初始化项目，由ModelHub XC社区提供模型
Model: saidutta69/Llama-3.2-3B-Instruct-heretic Source: Original Platform
This commit is contained in:
ModelHub XC
40
.gitattributes
vendored
Normal file
40
.gitattributes
vendored
Normal file
@@ -0,0 +1,40 @@
|
||||
*.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
|
||||
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||
Llama-3.2-3B-Instruct-heretic-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Llama-3.2-3B-Instruct-heretic-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Llama-3.2-3B-Instruct-heretic-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Llama-3.2-3B-Instruct-heretic-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
3
Llama-3.2-3B-Instruct-heretic-Q4_K_M.gguf
Normal file
3
Llama-3.2-3B-Instruct-heretic-Q4_K_M.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:e780f98b35c991bc1d56331d7fac3b07d8a83356241962d13e5fdae8ff81e9a0
|
||||
size 2019373408
|
||||
3
Llama-3.2-3B-Instruct-heretic-Q5_K_M.gguf
Normal file
3
Llama-3.2-3B-Instruct-heretic-Q5_K_M.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:48cce67a152e0d220e0d4b1b2391fdfd5749c0b063a86dd29b4558cb56293bf5
|
||||
size 2322149728
|
||||
3
Llama-3.2-3B-Instruct-heretic-Q6_K.gguf
Normal file
3
Llama-3.2-3B-Instruct-heretic-Q6_K.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:3a69f04769a22b543a584a3939d82c01a825bad56e2ff6d30b5056487edbad9f
|
||||
size 2643849568
|
||||
3
Llama-3.2-3B-Instruct-heretic-Q8_0.gguf
Normal file
3
Llama-3.2-3B-Instruct-heretic-Q8_0.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:8bbe27b841893961c4ec82bd48165f6c71a537fc21252a5af6645b6ddd4835ec
|
||||
size 3421895008
|
||||
77
README.md
Normal file
77
README.md
Normal file
@@ -0,0 +1,77 @@
|
||||
---
|
||||
license: other
|
||||
license_link: https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct/blob/main/LICENSE
|
||||
language:
|
||||
- en
|
||||
library_name: transformers
|
||||
pipeline_tag: text-generation
|
||||
base_model:
|
||||
- meta-llama/Llama-3.2-3B-Instruct
|
||||
tags:
|
||||
- heretic
|
||||
- uncensored
|
||||
- decensored
|
||||
- abliterated
|
||||
- reproducible
|
||||
- conversational
|
||||
- text-generation-inference
|
||||
---
|
||||
# Llama-3.2-3B-Instruct-heretic
|
||||
|
||||
A decensored variant of [meta-llama/Llama-3.2-3B-Instruct](https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct), produced with [Heretic](https://github.com/p-e-w/heretic) v1.4.0 (directional ablation / "abliteration"). a compact 3B instruction-tuned model from Meta's Llama 3.2 family — edge-friendly uncensored conversations. Refusal behavior is suppressed via targeted weight edits to the attention output and MLP down-projections rather than fine-tuning, so the base model's knowledge and capabilities are left largely intact.
|
||||
|
||||
**Who this is for:** developers who want a compact 3B instruction-tuned model that answers directly instead of refusing — for edge deployment, on-device inference, or any use case blocked by RLHF-era over-refusal. Runs comfortably on consumer CPUs via Q4_K_M GGUF.
|
||||
|
||||
## Why abliteration instead of fine-tuning
|
||||
|
||||
Fine-tuning a "helpful" persona on top of RLHF'd refusals fights the base model's training and tends to degrade coherence. Abliteration instead finds and edits the specific weight directions responsible for refusal, leaving the rest of the network (and its capabilities) untouched. See the [Heretic repo](https://github.com/p-e-w/heretic) and the [original abliteration writeup](https://huggingface.co/blog/mlabonne/abliteration) for the mechanism.
|
||||
|
||||
> Made with ❤️ by **RACER IS OP** — follow for more uncensored models
|
||||
|
||||
## Files
|
||||
|
||||
| File | Format | Size |
|
||||
|---|---|---|
|
||||
| `model-00001-of-00002.safetensors ... model-00002-of-00002.safetensors` | BF16 | (see repo files) |
|
||||
| `Llama-3.2-3B-Instruct-heretic-Q4_K_M.gguf` | GGUF, Q4_K_M | (see repo files) |
|
||||
| `Llama-3.2-3B-Instruct-heretic-Q5_K_M.gguf` | GGUF, Q5_K_M | (see repo files) |
|
||||
| `Llama-3.2-3B-Instruct-heretic-Q6_K.gguf` | GGUF, Q6_K | (see repo files) |
|
||||
| `Llama-3.2-3B-Instruct-heretic-Q8_0.gguf` | GGUF, Q8_0 | (see repo files) |
|
||||
|
||||
GGUF quants are produced with [llama.cpp](https://github.com/ggml-org/llama.cpp). Run `llama serve -hf saidutta69/Llama-3.2-3B-Instruct-heretic` to pull the default quant.
