aryxn323/vaultagent
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: aryxn323/vaultagent
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-08-05 16:05:17 +08:00
commit df1f21ab66
62 changed files with 15303 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

41
.gitattributes vendored Normal file
View File

@@ -0,0 +1,41 @@
*.7z filter=lfs diff=lfs merge=lfs -text
*.arrow filter=lfs diff=lfs merge=lfs -text
*.bin filter=lfs diff=lfs merge=lfs -text
*.bz2 filter=lfs diff=lfs merge=lfs -text
*.ckpt filter=lfs diff=lfs merge=lfs -text
*.ftz filter=lfs diff=lfs merge=lfs -text
*.gz filter=lfs diff=lfs merge=lfs -text
*.h5 filter=lfs diff=lfs merge=lfs -text
*.joblib filter=lfs diff=lfs merge=lfs -text
*.lfs.* filter=lfs diff=lfs merge=lfs -text
*.mlmodel filter=lfs diff=lfs merge=lfs -text
*.model filter=lfs diff=lfs merge=lfs -text
*.msgpack filter=lfs diff=lfs merge=lfs -text
*.npy filter=lfs diff=lfs merge=lfs -text
*.npz filter=lfs diff=lfs merge=lfs -text
*.onnx filter=lfs diff=lfs merge=lfs -text
*.ot filter=lfs diff=lfs merge=lfs -text
*.parquet filter=lfs diff=lfs merge=lfs -text
*.pb filter=lfs diff=lfs merge=lfs -text
*.pickle filter=lfs diff=lfs merge=lfs -text
*.pkl filter=lfs diff=lfs merge=lfs -text
*.pt filter=lfs diff=lfs merge=lfs -text
*.pth filter=lfs diff=lfs merge=lfs -text
*.rar filter=lfs diff=lfs merge=lfs -text
*.safetensors filter=lfs diff=lfs merge=lfs -text
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
*.tar.* filter=lfs diff=lfs merge=lfs -text
*.tar filter=lfs diff=lfs merge=lfs -text
*.tflite filter=lfs diff=lfs merge=lfs -text
*.tgz filter=lfs diff=lfs merge=lfs -text
*.wasm filter=lfs diff=lfs merge=lfs -text
*.xz filter=lfs diff=lfs merge=lfs -text
*.zip filter=lfs diff=lfs merge=lfs -text
*.zst filter=lfs diff=lfs merge=lfs -text
*tfevents* filter=lfs diff=lfs merge=lfs -text
stage1-sft/checkpoint-123/tokenizer.json filter=lfs diff=lfs merge=lfs -text
stage1-sft/checkpoint-82/tokenizer.json filter=lfs diff=lfs merge=lfs -text
stage1-sft/tokenizer.json filter=lfs diff=lfs merge=lfs -text
stage2-grpo/checkpoint-90/tokenizer.json filter=lfs diff=lfs merge=lfs -text
stage2-grpo/tokenizer.json filter=lfs diff=lfs merge=lfs -text
tokenizer.json filter=lfs diff=lfs merge=lfs -text

12
README.md Normal file
View File

@@ -0,0 +1,12 @@
---
license: apache-2.0
base_model: meta-llama/Meta-Llama-3.1-8B-Instruct
tags:
- text-generation-inference
- llama
- reinforcement-learning
- grpo
pipeline_tag: text-generation
---
# VaultAgent
This is the VaultAgent model, fine-tuned on Llama 3.1 8B Instruct.

109
chat_template.jinja Normal file
View File

@@ -0,0 +1,109 @@
{{- bos_token }}
{%- if custom_tools is defined %}
{%- set tools = custom_tools %}
{%- endif %}
{%- if not tools_in_user_message is defined %}
{%- set tools_in_user_message = true %}
{%- endif %}
{%- if not date_string is defined %}
{%- set date_string = "26 Jul 2024" %}
{%- endif %}
{%- if not tools is defined %}
{%- set tools = none %}
{%- endif %}
{#- This block extracts the system message, so we can slot it into the right place. #}
{%- if messages[0]['role'] == 'system' %}
{%- set system_message = messages[0]['content']|trim %}
{%- set messages = messages[1:] %}
{%- else %}
{%- set system_message = "" %}
{%- endif %}
{#- System message + builtin tools #}
{{- "<|start_header_id|>system<|end_header_id|>\n\n" }}
{%- if builtin_tools is defined or tools is not none %}
{{- "Environment: ipython\n" }}
{%- endif %}
{%- if builtin_tools is defined %}
{{- "Tools: " + builtin_tools | reject('equalto', 'code_interpreter') | join(", ") + "\n\n"}}
{%- endif %}
{{- "Cutting Knowledge Date: December 2023\n" }}
{{- "Today Date: " + date_string + "\n\n" }}
{%- if tools is not none and not tools_in_user_message %}
{{- "You have access to the following functions. To call a function, please respond with JSON for a function call." }}
{{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
{{- "Do not use variables.\n\n" }}
{%- for t in tools %}
{{- t | tojson(indent=4) }}
{{- "\n\n" }}
{%- endfor %}
{%- endif %}
{{- system_message }}
{{- "<|eot_id|>" }}
{#- Custom tools are passed in a user message with some extra guidance #}
{%- if tools_in_user_message and not tools is none %}
{#- Extract the first user message so we can plug it in here #}
{%- if messages | length != 0 %}
{%- set first_user_message = messages[0]['content']|trim %}
{%- set messages = messages[1:] %}
{%- else %}
{{- raise_exception("Cannot put tools in the first user message when there's no first user message!") }}
{%- endif %}
{{- '<|start_header_id|>user<|end_header_id|>\n\n' -}}
{{- "Given the following functions, please respond with a JSON for a function call " }}
{{- "with its proper arguments that best answers the given prompt.\n\n" }}
{{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
{{- "Do not use variables.\n\n" }}
{%- for t in tools %}
{{- t | tojson(indent=4) }}
{{- "\n\n" }}
{%- endfor %}
{{- first_user_message + "<|eot_id|>"}}
{%- endif %}
{%- for message in messages %}
{%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}
{{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' }}
{%- elif 'tool_calls' in message %}
{%- if not message.tool_calls|length == 1 %}
{{- raise_exception("This model only supports single tool-calls at once!") }}
{%- endif %}
{%- set tool_call = message.tool_calls[0].function %}
{%- if builtin_tools is defined and tool_call.name in builtin_tools %}
{{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}
{{- "<|python_tag|>" + tool_call.name + ".call(" }}
{%- for arg_name, arg_val in tool_call.arguments | items %}
{{- arg_name + '="' + arg_val + '"' }}
{%- if not loop.last %}
{{- ", " }}
{%- endif %}
{%- endfor %}
{{- ")" }}
{%- else %}
{{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}
{{- '{"name": "' + tool_call.name + '", ' }}
{{- '"parameters": ' }}
{{- tool_call.arguments | tojson }}
{{- "}" }}
{%- endif %}
{%- if builtin_tools is defined %}
{#- This means we're in ipython mode #}
{{- "<|eom_id|>" }}
{%- else %}
{{- "<|eot_id|>" }}
{%- endif %}
{%- elif message.role == "tool" or message.role == "ipython" %}
{{- "<|start_header_id|>ipython<|end_header_id|>\n\n" }}
{%- if message.content is mapping or message.content is iterable %}
{{- message.content | tojson }}
{%- else %}
{{- message.content }}
{%- endif %}
{{- "<|eot_id|>" }}
{%- endif %}
{%- endfor %}
{%- if add_generation_prompt %}
{{- '<|start_header_id|>assistant<|end_header_id|>\n\n' }}
{%- endif %}

37
config.json Normal file
View File

@@ -0,0 +1,37 @@
{
"architectures": [
"LlamaForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 128000,
"torch_dtype": "bfloat16",
"eos_token_id": 128009,
"head_dim": 128,
"hidden_act": "silu",
"hidden_size": 4096,
"initializer_range": 0.02,
"intermediate_size": 14336,
"max_position_embeddings": 131072,
"mlp_bias": false,
"model_type": "llama",
"num_attention_heads": 32,
"num_hidden_layers": 32,
"num_key_value_heads": 8,
"pad_token_id": 128004,
"pretraining_tp": 1,
"rms_norm_eps": 1e-05,
"rope_parameters": {
"factor": 8.0,
"high_freq_factor": 4.0,
"low_freq_factor": 1.0,
"original_max_position_embeddings": 8192,
"rope_theta": 500000.0,
"rope_type": "llama3"
},
"tie_word_embeddings": false,
"unsloth_fixed": true,
"unsloth_version": "2026.6.9",
"use_cache": false,
"vocab_size": 128256
}

