Upload folder using huggingface_hub
Browse filesThis view is limited to 50 files because it contains too many changes. See raw diff
- adapter_config.json +46 -0
- adapter_model.bin +3 -0
- chat_template.jinja +109 -0
- final/adapter_config.json +46 -0
- final/adapter_model.bin +3 -0
- special_tokens_map.json +30 -0
- step_0/adapter_config.json +46 -0
- step_0/adapter_model.bin +3 -0
- step_1000/adapter_config.json +46 -0
- step_1000/adapter_model.bin +3 -0
- step_1008/adapter_config.json +46 -0
- step_1008/adapter_model.bin +3 -0
- step_1016/adapter_config.json +46 -0
- step_1016/adapter_model.bin +3 -0
- step_1024/adapter_config.json +46 -0
- step_1024/adapter_model.bin +3 -0
- step_1032/adapter_config.json +46 -0
- step_1032/adapter_model.bin +3 -0
- step_104/adapter_config.json +46 -0
- step_104/adapter_model.bin +3 -0
- step_1040/adapter_config.json +46 -0
- step_1040/adapter_model.bin +3 -0
- step_1048/adapter_config.json +46 -0
- step_1048/adapter_model.bin +3 -0
- step_1056/adapter_config.json +46 -0
- step_1056/adapter_model.bin +3 -0
- step_1064/adapter_config.json +46 -0
- step_1064/adapter_model.bin +3 -0
- step_1072/adapter_config.json +46 -0
- step_1072/adapter_model.bin +3 -0
- step_1080/adapter_config.json +46 -0
- step_1080/adapter_model.bin +3 -0
- step_1088/adapter_config.json +46 -0
- step_1088/adapter_model.bin +3 -0
- step_1096/adapter_config.json +46 -0
- step_1096/adapter_model.bin +3 -0
- step_1104/adapter_config.json +46 -0
- step_1104/adapter_model.bin +3 -0
- step_1112/adapter_config.json +46 -0
- step_1112/adapter_model.bin +3 -0
- step_112/adapter_config.json +46 -0
- step_112/adapter_model.bin +3 -0
- step_1120/adapter_config.json +46 -0
- step_1120/adapter_model.bin +3 -0
- step_1128/adapter_config.json +46 -0
- step_1128/adapter_model.bin +3 -0
- step_1136/adapter_config.json +46 -0
- step_1136/adapter_model.bin +3 -0
- step_1144/adapter_config.json +46 -0
- step_1144/adapter_model.bin +3 -0
adapter_config.json
ADDED
|
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "AlignmentResearch/Llama-3.3-Tiny-Instruct-boolq",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"corda_config": null,
|
| 7 |
+
"eva_config": null,
|
| 8 |
+
"exclude_modules": null,
|
| 9 |
+
"fan_in_fan_out": false,
|
| 10 |
+
"inference_mode": false,
|
| 11 |
+
"init_lora_weights": true,
|
| 12 |
+
"layer_replication": null,
|
| 13 |
+
"layers_pattern": null,
|
| 14 |
+
"layers_to_transform": null,
|
| 15 |
+
"loftq_config": {},
|
| 16 |
+
"lora_alpha": 256,
|
| 17 |
+
"lora_bias": false,
|
| 18 |
+
"lora_dropout": 0.0,
|
| 19 |
+
"megatron_config": null,
|
| 20 |
+
"megatron_core": "megatron.core",
|
| 21 |
+
"modules_to_save": null,
|
| 22 |
+
"peft_type": "LORA",
|
| 23 |
+
"r": 128,
|
| 24 |
+
"rank_pattern": {},
|
| 25 |
+
"revision": null,
|
| 26 |
+
"target_modules": [
|
| 27 |
+
"model.layers.1.mlp.gate_proj",
|
| 28 |
+
"model.layers.1.mlp.down_proj",
|
| 29 |
+
"model.layers.0.self_attn.o_proj",
|
| 30 |
+
"model.layers.1.self_attn.v_proj",
|
| 31 |
+
"model.layers.1.self_attn.q_proj",
|
| 32 |
+
"model.layers.0.mlp.up_proj",
|
| 33 |
+
"model.layers.0.mlp.gate_proj",
|
| 34 |
+
"model.layers.0.mlp.down_proj",
|
| 35 |
+
"model.layers.1.self_attn.o_proj",
|
| 36 |
+
"model.layers.0.self_attn.v_proj",
|
| 37 |
+
"model.layers.1.self_attn.k_proj",
|
| 38 |
+
"model.layers.0.self_attn.k_proj",
|
| 39 |
+
"model.layers.1.mlp.up_proj",
|
| 40 |
+
"model.layers.0.self_attn.q_proj"
|
| 41 |
+
],
|
| 42 |
+
"task_type": "CAUSAL_LM",
|
| 43 |
+
"trainable_token_indices": null,
|
| 44 |
+
"use_dora": false,
|
| 45 |
+
"use_rslora": false
|
| 46 |
+
}
|
adapter_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4e9e0027bbdf7ccaff18bbb895264e1610d96dd30b2b0398f1011146d515d7c7
|
| 3 |
+
size 18098267
|
chat_template.jinja
ADDED
|
@@ -0,0 +1,109 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
{%- set date_string = "26 Jul 2024" %}
|
| 10 |
+
{%- endif %}
|
| 11 |
+
{%- if not tools is defined %}
|
| 12 |
+
{%- set tools = none %}
|
| 13 |
+
{%- endif %}
|
| 14 |
+
|
| 15 |
+
{#- This block extracts the system message, so we can slot it into the right place. #}
|
| 16 |
+
{%- if messages[0]['role'] == 'system' %}
|
| 17 |
+
{%- set system_message = messages[0]['content']|trim %}
|
| 18 |
+
{%- set messages = messages[1:] %}
|
| 19 |
+
{%- else %}
|
| 20 |
+
{%- set system_message = "" %}
|
| 21 |
+
{%- endif %}
|
| 22 |
+
|
| 23 |
+
{#- System message + builtin tools #}
|
| 24 |
+
{{- "<|start_header_id|>system<|end_header_id|>\n\n" }}
|
| 25 |
+
{%- if builtin_tools is defined or tools is not none %}
|
| 26 |
+
{{- "Environment: ipython\n" }}
|
| 27 |
+
{%- endif %}
|
| 28 |
+
{%- if builtin_tools is defined %}
|
| 29 |
+
{{- "Tools: " + builtin_tools | reject('equalto', 'code_interpreter') | join(", ") + "\n\n"}}
|
| 30 |
+
{%- endif %}
|
| 31 |
+
{{- "Cutting Knowledge Date: December 2023\n" }}
|
| 32 |
+
{{- "Today Date: " + date_string + "\n\n" }}
|
| 33 |
+
{%- if tools is not none and not tools_in_user_message %}
|
| 34 |
+
{{- "You have access to the following functions. To call a function, please respond with JSON for a function call." }}
|
| 35 |
+
{{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
|
| 36 |
+
{{- "Do not use variables.\n\n" }}
|
| 37 |
+
{%- for t in tools %}
|
| 38 |
+
{{- t | tojson(indent=4) }}
|
| 39 |
+
{{- "\n\n" }}
|
| 40 |
+
{%- endfor %}
|
| 41 |
+
{%- endif %}
|
| 42 |
+
{{- system_message }}
|
| 43 |
+
{{- "<|eot_id|>" }}
|
| 44 |
+
|
| 45 |
+
{#- Custom tools are passed in a user message with some extra guidance #}
|
| 46 |
+
{%- if tools_in_user_message and not tools is none %}
|
| 47 |
+
{#- Extract the first user message so we can plug it in here #}
|
| 48 |
+
{%- if messages | length != 0 %}
|
| 49 |
+
{%- set first_user_message = messages[0]['content']|trim %}
|
| 50 |
+
{%- set messages = messages[1:] %}
|
| 51 |
+
{%- else %}
|
| 52 |
+
{{- raise_exception("Cannot put tools in the first user message when there's no first user message!") }}
|
| 53 |
+
{%- endif %}
|
| 54 |
+
{{- '<|start_header_id|>user<|end_header_id|>\n\n' -}}
|
| 55 |
+
{{- "Given the following functions, please respond with a JSON for a function call " }}
|
| 56 |
+
{{- "with its proper arguments that best answers the given prompt.\n\n" }}
|
| 57 |
+
{{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
|
| 58 |
+
{{- "Do not use variables.\n\n" }}
|
| 59 |
+
{%- for t in tools %}