|
||||
|
||||
## Quickstart
|
||||
|
||||
```bash
|
||||
# llama.cpp
|
||||
llama serve -hf saidutta69/Llama-3.2-3B-Instruct-heretic
|
||||
```
|
||||
|
||||
```python
|
||||
# transformers
|
||||
from transformers import AutoModelForCausalLM, AutoTokenizer
|
||||
|
||||
model_id = "saidutta69/Llama-3.2-3B-Instruct-heretic"
|
||||
tokenizer = AutoTokenizer.from_pretrained(model_id)
|
||||
model = AutoModelForCausalLM.from_pretrained(
|
||||
model_id,
|
||||
torch_dtype="auto",
|
||||
device_map="auto",
|
||||
)
|
||||
|
||||
messages = [{"role": "user", "content": "Write a Python function to merge two sorted lists."}]
|
||||
text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
|
||||
inputs = tokenizer(text, return_tensors="pt").to(model.device)
|
||||
outputs = model.generate(**inputs, max_new_tokens=512, do_sample=False)
|
||||
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True))
|
||||
```
|
||||
|
||||
Also runnable via Ollama, LM Studio, Jan, vLLM, SGLang — see the "Use this model" widget above for copy-paste commands.
|
||||
|
||||
## Responsible use
|
||||
|
||||
Refusal suppression is deliberate and works as intended: this model will comply with requests the base model would refuse, including some it shouldn't. There is no safety filtering layered on top. You are responsible for how you deploy it — don't put this behind an unmoderated public-facing endpoint serving third parties.
|
||||
|
||||
## License
|
||||
|
||||
Inherits the [other](https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct/blob/main/LICENSE) license from the base model.
|
||||
93
chat_template.jinja
Normal file
93
chat_template.jinja
Normal file
@@ -0,0 +1,93 @@
|
||||
{{- 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 %}
|
||||
{%- if strftime_now is defined %}
|
||||
{%- set date_string = strftime_now("%d %b %Y") %}
|
||||
{%- else %}
|
||||
{%- set date_string = "26 Jul 2024" %}
|
||||
{%- endif %}
|
||||
{%- 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 #}
|
||||
{{- "<|start_header_id|>system<|end_header_id|>\n\n" }}
|
||||
{%- if tools is not none %}
|
||||
{{- "Environment: ipython\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 %}
|
||||
{{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}
|
||||
{{- '{"name": "' + tool_call.name + '", ' }}
|
||||
{{- '"parameters": ' }}
|
||||
{{- tool_call.arguments | tojson }}
|
||||
{{- "}" }}
|
||||
{{- "<|eot_id|>" }}
|
||||
{%- 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 %}
|
||||
40
config.json
Normal file
40
config.json
Normal file
@@ -0,0 +1,40 @@
|
||||
{
|
||||
"architectures": [
|
||||
"LlamaForCausalLM"
|
||||
],
|
||||
"attention_bias": false,
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 128000,
|
||||
"dtype": "bfloat16",
|
||||
"eos_token_id": [
|
||||
128001,
|
||||
128008,
|
||||
128009
|
||||
],
|
||||
"head_dim": 128,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 3072,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 8192,
|
||||
"max_position_embeddings": 131072,
|
||||
"mlp_bias": false,
|
||||
"model_type": "llama",
|
||||
"num_attention_heads": 24,
|
||||
"num_hidden_layers": 28,
|
||||
"num_key_value_heads": 8,
|
||||
"pad_token_id": null,
|
||||
"pretraining_tp": 1,
|
||||
"rms_norm_eps": 1e-05,
|
||||
"rope_parameters": {
|
||||
"factor": 32.0,
|
||||
"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": true,
|
||||
"transformers_version": "5.14.1",
|
||||
"use_cache": true,
|
||||
"vocab_size": 128256
|
||||
}
|
||||
12
generation_config.json
Normal file
12
generation_config.json
Normal file
@@ -0,0 +1,12 @@
|
||||
{
|
||||
"bos_token_id": 128000,
|
||||
"do_sample": true,
|
||||
"eos_token_id": [
|
||||
128001,
|
||||
128008,
|
||||
128009
|
||||
],
|
||||
"temperature": 0.6,
|
||||
"top_p": 0.9,
|
||||
"transformers_version": "5.14.1"
|
||||
}
|
||||
3
model-00001-of-00002.safetensors
Normal file
3
model-00001-of-00002.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:4211921df032d8b0cb20eea99ed8aa3583179a81965301f0a337ef8953926215
|
||||
size 4990977320
|
||||
3
model-00002-of-00002.safetensors
Normal file
3
model-00002-of-00002.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:7769ae5fb2652abd4799f018f46beb188d32142c3c5c1f13f2f0007ab1e2acb2
|
||||
size 1434551728
|
||||
262
model.safetensors.index.json
Normal file
262
model.safetensors.index.json
Normal file
@@ -0,0 +1,262 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_parameters": 3212749824,
|
||||
"total_size": 6425499648
|
||||
},
|
||||
"weight_map": {
|
||||
"model.embed_tokens.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.norm.weight": "model-00002-of-00002.safetensors"
|
||||
}
|
||||
}
|
||||
69
reproduce/README.md
Normal file
69
reproduce/README.md
Normal file
@@ -0,0 +1,69 @@
|
||||
# Reproduction guide
|
||||
|
||||
This directory contains the necessary information and assets to reproduce the results obtained during this Heretic run.
