Upload folder using huggingface_hub
#3
by
MaziyarPanahi
- opened
This view is limited to 50 files because it contains too many changes.
See the raw diff here.
- .ipynb_checkpoints/config-checkpoint.json +31 -0
- .ipynb_checkpoints/tokenizer_config-checkpoint.json +61 -0
- adapter/.ipynb_checkpoints/config-checkpoint.json +46 -0
- adapter/.ipynb_checkpoints/tokenizer_config-checkpoint.json +61 -0
- adapter/adapter_config.json +38 -0
- adapter/adapter_model.safetensors +3 -0
- adapter/added_tokens.json +4 -0
- adapter/config.json +46 -0
- adapter/special_tokens_map.json +24 -0
- adapter/tokenizer.model +3 -0
- adapter/tokenizer_config.json +61 -0
- added_tokens.json +4 -0
- config.json +31 -0
- generation_config.json +7 -0
- model-00001-of-00117.safetensors +3 -0
- model-00002-of-00117.safetensors +3 -0
- model-00003-of-00117.safetensors +3 -0
- model-00004-of-00117.safetensors +3 -0
- model-00005-of-00117.safetensors +3 -0
- model-00006-of-00117.safetensors +3 -0
- model-00007-of-00117.safetensors +3 -0
- model-00008-of-00117.safetensors +3 -0
- model-00009-of-00117.safetensors +3 -0
- model-00010-of-00117.safetensors +3 -0
- model-00011-of-00117.safetensors +3 -0
- model-00012-of-00117.safetensors +3 -0
- model-00013-of-00117.safetensors +3 -0
- model-00014-of-00117.safetensors +3 -0
- model-00015-of-00117.safetensors +3 -0
- model-00016-of-00117.safetensors +3 -0
- model-00017-of-00117.safetensors +3 -0
- model-00018-of-00117.safetensors +3 -0
- model-00019-of-00117.safetensors +3 -0
- model-00020-of-00117.safetensors +3 -0
- model-00021-of-00117.safetensors +3 -0
- model-00022-of-00117.safetensors +3 -0
- model-00023-of-00117.safetensors +3 -0
- model-00024-of-00117.safetensors +3 -0
- model-00025-of-00117.safetensors +3 -0
- model-00026-of-00117.safetensors +3 -0
- model-00027-of-00117.safetensors +3 -0
- model-00028-of-00117.safetensors +3 -0
- model-00029-of-00117.safetensors +3 -0
- model-00030-of-00117.safetensors +3 -0
- model-00031-of-00117.safetensors +3 -0
- model-00032-of-00117.safetensors +3 -0
- model-00033-of-00117.safetensors +3 -0
- model-00034-of-00117.safetensors +3 -0
- model-00035-of-00117.safetensors +3 -0
- model-00036-of-00117.safetensors +3 -0
.ipynb_checkpoints/config-checkpoint.json
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "v2ray/Mixtral-8x22B-v0.1",
|
3 |
+
"architectures": [
|
4 |
+
"MixtralForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"bos_token_id": 1,
|
8 |
+
"eos_token_id": 32000,
|
9 |
+
"hidden_act": "silu",
|
10 |
+
"hidden_size": 6144,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"intermediate_size": 16384,
|
13 |
+
"max_position_embeddings": 65536,
|
14 |
+
"model_type": "mixtral",
|
15 |
+
"num_attention_heads": 48,
|
16 |
+
"num_experts_per_tok": 2,
|
17 |
+
"num_hidden_layers": 56,
|
18 |
+
"num_key_value_heads": 8,
|
19 |
+
"num_local_experts": 8,
|
20 |
+
"output_router_logits": false,
|
21 |
+
"rms_norm_eps": 1e-05,
|
22 |
+
"rope_theta": 1000000,
|
23 |
+
"router_aux_loss_coef": 0.001,
|
24 |
+
"router_jitter_noise": 0.0,
|
25 |
+
"sliding_window": null,
|
26 |
+
"tie_word_embeddings": false,
|
27 |
+
"torch_dtype": "float32",
|
28 |
+
"transformers_version": "4.40.0.dev0",
|
29 |
+
"use_cache": false,
|
30 |
+
"vocab_size": 32002
|
31 |
+
}
|
.ipynb_checkpoints/tokenizer_config-checkpoint.json
ADDED
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"add_prefix_space": true,
|
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 |
+
"32000": {
|
31 |
+
"content": "<|im_end|>",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": false,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false,
|
36 |
+
"special": true
|
37 |
+
},
|
38 |
+
"32001": {
|
39 |
+
"content": "<|im_start|>",
|
40 |
+
"lstrip": false,
|
41 |
+
"normalized": false,