|
| 60 |
+
{{- t | tojson(indent=4) }}
|
| 61 |
+
{{- "\n\n" }}
|
| 62 |
+
{%- endfor %}
|
| 63 |
+
{{- first_user_message + "<|eot_id|>"}}
|
| 64 |
+
{%- endif %}
|
| 65 |
+
|
| 66 |
+
{%- for message in messages %}
|
| 67 |
+
{%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}
|
| 68 |
+
{{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' }}
|
| 69 |
+
{%- elif 'tool_calls' in message %}
|
| 70 |
+
{%- if not message.tool_calls|length == 1 %}
|
| 71 |
+
{{- raise_exception("This model only supports single tool-calls at once!") }}
|
| 72 |
+
{%- endif %}
|
| 73 |
+
{%- set tool_call = message.tool_calls[0].function %}
|
| 74 |
+
{%- if builtin_tools is defined and tool_call.name in builtin_tools %}
|
| 75 |
+
{{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}
|
| 76 |
+
{{- "<|python_tag|>" + tool_call.name + ".call(" }}
|
| 77 |
+
{%- for arg_name, arg_val in tool_call.arguments | items %}
|
| 78 |
+
{{- arg_name + '="' + arg_val + '"' }}
|
| 79 |
+
{%- if not loop.last %}
|
| 80 |
+
{{- ", " }}
|
| 81 |
+
{%- endif %}
|
| 82 |
+
{%- endfor %}
|
| 83 |
+
{{- ")" }}
|
| 84 |
+
{%- else %}
|
| 85 |
+
{{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}
|
| 86 |
+
{{- '{"name": "' + tool_call.name + '", ' }}
|
| 87 |
+
{{- '"parameters": ' }}
|
| 88 |
+
{{- tool_call.arguments | tojson }}
|
| 89 |
+
{{- "}" }}
|
| 90 |
+
{%- endif %}
|
| 91 |
+
{%- if builtin_tools is defined %}
|
| 92 |
+
{#- This means we're in ipython mode #}
|
| 93 |
+
{{- "<|eom_id|>" }}
|
| 94 |
+
{%- else %}
|
| 95 |
+
{{- "<|eot_id|>" }}
|
| 96 |
+
{%- endif %}
|
| 97 |
+
{%- elif message.role == "tool" or message.role == "ipython" %}
|
| 98 |
+
{{- "<|start_header_id|>ipython<|end_header_id|>\n\n" }}
|
| 99 |
+
{%- if message.content is mapping or message.content is iterable %}
|
| 100 |
+
{{- message.content | tojson }}
|
| 101 |
+
{%- else %}
|
| 102 |
+
{{- message.content }}
|
| 103 |
+
{%- endif %}
|
| 104 |
+
{{- "<|eot_id|>" }}
|
| 105 |
+
{%- endif %}
|
| 106 |
+
{%- endfor %}
|
| 107 |
+
{%- if add_generation_prompt %}
|
| 108 |
+
{{- '<|start_header_id|>assistant<|end_header_id|>\n\n' }}
|
| 109 |
+
{%- endif %}
|
final/adapter_config.json
ADDED
|
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "AlignmentResearch/Llama-3.3-Tiny-Instruct-boolq",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"corda_config": null,
|
| 7 |
+
"eva_config": null,
|
| 8 |
+
"exclude_modules": null,
|
| 9 |
+
"fan_in_fan_out": false,
|
| 10 |
+
"inference_mode": false,
|
| 11 |
+
"init_lora_weights": true,
|
| 12 |
+
"layer_replication": null,
|
| 13 |
+
"layers_pattern": null,
|
| 14 |
+
"layers_to_transform": null,
|
| 15 |
+
"loftq_config": {},
|
| 16 |
+
"lora_alpha": 256,
|
| 17 |
+
"lora_bias": false,
|
| 18 |
+
"lora_dropout": 0.0,
|
| 19 |
+
"megatron_config": null,
|
| 20 |
+
"megatron_core": "megatron.core",
|
| 21 |
+
"modules_to_save": null,
|
| 22 |
+
"peft_type": "LORA",
|
| 23 |
+
"r": 128,
|
| 24 |
+
"rank_pattern": {},
|
| 25 |
+
"revision": null,
|
| 26 |
+
"target_modules": [
|
| 27 |
+
"model.layers.1.mlp.gate_proj",
|
| 28 |
+
"model.layers.1.mlp.down_proj",
|
| 29 |
+
"model.layers.0.self_attn.o_proj",
|
| 30 |
+
"model.layers.1.self_attn.v_proj",
|
| 31 |
+
"model.layers.1.self_attn.q_proj",
|
| 32 |
+
"model.layers.0.mlp.up_proj",
|
| 33 |
+
"model.layers.0.mlp.gate_proj",
|
| 34 |
+
"model.layers.0.mlp.down_proj",
|
| 35 |
+
"model.layers.1.self_attn.o_proj",
|
| 36 |
+
"model.layers.0.self_attn.v_proj",
|
| 37 |
+
"model.layers.1.self_attn.k_proj",
|
| 38 |
+
"model.layers.0.self_attn.k_proj",
|
| 39 |
+
"model.layers.1.mlp.up_proj",
|
| 40 |
+
"model.layers.0.self_attn.q_proj"
|
| 41 |
+
],
|
| 42 |
+
"task_type": "CAUSAL_LM",
|
| 43 |
+
"trainable_token_indices": null,
|
| 44 |
+
"use_dora": false,
|
| 45 |
+
"use_rslora": false
|
| 46 |
+
}
|
final/adapter_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4e9e0027bbdf7ccaff18bbb895264e1610d96dd30b2b0398f1011146d515d7c7
|
| 3 |
+
size 18098267
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": true,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "</s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": true,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "</s>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": true,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"unk_token": {
|
| 24 |
+
"content": "<unk>",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": true,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
}
|
| 30 |
+
}
|
step_0/adapter_config.json
ADDED
|
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "AlignmentResearch/Llama-3.3-Tiny-Instruct-boolq",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"corda_config": null,
|
| 7 |
+
"eva_config": null,
|
| 8 |
+
"exclude_modules": null,
|
| 9 |
+
"fan_in_fan_out": false,
|
| 10 |
+
"inference_mode": false,
|
| 11 |
+
"init_lora_weights": true,
|
| 12 |
+
"layer_replication": null,
|
| 13 |
+
"layers_pattern": null,
|
| 14 |
+
"layers_to_transform": null,
|
| 15 |
+
"loftq_config": {},
|
| 16 |
+
"lora_alpha": 256,
|
| 17 |
+
"lora_bias": false,
|
| 18 |
+
"lora_dropout": 0.0,
|
| 19 |
+
"megatron_config": null,
|
| 20 |
+
"megatron_core": "megatron.core",
|
| 21 |
+
"modules_to_save": null,
|
| 22 |
+
"peft_type": "LORA",
|
| 23 |
+
"r": 128,
|
| 24 |
+
"rank_pattern": {},
|
| 25 |
+
"revision": null,
|
| 26 |
+
"target_modules": [
|
| 27 |
+
"model.layers.1.mlp.gate_proj",
|
| 28 |
+
"model.layers.1.mlp.down_proj",
|
| 29 |
+
"model.layers.0.self_attn.o_proj",
|
| 30 |
+
"model.layers.1.self_attn.v_proj",
|
| 31 |
+
"model.layers.1.self_attn.q_proj",
|
| 32 |
+
"model.layers.0.mlp.up_proj",
|
| 33 |
+
"model.layers.0.mlp.gate_proj",
|
| 34 |
+
"model.layers.0.mlp.down_proj",
|
| 35 |
+
"model.layers.1.self_attn.o_proj",
|
| 36 |
+
"model.layers.0.self_attn.v_proj",
|
| 37 |
+
"model.layers.1.self_attn.k_proj",
|
| 38 |
+
"model.layers.0.self_attn.k_proj",
|
| 39 |
+
"model.layers.1.mlp.up_proj",
|
| 40 |
+
"model.layers.0.self_attn.q_proj"
|
| 41 |
+
],
|
| 42 |
+
"task_type": "CAUSAL_LM",
|
| 43 |
+
"trainable_token_indices": null,
|
| 44 |
+
"use_dora": false,
|
| 45 |
+
"use_rslora": false
|
| 46 |
+
}
|
step_0/adapter_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a255dc47e5ab8a4cd30d6b741c61321b2efc141ea76ffb12f2ccec5f81f548c3
|
| 3 |
+
size 18098267
|
step_1000/adapter_config.json
ADDED
|