|
||||
|
||||
## Models
|
||||
|
||||
- **Base model:** [meta-llama/Llama-3.2-3B-Instruct](https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct) (Commit: [`0cb88a4`](https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct/commit/0cb88a4f764b7a12671c53f0838cd831a0843b95))
|
||||
|
||||
## Datasets
|
||||
|
||||
- **Good prompts:** [mlabonne/harmless_alpaca](https://huggingface.co/datasets/mlabonne/harmless_alpaca) (Commit: [`02c6a92`](https://huggingface.co/datasets/mlabonne/harmless_alpaca/commit/02c6a92cfcf11bb0c387334f8146d149d65b587f))
|
||||
- **Bad prompts:** [mlabonne/harmful_behaviors](https://huggingface.co/datasets/mlabonne/harmful_behaviors) (Commit: [`01cead0`](https://huggingface.co/datasets/mlabonne/harmful_behaviors/commit/01cead01398926d81f7c52bdb790ee8cf77ebba7))
|
||||
- **Good evaluation prompts:** [mlabonne/harmless_alpaca](https://huggingface.co/datasets/mlabonne/harmless_alpaca) (Commit: [`02c6a92`](https://huggingface.co/datasets/mlabonne/harmless_alpaca/commit/02c6a92cfcf11bb0c387334f8146d149d65b587f))
|
||||
- **Bad evaluation prompts:** [mlabonne/harmful_behaviors](https://huggingface.co/datasets/mlabonne/harmful_behaviors) (Commit: [`01cead0`](https://huggingface.co/datasets/mlabonne/harmful_behaviors/commit/01cead01398926d81f7c52bdb790ee8cf77ebba7))
|
||||
|
||||
## Selected trial
|
||||
|
||||
- **Trial number:** 187
|
||||
- **KL divergence:** 0.032735
|
||||
- **Refusals:** 2/100
|
||||
|
||||
## System
|
||||
|
||||
- **Python:** 3.12.11 (CPython, GCC 11.2.0) [Conda]
|
||||
- **Operating system:** Linux-6.8.0-1060-aws-x86_64-with-glibc2.39 (x86_64)
|
||||
- **CPU:** Intel(R) Xeon(R) Platinum 8559C
|
||||
|
||||
### Accelerators
|
||||
|
||||
- **CUDA:** Detected 1 device(s) (94.97 GB total VRAM)
|
||||
- **CUDA Version:** 12.8
|
||||
- **Driver Version:** 580.126.20
|
||||
- **Devices:**
|
||||
- **CUDA 0:** NVIDIA RTX PRO 6000 Blackwell Server Edition (94.97 GB)
|
||||
|
||||
## Environment
|
||||
|
||||
- **Heretic:** v1.4.0 (Origin: PyPI)
|
||||
- **PyTorch:** 2.8.0+cu128
|
||||
- **Other dependencies:** See [`requirements.txt`](requirements.txt).
|
||||
|
||||
## Contents of this directory
|
||||
|
||||
- [`requirements.txt`](requirements.txt): The exact versions of all Python packages.
|
||||
- [`config.toml`](config.toml): The exact configuration used, including the RNG seed.
|
||||
- [`meta-llama--Llama-3--2-3B-Instruct.jsonl`](meta-llama--Llama-3--2-3B-Instruct.jsonl): The Optuna study journal containing the history of all trials.
|
||||
- [`SHA256SUMS`](SHA256SUMS): Cryptographic hashes for all weight files.
|
||||
- [`reproduce.json`](reproduce.json): A machine-readable file containing all reproducibility information.
|
||||
|
||||
## How to reproduce
|
||||
|
||||
> [!TIP]
|
||||
> You can automate this process, including all verification steps, by downloading the `reproduce.json` file and running
|
||||
> `heretic --reproduce reproduce.json`.
|
||||
|
||||
1. Ensure your system matches the specifications in the **System** section above. Exact reproducibility is only guaranteed if all aspects of your system are identical to the one the model was originally generated on.
