "targets": [
24
+ "Linear"
25
+ ],
26
+ "weights": {
27
+ "block_structure": null,
28
+ "dynamic": false,
29
+ "group_size": null,
30
+ "num_bits": 8,
31
+ "observer": "minmax",
32
+ "observer_kwargs": {},
33
+ "strategy": "tensor",
34
+ "symmetric": true,
35
+ "type": "float"
36
+ }
37
+ }
38
+ },
39
+ "format": "float-quantized",
40
+ "global_compression_ratio": 1.5665445489093042,
41
+ "ignore": [
42
+ "lm_head"
43
+ ],
44
+ "kv_cache_scheme": null,
45
+ "quant_method": "compressed_tensors",
46
+ "quantization_status": "frozen"
47
+ },
48
+ "eos_token_id": 2,
49
+ "hidden_act": "silu",
50
+ "hidden_size": 4096,
51
+ "initializer_range": 0.02,
52
+ "intermediate_size": 14336,
53
+ "max_position_embeddings": 32768,
54
+ "model_type": "mixtral",
55
+ "num_attention_heads": 32,
56
+ "num_experts_per_tok": 2,
57
+ "num_hidden_layers": 32,
58
+ "num_key_value_heads": 8,
59
+ "num_local_experts": 8,
60
+ "output_router_logits": false,
61
+ "rms_norm_eps": 1e-05,
62
+ "rope_theta": 1000000.0,
63
+ "router_aux_loss_coef": 0.02,
64
+ "router_jitter_noise": 0.0,
65
+ "sliding_window": null,
66
+ "tie_word_embeddings": false,
67
+ "torch_dtype": "float16",
68
+ "transformers_version": "4.43.4",
69
+ "use_cache": true,
70
+ "vocab_size": 32000
71
+ }
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": "4.43.4"
6
+ }
model-00001-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83fe88bab3b75460b3d4fc314dbae818b74e232b201db603f163d77f13213d32
3
+ size 4951593668
model-00002-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c6b8153c76b2de19367df6ae98d1bfe4ff94a59a3e9a0b31cbd5f9baf1a3530f
3
+ size 4999794008
model-00003-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57e85d53f9724db29089edb268c4b683cd653dc18675e0a6f99023a757cc0b82
3
+ size 4983067504
model-00004-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3cfd20e11eed48f167cd5ac797b44515508896f66824cd912a80623c01694d5b
3
+ size 4999794272
model-00005-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83f096f8676f70399d4407e92b1c5a29c4b25e4ef9385a1b3a82fd88ff4e14b8
3
+ size 4999811000
model-00006-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:69d9a13590fa8bf67badf7d9a49d3a65b62e06ff521b6143e06d2145d24010dd
3
+ size 4983051096
model-00007-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:94c3be7ddcfc58d266160c55c527353310f58f870601fe712afcccde484bb594
3
+ size 4999794368
model-00008-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d3e6f5c1f7fc2fd10a3d6056666821987fdd0395b76cbaf891b25cb690a4f64
3
+ size 4983067952
model-00009-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:53c9a3c45bc0c9380eb9666d19d58df038aa8b923e7cff3e3c5359db5fa2fcff
3
+ size 4999794328
model-00010-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5790ae0f83226f33e1e3d059f15ce073297e27c643668ab498ced4447c943b5
3
+ size 2065782556
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
recipe.yaml ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ DEFAULT_stage:
2
+ DEFAULT_modifiers:
3
+ QuantizationModifier:
4
+ ignore: [lm_head]
5
+ targets: Linear
6
+ scheme: FP8
special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "pad_token": "</s>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": null,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<unk>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "2": {
23
+ "content": "</s>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": true
29
+ }
30
+ },
31
+ "additional_special_tokens": [],
32
+ "bos_token": "<s>",
33
+ "chat_template": "{%- if messages[0]['role'] == 'system' %}\n {%- set system_message = messages[0]['content'] %}\n {%- set loop_messages = messages[1:] %}\n{%- else %}\n {%- set loop_messages = messages %}\n{%- endif %}\n\n{{- bos_token }}\n{%- for message in loop_messages %}\n {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}\n {{- raise_exception('After the optional system message, conversation roles must alternate user/assistant/user/assistant/...') }}\n {%- endif %}\n {%- if message['role'] == 'user' %}\n {%- if loop.first and system_message is defined %}\n {{- ' [INST] ' + system_message + '\\n\\n' + message['content'] + ' [/INST]' }}\n {%- else %}\n {{- ' [INST] ' + message['content'] + ' [/INST]' }}\n {%- endif %}\n {%- elif message['role'] == 'assistant' %}\n {{- ' ' + message['content'] + eos_token}}\n {%- else %}\n {{- raise_exception('Only user and assistant roles are supported, with the exception of an initial optional system message!') }}\n {%- endif %}\n{%- endfor %}\n",
34
+ "clean_up_tokenization_spaces": false,
35
+ "eos_token": "</s>",
36
+ "legacy": false,
37
+ "model_max_length": 1000000000000000019884624838656,
38
+ "pad_token": "</s>",
39
+ "sp_model_kwargs": {},
40
+ "spaces_between_special_tokens": false,
41
+ "tokenizer_class": "LlamaTokenizer",
42
+ "unk_token": "<unk>",
43
+ "use_default_system_prompt": false
44
+ }