14
generation_config.json Normal file
View File

@@ -0,0 +1,14 @@
{
"bos_token_id": 128000,
"do_sample": true,
"eos_token_id": [
128001,
128008,
128009
],
"max_length": 131072,
"pad_token_id": 128004,
"temperature": 0.6,
"top_p": 0.9,
"transformers_version": "5.5.0"
}

3
model-00001-of-00004.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:654b0529d6c1c7fe75896c66f801dca1d7d60a5d2fc7763e9e386e33bac61d33
size 4976698672

3
model-00002-of-00004.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:2af0e6a6bc3e0c23573b2fa1f18e0e35d2c858302566767a68b264ccb7093102
size 4999802720

3
model-00003-of-00004.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:c2b43418670a82068455235dc062bacb091df72e9b0cc614f3679809c1bc0cbd
size 4915916176

3
model-00004-of-00004.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:2853b1dce09f3018a0eb2dd03a3e4ad9a2f637a53a676a6d5b58b6f5392bb2c6
size 1168138808

298
model.safetensors.index.json Normal file
View File

@@ -0,0 +1,298 @@
{
"metadata": {
"total_size": 16060522496
},
"weight_map": {
"lm_head.weight": "model-00004-of-00004.safetensors",
"model.embed_tokens.weight": "model-00001-of-00004.safetensors",
"model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
"model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
"model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
"model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
"model.norm.weight": "model-00004-of-00004.safetensors"
}
}

63
stage1-sft/README.md Normal file
View File

@@ -0,0 +1,63 @@
---
base_model: unsloth/llama-3.1-8b-instruct-bnb-4bit
library_name: peft
model_name: stage1-sft
tags:
- base_model:adapter:unsloth/llama-3.1-8b-instruct-bnb-4bit
- lora
- sft
- transformers
- trl
- unsloth
licence: license
pipeline_tag: text-generation
---
# Model Card for stage1-sft
This model is a fine-tuned version of [unsloth/llama-3.1-8b-instruct-bnb-4bit](https://huggingface.co/unsloth/llama-3.1-8b-instruct-bnb-4bit).
It has been trained using [TRL](https://github.com/huggingface/trl).
## Quick start
```python
from transformers import pipeline
question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
generator = pipeline("text-generation", model="None", device="cuda")
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
print(output["generated_text"])
```
## Training procedure
This model was trained with SFT.
### Framework versions
- PEFT 0.19.1
- TRL: 0.24.0
- Transformers: 5.5.0
- Pytorch: 2.10.0+cu128
- Datasets: 4.3.0
- Tokenizers: 0.22.2
## Citations
Cite TRL as:
```bibtex
@misc{vonwerra2022trl,
title = {{TRL: Transformer Reinforcement Learning}},
author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
year = 2020,
journal = {GitHub repository},
publisher = {GitHub},
howpublished = {\url{https://github.com/huggingface/trl}}
}
```

52
stage1-sft/adapter_config.json Normal file
View File

@@ -0,0 +1,52 @@
{
"alora_invocation_tokens": null,
"alpha_pattern": {},
"arrow_config": null,
"auto_mapping": {
"base_model_class": "LlamaForCausalLM",
"parent_library": "transformers.models.llama.modeling_llama",
"unsloth_fixed": true
},
"base_model_name_or_path": "unsloth/llama-3.1-8b-instruct-bnb-4bit",
"bias": "none",
"corda_config": null,
"ensure_weight_tying": false,
"eva_config": null,
"exclude_modules": null,
"fan_in_fan_out": false,
"inference_mode": true,
"init_lora_weights": true,
"layer_replication": null,
"layers_pattern": null,
"layers_to_transform": null,
"loftq_config": {},
"lora_alpha": 64,
"lora_bias": false,
"lora_dropout": 0.05,
"lora_ga_config": null,
"megatron_config": null,
"megatron_core": "megatron.core",
"modules_to_save": null,
"peft_type": "LORA",
"peft_version": "0.19.1",
"qalora_group_size": 16,
"r": 32,
"rank_pattern": {},
"revision": null,
"target_modules": [
"down_proj",
"up_proj",
"k_proj",
"o_proj",
"q_proj",
"v_proj",
"gate_proj"
],
"target_parameters": null,
"task_type": "CAUSAL_LM",
"trainable_token_indices": null,
"use_bdlora": null,
"use_dora": false,
"use_qalora": false,
"use_rslora": false
}

3
stage1-sft/adapter_model.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:1923fc5740f8e2206b488ac3d937fdccbc09dc2882f041c6bb73e5c397a91679
size 335604696

109
stage1-sft/chat_template.jinja Normal file
View File

@@ -0,0 +1,109 @@
{{- bos_token }}
{%- if custom_tools is defined %}
{%- set tools = custom_tools %}
{%- endif %}
{%- if not tools_in_user_message is defined %}
{%- set tools_in_user_message = true %}
{%- endif %}
{%- if not date_string is defined %}
{%- set date_string = "26 Jul 2024" %}
{%- endif %}
{%- if not tools is defined %}
{%- set tools = none %}
{%- endif %}
{#- This block extracts the system message, so we can slot it into the right place. #}
{%- if messages[0]['role'] == 'system' %}
{%- set system_message = messages[0]['content']|trim %}
{%- set messages = messages[1:] %}
{%- else %}
{%- set system_message = "" %}
{%- endif %}
{#- System message + builtin tools #}
{{- "<|start_header_id|>system<|end_header_id|>\n\n" }}
{%- if builtin_tools is defined or tools is not none %}
{{- "Environment: ipython\n" }}
{%- endif %}
{%- if builtin_tools is defined %}
{{- "Tools: " + builtin_tools | reject('equalto', 'code_interpreter') | join(", ") + "\n\n"}}
{%- endif %}
{{- "Cutting Knowledge Date: December 2023\n" }}
{{- "Today Date: " + date_string + "\n\n" }}
{%- if tools is not none and not tools_in_user_message %}
{{- "You have access to the following functions. To call a function, please respond with JSON for a function call." }}
{{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
{{- "Do not use variables.\n\n" }}
{%- for t in tools %}
{{- t | tojson(indent=4) }}
{{- "\n\n" }}
{%- endfor %}
{%- endif %}
{{- system_message }}
{{- "<|eot_id|>" }}
{#- Custom tools are passed in a user message with some extra guidance #}
{%- if tools_in_user_message and not tools is none %}
{#- Extract the first user message so we can plug it in here #}
{%- if messages | length != 0 %}
{%- set first_user_message = messages[0]['content']|trim %}
{%- set messages = messages[1:] %}
{%- else %}
{{- raise_exception("Cannot put tools in the first user message when there's no first user message!") }}
{%- endif %}
{{- '<|start_header_id|>user<|end_header_id|>\n\n' -}}
{{- "Given the following functions, please respond with a JSON for a function call " }}
{{- "with its proper arguments that best answers the given prompt.\n\n" }}
{{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
{{- "Do not use variables.\n\n" }}
{%- for t in tools %}
{{- t | tojson(indent=4) }}
{{- "\n\n" }}
{%- endfor %}
{{- first_user_message + "<|eot_id|>"}}
{%- endif %}
{%- for message in messages %}
{%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}
{{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' }}
{%- elif 'tool_calls' in message %}
{%- if not message.tool_calls|length == 1 %}
{{- raise_exception("This model only supports single tool-calls at once!") }}
{%- endif %}
{%- set tool_call = message.tool_calls[0].function %}
{%- if builtin_tools is defined and tool_call.name in builtin_tools %}
{{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}
{{- "<|python_tag|>" + tool_call.name + ".call(" }}
{%- for arg_name, arg_val in tool_call.arguments | items %}
{{- arg_name + '="' + arg_val + '"' }}
{%- if not loop.last %}
{{- ", " }}
{%- endif %}
{%- endfor %}
{{- ")" }}
{%- else %}
{{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}
{{- '{"name": "' + tool_call.name + '", ' }}
{{- '"parameters": ' }}
{{- tool_call.arguments | tojson }}
{{- "}" }}
{%- endif %}
{%- if builtin_tools is defined %}
{#- This means we're in ipython mode #}
{{- "<|eom_id|>" }}
{%- else %}
{{- "<|eot_id|>" }}
{%- endif %}
{%- elif message.role == "tool" or message.role == "ipython" %}
{{- "<|start_header_id|>ipython<|end_header_id|>\n\n" }}
{%- if message.content is mapping or message.content is iterable %}
{{- message.content | tojson }}
{%- else %}
{{- message.content }}
{%- endif %}
{{- "<|eot_id|>" }}
{%- endif %}
{%- endfor %}
{%- if add_generation_prompt %}
{{- '<|start_header_id|>assistant<|end_header_id|>\n\n' }}
{%- endif %}