|
42 |
+
"rstrip": false,
|
43 |
+
"single_word": false,
|
44 |
+
"special": false
|
45 |
+
}
|
46 |
+
},
|
47 |
+
"additional_special_tokens": [],
|
48 |
+
"bos_token": "<s>",
|
49 |
+
"chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
50 |
+
"clean_up_tokenization_spaces": false,
|
51 |
+
"eos_token": "<|im_end|>",
|
52 |
+
"legacy": true,
|
53 |
+
"model_max_length": 1000000000000000019884624838656,
|
54 |
+
"pad_token": "</s>",
|
55 |
+
"sp_model_kwargs": {},
|
56 |
+
"spaces_between_special_tokens": false,
|
57 |
+
"tokenizer_class": "LlamaTokenizer",
|
58 |
+
"unk_token": "<unk>",
|
59 |
+
"use_default_system_prompt": false,
|
60 |
+
"use_fast": true
|
61 |
+
}
|
adapter/.ipynb_checkpoints/config-checkpoint.json
ADDED
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "v2ray/Mixtral-8x22B-v0.1",
|
3 |
+
"architectures": [
|
4 |
+
"MixtralForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"bos_token_id": 1,
|
8 |
+
"eos_token_id": 32000,
|
9 |
+
"hidden_act": "silu",
|
10 |
+
"hidden_size": 6144,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"intermediate_size": 16384,
|
13 |
+
"max_position_embeddings": 65536,
|
14 |
+
"model_type": "mixtral",
|
15 |
+
"num_attention_heads": 48,
|
16 |
+
"num_experts_per_tok": 2,
|
17 |
+
"num_hidden_layers": 56,
|
18 |
+
"num_key_value_heads": 8,
|
19 |
+
"num_local_experts": 8,
|
20 |
+
"output_router_logits": false,
|
21 |
+
"quantization_config": {
|
22 |
+
"_load_in_4bit": true,
|
23 |
+
"_load_in_8bit": false,
|
24 |
+
"bnb_4bit_compute_dtype": "bfloat16",
|
25 |
+
"bnb_4bit_quant_storage": "bfloat16",
|
26 |
+
"bnb_4bit_quant_type": "nf4",
|
27 |
+
"bnb_4bit_use_double_quant": true,
|
28 |
+
"llm_int8_enable_fp32_cpu_offload": false,
|
29 |
+
"llm_int8_has_fp16_weight": false,
|
30 |
+
"llm_int8_skip_modules": null,
|
31 |
+
"llm_int8_threshold": 6.0,
|
32 |
+
"load_in_4bit": true,
|
33 |
+
"load_in_8bit": false,
|
34 |
+
"quant_method": "bitsandbytes"
|
35 |
+
},
|
36 |
+
"rms_norm_eps": 1e-05,
|
37 |
+
"rope_theta": 1000000,
|
38 |
+
"router_aux_loss_coef": 0.001,
|
39 |
+
"router_jitter_noise": 0.0,
|
40 |
+
"sliding_window": null,
|
41 |
+
"tie_word_embeddings": false,
|
42 |
+
"torch_dtype": "bfloat16",
|
43 |
+
"transformers_version": "4.40.0.dev0",
|
44 |
+
"use_cache": false,
|
45 |
+
"vocab_size": 32002
|
46 |
+
}
|
adapter/.ipynb_checkpoints/tokenizer_config-checkpoint.json
ADDED
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"add_prefix_space": true,
|
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 |
+
"32000": {
|
31 |
+
"content": "<|im_end|>",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": false,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false,
|
36 |
+
"special": true
|
37 |
+
},
|
38 |
+
"32001": {
|
39 |
+
"content": "<|im_start|>",
|
40 |
+
"lstrip": false,
|
41 |
+
"normalized": false,
|
42 |
+
"rstrip": false,
|
43 |
+
"single_word": false,
|
44 |
+
"special": false
|
45 |
+
}
|
46 |
+
},
|
47 |
+
"additional_special_tokens": [],
|
48 |
+
"bos_token": "<s>",
|
49 |
+
"chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
50 |
+
"clean_up_tokenization_spaces": false,
|
51 |
+
"eos_token": "<|im_end|>",
|
52 |
+
"legacy": true,
|
53 |
+
"model_max_length": 1000000000000000019884624838656,
|
54 |
+
"pad_token": "</s>",
|
55 |
+
"sp_model_kwargs": {},
|
56 |
+
"spaces_between_special_tokens": false,
|
57 |
+
"tokenizer_class": "LlamaTokenizer",
|
58 |
+
"unk_token": "<unk>",
|
59 |
+
"use_default_system_prompt": false,
|
60 |
+
"use_fast": true
|
61 |
+
}
|
adapter/adapter_config.json
ADDED
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "v2ray/Mixtral-8x22B-v0.1",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": null,
|
7 |
+
"inference_mode": true,
|
8 |
+
"init_lora_weights": true,
