Ubuntu
		
	commited on
		
		
					Commit 
							
							·
						
						7f68a15
	
1
								Parent(s):
							
							fff975f
								
add awq model
Browse files- config.json +40 -0
- generation_config.json +7 -0
- model-00001-of-00002.safetensors +3 -0
- model-00002-of-00002.safetensors +3 -0
- model.safetensors.index.json +0 -0
- quant_config.json +6 -0
- special_tokens_map.json +30 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +50 -0
    	
        config.json
    ADDED
    
    | @@ -0,0 +1,40 @@ | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | 
|  | |
| 1 | 
            +
            {
         | 
| 2 | 
            +
              "_name_or_path": "/home/ubuntu/.cache/huggingface/hub/models--perlthoughts--Mistral-7B-Instruct-v0.2-2x7B-MoE/snapshots/1633c2583cb05fb1df5525ab9f786578366d1c97",
         | 
| 3 | 
            +
              "architectures": [
         | 
| 4 | 
            +
                "MixtralForCausalLM"
         | 
| 5 | 
            +
              ],
         | 
| 6 | 
            +
              "attention_dropout": 0.0,
         | 
| 7 | 
            +
              "bos_token_id": 1,
         | 
| 8 | 
            +
              "eos_token_id": 2,
         | 
| 9 | 
            +
              "hidden_act": "silu",
         | 
| 10 | 
            +
              "hidden_size": 4096,
         | 
| 11 | 
            +
              "initializer_range": 0.02,
         | 
| 12 | 
            +
              "intermediate_size": 14336,
         | 
| 13 | 
            +
              "max_position_embeddings": 32768,
         | 
| 14 | 
            +
              "model_type": "mixtral",
         | 
| 15 | 
            +
              "num_attention_heads": 32,
         | 
| 16 | 
            +
              "num_experts_per_tok": 2,
         | 
| 17 | 
            +
              "num_hidden_layers": 32,
         | 
| 18 | 
            +
              "num_key_value_heads": 8,
         | 
| 19 | 
            +
              "num_local_experts": 2,
         | 
| 20 | 
            +
              "output_router_logits": false,
         | 
| 21 | 
            +
              "quantization_config": {
         | 
| 22 | 
            +
                "bits": 4,
         | 
| 23 | 
            +
                "group_size": 128,
         | 
| 24 | 
            +
                "modules_to_not_convert": [
         | 
| 25 | 
            +
                  "gate"
         | 
| 26 | 
            +
                ],
         | 
| 27 | 
            +
                "quant_method": "awq",
         | 
| 28 | 
            +
                "version": "gemm",
         | 
| 29 | 
            +
                "zero_point": true
         | 
| 30 | 
            +
              },
         | 
| 31 | 
            +
              "rms_norm_eps": 1e-05,
         | 
| 32 | 
            +
              "rope_theta": 100000.0,
         | 
| 33 | 
            +
              "router_aux_loss_coef": 0.001,
         | 
| 34 | 
            +
              "sliding_window": null,
         | 
| 35 | 
            +
              "tie_word_embeddings": false,
         | 
| 36 | 
            +
              "torch_dtype": "float16",
         | 
| 37 | 
            +
              "transformers_version": "4.38.2",
         | 
| 38 | 
            +
              "use_cache": false,
         | 
| 39 | 
            +
              "vocab_size": 32000
         | 
| 40 | 
            +
            }
         | 
    	
        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": "4.38.2"
         | 
| 7 | 
            +
            }
         | 
    	
        model-00001-of-00002.safetensors
    ADDED
    
    | @@ -0,0 +1,3 @@ | |
|  | |
|  | |
|  | 
|  | |
| 1 | 
            +
            version https://git-lfs.github.com/spec/v1
         | 
| 2 | 
            +
            oid sha256:006f1ec3982a6b6c601de1860c60b23a305fa6375636d9e58ab02ad0fed98e3a
         | 
| 3 | 
            +
            size 4995952960
         | 
    	
        model-00002-of-00002.safetensors
    ADDED
    
    | @@ -0,0 +1,3 @@ | |
|  | |
|  | |
|  | 
|  | |
| 1 | 
            +
            version https://git-lfs.github.com/spec/v1
         | 
| 2 | 
            +
            oid sha256:f78a05ae1a51a4deba2621791aa5401f93564612fb7279834016f009ecac1d9c
         | 
| 3 | 
            +
            size 2084169992
         | 
    	