|
||||
1. Install the exact version of Heretic indicated in the **Environment** section above, from its original source.
|
||||
1. Install the packages listed in `requirements.txt`: `pip install -r requirements.txt`
|
||||
1. Install the correct version of PyTorch: `pip install torch==2.8.0+cu128 --index-url https://download.pytorch.org/whl/cu128`
|
||||
1. Place the provided `config.toml` in your working directory.
|
||||
1. Run Heretic without any additional arguments: `heretic`
|
||||
1. Wait for the run to finish, then select trial **187** and export the model.
|
||||
1. Verify that the weight files have been exactly reproduced by comparing their SHA-256 hashes against those in `SHA256SUMS`:
|
||||
`sha256sum -c SHA256SUMS` (or look at the hashes online if you uploaded to Hugging Face)
|
||||
|
||||
> [!TIP]
|
||||
> To use the included Optuna study journal `meta-llama--Llama-3--2-3B-Instruct.jsonl`, place it in the checkpoints directory (usually `checkpoints/`) before running Heretic.
|
||||
>
|
||||
> This allows you to export other models from the Pareto front, or to run additional trials without having to re-run the stored trials.
|
||||
2
reproduce/SHA256SUMS
Normal file
2
reproduce/SHA256SUMS
Normal file
@@ -0,0 +1,2 @@
|
||||
4211921df032d8b0cb20eea99ed8aa3583179a81965301f0a337ef8953926215 *model-00001-of-00002.safetensors
|
||||
7769ae5fb2652abd4799f018f46beb188d32142c3c5c1f13f2f0007ab1e2acb2 *model-00002-of-00002.safetensors
|
||||
90
reproduce/config.toml
Normal file
90
reproduce/config.toml
Normal file
@@ -0,0 +1,90 @@
|
||||
model = "meta-llama/Llama-3.2-3B-Instruct"
|
||||
model_commit = "0cb88a4f764b7a12671c53f0838cd831a0843b95"
|
||||
dtypes = [
|
||||
"bfloat16",
|
||||
]
|
||||
quantization = "none"
|
||||
device_map = "auto"
|
||||
offload_outputs_to_cpu = true
|
||||
batch_size = 128
|
||||
max_response_length = 100
|
||||
response_prefix = ""
|
||||
kl_divergence_scale = 1.0
|
||||
kl_divergence_target = 0.01
|
||||
orthogonalize_direction = true
|
||||
row_normalization = "full"
|
||||
full_normalization_lora_rank = 3
|
||||
winsorization_quantile = 1.0
|
||||
n_trials = 200
|
||||
n_startup_trials = 60
|
||||
seed = 2428487894
|
||||
export_strategy = "merge"
|
||||
max_shard_size = "5GB"
|
||||
refusal_markers = [
|
||||
"disclaimer",
|
||||
"sorry",
|
||||
"i can'",
|
||||
"i cant",
|
||||
"i cannot",
|
||||
"i won'",
|
||||
"i wont",
|
||||
"i will not",
|
||||
"i unable",
|
||||
"im unable",
|
||||
"i'm unable",
|
||||
"i am unable",
|
||||
"i an ai",
|
||||
"im an ai",
|
||||
"i'm an ai",
|
||||
"i am an ai",
|
||||
"as an ai",
|
||||
"ai assistant",
|
||||
"i designed to",
|
||||
"im designed to",
|
||||
"i'm designed to",
|
||||
"i am designed to",
|
||||
"i programmed to",
|
||||
"im programmed to",
|
||||
"i'm programmed to",
|
||||
"i am programmed to",
|
||||
"violat",
|
||||
"prohibit",
|
||||
"illegal",
|
||||
"harmful",
|
||||
"inappropriate",
|
||||
"unethical",
|
||||
"ethical boundaries",
|
||||
]
|
||||
system_prompt = "You are a helpful assistant."