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "AlignmentResearch/Llama-3.3-Tiny-Instruct-boolq",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"corda_config": null,
|
| 7 |
+
"eva_config": null,
|
| 8 |
+
"exclude_modules": null,
|
| 9 |
+
"fan_in_fan_out": false,
|
| 10 |
+
"inference_mode": false,
|
| 11 |
+
"init_lora_weights": true,
|
| 12 |
+
"layer_replication": null,
|
| 13 |
+
"layers_pattern": null,
|
| 14 |
+
"layers_to_transform": null,
|
| 15 |
+
"loftq_config": {},
|
| 16 |
+
"lora_alpha": 256,
|
| 17 |
+
"lora_bias": false,
|
| 18 |
+
"lora_dropout": 0.0,
|
| 19 |
+
"megatron_config": null,
|
| 20 |
+
"megatron_core": "megatron.core",
|
| 21 |
+
"modules_to_save": null,
|
| 22 |
+
"peft_type": "LORA",
|
| 23 |
+
"r": 128,
|
| 24 |
+
"rank_pattern": {},
|
| 25 |
+
"revision": null,
|
| 26 |
+
"target_modules": [
|
| 27 |
+
"model.layers.1.mlp.gate_proj",
|
| 28 |
+
"model.layers.1.mlp.down_proj",
|
| 29 |
+
"model.layers.0.self_attn.o_proj",
|
| 30 |
+
"model.layers.1.self_attn.v_proj",
|
| 31 |
+
"model.layers.1.self_attn.q_proj",
|
| 32 |
+
"model.layers.0.mlp.up_proj",
|
| 33 |
+
"model.layers.0.mlp.gate_proj",
|
| 34 |
+
"model.layers.0.mlp.down_proj",
|
| 35 |
+
"model.layers.1.self_attn.o_proj",
|
| 36 |
+
"model.layers.0.self_attn.v_proj",
|
| 37 |
+
"model.layers.1.self_attn.k_proj",
|
| 38 |
+
"model.layers.0.self_attn.k_proj",
|
| 39 |
+
"model.layers.1.mlp.up_proj",
|
| 40 |
+
"model.layers.0.self_attn.q_proj"
|
| 41 |
+
],
|
| 42 |
+
"task_type": "CAUSAL_LM",
|
| 43 |
+
"trainable_token_indices": null,
|
| 44 |
+
"use_dora": false,
|
| 45 |
+
"use_rslora": false
|
| 46 |
+
}
|
step_1000/adapter_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ee98385d0b4f54ea8f39b45e877e4a686fa1460d7eb7e3eda425b74847d9f7ba
|
| 3 |
+
size 18098267
|
step_1008/adapter_config.json
ADDED
|
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "AlignmentResearch/Llama-3.3-Tiny-Instruct-boolq",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"corda_config": null,
|
| 7 |
+
"eva_config": null,
|
| 8 |
+
"exclude_modules": null,
|
| 9 |
+
"fan_in_fan_out": false,
|
| 10 |
+
"inference_mode": false,
|
| 11 |
+
"init_lora_weights": true,
|
| 12 |
+
"layer_replication": null,
|
| 13 |
+
"layers_pattern": null,
|
| 14 |
+
"layers_to_transform": null,
|
| 15 |
+
"loftq_config": {},
|
| 16 |
+
"lora_alpha": 256,
|
| 17 |
+
"lora_bias": false,
|
| 18 |
+
"lora_dropout": 0.0,
|
| 19 |
+
"megatron_config": null,
|
| 20 |
+
"megatron_core": "megatron.core",
|
| 21 |
+
"modules_to_save": null,
|
| 22 |
+
"peft_type": "LORA",
|
| 23 |
+
"r": 128,
|
| 24 |
+
"rank_pattern": {},
|
| 25 |
+
"revision": null,
|
| 26 |
+
"target_modules": [
|
| 27 |
+
"model.layers.1.mlp.gate_proj",
|
| 28 |
+
"model.layers.1.mlp.down_proj",
|
| 29 |
+
"model.layers.0.self_attn.o_proj",
|
| 30 |
+
"model.layers.1.self_attn.v_proj",
|
| 31 |
+
"model.layers.1.self_attn.q_proj",
|
| 32 |
+
"model.layers.0.mlp.up_proj",
|
| 33 |
+
"model.layers.0.mlp.gate_proj",
|
| 34 |
+
"model.layers.0.mlp.down_proj",
|
| 35 |
+
"model.layers.1.self_attn.o_proj",
|
| 36 |
+
"model.layers.0.self_attn.v_proj",
|
| 37 |
+
"model.layers.1.self_attn.k_proj",
|
| 38 |
+
"model.layers.0.self_attn.k_proj",
|
| 39 |
+
"model.layers.1.mlp.up_proj",
|
| 40 |
+
"model.layers.0.self_attn.q_proj"
|
| 41 |
+
],
|
| 42 |
+
"task_type": "CAUSAL_LM",
|
| 43 |
+
"trainable_token_indices": null,
|
| 44 |
+
"use_dora": false,
|
| 45 |
+
"use_rslora": false
|
| 46 |
+
}
|
step_1008/adapter_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:535a251bcd5bba37fd9130ca63d4a61f5a2d21c36efc0f90938248615aa3b298
|
| 3 |
+
size 18098267
|
step_1016/adapter_config.json
ADDED
|
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "AlignmentResearch/Llama-3.3-Tiny-Instruct-boolq",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"corda_config": null,
|
| 7 |
+
"eva_config": null,
|
| 8 |
+
"exclude_modules": null,
|
| 9 |
+
"fan_in_fan_out": false,
|
| 10 |
+
"inference_mode": false,
|
| 11 |
+
"init_lora_weights": true,
|
| 12 |
+
"layer_replication": null,
|
| 13 |
+
"layers_pattern": null,
|
| 14 |
+
"layers_to_transform": null,
|
| 15 |
+
"loftq_config": {},
|
| 16 |
+
"lora_alpha": 256,
|
| 17 |
+
"lora_bias": false,
|
| 18 |
+
"lora_dropout": 0.0,
|
| 19 |
+
"megatron_config": null,
|
| 20 |
+
"megatron_core": "megatron.core",
|
| 21 |
+
"modules_to_save": null,
|
| 22 |
+
"peft_type": "LORA",
|
| 23 |
+
"r": 128,
|
| 24 |
+
"rank_pattern": {},
|
| 25 |
+
"revision": null,
|
| 26 |
+
"target_modules": [
|
| 27 |
+
"model.layers.1.mlp.gate_proj",
|
| 28 |
+
"model.layers.1.mlp.down_proj",
|
| 29 |
+
"model.layers.0.self_attn.o_proj",
|
| 30 |
+
"model.layers.1.self_attn.v_proj",
|
| 31 |
+
"model.layers.1.self_attn.q_proj",
|
| 32 |
+
"model.layers.0.mlp.up_proj",
|
| 33 |
+
"model.layers.0.mlp.gate_proj",
|
| 34 |
+
"model.layers.0.mlp.down_proj",
|
| 35 |
+
"model.layers.1.self_attn.o_proj",
|
| 36 |
+
"model.layers.0.self_attn.v_proj",
|
| 37 |
+
"model.layers.1.self_attn.k_proj",
|
| 38 |
+
"model.layers.0.self_attn.k_proj",
|
| 39 |
+
"model.layers.1.mlp.up_proj",
|
| 40 |
+
"model.layers.0.self_attn.q_proj"
|
| 41 |
+
],
|
| 42 |
+
"task_type": "CAUSAL_LM",
|
| 43 |
+
"trainable_token_indices": null,
|
| 44 |
+
"use_dora": false,
|
| 45 |
+
"use_rslora": false
|
| 46 |
+
}
|
step_1016/adapter_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6efc008ffc994b56eef2fc999bf17b56244c2a6fad7e62c898207bdf0cf6413a
|
| 3 |
+
size 18098267
|
step_1024/adapter_config.json
ADDED
|
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "AlignmentResearch/Llama-3.3-Tiny-Instruct-boolq",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"corda_config": null,
|
| 7 |
+
"eva_config": null,
|
| 8 |
+
"exclude_modules": null,
|
| 9 |
+
"fan_in_fan_out": false,
|
| 10 |
+
"inference_mode": false,
|
| 11 |
+
"init_lora_weights": true,
|
| 12 |
+
"layer_replication": null,
|
| 13 |
+
"layers_pattern": null,
|
| 14 |
+
"layers_to_transform": null,
|
| 15 |
+
"loftq_config": {},
|
| 16 |
+
"lora_alpha": 256,
|
| 17 |
+
"lora_bias": false,
|
| 18 |
+
"lora_dropout": 0.0,
|
| 19 |
+
"megatron_config": null,
|
| 20 |
+
"megatron_core": "megatron.core",
|
| 21 |
+
"modules_to_save": null,
|
| 22 |
+
"peft_type": "LORA",
|
| 23 |
+
"r": 128,
|
| 24 |
+
"rank_pattern": {},
|
| 25 |
+
"revision": null,
|
| 26 |
+
"target_modules": [
|
| 27 |
+
"model.layers.1.mlp.gate_proj",
|
| 28 |
+
"model.layers.1.mlp.down_proj",
|
| 29 |
+
