Training in progress, epoch 1
Browse files- README.md +6 -6
- adapter_config.json +1 -1
- adapter_model.safetensors +1 -1
- chat_template.jinja +93 -0
- runs/Sep26_11-36-10_44b6a415a91c/events.out.tfevents.1758886614.44b6a415a91c.540.1 +3 -0
- runs/Sep26_11-37-25_44b6a415a91c/events.out.tfevents.1758886654.44b6a415a91c.540.2 +3 -0
- special_tokens_map.json +1 -1
- tokenizer_config.json +1 -1
- training_args.bin +1 -1
    	
        README.md
    CHANGED
    
    | @@ -1,5 +1,5 @@ | |
| 1 | 
             
            ---
         | 
| 2 | 
            -
            base_model: unsloth/Llama-3.2-1B
         | 
| 3 | 
             
            library_name: transformers
         | 
| 4 | 
             
            model_name: try1
         | 
| 5 | 
             
            tags:
         | 
| @@ -11,7 +11,7 @@ licence: license | |
| 11 |  | 
| 12 | 
             
            # Model Card for try1
         | 
| 13 |  | 
| 14 | 
            -
            This model is a fine-tuned version of [unsloth/Llama-3.2-1B](https://huggingface.co/unsloth/Llama-3.2-1B).
         | 
| 15 | 
             
            It has been trained using [TRL](https://github.com/huggingface/trl).
         | 
| 16 |  | 
| 17 | 
             
            ## Quick start
         | 
| @@ -34,11 +34,11 @@ This model was trained with SFT. | |
| 34 |  | 
| 35 | 
             
            ### Framework versions
         | 
| 36 |  | 
| 37 | 
            -
            - TRL: 0. | 
| 38 | 
            -
            - Transformers: 4. | 
| 39 | 
             
            - Pytorch: 2.8.0+cu126
         | 
| 40 | 
            -
            - Datasets:  | 
| 41 | 
            -
            - Tokenizers: 0. | 
| 42 |  | 
| 43 | 
             
            ## Citations
         | 
| 44 |  | 
|  | |
| 1 | 
             
            ---
         | 
| 2 | 
            +
            base_model: unsloth/Llama-3.2-1B-Instruct
         | 
| 3 | 
             
            library_name: transformers
         | 
| 4 | 
             
            model_name: try1
         | 
| 5 | 
             
            tags:
         | 
|  | |
| 11 |  | 
| 12 | 
             
            # Model Card for try1
         | 
| 13 |  | 
| 14 | 
            +
            This model is a fine-tuned version of [unsloth/Llama-3.2-1B-Instruct](https://huggingface.co/unsloth/Llama-3.2-1B-Instruct).
         | 
| 15 | 
             
            It has been trained using [TRL](https://github.com/huggingface/trl).
         | 
| 16 |  | 
| 17 | 
             
            ## Quick start
         | 
|  | |
| 34 |  | 
| 35 | 
             
            ### Framework versions
         | 
| 36 |  | 
| 37 | 
            +
            - TRL: 0.22.2
         | 
| 38 | 
            +
            - Transformers: 4.55.4
         | 
| 39 | 
             
            - Pytorch: 2.8.0+cu126
         | 
| 40 | 
            +
            - Datasets: 3.6.0
         | 
| 41 | 
            +
            - Tokenizers: 0.21.4
         | 
| 42 |  | 
| 43 | 
             
            ## Citations
         | 
| 44 |  | 
    	
        adapter_config.json
    CHANGED
    
    | @@ -1,7 +1,7 @@ | |
| 1 | 
             
            {
         | 
| 2 | 
             
              "alpha_pattern": {},
         | 
| 3 | 
             
              "auto_mapping": null,
         | 
| 4 | 
            -
              "base_model_name_or_path": "unsloth/Llama-3.2-1B",
         | 
| 5 | 
             