210
stage1-sft/checkpoint-123/README.md Normal file
View File

@@ -0,0 +1,210 @@
---
base_model: unsloth/llama-3.1-8b-instruct-bnb-4bit
library_name: peft
pipeline_tag: text-generation
tags:
- base_model:adapter:unsloth/llama-3.1-8b-instruct-bnb-4bit
- lora
- sft
- transformers
- trl
- unsloth
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
### Framework versions
- PEFT 0.19.1

52
stage1-sft/checkpoint-123/adapter_config.json Normal file
View File

@@ -0,0 +1,52 @@
{
"alora_invocation_tokens": null,
"alpha_pattern": {},
"arrow_config": null,
"auto_mapping": {
"base_model_class": "LlamaForCausalLM",
"parent_library": "transformers.models.llama.modeling_llama",
"unsloth_fixed": true
},
"base_model_name_or_path": "unsloth/llama-3.1-8b-instruct-bnb-4bit",
"bias": "none",
"corda_config": null,
"ensure_weight_tying": false,
"eva_config": null,
"exclude_modules": null,
"fan_in_fan_out": false,
"inference_mode": true,
"init_lora_weights": true,
"layer_replication": null,
"layers_pattern": null,
"layers_to_transform": null,
"loftq_config": {},
"lora_alpha": 64,
"lora_bias": false,
"lora_dropout": 0.05,
"lora_ga_config": null,
"megatron_config": null,
"megatron_core": "megatron.core",
"modules_to_save": null,
"peft_type": "LORA",
"peft_version": "0.19.1",
"qalora_group_size": 16,
"r": 32,
"rank_pattern": {},
"revision": null,
"target_modules": [
"down_proj",
"up_proj",
"k_proj",
"o_proj",
"q_proj",
"v_proj",
"gate_proj"
],
"target_parameters": null,
"task_type": "CAUSAL_LM",
"trainable_token_indices": null,
"use_bdlora": null,
"use_dora": false,
"use_qalora": false,
"use_rslora": false
}

3
stage1-sft/checkpoint-123/adapter_model.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:1923fc5740f8e2206b488ac3d937fdccbc09dc2882f041c6bb73e5c397a91679
size 335604696

109
stage1-sft/checkpoint-123/chat_template.jinja Normal file
View File

@@ -0,0 +1,109 @@
{{- bos_token }}
{%- if custom_tools is defined %}
{%- set tools = custom_tools %}
{%- endif %}
{%- if not tools_in_user_message is defined %}
{%- set tools_in_user_message = true %}
{%- endif %}
{%- if not date_string is defined %}
{%- set date_string = "26 Jul 2024" %}
{%- endif %}
{%- if not tools is defined %}
{%- set tools = none %}
{%- endif %}
{#- This block extracts the system message, so we can slot it into the right place. #}
{%- if messages[0]['role'] == 'system' %}
{%- set system_message = messages[0]['content']|trim %}
{%- set messages = messages[1:] %}
{%- else %}
{%- set system_message = "" %}
{%- endif %}
{#- System message + builtin tools #}
{{- "<|start_header_id|>system<|end_header_id|>\n\n" }}
{%- if builtin_tools is defined or tools is not none %}
{{- "Environment: ipython\n" }}
{%- endif %}
{%- if builtin_tools is defined %}
{{- "Tools: " + builtin_tools | reject('equalto', 'code_interpreter') | join(", ") + "\n\n"}}
{%- endif %}
{{- "Cutting Knowledge Date: December 2023\n" }}
{{- "Today Date: " + date_string + "\n\n" }}
{%- if tools is not none and not tools_in_user_message %}
{{- "You have access to the following functions. To call a function, please respond with JSON for a function call." }}
{{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
{{- "Do not use variables.\n\n" }}
{%- for t in tools %}
{{- t | tojson(indent=4) }}
{{- "\n\n" }}
{%- endfor %}
{%- endif %}
{{- system_message }}
{{- "<|eot_id|>" }}
{#- Custom tools are passed in a user message with some extra guidance #}
{%- if tools_in_user_message and not tools is none %}
{#- Extract the first user message so we can plug it in here #}
{%- if messages | length != 0 %}
{%- set first_user_message = messages[0]['content']|trim %}
{%- set messages = messages[1:] %}
{%- else %}
{{- raise_exception("Cannot put tools in the first user message when there's no first user message!") }}
{%- endif %}
{{- '<|start_header_id|>user<|end_header_id|>\n\n' -}}
{{- "Given the following functions, please respond with a JSON for a function call " }}
{{- "with its proper arguments that best answers the given prompt.\n\n" }}
{{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
{{- "Do not use variables.\n\n" }}
{%- for t in tools %}
{{- t | tojson(indent=4) }}
{{- "\n\n" }}
{%- endfor %}
{{- first_user_message + "<|eot_id|>"}}
{%- endif %}
{%- for message in messages %}
{%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}
{{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' }}
{%- elif 'tool_calls' in message %}
{%- if not message.tool_calls|length == 1 %}
{{- raise_exception("This model only supports single tool-calls at once!") }}
{%- endif %}
{%- set tool_call = message.tool_calls[0].function %}
{%- if builtin_tools is defined and tool_call.name in builtin_tools %}
{{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}
{{- "<|python_tag|>" + tool_call.name + ".call(" }}
{%- for arg_name, arg_val in tool_call.arguments | items %}
{{- arg_name + '="' + arg_val + '"' }}
{%- if not loop.last %}
{{- ", " }}
{%- endif %}
{%- endfor %}
{{- ")" }}
{%- else %}
{{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}
{{- '{"name": "' + tool_call.name + '", ' }}
{{- '"parameters": ' }}
{{- tool_call.arguments | tojson }}
{{- "}" }}
{%- endif %}
{%- if builtin_tools is defined %}
{#- This means we're in ipython mode #}
{{- "<|eom_id|>" }}
{%- else %}
{{- "<|eot_id|>" }}
{%- endif %}
{%- elif message.role == "tool" or message.role == "ipython" %}
{{- "<|start_header_id|>ipython<|end_header_id|>\n\n" }}
{%- if message.content is mapping or message.content is iterable %}
{{- message.content | tojson }}
{%- else %}
{{- message.content }}
{%- endif %}
{{- "<|eot_id|>" }}
{%- endif %}
{%- endfor %}
{%- if add_generation_prompt %}
{{- '<|start_header_id|>assistant<|end_header_id|>\n\n' }}
{%- endif %}

3
stage1-sft/checkpoint-123/optimizer.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:c9016db3c4cfda1106af2147a2178a86a61e0b40fc96d4a6a7f9d1d7cb6794bb
size 170925029

3
stage1-sft/checkpoint-123/rng_state.pth Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:fcb83bc864effafc363bd8229176c8fe863b8662d21b12ab9f406c0c212d3711
size 14645

3
stage1-sft/checkpoint-123/scaler.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:000d3c97163a196c971db119da9d64fc6e0161b9e1f5c073d76ed8f6dc020e45
size 1383

3
stage1-sft/checkpoint-123/scheduler.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:562e0fad31141590d8b1dde06be733f12704d79d83c4895f5ece63a05bde994f
size 1465

BIN
stage1-sft/checkpoint-123/tokenizer.json (Stored with Git LFS) Normal file
View File

Binary file not shown.