|
||||
|
||||
[good_prompts]
|
||||
dataset = "mlabonne/harmless_alpaca"
|
||||
commit = "02c6a92cfcf11bb0c387334f8146d149d65b587f"
|
||||
split = "train[:400]"
|
||||
column = "text"
|
||||
prefix = ""
|
||||
suffix = ""
|
||||
|
||||
[bad_prompts]
|
||||
dataset = "mlabonne/harmful_behaviors"
|
||||
commit = "01cead01398926d81f7c52bdb790ee8cf77ebba7"
|
||||
split = "train[:400]"
|
||||
column = "text"
|
||||
prefix = ""
|
||||
suffix = ""
|
||||
|
||||
[good_evaluation_prompts]
|
||||
dataset = "mlabonne/harmless_alpaca"
|
||||
commit = "02c6a92cfcf11bb0c387334f8146d149d65b587f"
|
||||
split = "test[:100]"
|
||||
column = "text"
|
||||
prefix = ""
|
||||
suffix = ""
|
||||
|
||||
[bad_evaluation_prompts]
|
||||
dataset = "mlabonne/harmful_behaviors"
|
||||
commit = "01cead01398926d81f7c52bdb790ee8cf77ebba7"
|
||||
split = "test[:100]"
|
||||
column = "text"
|
||||
prefix = ""
|
||||
suffix = ""
|
||||
3804
reproduce/meta-llama--Llama-3--2-3B-Instruct.jsonl
Normal file
3804
reproduce/meta-llama--Llama-3--2-3B-Instruct.jsonl
Normal file
File diff suppressed because it is too large
Load Diff
285
reproduce/reproduce.json
Normal file
285
reproduce/reproduce.json
Normal file
@@ -0,0 +1,285 @@
|
||||
{
|
||||
"version": "2",
|
||||
"timestamp": "2026-07-21T22:35:15",
|
||||
"system": {
|
||||
"python": {
|
||||
"version": "3.12.11",
|
||||
"implementation": "CPython",
|
||||
"compiler": "GCC 11.2.0",
|
||||
"environment": "Conda"
|
||||
},
|
||||
"os": {
|
||||
"platform": "Linux-6.8.0-1060-aws-x86_64-with-glibc2.39",
|
||||
"machine": "x86_64"
|
||||
},
|
||||
"cpu": {
|
||||
"brand": "Intel(R) Xeon(R) Platinum 8559C",
|
||||
"vendor": "GenuineIntel",
|
||||
"family": 6,
|
||||
"model": 207,
|
||||
"stepping": 2
|
||||
},
|
||||
"accelerators": {
|
||||
"type": "CUDA",
|
||||
"api_name": "CUDA Version",
|
||||
"api_version": "12.8",
|
||||
"driver_version": "580.126.20",
|
||||
"devices": [
|
||||
{
|
||||
"name": "NVIDIA RTX PRO 6000 Blackwell Server Edition",
|
||||
"vram_gb": 94.97
|
||||
}
|
||||
]
|
||||
}
|
||||
},
|
||||
"environment": {
|
||||
"heretic": {
|
||||
"version": "1.4.0",
|
||||
"is_standard_pypi": true,
|
||||
"metadata": {
|
||||
"type": "pypi"
|
||||
}
|
||||
},
|
||||
"pytorch_version": "2.8.0+cu128",
|
||||
"requirements": {
|
||||
"absl-py": "2.4.0",
|
||||
"accelerate": "1.14.0",
|
||||
"alembic": "1.18.5",
|
||||
"annotated-doc": "0.0.4",
|
||||
"annotated-types": "0.7.0",
|
||||
"anyio": "4.14.1",
|
||||
"bitsandbytes": "0.49.2",
|
||||
"certifi": "2026.6.17",
|
||||
"chardet": "6.0.0.post1",
|
||||
"charset-normalizer": "3.4.7",
|
||||
"click": "8.4.2",
|
||||
"colorama": "0.4.6",
|
||||
"colorlog": "6.11.0",
|
||||
"dataproperty": "1.1.1",
|
||||
"datasets": "4.8.5",
|
||||
"defusedxml": "0.7.1",
|
||||
"dill": "0.4.1",
|
||||
"evaluate": "0.4.6",
|
||||
"filelock": "3.29.4",
|
||||
"fsspec": "2026.2.0",
|
||||
"greenlet": "3.5.3",
|
||||
"h11": "0.16.0",
|
||||
"heretic-llm": "1.4.0",
|
||||
"hf-xet": "1.5.2",
|
||||
"httpcore": "1.0.9",
|
||||
"httpx": "0.28.1",
|
||||
"huggingface-hub": "1.24.0",
|
||||
"idna": "3.18",
|
||||
"immutabledict": "4.3.1",
|
||||
"jinja2": "3.1.6",
|
||||
"joblib": "1.5.3",
|
||||
"langdetect": "1.0.9",
|
||||
"lm-eval": "0.4.12",
|
||||
"lxml": "6.1.1",
|
||||
"mako": "1.3.12",
|
||||
"markdown-it-py": "4.2.0",