"model.layers.0.self_attn.o_proj",
|
| 30 |
+
"model.layers.1.self_attn.v_proj",
|
| 31 |
+
"model.layers.1.self_attn.q_proj",
|
| 32 |
+
"model.layers.0.mlp.up_proj",
|
| 33 |
+
"model.layers.0.mlp.gate_proj",
|
| 34 |
+
"model.layers.0.mlp.down_proj",
|
| 35 |
+
"model.layers.1.self_attn.o_proj",
|
| 36 |
+
"model.layers.0.self_attn.v_proj",
|
| 37 |
+
"model.layers.1.self_attn.k_proj",
|
| 38 |
+
"model.layers.0.self_attn.k_proj",
|
| 39 |
+
"model.layers.1.mlp.up_proj",
|
| 40 |
+
"model.layers.0.self_attn.q_proj"
|
| 41 |
+
],
|
| 42 |
+
"task_type": "CAUSAL_LM",
|
| 43 |
+
"trainable_token_indices": null,
|
| 44 |
+
"use_dora": false,
|
| 45 |
+
"use_rslora": false
|
| 46 |
+
}
|
step_1024/adapter_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e1c6303f6e823186242760de2ad7cbcc1a5b2b6fa469f6f30e3e0c34f3803e91
|
| 3 |
+
size 18098267
|
step_1032/adapter_config.json
ADDED
|
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "AlignmentResearch/Llama-3.3-Tiny-Instruct-boolq",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"corda_config": null,
|
| 7 |
+
"eva_config": null,
|
| 8 |
+
"exclude_modules": null,
|
| 9 |
+
"fan_in_fan_out": false,
|
| 10 |
+
"inference_mode": false,
|
| 11 |
+
"init_lora_weights": true,
|
| 12 |
+
"layer_replication": null,
|
| 13 |
+
"layers_pattern": null,
|
| 14 |
+
"layers_to_transform": null,
|
| 15 |
+
"loftq_config": {},
|
| 16 |
+
"lora_alpha": 256,
|
| 17 |
+
"lora_bias": false,
|
| 18 |
+
"lora_dropout": 0.0,
|
| 19 |
+
"megatron_config": null,
|
| 20 |
+
"megatron_core": "megatron.core",
|
| 21 |
+
"modules_to_save": null,
|
| 22 |
+
"peft_type": "LORA",
|
| 23 |
+
"r": 128,
|
| 24 |
+
"rank_pattern": {},
|
| 25 |
+
"revision": null,
|
| 26 |
+
"target_modules": [
|
| 27 |
+
"model.layers.1.mlp.gate_proj",
|
| 28 |
+
"model.layers.1.mlp.down_proj",
|
| 29 |
+
"model.layers.0.self_attn.o_proj",
|
| 30 |
+
"model.layers.1.self_attn.v_proj",
|
| 31 |
+
"model.layers.1.self_attn.q_proj",
|
| 32 |
+
"model.layers.0.mlp.up_proj",
|
| 33 |
+
"model.layers.0.mlp.gate_proj",
|
| 34 |
+
"model.layers.0.mlp.down_proj",
|
| 35 |
+
"model.layers.1.self_attn.o_proj",
|
| 36 |
+
"model.layers.0.self_attn.v_proj",
|
| 37 |
+
"model.layers.1.self_attn.k_proj",
|
| 38 |
+
"model.layers.0.self_attn.k_proj",
|
| 39 |
+
"model.layers.1.mlp.up_proj",
|
| 40 |
+
"model.layers.0.self_attn.q_proj"
|
| 41 |
+
],
|
| 42 |
+
"task_type": "CAUSAL_LM",
|
| 43 |
+
"trainable_token_indices": null,
|
| 44 |
+
"use_dora": false,
|
| 45 |
+
"use_rslora": false
|
| 46 |
+
}
|
step_1032/adapter_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7bf9fa05f45c5d9408a1d77f4e8035e262a7069c16ddecca54e291067ba4eff5
|
| 3 |
+
size 18098267
|
step_104/adapter_config.json
ADDED
|
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "AlignmentResearch/Llama-3.3-Tiny-Instruct-boolq",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"corda_config": null,
|
| 7 |
+
"eva_config": null,
|
| 8 |
+
"exclude_modules": null,
|
| 9 |
+
"fan_in_fan_out": false,
|
| 10 |
+
"inference_mode": false,
|
| 11 |
+
"init_lora_weights": true,
|
| 12 |
+
"layer_replication": null,
|
| 13 |
+
"layers_pattern": null,
|
| 14 |
+
"layers_to_transform": null,
|
| 15 |
+
"loftq_config": {},
|
| 16 |
+
"lora_alpha": 256,
|
| 17 |
+
"lora_bias": false,
|
| 18 |
+
"lora_dropout": 0.0,
|
| 19 |
+
"megatron_config": null,
|
| 20 |
+
"megatron_core": "megatron.core",
|
| 21 |
+
"modules_to_save": null,
|
| 22 |
+
"peft_type": "LORA",
|
| 23 |
+
"r": 128,
|
| 24 |
+
"rank_pattern": {},
|
| 25 |
+
"revision": null,
|
| 26 |
+
"target_modules": [
|
| 27 |
+
"model.layers.1.mlp.gate_proj",
|
| 28 |
+
"model.layers.1.mlp.down_proj",
|
| 29 |
+
"model.layers.0.self_attn.o_proj",
|
| 30 |
+
"model.layers.1.self_attn.v_proj",
|
| 31 |
+
"model.layers.1.self_attn.q_proj",
|
| 32 |
+
"model.layers.0.mlp.up_proj",
|
| 33 |
+
"model.layers.0.mlp.gate_proj",
|
| 34 |
+
"model.layers.0.mlp.down_proj",
|
| 35 |
+
"model.layers.1.self_attn.o_proj",
|
| 36 |
+
"model.layers.0.self_attn.v_proj",
|
| 37 |
+
"model.layers.1.self_attn.k_proj",
|
| 38 |
+
"model.layers.0.self_attn.k_proj",
|
| 39 |
+
"model.layers.1.mlp.up_proj",
|
| 40 |
+
"model.layers.0.self_attn.q_proj"
|
| 41 |
+
],
|
| 42 |
+
"task_type": "CAUSAL_LM",
|
| 43 |
+
"trainable_token_indices": null,
|
| 44 |
+
"use_dora": false,
|
| 45 |
+
"use_rslora": false
|
| 46 |
+
}
|
step_104/adapter_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3477931800dd7a8f1b2f3e5c7e5e208de119cfdd4d9fb66401db1e52146fa192
|
| 3 |
+
size 18098267
|
step_1040/adapter_config.json
ADDED
|
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "AlignmentResearch/Llama-3.3-Tiny-Instruct-boolq",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"corda_config": null,
|
| 7 |
+
"eva_config": null,
|
| 8 |
+
"exclude_modules": null,
|
| 9 |
+
"fan_in_fan_out": false,
|
| 10 |
+
"inference_mode": false,
|
| 11 |
+
"init_lora_weights": true,
|
| 12 |
+
"layer_replication": null,
|
| 13 |
+
"layers_pattern": null,
|
| 14 |
+
"layers_to_transform": null,
|
| 15 |
+
"loftq_config": {},
|
| 16 |
+
"lora_alpha": 256,
|
| 17 |
+
"lora_bias": false,
|
| 18 |
+
"lora_dropout": 0.0,
|
| 19 |
+
"megatron_config": null,
|
| 20 |
+
"megatron_core": "megatron.core",
|
| 21 |
+
"modules_to_save": null,
|
| 22 |
+
"peft_type": "LORA",
|
| 23 |
+
"r": 128,
|
| 24 |
+
"rank_pattern": {},
|
| 25 |
+
"revision": null,
|
| 26 |
+
"target_modules": [
|
| 27 |
+
"model.layers.1.mlp.gate_proj",
|
| 28 |
+
"model.layers.1.mlp.down_proj",
|
| 29 |
+
"model.layers.0.self_attn.o_proj",
|
| 30 |
+
"model.layers.1.self_attn.v_proj",
|
| 31 |
+
"model.layers.1.self_attn.q_proj",
|
| 32 |
+
"model.layers.0.mlp.up_proj",
|
| 33 |
+
"model.layers.0.mlp.gate_proj",
|
| 34 |
+
"model.layers.0.mlp.down_proj",
|
| 35 |
+
"model.layers.1.self_attn.o_proj",
|
| 36 |
+
"model.layers.0.self_attn.v_proj",
|
| 37 |
+
"model.layers.1.self_attn.k_proj",
|
| 38 |
+
"model.layers.0.self_attn.k_proj",
|
| 39 |
+
"model.layers.1.mlp.up_proj",
|
| 40 |
+
"model.layers.0.self_attn.q_proj"
|
| 41 |
+
],
|
| 42 |
+
"task_type": "CAUSAL_LM",
|
| 43 |
+
"trainable_token_indices": null,
|
| 44 |
+
"use_dora": false,
|
| 45 |
+
"use_rslora": false
|
| 46 |
+
}
|
step_1040/adapter_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:92c339b7a1f2ab41fc42933c3d46843b0c76bc012764ee169e1ca7a7cb02e14b
|
| 3 |
+
size 18098267
|
step_1048/adapter_config.json
ADDED
|