2068
stage1-sft/checkpoint-123/tokenizer_config.json Normal file
View File

File diff suppressed because it is too large Load Diff

258
stage1-sft/checkpoint-123/trainer_state.json Normal file
View File

@@ -0,0 +1,258 @@
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 3.0,
"eval_steps": 20,
"global_step": 123,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.12345679012345678,
"grad_norm": 1.2859091758728027,
"learning_rate": 6.153846153846155e-05,
"loss": 1.9271413803100585,
"step": 5
},
{
"epoch": 0.24691358024691357,
"grad_norm": 1.5679012537002563,
"learning_rate": 0.00013846153846153847,
"loss": 1.0801850318908692,
"step": 10
},
{
"epoch": 0.37037037037037035,
"grad_norm": 1.2908324003219604,
"learning_rate": 0.00019995921928281894,
"loss": 0.3495574951171875,
"step": 15
},
{
"epoch": 0.49382716049382713,
"grad_norm": 0.7217243313789368,
"learning_rate": 0.00019853538358476932,
"loss": 0.16377259492874147,
"step": 20
},
{
"epoch": 0.49382716049382713,
"eval_loss": 0.11601115763187408,
"eval_runtime": 31.3631,
"eval_samples_per_second": 1.148,
"eval_steps_per_second": 1.148,
"step": 20
},
{
"epoch": 0.6172839506172839,
"grad_norm": 0.3617861270904541,
"learning_rate": 0.00019510565162951537,
"loss": 0.09877997040748596,
"step": 25
},
{
"epoch": 0.7407407407407407,
"grad_norm": 0.2274777591228485,
"learning_rate": 0.00018973984286913584,
"loss": 0.07389195561408997,
"step": 30
},
{
"epoch": 0.8641975308641975,
"grad_norm": 0.27818748354911804,
"learning_rate": 0.0001825471896962774,
"loss": 0.05940691232681274,
"step": 35
},
{
"epoch": 0.9876543209876543,
"grad_norm": 0.3490578234195709,
"learning_rate": 0.0001736741137876405,
"loss": 0.061438959836959836,
"step": 40
},
{
"epoch": 0.9876543209876543,
"eval_loss": 0.0585002563893795,
"eval_runtime": 31.3163,
"eval_samples_per_second": 1.15,
"eval_steps_per_second": 1.15,
"step": 40
},
{
"epoch": 1.0987654320987654,
"grad_norm": 0.3012445569038391,
"learning_rate": 0.00016330124538088705,
"loss": 0.0581305980682373,
"step": 45
},
{
"epoch": 1.2222222222222223,
"grad_norm": 0.11500085145235062,
"learning_rate": 0.0001516397461638962,
"loss": 0.052752095460891726,
"step": 50
},
{
"epoch": 1.345679012345679,
"grad_norm": 0.269403338432312,
"learning_rate": 0.00013892701063173918,
"loss": 0.055076193809509275,
"step": 55
},
{
"epoch": 1.4691358024691357,
"grad_norm": 0.09471635520458221,
"learning_rate": 0.00012542183341934872,
"loss": 0.05141226053237915,
"step": 60
},
{
"epoch": 1.4691358024691357,
"eval_loss": 0.05293593928217888,
"eval_runtime": 30.9791,
"eval_samples_per_second": 1.162,
"eval_steps_per_second": 1.162,
"step": 60
},
{
"epoch": 1.5925925925925926,
"grad_norm": 0.10104531794786453,
"learning_rate": 0.00011139914098905406,
"loss": 0.051540708541870116,
"step": 65
},
{
"epoch": 1.7160493827160495,
"grad_norm": 0.1660510152578354,
"learning_rate": 9.71443949206304e-05,
"loss": 0.05324012041091919,
"step": 70
},
{
"epoch": 1.8395061728395061,
"grad_norm": 0.08400571346282959,
"learning_rate": 8.294778073673762e-05,
"loss": 0.05077423453330994,
"step": 75
},
{
"epoch": 1.9629629629629628,
"grad_norm": 0.10372541099786758,
"learning_rate": 6.909830056250527e-05,
"loss": 0.053344011306762695,
"step": 80
},
{
"epoch": 1.9629629629629628,
"eval_loss": 0.049684152007102966,
"eval_runtime": 30.9982,
"eval_samples_per_second": 1.161,
"eval_steps_per_second": 1.161,
"step": 80
},
{
"epoch": 2.074074074074074,
"grad_norm": 0.10688848048448563,
"learning_rate": 5.5877889875677845e-05,
"loss": 0.04975573420524597,
"step": 85
},
{
"epoch": 2.197530864197531,
"grad_norm": 0.09048020094633102,
"learning_rate": 4.355567811332311e-05,
"loss": 0.04622272253036499,
"step": 90
},
{
"epoch": 2.3209876543209877,
"grad_norm": 0.10293108224868774,
"learning_rate": 3.238250997259808e-05,
"loss": 0.0488657683134079,
"step": 95
},
{
"epoch": 2.4444444444444446,
"grad_norm": 0.0953356996178627,
"learning_rate": 2.2585838936091754e-05,
"loss": 0.04651863873004913,
"step": 100
},
{
"epoch": 2.4444444444444446,
"eval_loss": 0.04865232855081558,
"eval_runtime": 31.2086,
"eval_samples_per_second": 1.154,
"eval_steps_per_second": 1.154,
"step": 100
},
{
"epoch": 2.567901234567901,
"grad_norm": 0.09343387186527252,
"learning_rate": 1.4365096974841108e-05,
"loss": 0.04507680833339691,
"step": 105
},
{
"epoch": 2.691358024691358,
"grad_norm": 0.08703113347291946,
"learning_rate": 7.887634688515e-06,
"loss": 0.046429067850112915,
"step": 110
},
{
"epoch": 2.814814814814815,
"grad_norm": 0.10216418653726578,
"learning_rate": 3.2853145298042953e-06,
"loss": 0.045730876922607425,
"step": 115
},
{
"epoch": 2.9382716049382713,
"grad_norm": 0.08843164891004562,
"learning_rate": 6.518264651449779e-07,
"loss": 0.04855655431747437,
"step": 120
},
{
"epoch": 2.9382716049382713,
"eval_loss": 0.048195596784353256,
"eval_runtime": 31.1824,
"eval_samples_per_second": 1.154,
"eval_steps_per_second": 1.154,
"step": 120
},
{
"epoch": 3.0,
"eval_loss": 0.04818538948893547,
"eval_runtime": 31.1049,
"eval_samples_per_second": 1.157,
"eval_steps_per_second": 1.157,
"step": 123
}
],
"logging_steps": 5,
"max_steps": 123,
"num_input_tokens_seen": 0,
"num_train_epochs": 3,
"save_steps": 500,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 2.273314773204173e+16,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}

3
stage1-sft/checkpoint-123/training_args.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:35f21193165fb35ee40dfb67dcb04982fd2affbd9c865841951ae75e975e484a
size 5777

210
stage1-sft/checkpoint-82/README.md Normal file
View File

@@ -0,0 +1,210 @@
---
base_model: unsloth/llama-3.1-8b-instruct-bnb-4bit
library_name: peft
pipeline_tag: text-generation
tags:
- base_model:adapter:unsloth/llama-3.1-8b-instruct-bnb-4bit
- lora
- sft
- transformers
- trl
- unsloth
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
### Framework versions
- PEFT 0.19.1

52
stage1-sft/checkpoint-82/adapter_config.json Normal file
View File

@@ -0,0 +1,52 @@
{
"alora_invocation_tokens": null,
"alpha_pattern": {},
"arrow_config": null,
"auto_mapping": {
"base_model_class": "LlamaForCausalLM",
"parent_library": "transformers.models.llama.modeling_llama",
"unsloth_fixed": true
},
"base_model_name_or_path": "unsloth/llama-3.1-8b-instruct-bnb-4bit",
"bias": "none",
"corda_config": null,
"ensure_weight_tying": false,
"eva_config": null,
"exclude_modules": null,
"fan_in_fan_out": false,
"inference_mode": true,
"init_lora_weights": true,
"layer_replication": null,
"layers_pattern": null,
"layers_to_transform": null,
"loftq_config": {},
"lora_alpha": 64,
"lora_bias": false,
"lora_dropout": 0.05,
"lora_ga_config": null,
"megatron_config": null,
"megatron_core": "megatron.core",
"modules_to_save": null,
"peft_type": "LORA",
"peft_version": "0.19.1",
"qalora_group_size": 16,
"r": 32,
"rank_pattern": {},
"revision": null,
"target_modules": [
"down_proj",
"up_proj",
"k_proj",
"o_proj",
"q_proj",
"v_proj",
"gate_proj"
],
"target_parameters": null,
"task_type": "CAUSAL_LM",
"trainable_token_indices": null,
"use_bdlora": null,
"use_dora": false,
"use_qalora": false,
"use_rslora": false
}

3
stage1-sft/checkpoint-82/adapter_model.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b46704382fdd2d1c5c250e67a18bf1836e422df24ad7bd91322fb7498e84dee6
size 335604696

