Training in progress, step 2
Browse files- adapter_config.json +34 -0
- adapter_model.safetensors +3 -0
- config.json +30 -0
- special_tokens_map.json +30 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +45 -0
- training_args.bin +3 -0
    	
        adapter_config.json
    ADDED
    
    | @@ -0,0 +1,34 @@ | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | 
|  | |
| 1 | 
            +
            {
         | 
| 2 | 
            +
              "alpha_pattern": {},
         | 
| 3 | 
            +
              "auto_mapping": null,
         | 
| 4 | 
            +
              "base_model_name_or_path": "unsloth/mistral-7b-instruct-v0.2",
         | 
| 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": 16,
         | 
| 14 | 
            +
              "lora_dropout": 0.05,
         | 
| 15 | 
            +
              "megatron_config": null,
         | 
| 16 | 
            +
              "megatron_core": "megatron.core",
         | 
| 17 | 
            +
              "modules_to_save": null,
         | 
| 18 | 
            +
              "peft_type": "LORA",
         | 
| 19 | 
            +
              "r": 8,
         | 
| 20 | 
            +
              "rank_pattern": {},
         | 
| 21 | 
            +
              "revision": null,
         | 
| 22 | 
            +
              "target_modules": [
         | 
| 23 | 
            +
                "gate_proj",
         | 
| 24 | 
            +
                "q_proj",
         | 
| 25 | 
            +
                "o_proj",
         | 
| 26 | 
            +
                "k_proj",
         | 
| 27 | 
            +
                "up_proj",
         | 
| 28 | 
            +
                "v_proj",
         | 
| 29 | 
            +
                "down_proj"
         | 
| 30 | 
            +
              ],
         | 
| 31 | 
            +
              "task_type": "CAUSAL_LM",
         | 
| 32 | 
            +
              "use_dora": false,
         | 
| 33 | 
            +
              "use_rslora": false
         | 
| 34 | 
            +
            }
         | 
    	
        adapter_model.safetensors
    ADDED
    
    | @@ -0,0 +1,3 @@ | |
|  | |
|  | |
|  | 
|  | |
| 1 | 
            +
            version https://git-lfs.github.com/spec/v1
         | 
| 2 | 
            +
            oid sha256:3a6a6ee1129f2c59c02c9364db7d6a4975739f08bdaa9ef14736bf08f1c15081
         | 
| 3 | 
            +
            size 83945296
         | 
    	
        config.json
    ADDED
    
    | @@ -0,0 +1,30 @@ | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | 
|  | |
| 1 | 
            +
            {
         | 
| 2 | 
            +
              "_attn_implementation_autoset": true,
         | 
| 3 | 
            +
              "_name_or_path": "unsloth/mistral-7b-instruct-v0.2",
         | 
| 4 | 
            +
              "architectures": [
         | 
| 5 | 
            +
                "MistralForCausalLM"
         | 
| 6 | 
            +
              ],
         | 
| 7 | 
            +
              "attention_dropout": 0.0,
         | 
| 8 | 
            +
              "bos_token_id": 1,
         | 
| 9 | 
            +
              "eos_token_id": 2,
         | 
| 10 | 
            +
              "head_dim": 128,
         | 
| 11 | 
            +
              "hidden_act": "silu",
         | 
| 12 | 
            +
              "hidden_size": 4096,
         | 
| 13 | 
            +
              "initializer_range": 0.02,
         | 
| 14 | 
            +
              "intermediate_size": 14336,
         | 
| 15 | 
            +
              "max_position_embeddings": 32768,
         | 
| 16 | 
            +
              "model_type": "mistral",
         | 
| 17 | 
            +
              "num_attention_heads": 32,
         | 
| 18 | 
            +
              "num_hidden_layers": 32,
         | 
| 19 | 
            +
              "num_key_value_heads": 8,
         | 
| 20 | 
            +
              "pad_token_id": 0,
         | 
| 21 | 
            +
              "rms_norm_eps": 1e-05,
         | 
| 22 | 
            +
              "rope_theta": 1000000.0,
         | 
| 23 | 
            +
              "sliding_window": null,
         | 
| 24 | 
            +
              "tie_word_embeddings": false,
         | 
| 25 | 
            +
              "torch_dtype": "bfloat16",
         | 
| 26 | 
            +
              "transformers_version": "4.46.0",
         | 
| 27 | 
            +
              "unsloth_version": "2024.9",
         | 
| 28 | 
            +
              "use_cache": false,
         | 
| 29 | 
            +
              "vocab_size": 32000
         | 
| 30 | 
            +
            }
         | 
    	
        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": "<unk>",
         | 
| 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 +1,45 @@ | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | 
|  | |
| 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 not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
         | 
| 34 | 
            +
              "clean_up_tokenization_spaces": false,
         | 
| 35 | 
            +
              "eos_token": "</s>",
         | 
| 36 | 
            +
              "legacy": false,
         | 
| 37 | 
            +
              "model_max_length": 1000000000000000019884624838656,
         | 
| 38 | 
            +
              "pad_token": "<unk>",
         | 
| 39 | 
            +
              "padding_side": "left",
         | 
| 40 | 
            +
              "sp_model_kwargs": {},
         | 
| 41 | 
            +
              "spaces_between_special_tokens": false,
         | 
| 42 | 
            +
              "tokenizer_class": "LlamaTokenizer",
         | 
| 43 | 
            +
              "unk_token": "<unk>",
         | 
| 44 | 
            +
              "use_default_system_prompt": false
         | 
| 45 | 
            +
            }
         | 
    	
        training_args.bin
    ADDED
    
    | @@ -0,0 +1,3 @@ | |
|  | |
|  | |
|  | 
|  | |
| 1 | 
            +
            version https://git-lfs.github.com/spec/v1
         | 
| 2 | 
            +
            oid sha256:51304f4a7479b1ec0ce62acbc1c023dc64963a2575c02173214682c62afc18e6
         | 
| 3 | 
            +
            size 6776
         |