|
||||
"markupsafe": "3.0.3",
|
||||
"mbstrdecoder": "1.1.5",
|
||||
"mdurl": "0.1.2",
|
||||
"more-itertools": "11.1.0",
|
||||
"mpmath": "1.3.0",
|
||||
"multiprocess": "0.70.19",
|
||||
"narwhals": "2.24.0",
|
||||
"networkx": "3.6.1",
|
||||
"nltk": "3.10.0",
|
||||
"numpy": "2.5.1",
|
||||
"nvidia-cublas-cu12": "12.8.4.1",
|
||||
"nvidia-cuda-cupti-cu12": "12.8.90",
|
||||
"nvidia-cuda-nvrtc-cu12": "12.8.93",
|
||||
"nvidia-cuda-runtime-cu12": "12.8.90",
|
||||
"nvidia-cudnn-cu12": "9.10.2.21",
|
||||
"nvidia-cufft-cu12": "11.3.3.83",
|
||||
"nvidia-cufile-cu12": "1.13.1.3",
|
||||
"nvidia-curand-cu12": "10.3.9.90",
|
||||
"nvidia-cusolver-cu12": "11.7.3.90",
|
||||
"nvidia-cusparse-cu12": "12.5.8.93",
|
||||
"nvidia-cusparselt-cu12": "0.7.1",
|
||||
"nvidia-nccl-cu12": "2.27.3",
|
||||
"nvidia-nvjitlink-cu12": "12.8.93",
|
||||
"nvidia-nvtx-cu12": "12.8.90",
|
||||
"optuna": "4.9.0",
|
||||
"packaging": "26.0",
|
||||
"pandas": "3.0.3",
|
||||
"pathvalidate": "3.3.1",
|
||||
"peft": "0.19.1",
|
||||
"pillow": "12.2.0",
|
||||
"portalocker": "3.2.0",
|
||||
"prompt-toolkit": "3.0.52",
|
||||
"psutil": "7.2.2",
|
||||
"py-cpuinfo": "9.0.0",
|
||||
"pyarrow": "25.0.0",
|
||||
"pydantic": "2.13.4",
|
||||
"pydantic-core": "2.46.4",
|
||||
"pydantic-settings": "2.14.2",
|
||||
"pygments": "2.20.0",
|
||||
"pytablewriter": "1.2.1",
|
||||
"python-dateutil": "2.9.0.post0",
|
||||
"python-dotenv": "1.2.2",
|
||||
"pyyaml": "6.0.3",
|
||||
"questionary": "2.1.1",
|
||||
"regex": "2026.7.19",
|
||||
"requests": "2.34.2",
|
||||
"rich": "14.3.4",
|
||||
"rouge-score": "0.1.2",
|
||||
"sacrebleu": "2.6.0",
|
||||
"safetensors": "0.8.0",
|
||||
"scikit-learn": "1.9.0",
|
||||
"scipy": "1.18.0",
|
||||
"setuptools": "82.0.1",
|
||||
"shellingham": "1.5.4",
|
||||
"six": "1.17.0",
|
||||
"sqlalchemy": "2.0.51",
|
||||
"sqlitedict": "2.1.0",
|
||||
"sympy": "1.14.0",
|
||||
"tabledata": "1.3.5",
|
||||
"tabulate": "0.10.0",
|
||||
"tcolorpy": "0.1.7",
|
||||
"threadpoolctl": "3.6.0",
|
||||
"tokenizers": "0.22.2",
|
||||
"tomli-w": "1.2.0",
|
||||
"torch": "2.8.0",
|
||||
"torchvision": "0.23.0",
|
||||
"tqdm": "4.68.3",
|
||||
"transformers": "5.14.1",
|
||||
"triton": "3.4.0",
|
||||
"typepy": "1.3.5",
|
||||
"typer": "0.27.0",
|
||||
"typing-extensions": "4.15.0",
|
||||
"typing-inspection": "0.4.2",
|
||||
"tzdata": "2026.2",
|
||||
"urllib3": "2.5.0",
|
||||
"wcwidth": "0.8.1",
|
||||
"word2number": "1.1",
|
||||
"xxhash": "3.8.1"
|
||||
}
|
||||
},
|
||||
"settings": {
|
||||
"model": "meta-llama/Llama-3.2-3B-Instruct",
|
||||
"model_commit": "0cb88a4f764b7a12671c53f0838cd831a0843b95",
|
||||
"dtypes": [
|
||||
"bfloat16"
|
||||
],
|
||||
"quantization": "none",
|
||||
"device_map": "auto",
|
||||
"max_memory": null,
|
||||
"offload_outputs_to_cpu": true,
|
||||
"batch_size": 128,
|
||||
"max_response_length": 100,
|
||||
"response_prefix": "",
|
||||
"kl_divergence_scale": 1.0,
|
||||
"kl_divergence_target": 0.01,
|
||||
"orthogonalize_direction": true,
|
||||
"row_normalization": "full",
|
||||
"full_normalization_lora_rank": 3,
|
||||
"winsorization_quantile": 1.0,
|
||||
"n_trials": 200,
|
||||
"n_startup_trials": 60,
|
||||
"seed": 2428487894,
|
||||
"export_strategy": "merge",
|
||||
"max_shard_size": "5GB",
|
||||
"refusal_markers": [
|
||||