              "bias": "none",
         | 
| 6 | 
             
              "corda_config": null,
         | 
| 7 | 
             
              "eva_config": null,
         | 
|  | |
| 1 | 
             
            {
         | 
| 2 | 
             
              "alpha_pattern": {},
         | 
| 3 | 
             
              "auto_mapping": null,
         | 
| 4 | 
            +
              "base_model_name_or_path": "unsloth/Llama-3.2-1B-Instruct",
         | 
| 5 | 
             
              "bias": "none",
         | 
| 6 | 
             
              "corda_config": null,
         | 
| 7 | 
             
              "eva_config": null,
         | 
    	
        adapter_model.safetensors
    CHANGED
    
    | @@ -1,3 +1,3 @@ | |
| 1 | 
             
            version https://git-lfs.github.com/spec/v1
         | 
| 2 | 
            -
            oid sha256: | 
| 3 | 
             
            size 3416264
         | 
|  | |
| 1 | 
             
            version https://git-lfs.github.com/spec/v1
         | 
| 2 | 
            +
            oid sha256:cbe6b326af648547bab1477d28757ac4ff6cdcaa212f4b5cd030fcbeef1234b5
         | 
| 3 | 
             
            size 3416264
         | 
    	
        chat_template.jinja
    ADDED
    
    | @@ -0,0 +1,93 @@ | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | 
|  | |
| 1 | 
            +
            {{- bos_token }}
         | 
| 2 | 
            +
            {%- if custom_tools is defined %}
         | 
| 3 | 
            +
                {%- set tools = custom_tools %}
         | 
| 4 | 
            +
            {%- endif %}
         | 
| 5 | 
            +
            {%- if not tools_in_user_message is defined %}
         | 
| 6 | 
            +
                {%- set tools_in_user_message = true %}
         | 
| 7 | 
            +
            {%- endif %}
         | 
| 8 | 
            +
            {%- if not date_string is defined %}
         | 
| 9 | 
            +
                {%- if strftime_now is defined %}
         | 
| 10 | 
            +
                    {%- set date_string = strftime_now("%d %b %Y") %}
         | 
| 11 | 
            +
                {%- else %}
         | 
| 12 | 
            +
                    {%- set date_string = "26 Jul 2024" %}
         | 
| 13 | 
            +
                {%- endif %}
         | 
| 14 | 
            +
            {%- endif %}
         | 
| 15 | 
            +
            {%- if not tools is defined %}
         | 
| 16 | 
            +
                {%- set tools = none %}
         | 
| 17 | 
            +
            {%- endif %}
         | 
| 18 | 
            +
             | 
| 19 | 
            +
            {#- This block extracts the system message, so we can slot it into the right place. #}
         | 
| 20 | 
            +
            {%- if messages[0]['role'] == 'system' %}
         | 
| 21 | 
            +
                {%- set system_message = messages[0]['content']|trim %}
         | 
| 22 | 
            +
                {%- set messages = messages[1:] %}
         | 
| 23 | 
            +
            {%- else %}
         | 
| 24 | 
            +
                {%- set system_message = "" %}
         | 
| 25 | 
            +
            {%- endif %}
         | 
| 26 | 
            +
             | 
| 27 | 
            +
            {#- System message #}
         | 
| 28 | 
            +
            {{- "<|start_header_id|>system<|end_header_id|>\n\n" }}
         | 
| 29 | 
            +
            {%- if tools is not none %}
         | 
| 30 | 
            +
                {{- "Environment: ipython\n" }}
         | 
| 31 | 
            +
            {%- endif %}
         | 
| 32 | 
            +
            {{- "Cutting Knowledge Date: December 2023\n" }}
         | 
| 33 | 
            +
            {{- "Today Date: " + date_string + "\n\n" }}
         | 
| 34 | 
            +
            {%- if tools is not none and not tools_in_user_message %}
         | 
| 35 | 
            +
                {{- "You have access to the following functions. To call a function, please respond with JSON for a function call." }}
         | 
| 36 | 
            +
                {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
         | 
| 37 | 
            +
                {{- "Do not use variables.\n\n" }}
         | 
| 38 | 
            +
                {%- for t in tools %}
         | 
| 39 | 
            +
                    {{- t | tojson(indent=4) }}
         | 
| 40 | 
            +
                    {{- "\n\n" }}
         | 
| 41 | 
            +