109
stage1-sft/checkpoint-82/chat_template.jinja Normal file
View File

@@ -0,0 +1,109 @@
{{- bos_token }}
{%- if custom_tools is defined %}
{%- set tools = custom_tools %}
{%- endif %}
{%- if not tools_in_user_message is defined %}
{%- set tools_in_user_message = true %}
{%- endif %}
{%- if not date_string is defined %}
{%- set date_string = "26 Jul 2024" %}
{%- endif %}
{%- if not tools is defined %}
{%- set tools = none %}
{%- endif %}
{#- This block extracts the system message, so we can slot it into the right place. #}
{%- if messages[0]['role'] == 'system' %}
{%- set system_message = messages[0]['content']|trim %}
{%- set messages = messages[1:] %}
{%- else %}
{%- set system_message = "" %}
{%- endif %}
{#- System message + builtin tools #}
{{- "<|start_header_id|>system<|end_header_id|>\n\n" }}
{%- if builtin_tools is defined or tools is not none %}
{{- "Environment: ipython\n" }}
{%- endif %}
{%- if builtin_tools is defined %}
{{- "Tools: " + builtin_tools | reject('equalto', 'code_interpreter') | join(", ") + "\n\n"}}
{%- endif %}
{{- "Cutting Knowledge Date: December 2023\n" }}
{{- "Today Date: " + date_string + "\n\n" }}
{%- if tools is not none and not tools_in_user_message %}
{{- "You have access to the following functions. To call a function, please respond with JSON for a function call." }}
{{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
{{- "Do not use variables.\n\n" }}
{%- for t in tools %}
{{- t | tojson(indent=4) }}
{{- "\n\n" }}
{%- endfor %}
{%- endif %}
{{- system_message }}
{{- "<|eot_id|>" }}
{#- Custom tools are passed in a user message with some extra guidance #}
{%- if tools_in_user_message and not tools is none %}
{#- Extract the first user message so we can plug it in here #}
{%- if messages | length != 0 %}
{%- set first_user_message = messages[0]['content']|trim %}
{%- set messages = messages[1:] %}
{%- else %}
{{- raise_exception("Cannot put tools in the first user message when there's no first user message!") }}
{%- endif %}
{{- '<|start_header_id|>user<|end_header_id|>\n\n' -}}
{{- "Given the following functions, please respond with a JSON for a function call " }}
{{- "with its proper arguments that best answers the given prompt.\n\n" }}
{{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
{{- "Do not use variables.\n\n" }}
{%- for t in tools %}
{{- t | tojson(indent=4) }}
{{- "\n\n" }}
{%- endfor %}
{{- first_user_message + "<|eot_id|>"}}
{%- endif %}
{%- for message in messages %}
{%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}
{{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' }}
{%- elif 'tool_calls' in message %}
{%- if not message.tool_calls|length == 1 %}
{{- raise_exception("This model only supports single tool-calls at once!") }}
{%- endif %}
{%- set tool_call = message.tool_calls[0].function %}
{%- if builtin_tools is defined and tool_call.name in builtin_tools %}
{{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}
{{- "<|python_tag|>" + tool_call.name + ".call(" }}
{%- for arg_name, arg_val in tool_call.arguments | items %}
{{- arg_name + '="' + arg_val + '"' }}
{%- if not loop.last %}
{{- ", " }}
{%- endif %}
{%- endfor %}
{{- ")" }}
{%- else %}
{{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}
{{- '{"name": "' + tool_call.name + '", ' }}
{{- '"parameters": ' }}
{{- tool_call.arguments | tojson }}
{{- "}" }}
{%- endif %}
{%- if builtin_tools is defined %}
{#- This means we're in ipython mode #}
{{- "<|eom_id|>" }}
{%- else %}
{{- "<|eot_id|>" }}
{%- endif %}
{%- elif message.role == "tool" or message.role == "ipython" %}
{{- "<|start_header_id|>ipython<|end_header_id|>\n\n" }}
{%- if message.content is mapping or message.content is iterable %}
{{- message.content | tojson }}
{%- else %}
{{- message.content }}
{%- endif %}
{{- "<|eot_id|>" }}
{%- endif %}
{%- endfor %}
{%- if add_generation_prompt %}
{{- '<|start_header_id|>assistant<|end_header_id|>\n\n' }}
{%- endif %}

3
stage1-sft/checkpoint-82/optimizer.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:6f0d9d58f57b1790be8b6ecdb6d67a77289ce1b07783c9a55685be3264084aa9
size 170925029

3
stage1-sft/checkpoint-82/rng_state.pth Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:0e65c3eb84d549541d56e5a170dbb45492cfbf9994b239ef287bb543f28e1e83
size 14645

3
stage1-sft/checkpoint-82/scaler.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:3011c3980b7b6e77f31ea70ef726a3c9b31792876b41648eec1b72466a39235a
size 1383

3
stage1-sft/checkpoint-82/scheduler.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:80a83d2b534f719873fe6d970948d4fa96db0a8fde9b749bb75e2a7bab5a0504
size 1465

BIN
stage1-sft/checkpoint-82/tokenizer.json (Stored with Git LFS) Normal file
View File

Binary file not shown.

2068
stage1-sft/checkpoint-82/tokenizer_config.json Normal file
View File

File diff suppressed because it is too large Load Diff

178
stage1-sft/checkpoint-82/trainer_state.json Normal file
View File

@@ -0,0 +1,178 @@
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 2.0,
"eval_steps": 20,
"global_step": 82,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.12345679012345678,
"grad_norm": 1.2859091758728027,
"learning_rate": 6.153846153846155e-05,
"loss": 1.9271413803100585,
"step": 5
},
{
"epoch": 0.24691358024691357,
"grad_norm": 1.5679012537002563,
"learning_rate": 0.00013846153846153847,
"loss": 1.0801850318908692,
"step": 10
},
{
"epoch": 0.37037037037037035,
"grad_norm": 1.2908324003219604,
"learning_rate": 0.00019995921928281894,
"loss": 0.3495574951171875,
"step": 15
},
{
"epoch": 0.49382716049382713,
"grad_norm": 0.7217243313789368,
"learning_rate": 0.00019853538358476932,
"loss": 0.16377259492874147,
"step": 20
},
{
"epoch": 0.49382716049382713,
"eval_loss": 0.11601115763187408,
"eval_runtime": 31.3631,
"eval_samples_per_second": 1.148,
"eval_steps_per_second": 1.148,
"step": 20
},
{
"epoch": 0.6172839506172839,
"grad_norm": 0.3617861270904541,
"learning_rate": 0.00019510565162951537,
"loss": 0.09877997040748596,
"step": 25
},
{
"epoch": 0.7407407407407407,
"grad_norm": 0.2274777591228485,
"learning_rate": 0.00018973984286913584,
"loss": 0.07389195561408997,
"step": 30
},
{
"epoch": 0.8641975308641975,
"grad_norm": 0.27818748354911804,
"learning_rate": 0.0001825471896962774,
"loss": 0.05940691232681274,
"step": 35
},
{
"epoch": 0.9876543209876543,
"grad_norm": 0.3490578234195709,
"learning_rate": 0.0001736741137876405,
"loss": 0.061438959836959836,
"step": 40
},
{
"epoch": 0.9876543209876543,
"eval_loss": 0.0585002563893795,
"eval_runtime": 31.3163,
"eval_samples_per_second": 1.15,
"eval_steps_per_second": 1.15,
"step": 40
},
{
"epoch": 1.0987654320987654,
"grad_norm": 0.3012445569038391,
"learning_rate": 0.00016330124538088705,
"loss": 0.0581305980682373,
"step": 45
},
{
"epoch": 1.2222222222222223,
"grad_norm": 0.11500085145235062,
"learning_rate": 0.0001516397461638962,
"loss": 0.052752095460891726,
"step": 50
},
{
"epoch": 1.345679012345679,
"grad_norm": 0.269403338432312,
"learning_rate": 0.00013892701063173918,
"loss": 0.055076193809509275,
"step": 55
},
{
"epoch": 1.4691358024691357,
"grad_norm": 0.09471635520458221,
"learning_rate": 0.00012542183341934872,
"loss": 0.05141226053237915,
"step": 60
},
{
"epoch": 1.4691358024691357,
"eval_loss": 0.05293593928217888,
"eval_runtime": 30.9791,
"eval_samples_per_second": 1.162,
"eval_steps_per_second": 1.162,
"step": 60
},
{
"epoch": 1.5925925925925926,
"grad_norm": 0.10104531794786453,
"learning_rate": 0.00011139914098905406,
"loss": 0.051540708541870116,
"step": 65
},
{
"epoch": 1.7160493827160495,
"grad_norm": 0.1660510152578354,
"learning_rate": 9.71443949206304e-05,
"loss": 0.05324012041091919,
"step": 70
},
{
"epoch": 1.8395061728395061,
"grad_norm": 0.08400571346282959,
"learning_rate": 8.294778073673762e-05,
"loss": 0.05077423453330994,
"step": 75
},
{
"epoch": 1.9629629629629628,
"grad_norm": 0.10372541099786758,
"learning_rate": 6.909830056250527e-05,
"loss": 0.053344011306762695,
"step": 80
},
{
"epoch": 1.9629629629629628,
"eval_loss": 0.049684152007102966,
"eval_runtime": 30.9982,
"eval_samples_per_second": 1.161,
"eval_steps_per_second": 1.161,
"step": 80
}
],
"logging_steps": 5,
"max_steps": 123,
"num_input_tokens_seen": 0,
"num_train_epochs": 3,
"save_steps": 500,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 1.5155431821361152e+16,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}

3
stage1-sft/checkpoint-82/training_args.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:35f21193165fb35ee40dfb67dcb04982fd2affbd9c865841951ae75e975e484a
size 5777

BIN
stage1-sft/tokenizer.json (Stored with Git LFS) Normal file
View File

Binary file not shown.