|
9 |
+
"layer_replication": null,
|
10 |
+
"layers_pattern": null,
|
11 |
+
"layers_to_transform": null,
|
12 |
+
"loftq_config": {},
|
13 |
+
"lora_alpha": 8,
|
14 |
+
"lora_dropout": 0.05,
|
15 |
+
"megatron_config": null,
|
16 |
+
"megatron_core": "megatron.core",
|
17 |
+
"modules_to_save": [
|
18 |
+
"embed_tokens",
|
19 |
+
"lm_head"
|
20 |
+
],
|
21 |
+
"peft_type": "LORA",
|
22 |
+
"r": 16,
|
23 |
+
"rank_pattern": {},
|
24 |
+
"revision": null,
|
25 |
+
"target_modules": [
|
26 |
+
"q_proj",
|
27 |
+
"w2",
|
28 |
+
"w3",
|
29 |
+
"o_proj",
|
30 |
+
"v_proj",
|
31 |
+
"k_proj",
|
32 |
+
"gate",
|
33 |
+
"w1"
|
34 |
+
],
|
35 |
+
"task_type": "CAUSAL_LM",
|
36 |
+
"use_dora": false,
|
37 |
+
"use_rslora": false
|
38 |
+
}
|
adapter/adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e7c3e6eac571b2034dd287ea2c037b3187e9ea2a77b00a0166a08708fc006e87
|
3 |
+
size 3409573984
|
adapter/added_tokens.json
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<|im_end|>": 32000,
|
3 |
+
"<|im_start|>": 32001
|
4 |
+
}
|
adapter/config.json
ADDED
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "v2ray/Mixtral-8x22B-v0.1",
|
3 |
+
"architectures": [
|
4 |
+
"MixtralForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"bos_token_id": 1,
|
8 |
+
"eos_token_id": 32000,
|
9 |
+
"hidden_act": "silu",
|
10 |
+
"hidden_size": 6144,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"intermediate_size": 16384,
|
13 |
+
"max_position_embeddings": 65536,
|
14 |
+
"model_type": "mixtral",
|
15 |
+
"num_attention_heads": 48,
|
16 |
+
"num_experts_per_tok": 2,
|
17 |
+
"num_hidden_layers": 56,
|
18 |
+
"num_key_value_heads": 8,
|
19 |
+
"num_local_experts": 8,
|
20 |
+
"output_router_logits": false,
|
21 |
+
"quantization_config": {
|
22 |
+
"_load_in_4bit": true,
|
23 |
+
"_load_in_8bit": false,
|
24 |
+
"bnb_4bit_compute_dtype": "bfloat16",
|
25 |
+
"bnb_4bit_quant_storage": "bfloat16",
|
26 |
+
"bnb_4bit_quant_type": "nf4",
|
27 |
+
"bnb_4bit_use_double_quant": true,
|
28 |
+
"llm_int8_enable_fp32_cpu_offload": false,
|
29 |
+
"llm_int8_has_fp16_weight": false,
|
30 |
+
"llm_int8_skip_modules": null,
|
31 |
+
"llm_int8_threshold": 6.0,
|
32 |
+
"load_in_4bit": true,
|
33 |
+
"load_in_8bit": false,
|
34 |
+
"quant_method": "bitsandbytes"
|
35 |
+
},
|
36 |
+
"rms_norm_eps": 1e-05,
|
37 |
+
"rope_theta": 1000000,
|
38 |
+
"router_aux_loss_coef": 0.001,
|
39 |
+
"router_jitter_noise": 0.0,
|
40 |
+
"sliding_window": null,
|
41 |
+
"tie_word_embeddings": false,
|
42 |
+
"torch_dtype": "bfloat16",
|
43 |
+
"transformers_version": "4.40.0.dev0",
|
44 |
+
"use_cache": false,
|
45 |
+
"vocab_size": 32002
|
46 |
+
}
|
adapter/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": "<|im_end|>",
|
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 |
+
}
|
adapter/tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
|
3 |
+
size 493443
|
adapter/tokenizer_config.json
ADDED
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"add_prefix_space": true,
|
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 |
+
"32000": {
|
31 |
+
"content": "<|im_end|>",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": false,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false,
|
36 |
+
"special": true
|
37 |
+
},
|
38 |
+
"32001": {
|
39 |
+
"content": "<|im_start|>",
|
40 |
+
"lstrip": false,
|
41 |
+
"normalized": false,
|
42 |
+
"rstrip": false,
|
43 |
+
"single_word": false,
|
44 |
+
"special": false
|
45 |
+
}
|
46 |
+
},
|
47 |
+
"additional_special_tokens": [],
|
48 |
+
"bos_token": "<s>",
|
49 |
+
"chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
50 |
+
"clean_up_tokenization_spaces": false,
|
51 |
+
"eos_token": "<|im_end|>",
|
52 |
+
"legacy": true,
|
53 |
+
"model_max_length": 1000000000000000019884624838656,