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "AlignmentResearch/Llama-3.3-Tiny-Instruct-boolq",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"corda_config": null,
|
| 7 |
+
"eva_config": null,
|
| 8 |
+
"exclude_modules": null,
|
| 9 |
+
"fan_in_fan_out": false,
|
| 10 |
+
"inference_mode": false,
|
| 11 |
+
"init_lora_weights": true,
|
| 12 |
+
"layer_replication": null,
|
| 13 |
+
"layers_pattern": null,
|
| 14 |
+
"layers_to_transform": null,
|
| 15 |
+
"loftq_config": {},
|
| 16 |
+
"lora_alpha": 256,
|
| 17 |
+
"lora_bias": false,
|
| 18 |
+
"lora_dropout": 0.0,
|
| 19 |
+
"megatron_config": null,
|
| 20 |
+
"megatron_core": "megatron.core",
|
| 21 |
+
"modules_to_save": null,
|
| 22 |
+
"peft_type": "LORA",
|
| 23 |
+
"r": 128,
|
| 24 |
+
"rank_pattern": {},
|
| 25 |
+
"revision": null,
|
| 26 |
+
"target_modules": [
|
| 27 |
+
"model.layers.1.mlp.gate_proj",
|
| 28 |
+
"model.layers.1.mlp.down_proj",
|
| 29 |
+
"model.layers.0.self_attn.o_proj",
|
| 30 |
+
"model.layers.1.self_attn.v_proj",
|
| 31 |
+
"model.layers.1.self_attn.q_proj",
|
| 32 |
+
"model.layers.0.mlp.up_proj",
|
| 33 |
+
"model.layers.0.mlp.gate_proj",
|
| 34 |
+
"model.layers.0.mlp.down_proj",
|
| 35 |
+
"model.layers.1.self_attn.o_proj",
|
| 36 |
+
"model.layers.0.self_attn.v_proj",
|
| 37 |
+
"model.layers.1.self_attn.k_proj",
|
| 38 |
+
"model.layers.0.self_attn.k_proj",
|
| 39 |
+
"model.layers.1.mlp.up_proj",
|
| 40 |
+
"model.layers.0.self_attn.q_proj"
|
| 41 |
+
],
|
| 42 |
+
"task_type": "CAUSAL_LM",
|
| 43 |
+
"trainable_token_indices": null,
|
| 44 |
+
"use_dora": false,
|
| 45 |
+
"use_rslora": false
|
| 46 |
+
}
|
step_1048/adapter_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:59031984b5628fb81e8e813889ac6c5b87651715955a3ebb2e585fceeb386f2e
|
| 3 |
+
size 18098267
|
step_1056/adapter_config.json
ADDED
|
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "AlignmentResearch/Llama-3.3-Tiny-Instruct-boolq",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"corda_config": null,
|
| 7 |
+
"eva_config": null,
|
| 8 |
+
"exclude_modules": null,
|
| 9 |
+
"fan_in_fan_out": false,
|
| 10 |
+
"inference_mode": false,
|
| 11 |
+
"init_lora_weights": true,
|
| 12 |
+
"layer_replication": null,
|
| 13 |
+
"layers_pattern": null,
|
| 14 |
+
"layers_to_transform": null,
|
| 15 |
+
"loftq_config": {},
|
| 16 |
+
"lora_alpha": 256,
|
| 17 |
+
"lora_bias": false,
|
| 18 |
+
"lora_dropout": 0.0,
|
| 19 |
+
"megatron_config": null,
|
| 20 |
+
"megatron_core": "megatron.core",
|
| 21 |
+
"modules_to_save": null,
|
| 22 |
+
"peft_type": "LORA",
|
| 23 |
+
"r": 128,
|
| 24 |
+
"rank_pattern": {},
|
| 25 |
+
"revision": null,
|
| 26 |
+
"target_modules": [
|
| 27 |
+
"model.layers.1.mlp.gate_proj",
|
| 28 |
+
"model.layers.1.mlp.down_proj",
|
| 29 |
+
"model.layers.0.self_attn.o_proj",
|
| 30 |
+
"model.layers.1.self_attn.v_proj",
|
| 31 |
+
"model.layers.1.self_attn.q_proj",
|
| 32 |
+
"model.layers.0.mlp.up_proj",
|
| 33 |
+
"model.layers.0.mlp.gate_proj",
|
| 34 |
+
"model.layers.0.mlp.down_proj",
|
| 35 |
+
"model.layers.1.self_attn.o_proj",
|
| 36 |
+
"model.layers.0.self_attn.v_proj",
|
| 37 |
+
"model.layers.1.self_attn.k_proj",
|
| 38 |
+
"model.layers.0.self_attn.k_proj",
|
| 39 |
+
"model.layers.1.mlp.up_proj",
|
| 40 |
+
"model.layers.0.self_attn.q_proj"
|
| 41 |
+
],
|
| 42 |
+
"task_type": "CAUSAL_LM",
|
| 43 |
+
"trainable_token_indices": null,
|
| 44 |
+
"use_dora": false,
|
| 45 |
+
"use_rslora": false
|
| 46 |
+
}
|
step_1056/adapter_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0658e26c45226ddd1c5526d845acb1b7c361d5d049a203a10497741d1860d74b
|
| 3 |
+
size 18098267
|
step_1064/adapter_config.json
ADDED
|
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "AlignmentResearch/Llama-3.3-Tiny-Instruct-boolq",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"corda_config": null,
|
| 7 |
+
"eva_config": null,
|
| 8 |
+
"exclude_modules": null,
|
| 9 |
+
"fan_in_fan_out": false,
|
| 10 |
+
"inference_mode": false,
|
| 11 |
+
"init_lora_weights": true,
|
| 12 |
+
"layer_replication": null,
|
| 13 |
+
"layers_pattern": null,
|
| 14 |
+
"layers_to_transform": null,
|
| 15 |
+
"loftq_config": {},
|
| 16 |
+
"lora_alpha": 256,
|
| 17 |
+
"lora_bias": false,
|
| 18 |
+
"lora_dropout": 0.0,
|
| 19 |
+
"megatron_config": null,
|
| 20 |
+
"megatron_core": "megatron.core",
|
| 21 |
+
"modules_to_save": null,
|
| 22 |
+
"peft_type": "LORA",
|
| 23 |
+
"r": 128,
|
| 24 |
+
"rank_pattern": {},
|
| 25 |
+
"revision": null,
|
| 26 |
+
"target_modules": [
|
| 27 |
+
"model.layers.1.mlp.gate_proj",
|
| 28 |
+
"model.layers.1.mlp.down_proj",
|
| 29 |
+
"model.layers.0.self_attn.o_proj",
|
| 30 |
+
"model.layers.1.self_attn.v_proj",
|
| 31 |
+
"model.layers.1.self_attn.q_proj",
|
| 32 |
+
"model.layers.0.mlp.up_proj",
|
| 33 |
+
"model.layers.0.mlp.gate_proj",
|
| 34 |
+
"model.layers.0.mlp.down_proj",
|
| 35 |
+
"model.layers.1.self_attn.o_proj",
|
| 36 |
+
"model.layers.0.self_attn.v_proj",
|
| 37 |
+
"model.layers.1.self_attn.k_proj",
|
| 38 |
+
"model.layers.0.self_attn.k_proj",
|
| 39 |
+
"model.layers.1.mlp.up_proj",
|
| 40 |
+
"model.layers.0.self_attn.q_proj"
|
| 41 |
+
],
|
| 42 |
+
"task_type": "CAUSAL_LM",
|
| 43 |
+
"trainable_token_indices": null,
|
| 44 |
+
"use_dora": false,
|
| 45 |
+
"use_rslora": false
|
| 46 |
+
}
|
step_1064/adapter_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3224415d0ad8893517476a0ab336c05b3f57985c7bbd3849694a9e945b957e08
|
| 3 |
+
size 18098267
|
step_1072/adapter_config.json
ADDED
|
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "AlignmentResearch/Llama-3.3-Tiny-Instruct-boolq",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"corda_config": null,
|
| 7 |
+
"eva_config": null,
|
| 8 |
+
"exclude_modules": null,
|
| 9 |
+
"fan_in_fan_out": false,
|
| 10 |
+
"inference_mode": false,
|
| 11 |
+
"init_lora_weights": true,
|
| 12 |
+
"layer_replication": null,
|
| 13 |
+
"layers_pattern": null,
|
| 14 |
+
"layers_to_transform": null,
|
| 15 |
+
"loftq_config": {},
|
| 16 |
+
"lora_alpha": 256,
|
| 17 |
+
"lora_bias": false,
|
| 18 |
+
"lora_dropout": 0.0,
|
| 19 |
+
"megatron_config": null,
|
| 20 |
+
"megatron_core": "megatron.core",
|
| 21 |
+
"modules_to_save": null,
|
| 22 |
+
"peft_type": "LORA",
|
| 23 |
+
"r": 128,
|
| 24 |
+
"rank_pattern": {},
|
| 25 |
+
"revision": null,
|
| 26 |
+
"target_modules": [
|
| 27 |
+
"model.layers.1.mlp.gate_proj",
|
| 28 |
+
"model.layers.1.mlp.down_proj",