2068
stage1-sft/tokenizer_config.json Normal file
View File

File diff suppressed because it is too large Load Diff

3
stage1-sft/training_args.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:35f21193165fb35ee40dfb67dcb04982fd2affbd9c865841951ae75e975e484a
size 5777

73
stage2-grpo/README.md Normal file
View File

@@ -0,0 +1,73 @@
---
base_model: unsloth/llama-3.1-8b-instruct-bnb-4bit
library_name: peft
model_name: stage2-grpo
tags:
- base_model:adapter:unsloth/llama-3.1-8b-instruct-bnb-4bit
- grpo
- lora
- transformers
- trl
- unsloth
licence: license
pipeline_tag: text-generation
---
# Model Card for stage2-grpo
This model is a fine-tuned version of [unsloth/llama-3.1-8b-instruct-bnb-4bit](https://huggingface.co/unsloth/llama-3.1-8b-instruct-bnb-4bit).
It has been trained using [TRL](https://github.com/huggingface/trl).
## Quick start
```python
from transformers import pipeline
question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
generator = pipeline("text-generation", model="None", device="cuda")
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
print(output["generated_text"])
```
## Training procedure
This model was trained with GRPO, a method introduced in [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://huggingface.co/papers/2402.03300).
### Framework versions
- PEFT 0.19.1
- TRL: 0.24.0
- Transformers: 5.5.0
- Pytorch: 2.10.0+cu128
- Datasets: 4.3.0
- Tokenizers: 0.22.2
## Citations
Cite GRPO as:
```bibtex
@article{shao2024deepseekmath,
title = {{DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models}},
author = {Zhihong Shao and Peiyi Wang and Qihao Zhu and Runxin Xu and Junxiao Song and Mingchuan Zhang and Y. K. Li and Y. Wu and Daya Guo},
year = 2024,
eprint = {arXiv:2402.03300},
}
```
Cite TRL as:
```bibtex
@misc{vonwerra2022trl,
title = {{TRL: Transformer Reinforcement Learning}},
author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
year = 2020,
journal = {GitHub repository},
publisher = {GitHub},
howpublished = {\url{https://github.com/huggingface/trl}}
}
```

52
stage2-grpo/adapter_config.json Normal file
View File

@@ -0,0 +1,52 @@
{
"alora_invocation_tokens": null,
"alpha_pattern": {},
"arrow_config": null,
"auto_mapping": {
"base_model_class": "LlamaForCausalLM",
"parent_library": "transformers.models.llama.modeling_llama",
"unsloth_fixed": true
},
"base_model_name_or_path": "unsloth/llama-3.1-8b-instruct-bnb-4bit",
"bias": "none",
"corda_config": null,
"ensure_weight_tying": false,
"eva_config": null,
"exclude_modules": null,
"fan_in_fan_out": false,
"inference_mode": true,
"init_lora_weights": true,
"layer_replication": null,
"layers_pattern": null,
"layers_to_transform": null,
"loftq_config": {},
"lora_alpha": 64,
"lora_bias": false,
"lora_dropout": 0.05,
"lora_ga_config": null,
"megatron_config": null,
"megatron_core": "megatron.core",
"modules_to_save": null,
"peft_type": "LORA",
"peft_version": "0.19.1",
"qalora_group_size": 16,
"r": 32,
"rank_pattern": {},
"revision": null,
"target_modules": [
"o_proj",
"q_proj",
"k_proj",
"v_proj",
"up_proj",
"down_proj",
"gate_proj"
],
"target_parameters": null,
"task_type": "CAUSAL_LM",
"trainable_token_indices": null,
"use_bdlora": null,
"use_dora": false,
"use_qalora": false,
"use_rslora": false
}

3
stage2-grpo/adapter_model.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:30b3a5dedb2c7f6db6ef56e90a8989068cc978237507d33ebf2c577b27eb6ff7
size 335604696

109
stage2-grpo/chat_template.jinja Normal file
View File

@@ -0,0 +1,109 @@
{{- bos_token }}
{%- if custom_tools is defined %}
{%- set tools = custom_tools %}
{%- endif %}
{%- if not tools_in_user_message is defined %}
{%- set tools_in_user_message = true %}
{%- endif %}
{%- if not date_string is defined %}
{%- set date_string = "26 Jul 2024" %}
{%- endif %}
{%- if not tools is defined %}
{%- set tools = none %}
{%- endif %}
{#- This block extracts the system message, so we can slot it into the right place. #}
{%- if messages[0]['role'] == 'system' %}
{%- set system_message = messages[0]['content']|trim %}
{%- set messages = messages[1:] %}
{%- else %}
{%- set system_message = "" %}
{%- endif %}
{#- System message + builtin tools #}
{{- "<|start_header_id|>system<|end_header_id|>\n\n" }}
{%- if builtin_tools is defined or tools is not none %}
{{- "Environment: ipython\n" }}
{%- endif %}
{%- if builtin_tools is defined %}
{{- "Tools: " + builtin_tools | reject('equalto', 'code_interpreter') | join(", ") + "\n\n"}}
{%- endif %}
{{- "Cutting Knowledge Date: December 2023\n" }}
{{- "Today Date: " + date_string + "\n\n" }}
{%- if tools is not none and not tools_in_user_message %}
{{- "You have access to the following functions. To call a function, please respond with JSON for a function call." }}
{{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
{{- "Do not use variables.\n\n" }}
{%- for t in tools %}
{{- t | tojson(indent=4) }}
{{- "\n\n" }}
{%- endfor %}
{%- endif %}
{{- system_message }}
{{- "<|eot_id|>" }}
{#- Custom tools are passed in a user message with some extra guidance #}
{%- if tools_in_user_message and not tools is none %}
{#- Extract the first user message so we can plug it in here #}
{%- if messages | length != 0 %}
{%- set first_user_message = messages[0]['content']|trim %}
{%- set messages = messages[1:] %}
{%- else %}
{{- raise_exception("Cannot put tools in the first user message when there's no first user message!") }}
{%- endif %}
{{- '<|start_header_id|>user<|end_header_id|>\n\n' -}}
{{- "Given the following functions, please respond with a JSON for a function call " }}
{{- "with its proper arguments that best answers the given prompt.\n\n" }}
{{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
{{- "Do not use variables.\n\n" }}
{%- for t in tools %}
{{- t | tojson(indent=4) }}
{{- "\n\n" }}
{%- endfor %}
{{- first_user_message + "<|eot_id|>"}}
{%- endif %}
{%- for message in messages %}
{%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}
{{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' }}
{%- elif 'tool_calls' in message %}
{%- if not message.tool_calls|length == 1 %}
{{- raise_exception("This model only supports single tool-calls at once!") }}
{%- endif %}
{%- set tool_call = message.tool_calls[0].function %}
{%- if builtin_tools is defined and tool_call.name in builtin_tools %}
{{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}
{{- "<|python_tag|>" + tool_call.name + ".call(" }}
{%- for arg_name, arg_val in tool_call.arguments | items %}
{{- arg_name + '="' + arg_val + '"' }}
{%- if not loop.last %}
{{- ", " }}
{%- endif %}
{%- endfor %}
{{- ")" }}
{%- else %}
{{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}
{{- '{"name": "' + tool_call.name + '", ' }}
{{- '"parameters": ' }}
{{- tool_call.arguments | tojson }}
{{- "}" }}
{%- endif %}
{%- if builtin_tools is defined %}
{#- This means we're in ipython mode #}
{{- "<|eom_id|>" }}
{%- else %}
{{- "<|eot_id|>" }}
{%- endif %}
{%- elif message.role == "tool" or message.role == "ipython" %}
{{- "<|start_header_id|>ipython<|end_header_id|>\n\n" }}
{%- if message.content is mapping or message.content is iterable %}
{{- message.content | tojson }}
{%- else %}
{{- message.content }}
{%- endif %}
{{- "<|eot_id|>" }}
{%- endif %}
{%- endfor %}
{%- if add_generation_prompt %}
{{- '<|start_header_id|>assistant<|end_header_id|>\n\n' }}
{%- endif %}

210
stage2-grpo/checkpoint-90/README.md Normal file
View File

@@ -0,0 +1,210 @@
---
base_model: unsloth/llama-3.1-8b-instruct-bnb-4bit
library_name: peft
pipeline_tag: text-generation
tags:
- base_model:adapter:unsloth/llama-3.1-8b-instruct-bnb-4bit
- grpo
- lora
- transformers
- trl
- unsloth
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
### Framework versions
- PEFT 0.19.1

