armanibadboy commited on
Commit
5ed8a47
·
verified ·
1 Parent(s): 295cc6b

armanibadboy/llama3.1-kazllm-8b

Browse files
README.md CHANGED
@@ -1,5 +1,5 @@
1
  ---
2
- base_model: unsloth/Meta-Llama-3.1-8B-Instruct-bnb-4bit
3
  library_name: transformers
4
  model_name: outputs
5
  tags:
@@ -12,7 +12,7 @@ licence: license
12
 
13
  # Model Card for outputs
14
 
15
- This model is a fine-tuned version of [unsloth/Meta-Llama-3.1-8B-Instruct-bnb-4bit](https://huggingface.co/unsloth/Meta-Llama-3.1-8B-Instruct-bnb-4bit).
16
  It has been trained using [TRL](https://github.com/huggingface/trl).
17
 
18
  ## Quick start
 
1
  ---
2
+ base_model: unsloth/Meta-Llama-3.1-8B-bnb-4bit
3
  library_name: transformers
4
  model_name: outputs
5
  tags:
 
12
 
13
  # Model Card for outputs
14
 
15
+ This model is a fine-tuned version of [unsloth/Meta-Llama-3.1-8B-bnb-4bit](https://huggingface.co/unsloth/Meta-Llama-3.1-8B-bnb-4bit).
16
  It has been trained using [TRL](https://github.com/huggingface/trl).
17
 
18
  ## Quick start
adapter_config.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
  "alpha_pattern": {},
3
  "auto_mapping": null,
4
- "base_model_name_or_path": "unsloth/Meta-Llama-3.1-8B-Instruct-bnb-4bit",
5
  "bias": "none",
6
  "eva_config": null,
7
  "exclude_modules": null,
@@ -12,26 +12,29 @@
12
  "layers_pattern": null,
13
  "layers_to_transform": null,
14
  "loftq_config": {},
15
- "lora_alpha": 16,
16
  "lora_bias": false,
17
  "lora_dropout": 0,
18
  "megatron_config": null,
19
  "megatron_core": "megatron.core",
20
- "modules_to_save": null,
 
 
 
21
  "peft_type": "LORA",
22
- "r": 16,
23
  "rank_pattern": {},
24
  "revision": null,
25
  "target_modules": [
 
26
  "k_proj",
27
- "gate_proj",
28
  "o_proj",
29
  "q_proj",
30
- "v_proj",
31
  "down_proj",
32
- "up_proj"
33
  ],
34
  "task_type": "CAUSAL_LM",
35
  "use_dora": false,
36
- "use_rslora": false
37
  }
 
1
  {
2
  "alpha_pattern": {},
3
  "auto_mapping": null,
4
+ "base_model_name_or_path": "unsloth/Meta-Llama-3.1-8B-bnb-4bit",
5
  "bias": "none",
6
  "eva_config": null,
7
  "exclude_modules": null,
 
12
  "layers_pattern": null,
13
  "layers_to_transform": null,
14
  "loftq_config": {},
15
+ "lora_alpha": 32,
16
  "lora_bias": false,
17
  "lora_dropout": 0,
18
  "megatron_config": null,
19
  "megatron_core": "megatron.core",
20
+ "modules_to_save": [
21
+ "lm_head",
22
+ "embed_tokens"
23
+ ],
24
  "peft_type": "LORA",
25
+ "r": 128,
26
  "rank_pattern": {},
27
  "revision": null,
28
  "target_modules": [
29
+ "up_proj",
30
  "k_proj",
31
+ "v_proj",
32
  "o_proj",
33
  "q_proj",
 
34
  "down_proj",
35
+ "gate_proj"
36
  ],
37
  "task_type": "CAUSAL_LM",
38
  "use_dora": false,
39
+ "use_rslora": true
40
  }
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2502974ebdcb087fd83eef414bcbd1efc97102176fc85fc0324fd39986a6ae11
3
- size 167832240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db48ce54d30c13b9e81908838eb0850b18cfe662167b4c77afeaaa797541b32d
3
+ size 3443585096
special_tokens_map.json CHANGED
@@ -7,7 +7,7 @@
7
  "single_word": false
8
  },
9
  "eos_token": {
10
- "content": "<|eot_id|>",
11
  "lstrip": false,
12
  "normalized": false,
13
  "rstrip": false,
 