|
| 29 |
+
"model.layers.0.self_attn.o_proj",
|
| 30 |
+
"model.layers.1.self_attn.v_proj",
|
| 31 |
+
"model.layers.1.self_attn.q_proj",
|
| 32 |
+
"model.layers.0.mlp.up_proj",
|
| 33 |
+
"model.layers.0.mlp.gate_proj",
|
| 34 |
+
"model.layers.0.mlp.down_proj",
|
| 35 |
+
"model.layers.1.self_attn.o_proj",
|
| 36 |
+
"model.layers.0.self_attn.v_proj",
|
| 37 |
+
"model.layers.1.self_attn.k_proj",
|
| 38 |
+
"model.layers.0.self_attn.k_proj",
|
| 39 |
+
"model.layers.1.mlp.up_proj",
|
| 40 |
+
"model.layers.0.self_attn.q_proj"
|
| 41 |
+
],
|
| 42 |
+
"task_type": "CAUSAL_LM",
|
| 43 |
+
"trainable_token_indices": null,
|
| 44 |
+
"use_dora": false,
|
| 45 |
+
"use_rslora": false
|
| 46 |
+
}
|
step_1072/adapter_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:56133eecced379b1a043b464d42ddba58d1dbc6071223908620bca71fda48542
|
| 3 |
+
size 18098267
|
step_1080/adapter_config.json
ADDED
|
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "AlignmentResearch/Llama-3.3-Tiny-Instruct-boolq",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"corda_config": null,
|
| 7 |
+
"eva_config": null,
|
| 8 |
+
"exclude_modules": null,
|
| 9 |
+
"fan_in_fan_out": false,
|
| 10 |
+
"inference_mode": false,
|
| 11 |
+
"init_lora_weights": true,
|
| 12 |
+
"layer_replication": null,
|
| 13 |
+
"layers_pattern": null,
|
| 14 |
+
"layers_to_transform": null,
|
| 15 |
+
"loftq_config": {},
|
| 16 |
+
"lora_alpha": 256,
|
| 17 |
+
"lora_bias": false,
|
| 18 |
+
"lora_dropout": 0.0,
|
| 19 |
+
"megatron_config": null,
|
| 20 |
+
"megatron_core": "megatron.core",
|
| 21 |
+
"modules_to_save": null,
|
| 22 |
+
"peft_type": "LORA",
|
| 23 |
+
"r": 128,
|
| 24 |
+
"rank_pattern": {},
|
| 25 |
+
"revision": null,
|
| 26 |
+
"target_modules": [
|
| 27 |
+
"model.layers.1.mlp.gate_proj",
|
| 28 |
+
"model.layers.1.mlp.down_proj",
|
| 29 |
+
"model.layers.0.self_attn.o_proj",
|
| 30 |
+
"model.layers.1.self_attn.v_proj",
|
| 31 |
+
"model.layers.1.self_attn.q_proj",
|
| 32 |
+
"model.layers.0.mlp.up_proj",
|
| 33 |
+
"model.layers.0.mlp.gate_proj",
|
| 34 |
+
"model.layers.0.mlp.down_proj",
|
| 35 |
+
"model.layers.1.self_attn.o_proj",
|
| 36 |
+
"model.layers.0.self_attn.v_proj",
|
| 37 |
+
"model.layers.1.self_attn.k_proj",
|
| 38 |
+
"model.layers.0.self_attn.k_proj",
|
| 39 |
+
"model.layers.1.mlp.up_proj",
|
| 40 |
+
"model.layers.0.self_attn.q_proj"
|
| 41 |
+
],
|
| 42 |
+
"task_type": "CAUSAL_LM",
|
| 43 |
+
"trainable_token_indices": null,
|
| 44 |
+
"use_dora": false,
|
| 45 |
+
"use_rslora": false
|
| 46 |
+
}
|
step_1080/adapter_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:723925478d50014008c6289d566a0e4a8a6ff24a8e2435fb434ed9b4f1b2c2f5
|
| 3 |
+
size 18098267
|
step_1088/adapter_config.json
ADDED
|
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "AlignmentResearch/Llama-3.3-Tiny-Instruct-boolq",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"corda_config": null,
|
| 7 |
+
"eva_config": null,
|
| 8 |
+
"exclude_modules": null,
|
| 9 |
+
"fan_in_fan_out": false,
|
| 10 |
+
"inference_mode": false,
|
| 11 |
+
"init_lora_weights": true,
|
| 12 |
+
"layer_replication": null,
|
| 13 |
+
"layers_pattern": null,
|
| 14 |
+
"layers_to_transform": null,
|
| 15 |
+
"loftq_config": {},
|
| 16 |
+
"lora_alpha": 256,
|
| 17 |
+
"lora_bias": false,
|
| 18 |
+
"lora_dropout": 0.0,
|
| 19 |
+
"megatron_config": null,
|
| 20 |
+
"megatron_core": "megatron.core",
|
| 21 |
+
"modules_to_save": null,
|
| 22 |
+
"peft_type": "LORA",
|
| 23 |
+
"r": 128,
|
| 24 |
+
"rank_pattern": {},
|
| 25 |
+
"revision": null,
|
| 26 |
+
"target_modules": [
|
| 27 |
+
"model.layers.1.mlp.gate_proj",
|
| 28 |
+
"model.layers.1.mlp.down_proj",
|
| 29 |
+
"model.layers.0.self_attn.o_proj",
|
| 30 |
+
"model.layers.1.self_attn.v_proj",
|
| 31 |
+
"model.layers.1.self_attn.q_proj",
|
| 32 |
+
"model.layers.0.mlp.up_proj",
|
| 33 |
+
"model.layers.0.mlp.gate_proj",
|
| 34 |
+
"model.layers.0.mlp.down_proj",
|
| 35 |
+
"model.layers.1.self_attn.o_proj",
|
| 36 |
+
"model.layers.0.self_attn.v_proj",
|
| 37 |
+
"model.layers.1.self_attn.k_proj",
|
| 38 |
+
"model.layers.0.self_attn.k_proj",
|
| 39 |
+
"model.layers.1.mlp.up_proj",
|
| 40 |
+
"model.layers.0.self_attn.q_proj"
|
| 41 |
+
],
|
| 42 |
+
"task_type": "CAUSAL_LM",
|
| 43 |
+
"trainable_token_indices": null,
|
| 44 |
+
"use_dora": false,
|
| 45 |
+
"use_rslora": false
|
| 46 |
+
}
|
step_1088/adapter_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ed69d75a216116ae37ff689732a8c63570d34fcfa41763c4335e6ec936d125b9
|
| 3 |
+
size 18098267
|
step_1096/adapter_config.json
ADDED
|
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "AlignmentResearch/Llama-3.3-Tiny-Instruct-boolq",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"corda_config": null,
|
| 7 |
+
"eva_config": null,
|
| 8 |
+
"exclude_modules": null,
|
| 9 |
+
"fan_in_fan_out": false,
|
| 10 |
+
"inference_mode": false,
|
| 11 |
+
"init_lora_weights": true,
|
| 12 |
+
"layer_replication": null,
|
| 13 |
+
"layers_pattern": null,
|
| 14 |
+
"layers_to_transform": null,
|
| 15 |
+
"loftq_config": {},
|
| 16 |
+
"lora_alpha": 256,
|
| 17 |
+
"lora_bias": false,
|
| 18 |
+
"lora_dropout": 0.0,
|
| 19 |
+
"megatron_config": null,
|
| 20 |
+
"megatron_core": "megatron.core",
|
| 21 |
+
"modules_to_save": null,
|
| 22 |
+
"peft_type": "LORA",
|
| 23 |
+
"r": 128,
|
| 24 |
+
"rank_pattern": {},
|
| 25 |
+
"revision": null,
|
| 26 |
+
"target_modules": [
|
| 27 |
+
"model.layers.1.mlp.gate_proj",
|
| 28 |
+
"model.layers.1.mlp.down_proj",
|
| 29 |
+
"model.layers.0.self_attn.o_proj",
|
| 30 |
+
"model.layers.1.self_attn.v_proj",
|
| 31 |
+
"model.layers.1.self_attn.q_proj",
|
| 32 |
+
"model.layers.0.mlp.up_proj",
|
| 33 |
+
"model.layers.0.mlp.gate_proj",
|
| 34 |
+
"model.layers.0.mlp.down_proj",
|
| 35 |
+
"model.layers.1.self_attn.o_proj",
|
| 36 |
+
"model.layers.0.self_attn.v_proj",
|
| 37 |
+
"model.layers.1.self_attn.k_proj",
|
| 38 |
+
"model.layers.0.self_attn.k_proj",
|
| 39 |
+
"model.layers.1.mlp.up_proj",
|
| 40 |
+
"model.layers.0.self_attn.q_proj"
|
| 41 |
+
],
|
| 42 |
+
"task_type": "CAUSAL_LM",
|
| 43 |
+
"trainable_token_indices": null,
|
| 44 |
+
"use_dora": false,
|
| 45 |
+
"use_rslora": false
|
| 46 |
+
}
|
step_1096/adapter_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f249704ad30b478ea164acaa57465322470f5ea9573a1dafd6466857466cdd84
|
| 3 |
+
size 18098267
|
step_1104/adapter_config.json