                {%- endfor %}
         | 
| 42 | 
            +
            {%- endif %}
         | 
| 43 | 
            +
            {{- system_message }}
         | 
| 44 | 
            +
            {{- "<|eot_id|>" }}
         | 
| 45 | 
            +
             | 
| 46 | 
            +
            {#- Custom tools are passed in a user message with some extra guidance #}
         | 
| 47 | 
            +
            {%- if tools_in_user_message and not tools is none %}
         | 
| 48 | 
            +
                {#- Extract the first user message so we can plug it in here #}
         | 
| 49 | 
            +
                {%- if messages | length != 0 %}
         | 
| 50 | 
            +
                    {%- set first_user_message = messages[0]['content']|trim %}
         | 
| 51 | 
            +
                    {%- set messages = messages[1:] %}
         | 
| 52 | 
            +
                {%- else %}
         | 
| 53 | 
            +
                    {{- raise_exception("Cannot put tools in the first user message when there's no first user message!") }}
         | 
| 54 | 
            +
            {%- endif %}
         | 
| 55 | 
            +
                {{- '<|start_header_id|>user<|end_header_id|>\n\n' -}}
         | 
| 56 | 
            +
                {{- "Given the following functions, please respond with a JSON for a function call " }}
         | 
| 57 | 
            +
                {{- "with its proper arguments that best answers the given prompt.\n\n" }}
         | 
| 58 | 
            +
                {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
         | 
| 59 | 
            +
                {{- "Do not use variables.\n\n" }}
         | 
| 60 | 
            +
                {%- for t in tools %}
         | 
| 61 | 
            +
                    {{- t | tojson(indent=4) }}
         | 
| 62 | 
            +
                    {{- "\n\n" }}
         | 
| 63 | 
            +
                {%- endfor %}
         | 
| 64 | 
            +
                {{- first_user_message + "<|eot_id|>"}}
         | 
| 65 | 
            +
            {%- endif %}
         | 
| 66 | 
            +
             | 
| 67 | 
            +
            {%- for message in messages %}
         | 
| 68 | 
            +
                {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}
         | 
| 69 | 
            +
                    {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' }}
         | 
| 70 | 
            +
                {%- elif 'tool_calls' in message %}
         | 
| 71 | 
            +
                    {%- if not message.tool_calls|length == 1 %}
         | 
| 72 | 
            +
                        {{- raise_exception("This model only supports single tool-calls at once!") }}
         | 
| 73 | 
            +
                    {%- endif %}
         | 
| 74 | 
            +
                    {%- set tool_call = message.tool_calls[0].function %}
         | 
| 75 | 
            +
                    {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}
         | 
| 76 | 
            +
                    {{- '{"name": "' + tool_call.name + '", ' }}
         | 
| 77 | 
            +
                    {{- '"parameters": ' }}
         | 
| 78 | 
            +
                    {{- tool_call.arguments | tojson }}
         | 
| 79 | 
            +
                    {{- "}" }}
         | 
| 80 | 
            +
                    {{- "<|eot_id|>" }}
         | 
| 81 | 
            +
                {%- elif message.role == "tool" or message.role == "ipython" %}
         | 
| 82 | 
            +
                    {{- "<|start_header_id|>ipython<|end_header_id|>\n\n" }}
         | 
| 83 | 
            +
                    {%- if message.content is mapping or message.content is iterable %}
         | 
| 84 | 
            +
                        {{- message.content | tojson }}
         | 
| 85 | 
            +
                    {%- else %}
         | 
| 86 | 
            +
                        {{- message.content }}
         | 
| 87 | 
            +
                    {%- endif %}
         | 
| 88 | 
            +
                    {{- "<|eot_id|>" }}
         | 
| 89 | 
            +
                {%- endif %}
         | 
| 90 | 
            +
            {%- endfor %}
         | 
| 91 | 
            +
            {%- if add_generation_prompt %}
         | 
| 92 | 
            +
                {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' }}
         | 
| 93 | 
            +
            {%- endif %}
         | 
    	