|
54 |
+
"pad_token": "</s>",
|
55 |
+
"sp_model_kwargs": {},
|
56 |
+
"spaces_between_special_tokens": false,
|
57 |
+
"tokenizer_class": "LlamaTokenizer",
|
58 |
+
"unk_token": "<unk>",
|
59 |
+
"use_default_system_prompt": false,
|
60 |
+
"use_fast": true
|
61 |
+
}
|
added_tokens.json
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<|im_end|>": 32000,
|
3 |
+
"<|im_start|>": 32001
|
4 |
+
}
|
config.json
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "v2ray/Mixtral-8x22B-v0.1",
|
3 |
+
"architectures": [
|
4 |
+
"MixtralForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"bos_token_id": 1,
|
8 |
+
"eos_token_id": 32000,
|
9 |
+
"hidden_act": "silu",
|
10 |
+
"hidden_size": 6144,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"intermediate_size": 16384,
|
13 |
+
"max_position_embeddings": 65536,
|
14 |
+
"model_type": "mixtral",
|
15 |
+
"num_attention_heads": 48,
|
16 |
+
"num_experts_per_tok": 2,
|
17 |
+
"num_hidden_layers": 56,
|
18 |
+
"num_key_value_heads": 8,
|
19 |
+
"num_local_experts": 8,
|
20 |
+
"output_router_logits": false,
|
21 |
+
"rms_norm_eps": 1e-05,
|
22 |
+
"rope_theta": 1000000,
|
23 |
+
"router_aux_loss_coef": 0.001,
|
24 |
+
"router_jitter_noise": 0.0,
|
25 |
+
"sliding_window": null,
|
26 |
+
"tie_word_embeddings": false,
|
27 |
+
"torch_dtype": "float32",
|
28 |
+
"transformers_version": "4.40.0.dev0",
|
29 |
+
"use_cache": false,
|
30 |
+
"vocab_size": 32002
|
31 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 1,
|
4 |
+
"do_sample": true,
|
5 |
+
"eos_token_id": 2,
|
6 |
+
"transformers_version": "4.40.0.dev0"
|
7 |
+
}
|
model-00001-of-00117.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ed9ccee4b063e10c87cc2dfceff015e0a3e678e2fb90f3abbfb1fc8e7915aa9c
|
3 |
+
size 4762879840
|
model-00002-of-00117.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f22d549ed12f075f97104a759327e1f500f3d22693c2d1fde680317b123223ac
|
3 |
+
size 4831839800
|
model-00003-of-00117.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:69c6b76c9cce92c00ba519b615a8f06fbe59dafc4e3de4b79a06408c2a9c1514
|
3 |
+
size 4781754592
|
model-00004-of-00117.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:243be14b5542d668490df8848ff2b1589c6486165bf69c38cf8b48e47cb5d8f3
|
3 |
+
size 4831839800
|
model-00005-of-00117.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:570b13e32ac883b39d079ac4c34c836f13d681e67963d21f5b3f9c6404a39b22
|
3 |
+
size 4781754592
|
model-00006-of-00117.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3a8a5c88af32c56a7ca1dc2082402effcae75e4ea341241cbc56009820614845
|
3 |
+
size 4831839800
|
model-00007-of-00117.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1ca84f92b0c4bb27248d8e51a02cc5664fe3dc3f4121eed732b25a9ec53e3220
|
3 |
+
size 4781754592
|
model-00008-of-00117.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c5045952f7053f129a938a4c1f92f271d8662bf3302dc2544a309d015a244717
|
3 |
+
size 4831839800
|
model-00009-of-00117.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3d49115ba7f3eb498d8e90f46ee39fca11b8e8cd46e3b3650f192291a49e1e79
|
3 |
+
size 4781754592
|
model-00010-of-00117.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9c24577203ef245bf9c9c4733263ff803955aa45198ac695ef058e5223ec50c8
|
3 |
+
size 4831839800
|
model-00011-of-00117.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:61eb41a21b93c2762da0381320e8a2815ef22c72da0204217d05c064105b606b
|
3 |
+
size 4781754592
|
model-00012-of-00117.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cb9dbb091b3bff6126fd5cb482672d64df73f549e2f35e0ee0a0b05b6cef6114
|
3 |
+
size 4831839800
|
model-00013-of-00117.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:50fadd1d36aeaf2c6c97157c3668695113e86bc823a9510d29eff3d26685920d
|
3 |
+
size 4781754592
|
