sadkins65 commited on
Commit
9f5c3d2
1 Parent(s): e12c5af

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": true,
14
+ "group_size": null,
15
+ "num_bits": 8,
16
+ "observer": "memoryless",
17
+ "observer_kwargs": {},
18
+ "strategy": "token",
19
+ "symmetric": true,
20
+ "type": "int"
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": "channel",
34
+ "symmetric": true,
35
+ "type": "int"
36
+ }
37
+ }
38
+ },
39
+ "format": "int-quantized",
40
+ "global_compression_ratio": 1.2655668094430201,
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 sha256:6ca8b73b9b84cb885f6df3af49845fa64c49525e620eb12c5d661bb36e1a74dd
3
+ size 4953338784
model-00002-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c16a36842aa814f51e324292ea4f0b7f78fa11240bf174334bd8585096cf17f
3
+ size 4942922136
model-00003-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9f1c8bdecf1e54a35f2cd0526e4fd0d8720cb913889bfb65cfcd834024ff9e2
3
+ size 4984936160
model-00004-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d57401dc7ab22d01527984675a51db239eec481d1c339943e3508965a149ce9
3
+ size 4942901864
model-00005-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71da4b73a0eeebe9967d6814b8b7f87ced541ea82713a200fad7b3ae2a9c812b
3
+ size 4942922336
model-00006-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8847a09e84ce41f10a6c5a189f061026e404cfa911018aa5e5233aa5fab11c0
3
+ size 4984936392
model-00007-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f30dc5dab2db5b4f47c307205c3c9add5c9fa2022f48dacb0bd7d738fdd998c0
3
+ size 4942901856
model-00008-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d0cb955af208346b28116001d9db67e2d898fce4a9ea4cbf111d7c77f3b2e621
3
+ size 4984936400
model-00009-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:94cbf2de5c9478601300a488af241893fe4b202a159ec35cac2b63892fa3929c
3
+ size 4942922344
model-00010-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fdd642b4dd45cf7e7dfe0bd36689cb9d481cf40477151bf42c36158db0762d15
3
+ size 2360158960
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
+ GPTQModifier:
4
+ sequential_update: true
5
+ targets: Linear
6
+ ignore: [lm_head]
7
+ scheme: W8A8
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
+ }