        runs/Sep26_11-36-10_44b6a415a91c/events.out.tfevents.1758886614.44b6a415a91c.540.1
    ADDED
    
    | @@ -0,0 +1,3 @@ | |
|  | |
|  | |
|  | 
|  | |
| 1 | 
            +
            version https://git-lfs.github.com/spec/v1
         | 
| 2 | 
            +
            oid sha256:6d65ddc6c6d339c29a6cac0cc019f32eae4514e6c417bf6b86c597134c2e6b06
         | 
| 3 | 
            +
            size 6173
         | 
    	
        runs/Sep26_11-37-25_44b6a415a91c/events.out.tfevents.1758886654.44b6a415a91c.540.2
    ADDED
    
    | @@ -0,0 +1,3 @@ | |
|  | |
|  | |
|  | 
|  | |
| 1 | 
            +
            version https://git-lfs.github.com/spec/v1
         | 
| 2 | 
            +
            oid sha256:f1de4f4a4da41d76d8dbea73fb393996b15e53e4e491b40e8f967fcda9b9d169
         | 
| 3 | 
            +
            size 8423
         | 
    	
        special_tokens_map.json
    CHANGED
    
    | @@ -7,7 +7,7 @@ | |
| 7 | 
             
                "single_word": false
         | 
| 8 | 
             
              },
         | 
| 9 | 
             
              "eos_token": {
         | 
| 10 | 
            -
                "content": "<| | 
| 11 | 
             
                "lstrip": false,
         | 
| 12 | 
             
                "normalized": false,
         | 
| 13 | 
             
                "rstrip": false,
         | 
|  | |
| 7 | 
             
                "single_word": false
         | 
| 8 | 
             
              },
         | 
| 9 | 
             
              "eos_token": {
         | 
| 10 | 
            +
                "content": "<|eot_id|>",
         | 
| 11 | 
             
                "lstrip": false,
         | 
| 12 | 
             
                "normalized": false,
         | 
| 13 | 
             
                "rstrip": false,
         | 
    	
        tokenizer_config.json
    CHANGED
    
    | @@ -2052,7 +2052,7 @@ | |
| 2052 | 
             
              },
         | 
| 2053 | 
             
              "bos_token": "<|begin_of_text|>",
         | 
| 2054 | 
             
              "clean_up_tokenization_spaces": true,
         | 
| 2055 | 
            -
              "eos_token": "<| | 
| 2056 | 
             
              "extra_special_tokens": {},
         | 
| 2057 | 
             
              "model_input_names": [
         | 
| 2058 | 
             
                "input_ids",
         | 
|  | |
| 2052 | 
             
              },
         | 
| 2053 | 
             
              "bos_token": "<|begin_of_text|>",
         | 
| 2054 | 
             
              "clean_up_tokenization_spaces": true,
         | 
| 2055 | 
            +
              "eos_token": "<|eot_id|>",
         | 
| 2056 | 
             
              "extra_special_tokens": {},
         | 
| 2057 | 
             
              "model_input_names": [
         | 
| 2058 | 
             
                "input_ids",
         | 
    	
        training_args.bin
    CHANGED
    
    | @@ -1,3 +1,3 @@ | |
| 1 | 
             
            version https://git-lfs.github.com/spec/v1
         | 
| 2 | 
            -
            oid sha256: | 
| 3 | 
             
            size 6161
         | 
|  | |
| 1 | 
             
            version https://git-lfs.github.com/spec/v1
         | 
| 2 | 
            +
            oid sha256:e03456420a3b6527687552d7a1049b6e0568ab3a3822a276ebc93621d57601c9
         | 
| 3 | 
             
            size 6161
         |