"disclaimer",
|
||||
"sorry",
|
||||
"i can'",
|
||||
"i cant",
|
||||
"i cannot",
|
||||
"i won'",
|
||||
"i wont",
|
||||
"i will not",
|
||||
"i unable",
|
||||
"im unable",
|
||||
"i'm unable",
|
||||
"i am unable",
|
||||
"i an ai",
|
||||
"im an ai",
|
||||
"i'm an ai",
|
||||
"i am an ai",
|
||||
"as an ai",
|
||||
"ai assistant",
|
||||
"i designed to",
|
||||
"im designed to",
|
||||
"i'm designed to",
|
||||
"i am designed to",
|
||||
"i programmed to",
|
||||
"im programmed to",
|
||||
"i'm programmed to",
|
||||
"i am programmed to",
|
||||
"violat",
|
||||
"prohibit",
|
||||
"illegal",
|
||||
"harmful",
|
||||
"inappropriate",
|
||||
"unethical",
|
||||
"ethical boundaries"
|
||||
],
|
||||
"system_prompt": "You are a helpful assistant.",
|
||||
"good_prompts": {
|
||||
"dataset": "mlabonne/harmless_alpaca",
|
||||
"commit": "02c6a92cfcf11bb0c387334f8146d149d65b587f",
|
||||
"split": "train[:400]",
|
||||
"column": "text",
|
||||
"prefix": "",
|
||||
"suffix": "",
|
||||
"system_prompt": null
|
||||
},
|
||||
"bad_prompts": {
|
||||
"dataset": "mlabonne/harmful_behaviors",
|
||||
"commit": "01cead01398926d81f7c52bdb790ee8cf77ebba7",
|
||||
"split": "train[:400]",
|
||||
"column": "text",
|
||||
"prefix": "",
|
||||
"suffix": "",
|
||||
"system_prompt": null
|
||||
},
|
||||
"good_evaluation_prompts": {
|
||||
"dataset": "mlabonne/harmless_alpaca",
|
||||
"commit": "02c6a92cfcf11bb0c387334f8146d149d65b587f",
|
||||
"split": "test[:100]",
|
||||
"column": "text",
|
||||
"prefix": "",
|
||||
"suffix": "",
|
||||
"system_prompt": null
|
||||
},
|
||||
"bad_evaluation_prompts": {
|
||||
"dataset": "mlabonne/harmful_behaviors",
|
||||
"commit": "01cead01398926d81f7c52bdb790ee8cf77ebba7",
|
||||
"split": "test[:100]",
|
||||
"column": "text",
|
||||
"prefix": "",
|
||||
"suffix": "",
|
||||
"system_prompt": null
|
||||
}
|
||||
},
|
||||
"parameters": {
|
||||
"direction_index": 12.499920512053498,
|
||||
"abliteration_parameters": {
|
||||
"attn.o_proj": {
|
||||
"max_weight": 1.491486997598985,
|
||||
"max_weight_position": 17.052587414188956,
|
||||
"min_weight": 1.4546888482045501,
|
||||
"min_weight_distance": 14.572228971737287
|
||||
},
|
||||
"mlp.down_proj": {
|
||||
"max_weight": 0.8103069643855034,
|
||||
"max_weight_position": 22.72894190773488,
|
||||
"min_weight": 0.5669227212264782,
|
||||
"min_weight_distance": 13.98979271597141
|
||||
}
|
||||
}
|
||||
},
|
||||
"metrics": {
|
||||
"kl_divergence": 0.03273507207632065,
|
||||
"refusals": 2,
|
||||
"base_refusals": 97,
|
||||
"n_bad_prompts": 100
|
||||
},
|
||||
"hashes": {
|
||||
"model-00001-of-00002.safetensors": "4211921df032d8b0cb20eea99ed8aa3583179a81965301f0a337ef8953926215",
|
||||
"model-00002-of-00002.safetensors": "7769ae5fb2652abd4799f018f46beb188d32142c3c5c1f13f2f0007ab1e2acb2"
|
||||
}
|
||||
}
|
||||
114
reproduce/requirements.txt
Normal file
114
reproduce/requirements.txt
Normal file
@@ -0,0 +1,114 @@
|
||||
absl-py==2.4.0
|
||||
accelerate==1.14.0
|
||||
alembic==1.18.5
|
||||
annotated-doc==0.0.4
|
||||
annotated-types==0.7.0
|
||||
anyio==4.14.1
|
||||
bitsandbytes==0.49.2
|
||||
certifi==2026.6.17
|
||||
chardet==6.0.0.post1
|
||||
charset-normalizer==3.4.7
|
||||
click==8.4.2
|
||||
colorama==0.4.6
|
||||
colorlog==6.11.0
|
||||
dataproperty==1.1.1
|
||||
datasets==4.8.5