ADDED
|
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "AlignmentResearch/Llama-3.3-Tiny-Instruct-boolq",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"corda_config": null,
|
| 7 |
+
"eva_config": null,
|
| 8 |
+
"exclude_modules": null,
|
| 9 |
+
"fan_in_fan_out": false,
|
| 10 |
+
"inference_mode": false,
|
| 11 |
+
"init_lora_weights": true,
|
| 12 |
+
"layer_replication": null,
|
| 13 |
+
"layers_pattern": null,
|
| 14 |
+
"layers_to_transform": null,
|
| 15 |
+
"loftq_config": {},
|
| 16 |
+
"lora_alpha": 256,
|
| 17 |
+
"lora_bias": false,
|
| 18 |
+
"lora_dropout": 0.0,
|
| 19 |
+
"megatron_config": null,
|
| 20 |
+
"megatron_core": "megatron.core",
|
| 21 |
+
"modules_to_save": null,
|
| 22 |
+
"peft_type": "LORA",
|
| 23 |
+
"r": 128,
|
| 24 |
+
"rank_pattern": {},
|
| 25 |
+
"revision": null,
|
| 26 |
+
"target_modules": [
|
| 27 |
+
"model.layers.1.mlp.gate_proj",
|
| 28 |
+
"model.layers.1.mlp.down_proj",
|
| 29 |
+
"model.layers.0.self_attn.o_proj",
|
| 30 |
+
"model.layers.1.self_attn.v_proj",
|
| 31 |
+
"model.layers.1.self_attn.q_proj",
|
| 32 |
+
"model.layers.0.mlp.up_proj",
|
| 33 |
+
"model.layers.0.mlp.gate_proj",
|
| 34 |
+
"model.layers.0.mlp.down_proj",
|
| 35 |
+
"model.layers.1.self_attn.o_proj",
|
| 36 |
+
"model.layers.0.self_attn.v_proj",
|
| 37 |
+
"model.layers.1.self_attn.k_proj",
|
| 38 |
+
"model.layers.0.self_attn.k_proj",
|
| 39 |
+
"model.layers.1.mlp.up_proj",
|
| 40 |
+
"model.layers.0.self_attn.q_proj"
|
| 41 |
+
],
|
| 42 |
+
"task_type": "CAUSAL_LM",
|
| 43 |
+
"trainable_token_indices": null,
|
| 44 |
+
"use_dora": false,
|
| 45 |
+
"use_rslora": false
|
| 46 |
+
}
|
step_1104/adapter_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5de74099d4f7d680cfe59086a1477ad47211b6b48e9126013f291cb0d169779b
|
| 3 |
+
size 18098267
|
step_1112/adapter_config.json
ADDED
|
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "AlignmentResearch/Llama-3.3-Tiny-Instruct-boolq",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"corda_config": null,
|
| 7 |
+
"eva_config": null,
|
| 8 |
+
"exclude_modules": null,
|
| 9 |
+
"fan_in_fan_out": false,
|
| 10 |
+
"inference_mode": false,
|
| 11 |
+
"init_lora_weights": true,
|
| 12 |
+
"layer_replication": null,
|
| 13 |
+
"layers_pattern": null,
|
| 14 |
+
"layers_to_transform": null,
|
| 15 |
+
"loftq_config": {},
|
| 16 |
+
"lora_alpha": 256,
|
| 17 |
+
"lora_bias": false,
|
| 18 |
+
"lora_dropout": 0.0,
|
| 19 |
+
"megatron_config": null,
|
| 20 |
+
"megatron_core": "megatron.core",
|
| 21 |
+
"modules_to_save": null,
|
| 22 |
+
"peft_type": "LORA",
|
| 23 |
+
"r": 128,
|
| 24 |
+
"rank_pattern": {},
|
| 25 |
+
"revision": null,
|
| 26 |
+
"target_modules": [
|
| 27 |
+
"model.layers.1.mlp.gate_proj",
|
| 28 |
+
"model.layers.1.mlp.down_proj",
|
| 29 |
+
"model.layers.0.self_attn.o_proj",
|
| 30 |
+
"model.layers.1.self_attn.v_proj",
|
| 31 |
+
"model.layers.1.self_attn.q_proj",
|
| 32 |
+
"model.layers.0.mlp.up_proj",
|
| 33 |
+
"model.layers.0.mlp.gate_proj",
|
| 34 |
+
"model.layers.0.mlp.down_proj",
|
| 35 |
+
"model.layers.1.self_attn.o_proj",
|
| 36 |
+
"model.layers.0.self_attn.v_proj",
|
| 37 |
+
"model.layers.1.self_attn.k_proj",
|
| 38 |
+
"model.layers.0.self_attn.k_proj",
|
| 39 |
+
"model.layers.1.mlp.up_proj",
|
| 40 |
+
"model.layers.0.self_attn.q_proj"
|
| 41 |
+
],
|
| 42 |
+
"task_type": "CAUSAL_LM",
|
| 43 |
+
"trainable_token_indices": null,
|
| 44 |
+
"use_dora": false,
|
| 45 |
+
"use_rslora": false
|
| 46 |
+
}
|
step_1112/adapter_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dd5db267dd20fc0da5b1fc20411708b5fc3fcacf94928b581f6ee9692a622212
|
| 3 |
+
size 18098267
|
step_112/adapter_config.json
ADDED
|
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "AlignmentResearch/Llama-3.3-Tiny-Instruct-boolq",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"corda_config": null,
|
| 7 |
+
"eva_config": null,
|
| 8 |
+
"exclude_modules": null,
|
| 9 |
+
"fan_in_fan_out": false,
|
| 10 |
+
"inference_mode": false,
|
| 11 |
+
"init_lora_weights": true,
|
| 12 |
+
"layer_replication": null,
|
| 13 |
+
"layers_pattern": null,
|
| 14 |
+
"layers_to_transform": null,
|
| 15 |
+
"loftq_config": {},
|
| 16 |
+
"lora_alpha": 256,
|
| 17 |
+
"lora_bias": false,
|
| 18 |
+
"lora_dropout": 0.0,
|
| 19 |
+
"megatron_config": null,
|
| 20 |
+
"megatron_core": "megatron.core",
|
| 21 |
+
"modules_to_save": null,
|
| 22 |
+
"peft_type": "LORA",
|
| 23 |
+
"r": 128,
|
| 24 |
+
"rank_pattern": {},
|
| 25 |
+
"revision": null,
|
| 26 |
+
"target_modules": [
|
| 27 |
+
"model.layers.1.mlp.gate_proj",
|
| 28 |
+
"model.layers.1.mlp.down_proj",
|
| 29 |
+
"model.layers.0.self_attn.o_proj",
|
| 30 |
+
"model.layers.1.self_attn.v_proj",
|
| 31 |
+
"model.layers.1.self_attn.q_proj",
|
| 32 |
+
"model.layers.0.mlp.up_proj",
|
| 33 |
+
"model.layers.0.mlp.gate_proj",
|
| 34 |
+
"model.layers.0.mlp.down_proj",
|
| 35 |
+
"model.layers.1.self_attn.o_proj",
|
| 36 |
+
"model.layers.0.self_attn.v_proj",
|
| 37 |
+
"model.layers.1.self_attn.k_proj",
|
| 38 |
+
"model.layers.0.self_attn.k_proj",
|
| 39 |
+
"model.layers.1.mlp.up_proj",
|
| 40 |
+
"model.layers.0.self_attn.q_proj"
|
| 41 |
+
],
|
| 42 |
+
"task_type": "CAUSAL_LM",
|
| 43 |
+
"trainable_token_indices": null,
|
| 44 |
+
"use_dora": false,
|
| 45 |
+
"use_rslora": false
|
| 46 |
+
}
|
step_112/adapter_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b744a915cbfa6335d12a63fa8feb9846c82f2e093c2cd0da047e1680f31867e6
|
| 3 |
+
size 18098267
|
step_1120/adapter_config.json
ADDED
|
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "AlignmentResearch/Llama-3.3-Tiny-Instruct-boolq",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"corda_config": null,
|
| 7 |
+
"eva_config": null,
|
| 8 |
+
"exclude_modules": null,
|
| 9 |
+
"fan_in_fan_out": false,
|
| 10 |
+
"inference_mode": false,
|
| 11 |
+
"init_lora_weights": true,
|
| 12 |
+
"layer_replication": null,
|
| 13 |
+
"layers_pattern": null,
|
| 14 |
+
"layers_to_transform": null,
|
| 15 |
+
"loftq_config": {},
|
| 16 |
+
"lora_alpha": 256,
|
| 17 |
+
"lora_bias": false,
|
| 18 |
+
"lora_dropout": 0.0,
|
| 19 |
+
"megatron_config": null,
|
| 20 |
+
"megatron_core": "megatron.core",
|
| 21 |
+
"modules_to_save": null,
|
| 22 |
+
"peft_type": "LORA",
|
| 23 |
+
"r": 128,
|
| 24 |
+
"rank_pattern": {},
|
| 25 |
+
"revision": null,
|
| 26 |
+
"target_modules": [
|
| 27 |
+
"model.layers.1.mlp.gate_proj",
|