model-00014-of-00117.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e63553794ae97e292ccabcf8c279aa58e96fa7ffc366888f6fd28b61bf728094
|
3 |
+
size 4831839800
|
model-00015-of-00117.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9836e419e59e2997b020c82fabf89431def9fbeb30454fe472f1b245f9c280cf
|
3 |
+
size 4781754592
|
model-00016-of-00117.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:33bf7f116407b576afcaf16a7aef0a7daa43694ff49a90e6444ffb78d65819be
|
3 |
+
size 4831839800
|
model-00017-of-00117.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:29a9d2cf8345f044fba69fa5e3db916b922f23de90b33f1ca20af7c9a5888ed3
|
3 |
+
size 4781754592
|
model-00018-of-00117.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1aadacd71c89329cbb00956f5184a44e2b00ec70d990186fee188942faae39e3
|
3 |
+
size 4831839800
|
model-00019-of-00117.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fa2aa34ae8d24e7b01224c11e4d5d8fc68d824d56e948ac9329d670394442107
|
3 |
+
size 4781754592
|
model-00020-of-00117.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2e6e48d5f00e00a9722ade9d3aca8b11f984314c724fd1ed6f46009af47dd687
|
3 |
+
size 4831839800
|
model-00021-of-00117.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:044656ef715db71f006c4e9cdd6a790f0b90017d3378dc0ef44a75aa7dfa62f8
|
3 |
+
size 4982884240
|
model-00022-of-00117.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dc0bfa03e064a941ad41dfff8359414bce4ba670c065b42bd52bdcec3d18dfcd
|
3 |
+
size 4630710168
|
model-00023-of-00117.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b43e20babd6871217657425e7690a64407f62740150529ca6c7e27774a531c19
|
3 |
+
size 4831839808
|
model-00024-of-00117.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fcfff7ffae614189f50adff5519690df74290d122b241afd6de26319e051f011
|
3 |
+
size 4781754608
|
model-00025-of-00117.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:86ebf3ad56678d6860cac36cfcf9c42061129e91ebe8af6ac34c68ebefdece0b
|
3 |
+
size 4831839808
|
model-00026-of-00117.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3743756ea336fec881893a1236f70fc75d635783e42a574bfac763a7495f7d01
|
3 |
+
size 4781754608
|
model-00027-of-00117.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:41a7d915254a7191916791c7d26a700a3c9043f87e82b7244bdb88d554aff7f9
|
3 |
+
size 4831839808
|
model-00028-of-00117.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:804c38ba54981e0cc73ab557ed2e61676dc66802865b70d4363001ad53898ccf
|
3 |
+
size 4781754608
|
model-00029-of-00117.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8f9a91e9b92885c8f316f8a5bb966fdc7293bc82ebeb0f3e867f9d2ea8870623
|
3 |
+
size 4831839808
|
model-00030-of-00117.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fd9a6501726d7f0616eef570b17a26c9ff30a1295b7b2ffb7ffebb635f54347f
|
3 |
+
size 4781754608
|
model-00031-of-00117.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8f3ce74a0727d90631ffe4aa90a5c3c43caa32d3e8c7f0400f0bf18ed4ad6caf
|
3 |
+
size 4831839808
|
model-00032-of-00117.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:acd28605ac4b054904ed535da531cbd965e812b2b2d0a6a8fa5825a8973d4d11
|
3 |
+
size 4781754608
|
model-00033-of-00117.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c8ec7fee4a70220c3dae069c26858b6a8fa0ea8da756199ea005c77274800452
|
3 |
+
size 4831839808
|
model-00034-of-00117.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4cc54c2e044db500106bfff731c7d1ae0aa3c5cfa38e366f7b999c8fbf8f4cf5
|
3 |
+
size 4781754608
|
model-00035-of-00117.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:725e9151be7acebc2d1f40e10d8e11688254f540cbfa2d06effb0d19c43410e4
|
3 |
+
size 4831839808
|
model-00036-of-00117.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cdbc7a37fa36bea7902e2af4f7846f1be91b13900a5f6646589b2d16ac376058
|
3 |
+
size 4781754608
|