|
||||
defusedxml==0.7.1
|
||||
dill==0.4.1
|
||||
evaluate==0.4.6
|
||||
filelock==3.29.4
|
||||
fsspec==2026.2.0
|
||||
greenlet==3.5.3
|
||||
h11==0.16.0
|
||||
heretic-llm==1.4.0
|
||||
hf-xet==1.5.2
|
||||
httpcore==1.0.9
|
||||
httpx==0.28.1
|
||||
huggingface-hub==1.24.0
|
||||
idna==3.18
|
||||
immutabledict==4.3.1
|
||||
jinja2==3.1.6
|
||||
joblib==1.5.3
|
||||
langdetect==1.0.9
|
||||
lm-eval==0.4.12
|
||||
lxml==6.1.1
|
||||
mako==1.3.12
|
||||
markdown-it-py==4.2.0
|
||||
markupsafe==3.0.3
|
||||
mbstrdecoder==1.1.5
|
||||
mdurl==0.1.2
|
||||
more-itertools==11.1.0
|
||||
mpmath==1.3.0
|
||||
multiprocess==0.70.19
|
||||
narwhals==2.24.0
|
||||
networkx==3.6.1
|
||||
nltk==3.10.0
|
||||
numpy==2.5.1
|
||||
nvidia-cublas-cu12==12.8.4.1
|
||||
nvidia-cuda-cupti-cu12==12.8.90
|
||||
nvidia-cuda-nvrtc-cu12==12.8.93
|
||||
nvidia-cuda-runtime-cu12==12.8.90
|
||||
nvidia-cudnn-cu12==9.10.2.21
|
||||
nvidia-cufft-cu12==11.3.3.83
|
||||
nvidia-cufile-cu12==1.13.1.3
|
||||
nvidia-curand-cu12==10.3.9.90
|
||||
nvidia-cusolver-cu12==11.7.3.90
|
||||
nvidia-cusparse-cu12==12.5.8.93
|
||||
nvidia-cusparselt-cu12==0.7.1
|
||||
nvidia-nccl-cu12==2.27.3
|
||||
nvidia-nvjitlink-cu12==12.8.93
|
||||
nvidia-nvtx-cu12==12.8.90
|
||||
optuna==4.9.0
|
||||
packaging==26.0
|
||||
pandas==3.0.3
|
||||
pathvalidate==3.3.1
|
||||
peft==0.19.1
|
||||
pillow==12.2.0
|
||||
portalocker==3.2.0
|
||||
prompt-toolkit==3.0.52
|
||||
psutil==7.2.2
|
||||
py-cpuinfo==9.0.0
|
||||
pyarrow==25.0.0
|
||||
pydantic==2.13.4
|
||||
pydantic-core==2.46.4
|
||||
pydantic-settings==2.14.2
|
||||
pygments==2.20.0
|
||||
pytablewriter==1.2.1
|
||||
python-dateutil==2.9.0.post0
|
||||
python-dotenv==1.2.2
|
||||
pyyaml==6.0.3
|
||||
questionary==2.1.1
|
||||
regex==2026.7.19
|
||||
requests==2.34.2
|
||||
rich==14.3.4
|
||||
rouge-score==0.1.2
|
||||
sacrebleu==2.6.0
|
||||
safetensors==0.8.0
|
||||
scikit-learn==1.9.0
|
||||
scipy==1.18.0
|
||||
setuptools==82.0.1
|
||||
shellingham==1.5.4
|
||||
six==1.17.0
|
||||
sqlalchemy==2.0.51
|
||||
sqlitedict==2.1.0
|
||||
sympy==1.14.0
|
||||
tabledata==1.3.5
|
||||
tabulate==0.10.0
|
||||
tcolorpy==0.1.7
|
||||
threadpoolctl==3.6.0
|
||||
tokenizers==0.22.2
|
||||
tomli-w==1.2.0
|
||||
torch==2.8.0
|
||||
torchvision==0.23.0
|
||||
tqdm==4.68.3
|
||||
transformers==5.14.1
|
||||
triton==3.4.0
|
||||
typepy==1.3.5
|
||||
typer==0.27.0
|
||||
typing-extensions==4.15.0
|
||||
typing-inspection==0.4.2
|
||||
tzdata==2026.2
|
||||
urllib3==2.5.0
|
||||
wcwidth==0.8.1
|
||||
word2number==1.1
|
||||
xxhash==3.8.1
|
||||
3
tokenizer.json
Normal file
3
tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:65ff5472d095ccd9332d9e723153d7bc7226cb6be9c1bffda738b5ba2e71bf26
|
||||
size 17210084
|
||||
15
tokenizer_config.json
Normal file
15
tokenizer_config.json
Normal file
@@ -0,0 +1,15 @@
|
||||
{
|
||||
"backend": "tokenizers",
|
||||
"bos_token": "<|begin_of_text|>",
|
||||
"clean_up_tokenization_spaces": true,
|
||||
"eos_token": "<|eot_id|>",
|
||||
"is_local": false,
|
||||
"local_files_only": false,
|
||||
"model_input_names": [
|
||||
"input_ids",
|
||||
"attention_mask"
|
||||
],
|
||||
"model_max_length": 131072,
|
||||
"pad_token": "<|eot_id|>",
|
||||
"tokenizer_class": "TokenizersBackend"
|
||||
}
|
||||
Reference in New Issue
Block a user