52
stage2-grpo/checkpoint-90/adapter_config.json Normal file
View File

@@ -0,0 +1,52 @@
{
"alora_invocation_tokens": null,
"alpha_pattern": {},
"arrow_config": null,
"auto_mapping": {
"base_model_class": "LlamaForCausalLM",
"parent_library": "transformers.models.llama.modeling_llama",
"unsloth_fixed": true
},
"base_model_name_or_path": "unsloth/llama-3.1-8b-instruct-bnb-4bit",
"bias": "none",
"corda_config": null,
"ensure_weight_tying": false,
"eva_config": null,
"exclude_modules": null,
"fan_in_fan_out": false,
"inference_mode": true,
"init_lora_weights": true,
"layer_replication": null,
"layers_pattern": null,
"layers_to_transform": null,
"loftq_config": {},
"lora_alpha": 64,
"lora_bias": false,
"lora_dropout": 0.05,
"lora_ga_config": null,
"megatron_config": null,
"megatron_core": "megatron.core",
"modules_to_save": null,
"peft_type": "LORA",
"peft_version": "0.19.1",
"qalora_group_size": 16,
"r": 32,
"rank_pattern": {},
"revision": null,
"target_modules": [
"o_proj",
"q_proj",
"k_proj",
"v_proj",
"up_proj",
"down_proj",
"gate_proj"
],
"target_parameters": null,
"task_type": "CAUSAL_LM",
"trainable_token_indices": null,
"use_bdlora": null,
"use_dora": false,
"use_qalora": false,
"use_rslora": false
}

3
stage2-grpo/checkpoint-90/adapter_model.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:30b3a5dedb2c7f6db6ef56e90a8989068cc978237507d33ebf2c577b27eb6ff7
size 335604696

109
stage2-grpo/checkpoint-90/chat_template.jinja Normal file
View File

@@ -0,0 +1,109 @@
{{- bos_token }}
{%- if custom_tools is defined %}
{%- set tools = custom_tools %}
{%- endif %}
{%- if not tools_in_user_message is defined %}
{%- set tools_in_user_message = true %}
{%- endif %}
{%- if not date_string is defined %}
{%- set date_string = "26 Jul 2024" %}
{%- endif %}
{%- if not tools is defined %}
{%- set tools = none %}
{%- endif %}
{#- This block extracts the system message, so we can slot it into the right place. #}
{%- if messages[0]['role'] == 'system' %}
{%- set system_message = messages[0]['content']|trim %}
{%- set messages = messages[1:] %}
{%- else %}
{%- set system_message = "" %}
{%- endif %}
{#- System message + builtin tools #}
{{- "<|start_header_id|>system<|end_header_id|>\n\n" }}
{%- if builtin_tools is defined or tools is not none %}
{{- "Environment: ipython\n" }}
{%- endif %}
{%- if builtin_tools is defined %}
{{- "Tools: " + builtin_tools | reject('equalto', 'code_interpreter') | join(", ") + "\n\n"}}
{%- endif %}
{{- "Cutting Knowledge Date: December 2023\n" }}
{{- "Today Date: " + date_string + "\n\n" }}
{%- if tools is not none and not tools_in_user_message %}
{{- "You have access to the following functions. To call a function, please respond with JSON for a function call." }}
{{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
{{- "Do not use variables.\n\n" }}
{%- for t in tools %}
{{- t | tojson(indent=4) }}
{{- "\n\n" }}
{%- endfor %}
{%- endif %}
{{- system_message }}
{{- "<|eot_id|>" }}
{#- Custom tools are passed in a user message with some extra guidance #}
{%- if tools_in_user_message and not tools is none %}
{#- Extract the first user message so we can plug it in here #}
{%- if messages | length != 0 %}
{%- set first_user_message = messages[0]['content']|trim %}
{%- set messages = messages[1:] %}
{%- else %}
{{- raise_exception("Cannot put tools in the first user message when there's no first user message!") }}
{%- endif %}
{{- '<|start_header_id|>user<|end_header_id|>\n\n' -}}
{{- "Given the following functions, please respond with a JSON for a function call " }}
{{- "with its proper arguments that best answers the given prompt.\n\n" }}
{{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
{{- "Do not use variables.\n\n" }}
{%- for t in tools %}
{{- t | tojson(indent=4) }}
{{- "\n\n" }}
{%- endfor %}
{{- first_user_message + "<|eot_id|>"}}
{%- endif %}
{%- for message in messages %}
{%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}
{{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' }}
{%- elif 'tool_calls' in message %}
{%- if not message.tool_calls|length == 1 %}
{{- raise_exception("This model only supports single tool-calls at once!") }}
{%- endif %}
{%- set tool_call = message.tool_calls[0].function %}
{%- if builtin_tools is defined and tool_call.name in builtin_tools %}
{{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}
{{- "<|python_tag|>" + tool_call.name + ".call(" }}
{%- for arg_name, arg_val in tool_call.arguments | items %}
{{- arg_name + '="' + arg_val + '"' }}
{%- if not loop.last %}
{{- ", " }}
{%- endif %}
{%- endfor %}
{{- ")" }}
{%- else %}
{{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}
{{- '{"name": "' + tool_call.name + '", ' }}
{{- '"parameters": ' }}
{{- tool_call.arguments | tojson }}
{{- "}" }}
{%- endif %}
{%- if builtin_tools is defined %}
{#- This means we're in ipython mode #}
{{- "<|eom_id|>" }}
{%- else %}
{{- "<|eot_id|>" }}
{%- endif %}
{%- elif message.role == "tool" or message.role == "ipython" %}
{{- "<|start_header_id|>ipython<|end_header_id|>\n\n" }}
{%- if message.content is mapping or message.content is iterable %}
{{- message.content | tojson }}
{%- else %}
{{- message.content }}
{%- endif %}
{{- "<|eot_id|>" }}
{%- endif %}
{%- endfor %}
{%- if add_generation_prompt %}
{{- '<|start_header_id|>assistant<|end_header_id|>\n\n' }}
{%- endif %}

3
stage2-grpo/checkpoint-90/optimizer.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:4b97748b2f004acf8c00c2c82a88ab7a40dc55b58ef8994da99479b964ec4cda
size 170925029

3
stage2-grpo/checkpoint-90/rng_state.pth Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:7c40bb986a3edfb84af8a43b32eac7ec92194afb4fd05b33198a310e00fb3f59
size 14645

3
stage2-grpo/checkpoint-90/scaler.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:9fcfce7e32b31bead77e9e963d8e602c77a653a75c54ecbe876542fbeeba3fdc
size 1383

3
stage2-grpo/checkpoint-90/scheduler.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:54fc26fc8beada4d03ff10085b39a0a87f17ae896d977f9d181be9a4e684e655
size 1465

3
stage2-grpo/checkpoint-90/tokenizer.json Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a65c6c5f9764771aa485e6a1f5e63d7d9af8477fe0777148c17476ecb2e09a05
size 17210099