| 28 |
+
"model.layers.1.mlp.down_proj",
|
| 29 |
+
"model.layers.0.self_attn.o_proj",
|
| 30 |
+
"model.layers.1.self_attn.v_proj",
|
| 31 |
+
"model.layers.1.self_attn.q_proj",
|
| 32 |
+
"model.layers.0.mlp.up_proj",
|
| 33 |
+
"model.layers.0.mlp.gate_proj",
|
| 34 |
+
"model.layers.0.mlp.down_proj",
|
| 35 |
+
"model.layers.1.self_attn.o_proj",
|
| 36 |
+
"model.layers.0.self_attn.v_proj",
|
| 37 |
+
"model.layers.1.self_attn.k_proj",
|
| 38 |
+
"model.layers.0.self_attn.k_proj",
|
| 39 |
+
"model.layers.1.mlp.up_proj",
|
| 40 |
+
"model.layers.0.self_attn.q_proj"
|
| 41 |
+
],
|
| 42 |
+
"task_type": "CAUSAL_LM",
|
| 43 |
+
"trainable_token_indices": null,
|
| 44 |
+
"use_dora": false,
|
| 45 |
+
"use_rslora": false
|
| 46 |
+
}
|
step_1120/adapter_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0a5c1c0400c197d5f0be334d183e03d67cc5cde1a66077cdc0f5b0461e52180a
|
| 3 |
+
size 18098267
|
step_1128/adapter_config.json
ADDED
|
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "AlignmentResearch/Llama-3.3-Tiny-Instruct-boolq",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"corda_config": null,
|
| 7 |
+
"eva_config": null,
|
| 8 |
+
"exclude_modules": null,
|
| 9 |
+
"fan_in_fan_out": false,
|
| 10 |
+
"inference_mode": false,
|
| 11 |
+
"init_lora_weights": true,
|
| 12 |
+
"layer_replication": null,
|
| 13 |
+
"layers_pattern": null,
|
| 14 |
+
"layers_to_transform": null,
|
| 15 |
+
"loftq_config": {},
|
| 16 |
+
"lora_alpha": 256,
|
| 17 |
+
"lora_bias": false,
|
| 18 |
+
"lora_dropout": 0.0,
|
| 19 |
+
"megatron_config": null,
|
| 20 |
+
"megatron_core": "megatron.core",
|
| 21 |
+
"modules_to_save": null,
|
| 22 |
+
"peft_type": "LORA",
|
| 23 |
+
"r": 128,
|
| 24 |
+
"rank_pattern": {},
|
| 25 |
+
"revision": null,
|
| 26 |
+
"target_modules": [
|
| 27 |
+
"model.layers.1.mlp.gate_proj",
|
| 28 |
+
"model.layers.1.mlp.down_proj",
|
| 29 |
+
"model.layers.0.self_attn.o_proj",
|
| 30 |
+
"model.layers.1.self_attn.v_proj",
|
| 31 |
+
"model.layers.1.self_attn.q_proj",
|
| 32 |
+
"model.layers.0.mlp.up_proj",
|
| 33 |
+
"model.layers.0.mlp.gate_proj",
|
| 34 |
+
"model.layers.0.mlp.down_proj",
|
| 35 |
+
"model.layers.1.self_attn.o_proj",
|
| 36 |
+
"model.layers.0.self_attn.v_proj",
|
| 37 |
+
"model.layers.1.self_attn.k_proj",
|
| 38 |
+
"model.layers.0.self_attn.k_proj",
|
| 39 |
+
"model.layers.1.mlp.up_proj",
|
| 40 |
+
"model.layers.0.self_attn.q_proj"
|
| 41 |
+
],
|
| 42 |
+
"task_type": "CAUSAL_LM",
|
| 43 |
+
"trainable_token_indices": null,
|
| 44 |
+
"use_dora": false,
|
| 45 |
+
"use_rslora": false
|
| 46 |
+
}
|
step_1128/adapter_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c7437cc53e6cf01271bf34b5f93962e263eb96855debb42a69c2f3fd90ea7de0
|
| 3 |
+
size 18098267
|
step_1136/adapter_config.json
ADDED
|
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "AlignmentResearch/Llama-3.3-Tiny-Instruct-boolq",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"corda_config": null,
|
| 7 |
+
"eva_config": null,
|
| 8 |
+
"exclude_modules": null,
|
| 9 |
+
"fan_in_fan_out": false,
|
| 10 |
+
"inference_mode": false,
|
| 11 |
+
"init_lora_weights": true,
|
| 12 |
+
"layer_replication": null,
|
| 13 |
+
"layers_pattern": null,
|
| 14 |
+
"layers_to_transform": null,
|
| 15 |
+
"loftq_config": {},
|
| 16 |
+
"lora_alpha": 256,
|
| 17 |
+
"lora_bias": false,
|
| 18 |
+
"lora_dropout": 0.0,
|
| 19 |
+
"megatron_config": null,
|
| 20 |
+
"megatron_core": "megatron.core",
|
| 21 |
+
"modules_to_save": null,
|
| 22 |
+
"peft_type": "LORA",
|
| 23 |
+
"r": 128,
|
| 24 |
+
"rank_pattern": {},
|
| 25 |
+
"revision": null,
|
| 26 |
+
"target_modules": [
|
| 27 |
+
"model.layers.1.mlp.gate_proj",
|
| 28 |
+
"model.layers.1.mlp.down_proj",
|
| 29 |
+
"model.layers.0.self_attn.o_proj",
|
| 30 |
+
"model.layers.1.self_attn.v_proj",
|
| 31 |
+
"model.layers.1.self_attn.q_proj",
|
| 32 |
+
"model.layers.0.mlp.up_proj",
|
| 33 |
+
"model.layers.0.mlp.gate_proj",
|
| 34 |
+
"model.layers.0.mlp.down_proj",
|
| 35 |
+
"model.layers.1.self_attn.o_proj",
|
| 36 |
+
"model.layers.0.self_attn.v_proj",
|
| 37 |
+
"model.layers.1.self_attn.k_proj",
|
| 38 |
+
"model.layers.0.self_attn.k_proj",
|
| 39 |
+
"model.layers.1.mlp.up_proj",
|
| 40 |
+
"model.layers.0.self_attn.q_proj"
|
| 41 |
+
],
|
| 42 |
+
"task_type": "CAUSAL_LM",
|
| 43 |
+
"trainable_token_indices": null,
|
| 44 |
+
"use_dora": false,
|
| 45 |
+
"use_rslora": false
|
| 46 |
+
}
|
step_1136/adapter_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:55a1b92bb1559dd4961bf58aa4353bd72913d0480d081ee7fcbf9a82e379cc68
|
| 3 |
+
size 18098267
|
step_1144/adapter_config.json
ADDED
|
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "AlignmentResearch/Llama-3.3-Tiny-Instruct-boolq",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"corda_config": null,
|
| 7 |
+
"eva_config": null,
|
| 8 |
+
"exclude_modules": null,
|
| 9 |
+
"fan_in_fan_out": false,
|
| 10 |
+
"inference_mode": false,
|
| 11 |
+
"init_lora_weights": true,
|
| 12 |
+
"layer_replication": null,
|
| 13 |
+
"layers_pattern": null,
|
| 14 |
+
"layers_to_transform": null,
|
| 15 |
+
"loftq_config": {},
|
| 16 |
+
"lora_alpha": 256,
|
| 17 |
+
"lora_bias": false,
|
| 18 |
+
"lora_dropout": 0.0,
|
| 19 |
+
"megatron_config": null,
|
| 20 |
+
"megatron_core": "megatron.core",
|
| 21 |
+
"modules_to_save": null,
|
| 22 |
+
"peft_type": "LORA",
|
| 23 |
+
"r": 128,
|
| 24 |
+
"rank_pattern": {},
|
| 25 |
+
"revision": null,
|
| 26 |
+
"target_modules": [
|
| 27 |
+
"model.layers.1.mlp.gate_proj",
|
| 28 |
+
"model.layers.1.mlp.down_proj",
|
| 29 |
+
"model.layers.0.self_attn.o_proj",
|
| 30 |
+
"model.layers.1.self_attn.v_proj",
|
| 31 |
+
"model.layers.1.self_attn.q_proj",
|
| 32 |
+
"model.layers.0.mlp.up_proj",
|
| 33 |
+
"model.layers.0.mlp.gate_proj",
|
| 34 |
+
"model.layers.0.mlp.down_proj",
|
| 35 |
+
"model.layers.1.self_attn.o_proj",
|
| 36 |
+
"model.layers.0.self_attn.v_proj",
|
| 37 |
+
"model.layers.1.self_attn.k_proj",
|
| 38 |
+
"model.layers.0.self_attn.k_proj",
|
| 39 |
+
"model.layers.1.mlp.up_proj",
|
| 40 |
+
"model.layers.0.self_attn.q_proj"
|
| 41 |
+
],
|
| 42 |
+
"task_type": "CAUSAL_LM",
|
| 43 |
+
"trainable_token_indices": null,
|
| 44 |
+
"use_dora": false,
|
| 45 |
+
"use_rslora": false
|
| 46 |
+
}
|
step_1144/adapter_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3086cc8cbf006eb447141df61c5fd2ac9a1b29a2e7fe4d2b14887ab4a7dddb8d
|
| 3 |
+
size 18098267
|