        model.safetensors.index.json
    ADDED
    
    | The diff for this file is too large to render. 
		See raw diff | 
|  | 
    	
        quant_config.json
    ADDED
    
    | @@ -0,0 +1,6 @@ | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | 
|  | |
| 1 | 
            +
            {
         | 
| 2 | 
            +
              "zero_point": true,
         | 
| 3 | 
            +
              "q_group_size": 128,
         | 
| 4 | 
            +
              "w_bit": 4,
         | 
| 5 | 
            +
              "version": "GEMM"
         | 
| 6 | 
            +
            }
         | 
    	
        special_tokens_map.json
    ADDED
    
    | @@ -0,0 +1,30 @@ | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | 
|  | |
| 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": {
         | 
| 17 | 
            +
                "content": "<s>",
         | 
| 18 | 
            +
                "lstrip": false,
         | 
| 19 | 
            +
                "normalized": false,
         | 
| 20 | 
            +
                "rstrip": false,
         | 
| 21 | 
            +
                "single_word": false
         | 
| 22 | 
            +
              },
         | 
| 23 | 
            +
              "unk_token": {
         | 
| 24 | 
            +
                "content": "<unk>",
         | 
| 25 | 
            +
                "lstrip": false,
         | 
| 26 | 
            +
                "normalized": false,
         | 
| 27 | 
            +
                "rstrip": false,
         | 
| 28 | 
            +
                "single_word": false
         | 
| 29 | 
            +
              }
         | 
| 30 | 
            +
            }
         | 
    	
        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:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
         | 
| 3 | 
            +
            size 493443
         | 
    	
        tokenizer_config.json
    ADDED
    
    | @@ -0,0 +1,50 @@ | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | 
|  | |
| 1 | 
            +
            {
         | 
| 2 | 
            +
              "add_bos_token": true,
         | 
| 3 | 
            +
              "add_eos_token": false,
         | 
| 4 | 
            +
              "added_tokens_decoder": {
         | 
| 5 | 
            +
                "0": {
         | 
| 6 | 
            +
                  "content": "<unk>",
         | 
| 7 | 
            +
                  "lstrip": false,
         | 
| 8 | 
            +
                  "normalized": false,
         | 
| 9 | 
            +
                  "rstrip": false,
         | 
| 10 | 
            +
                  "single_word": false,
         | 
| 11 | 
            +
                  "special": true
         | 
| 12 | 
            +
                },
         | 
| 13 | 
            +
                "1": {
         | 
| 14 | 
            +
                  "content": "<s>",
         | 
| 15 | 
            +
                  "lstrip": false,
         | 
| 16 | 
            +
                  "normalized": false,
         | 
| 17 | 
            +
                  "rstrip": false,
         | 
| 18 | 
            +
                  "single_word": false,
         | 
| 19 | 
            +
                  "special": true
         | 
| 20 | 
            +
                },
         | 
| 21 | 
            +
                "2": {
         | 
| 22 | 
            +
                  "content": "</s>",
         | 
| 23 | 
            +
                  "lstrip": false,
         | 
| 24 | 
            +
                  "normalized": false,
         | 
| 25 | 
            +
                  "rstrip": false,
         | 
| 26 | 
            +
                  "single_word": false,
         | 
| 27 | 
            +
                  "special": true
         | 
| 28 | 
            +
                }
         | 
| 29 | 
            +
              },
         | 
| 30 | 
            +
              "additional_special_tokens": [],
         | 
| 31 | 
            +
              "bos_token": "<s>",
         | 
| 32 | 
            +
              "chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token}}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
         | 
| 33 | 
            +
              "clean_up_tokenization_spaces": false,
         | 
| 34 | 
            +
              "device_map": {
         | 
| 35 | 
            +
                "": "cuda"
         | 
| 36 | 
            +
              },
         | 
| 37 | 
            +
              "eos_token": "</s>",
         | 
| 38 | 
            +
              "legacy": true,
         | 
| 39 | 
            +
              "max_length": null,
         | 
| 40 | 
            +
              "model_max_length": 1000000000000000019884624838656,
         | 
| 41 | 
            +
              "pad_to_multiple_of": null,
         | 
| 42 | 
            +
              "pad_token": "<s>",
         | 
| 43 | 
            +
              "pad_token_type_id": 0,
         | 
| 44 | 
            +
              "padding_side": "left",
         | 
| 45 | 
            +
              "sp_model_kwargs": {},
         | 
| 46 | 
            +
              "spaces_between_special_tokens": false,
         | 
| 47 | 
            +
              "tokenizer_class": "LlamaTokenizer",
         | 
| 48 | 
            +
              "unk_token": "<unk>",
         | 
| 49 | 
            +
              "use_default_system_prompt": false
         | 
| 50 | 
            +
            }
         | 