2068
stage2-grpo/checkpoint-90/tokenizer_config.json Normal file
View File

File diff suppressed because it is too large Load Diff

277
stage2-grpo/checkpoint-90/trainer_state.json Normal file
View File

@@ -0,0 +1,277 @@
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.0,
"eval_steps": 500,
"global_step": 90,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"clip_ratio/high_max": 0.0,
"clip_ratio/high_mean": 0.0,
"clip_ratio/low_mean": 0.0,
"clip_ratio/low_min": 0.0,
"clip_ratio/region_mean": 0.0,
"completion_length": 760.425,
"completions/clipped_ratio": 0.95,
"completions/max_length": 768.0,
"completions/max_terminated_length": 246.6,
"completions/mean_length": 760.425,
"completions/mean_terminated_length": 246.6,
"completions/min_length": 707.4,
"completions/min_terminated_length": 246.6,
"epoch": 0.1111111111111111,
"frac_reward_zero_std": 0.55,
"grad_norm": 0.001028538914397359,
"kl": 0.5006327688694,
"learning_rate": 4.972729020927866e-06,
"loss": 0.0005006341263651848,
"num_tokens": 80284.0,
"reward": 0.19812500327825547,
"reward_std": 0.14407300129532813,
"rewards/logged_reward/mean": 0.19812500514090062,
"rewards/logged_reward/std": 0.4103552341461182,
"step": 10
},
{
"clip_ratio/high_max": 0.0,
"clip_ratio/high_mean": 0.0,
"clip_ratio/low_mean": 0.0,
"clip_ratio/low_min": 0.0,
"clip_ratio/region_mean": 0.0,
"completion_length": 754.175,
"completions/clipped_ratio": 0.925,
"completions/max_length": 768.0,
"completions/max_terminated_length": 292.2,
"completions/mean_length": 754.175,
"completions/mean_terminated_length": 286.85,
"completions/min_length": 665.5,
"completions/min_terminated_length": 281.5,
"epoch": 0.2222222222222222,
"frac_reward_zero_std": 0.675,
"grad_norm": 0.03615415841341019,
"kl": 0.5185602981597185,
"learning_rate": 4.672722365763821e-06,
"loss": 0.0005185471847653389,
"num_tokens": 159008.0,
"reward": 0.3037499986588955,
"reward_std": 0.11313708312809467,
"rewards/logged_reward/mean": 0.30374999940395353,
"rewards/logged_reward/std": 0.4017797887325287,
"step": 20
},
{
"clip_ratio/high_max": 0.0,
"clip_ratio/high_mean": 0.0,
"clip_ratio/low_mean": 0.0,
"clip_ratio/low_min": 0.0,
"clip_ratio/region_mean": 0.0,
"completion_length": 768.0,
"completions/clipped_ratio": 1.0,
"completions/max_length": 768.0,
"completions/max_terminated_length": 0.0,
"completions/mean_length": 768.0,
"completions/mean_terminated_length": 0.0,
"completions/min_length": 768.0,
"completions/min_terminated_length": 0.0,
"epoch": 0.3333333333333333,
"frac_reward_zero_std": 0.725,
"grad_norm": 0.17221924662590027,
"kl": 0.5021876730024815,
"learning_rate": 4.079277515633127e-06,
"loss": 0.0005021758377552032,
"num_tokens": 239920.0,
"reward": 0.39937499910593033,
"reward_std": 0.04154252391308546,
"rewards/logged_reward/mean": 0.3993750035762787,
"rewards/logged_reward/std": 0.3457350268959999,
"step": 30
},
{
"clip_ratio/high_max": 0.0,
"clip_ratio/high_mean": 0.0,
"clip_ratio/low_mean": 0.0,
"clip_ratio/low_min": 0.0,
"clip_ratio/region_mean": 0.0,
"completion_length": 763.45,
"completions/clipped_ratio": 0.9875,
"completions/max_length": 768.0,
"completions/max_terminated_length": 40.4,
"completions/mean_length": 763.45,
"completions/mean_terminated_length": 40.4,
"completions/min_length": 731.6,
"completions/min_terminated_length": 40.4,
"epoch": 0.4444444444444444,
"frac_reward_zero_std": 0.85,
"grad_norm": 0.008656619116663933,
"kl": 0.46648566871881486,
"learning_rate": 3.272542485937369e-06,
"loss": 0.0004664875566959381,
"num_tokens": 320264.0,
"reward": 0.39062500596046446,
"reward_std": 0.03977475762367248,
"rewards/logged_reward/mean": 0.39062500447034837,
"rewards/logged_reward/std": 0.271591111831367,
"step": 40
},
{
"clip_ratio/high_max": 0.0,
"clip_ratio/high_mean": 0.0,
"clip_ratio/low_mean": 0.0,
"clip_ratio/low_min": 0.0,
"clip_ratio/region_mean": 0.0,
"completion_length": 763.0,
"completions/clipped_ratio": 0.975,
"completions/max_length": 768.0,
"completions/max_terminated_length": 113.6,
"completions/mean_length": 763.0,
"completions/mean_terminated_length": 113.6,
"completions/min_length": 728.0,
"completions/min_terminated_length": 113.6,
"epoch": 0.5555555555555556,
"frac_reward_zero_std": 0.725,
"grad_norm": 0.0014952127821743488,
"kl": 0.47636983878910544,
"learning_rate": 2.3614713127100752e-06,
"loss": 0.0004763755947351456,
"num_tokens": 400450.0,
"reward": 0.4381250113248825,
"reward_std": 0.07689785957336426,
"rewards/logged_reward/mean": 0.4381250113248825,
"rewards/logged_reward/std": 0.355089807510376,
"step": 50
},
{
"clip_ratio/high_max": 0.0,
"clip_ratio/high_mean": 0.0,
"clip_ratio/low_mean": 0.0,
"clip_ratio/low_min": 0.0,
"clip_ratio/region_mean": 0.0,
"completion_length": 739.475,
"completions/clipped_ratio": 0.875,
"completions/max_length": 768.0,
"completions/max_terminated_length": 418.3,
"completions/mean_length": 739.475,
"completions/mean_terminated_length": 384.15,
"completions/min_length": 580.4,
"completions/min_terminated_length": 350.0,
"epoch": 0.6666666666666666,
"frac_reward_zero_std": 0.9,
"grad_norm": 0.1433563530445099,
"kl": 0.49970625154674053,
"learning_rate": 1.4691092063152417e-06,
"loss": 0.0004996967501938343,
"num_tokens": 478220.0,
"reward": 0.3912500023841858,
"reward_std": 0.026516504772007465,
"rewards/logged_reward/mean": 0.3912500023841858,
"rewards/logged_reward/std": 0.3306365102529526,
"step": 60
},
{
"clip_ratio/high_max": 0.0,
"clip_ratio/high_mean": 0.0,
"clip_ratio/low_mean": 0.0,
"clip_ratio/low_min": 0.0,
"clip_ratio/region_mean": 0.0,
"completion_length": 737.5,
"completions/clipped_ratio": 0.8375,
"completions/max_length": 768.0,
"completions/max_terminated_length": 433.7,
"completions/mean_length": 737.5,
"completions/mean_terminated_length": 397.225,
"completions/min_length": 581.3,
"completions/min_terminated_length": 350.9,
"epoch": 0.7777777777777778,
"frac_reward_zero_std": 1.0,
"grad_norm": 0.0008722825441509485,
"kl": 0.4948728669434786,
"learning_rate": 7.159746139706194e-07,
"loss": 0.0004948728252202273,
"num_tokens": 555874.0,
"reward": 0.34500000476837156,
"reward_std": 0.0,
"rewards/logged_reward/mean": 0.34500000476837156,
"rewards/logged_reward/std": 0.31715869903564453,
"step": 70
},
{
"clip_ratio/high_max": 0.0,
"clip_ratio/high_mean": 0.0,
"clip_ratio/low_mean": 0.0,
"clip_ratio/low_min": 0.0,
"clip_ratio/region_mean": 0.0,
"completion_length": 754.8875,
"completions/clipped_ratio": 0.9,
"completions/max_length": 768.0,
"completions/max_terminated_length": 318.1,
"completions/mean_length": 754.8875,
"completions/mean_terminated_length": 309.18333740234374,
"completions/min_length": 680.6,
"completions/min_terminated_length": 296.6,
"epoch": 0.8888888888888888,
"frac_reward_zero_std": 0.95,
"grad_norm": 0.1149626076221466,
"kl": 0.47000304274260996,
"learning_rate": 2.0378253563519247e-07,
"loss": 0.00047000362537801265,
"num_tokens": 634531.0,
"reward": 0.3325000084936619,
"reward_std": 0.005303300172090531,
"rewards/logged_reward/mean": 0.3325000084936619,
"rewards/logged_reward/std": 0.25604055523872377,
"step": 80
},
{
"clip_ratio/high_max": 0.0,
"clip_ratio/high_mean": 0.0,
"clip_ratio/low_mean": 0.0,
"clip_ratio/low_min": 0.0,
"clip_ratio/region_mean": 0.0,
"completion_length": 751.3375,
"completions/clipped_ratio": 0.925,
"completions/max_length": 768.0,
"completions/max_terminated_length": 192.5,
"completions/mean_length": 751.3375,
"completions/mean_terminated_length": 178.55,
"completions/min_length": 701.2,
"completions/min_terminated_length": 163.6,
"epoch": 1.0,
"frac_reward_zero_std": 0.95,
"grad_norm": 0.08985413610935211,
"kl": 0.503129281103611,
"learning_rate": 1.707349642442735e-09,
"loss": 0.0005031307693570853,
"num_tokens": 713612.0,
"reward": 0.37500000521540644,
"reward_std": 0.02121320366859436,
"rewards/logged_reward/mean": 0.37500000521540644,
"rewards/logged_reward/std": 0.3066870108246803,
"step": 90
}
],
"logging_steps": 10,
"max_steps": 90,
"num_input_tokens_seen": 713612,
"num_train_epochs": 1,
"save_steps": 200,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 0.0,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}

3
stage2-grpo/checkpoint-90/training_args.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:98fce3384f4e8f6d9c7f17de43938ea9940220db4e5ba68af11825025f98f6cd
size 6737

3
stage2-grpo/tokenizer.json Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a65c6c5f9764771aa485e6a1f5e63d7d9af8477fe0777148c17476ecb2e09a05
size 17210099

2068
stage2-grpo/tokenizer_config.json Normal file
View File

File diff suppressed because it is too large Load Diff

3
stage2-grpo/training_args.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:98fce3384f4e8f6d9c7f17de43938ea9940220db4e5ba68af11825025f98f6cd
size 6737

BIN
tokenizer.json (Stored with Git LFS) Normal file
View File

Binary file not shown.

2072
tokenizer_config.json Normal file
View File

File diff suppressed because it is too large Load Diff