7
  "single_word": false
8
  },
9
  "eos_token": {
10
+ "content": "<|end_of_text|>",
11
  "lstrip": false,
12
  "normalized": false,
13
  "rstrip": false,
tokenizer_config.json CHANGED
@@ -2050,9 +2050,8 @@
2050
  }
2051
  },
2052
  "bos_token": "<|begin_of_text|>",
2053
- "chat_template": "{{- bos_token }}\n{%- if custom_tools is defined %}\n {%- set tools = custom_tools %}\n{%- endif %}\n{%- if not tools_in_user_message is defined %}\n {%- set tools_in_user_message = true %}\n{%- endif %}\n{%- if not date_string is defined %}\n {%- set date_string = \"26 July 2024\" %}\n{%- endif %}\n{%- if not tools is defined %}\n {%- set tools = none %}\n{%- endif %}\n\n{#- This block extracts the system message, so we can slot it into the right place. #}\n{%- if messages[0]['role'] == 'system' %}\n {%- set system_message = messages[0]['content'] %}\n {%- set messages = messages[1:] %}\n{%- else %}\n {%- set system_message = \"\" %}\n{%- endif %}\n\n{#- System message + builtin tools #}\n{{- \"<|start_header_id|>system<|end_header_id|>\n\n\" }}\n{%- if builtin_tools is defined or tools is not none %}\n {{- \"Environment: ipython\n\" }}\n{%- endif %}\n{%- if builtin_tools is defined %}\n {{- \"Tools: \" + builtin_tools | reject('equalto', 'code_interpreter') | join(\", \") + \"\n\n\"}}\n{%- endif %}\n{{- \"Cutting Knowledge Date: December 2023\n\" }}\n{{- \"Today Date: \" + date_string + \"\n\n\" }}\n{%- if tools is not none and not tools_in_user_message %}\n {{- \"You have access to the following functions. To call a function, please respond with JSON for a function call.\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\n\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\n\n\" }}\n {%- endfor %}\n{%- endif %}\n{{- system_message }}\n{{- \"<|eot_id|>\" }}\n\n{#- Custom tools are passed in a user message with some extra guidance #}\n{%- if tools_in_user_message and not tools is none %}\n {#- Extract the first user message so we can plug it in here #}\n {%- if messages | length != 0 %}\n {%- set first_user_message = messages[0]['content'] %}\n {%- set messages = messages[1:] %}\n {%- else %}\n {{- raise_exception(\"Cannot put tools in the first user message when there's no first user message!\") }}\n{%- endif %}\n {{- '<|start_header_id|>user<|end_header_id|>\n\n' -}}\n {{- \"Given the following functions, please respond with a JSON for a function call \" }}\n {{- \"with its proper arguments that best answers the given prompt.\n\n\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\n\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\n\n\" }}\n {%- endfor %}\n {{- first_user_message + \"<|eot_id|>\"}}\n{%- endif %}\n\n{%- for message in messages %}\n {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}\n {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] + '<|eot_id|>' }}\n {%- elif 'tool_calls' in message %}\n {%- if not message.tool_calls|length == 1 %}\n {{- raise_exception(\"This model only supports single tool-calls at once!\") }}\n {%- endif %}\n {%- set tool_call = message.tool_calls[0].function %}\n {%- if builtin_tools is defined and tool_call.name in builtin_tools %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}\n {{- \"<|python_tag|>\" + tool_call.name + \".call(\" }}\n {%- for arg_name, arg_val in tool_call.arguments | items %}\n {{- arg_name + '=\"' + arg_val + '\"' }}\n {%- if not loop.last %}\n {{- \", \" }}\n {%- endif %}\n {%- endfor %}\n {{- \")\" }}\n {%- else %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}\n {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n {{- '\"parameters\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- \"}\" }}\n {%- endif %}\n {%- if builtin_tools is defined %}\n {#- This means we're in ipython mode #}\n {{- \"<|eom_id|>\" }}\n {%- else %}\n {{- \"<|eot_id|>\" }}\n {%- endif %}\n {%- elif message.role == \"tool\" or message.role == \"ipython\" %}\n {{- \"<|start_header_id|>ipython<|end_header_id|>\n\n\" }}\n {%- if message.content is mapping or message.content is iterable %}\n {{- message.content | tojson }}\n {%- else %}\n {{- message.content }}\n {%- endif %}\n {{- \"<|eot_id|>\" }}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' }}\n{%- endif %}\n",
2054
  "clean_up_tokenization_spaces": true,
2055
- "eos_token": "<|eot_id|>",
2056
  "extra_special_tokens": {},
2057
  "model_input_names": [
2058
  "input_ids",
@@ -2060,6 +2059,6 @@
2060
  ],
2061
  "model_max_length": 131072,
2062
  "pad_token": "<|finetune_right_pad_id|>",
2063
- "padding_side": "right",
2064
  "tokenizer_class": "PreTrainedTokenizerFast"
2065
  }
 
2050
  }
2051
  },
2052
  "bos_token": "<|begin_of_text|>",
 
2053
  "clean_up_tokenization_spaces": true,
2054
+ "eos_token": "<|end_of_text|>",
2055
  "extra_special_tokens": {},
2056
  "model_input_names": [
2057
  "input_ids",
 
2059
  ],
2060
  "model_max_length": 131072,
2061
  "pad_token": "<|finetune_right_pad_id|>",
2062
+ "padding_side": "left",
2063
  "tokenizer_class": "PreTrainedTokenizerFast"
2064
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6bc691856446b3e3718ee3654d52a89e3aa502368dc7cec5eeb1590e92f29be3
3
  size 5560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:742d8368f1f44d65696c221b1be12720d9c7f2d4fe5902b043fabd2375640d9a
3
  size 5560