初始化项目，由ModelHub XC社区提供模型
Model: 0xA50C1A1/Llama-3.3-8B-Instruct-128K-SOM-MPOA Source: Original Platform
This commit is contained in:
ModelHub XC
36
.gitattributes
vendored
Normal file
36
.gitattributes
vendored
Normal file
@@ -0,0 +1,36 @@
|
||||
*.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
|
||||
82
README.md
Normal file
82
README.md
Normal file
@@ -0,0 +1,82 @@
|
||||
---
|
||||
license: llama3.3
|
||||
base_model:
|
||||
- shb777/Llama-3.3-8B-Instruct-128K
|
||||
pipeline_tag: text-generation
|
||||
tags:
|
||||
- heretic
|
||||
- uncensored
|
||||
- decensored
|
||||
- abliterated
|
||||
---
|
||||
# This is a decensored version of [shb777/Llama-3.3-8B-Instruct-128K](https://huggingface.co/shb777/Llama-3.3-8B-Instruct-128K), made using [Heretic](https://github.com/p-e-w/heretic) v1.2.0
|
||||
|
||||
## Abliteration parameters
|
||||
|
||||
| Parameter | Value |
|
||||
| :-------- | :---: |
|
||||
| **direction_index** | 15.07 |
|
||||
| **attn.o_proj.max_weights.0** | 0: 1.40 |
|
||||
| **attn.o_proj.max_weights.1** | 1: 0.93 |
|
||||
| **attn.o_proj.max_weights.2** | 2: 1.06 |
|
||||
| **attn.o_proj.max_weights.3** | 3: 1.45 |
|
||||
| **attn.o_proj.max_weights.4** | 4: 1.41 |
|
||||
| **attn.o_proj.max_weights.5** | 5: 1.45 |
|
||||
| **attn.o_proj.max_weights.6** | 6: 1.25 |
|
||||
| **attn.o_proj.max_weights.7** | 7: 1.38 |
|
||||
| **attn.o_proj.max_weight_position** | 28.70 |
|
||||
| **attn.o_proj.min_weights.0** | 0: 0.71 |
|
||||
| **attn.o_proj.min_weights.1** | 1: 0.21 |
|
||||
| **attn.o_proj.min_weights.2** | 2: 0.94 |
|
||||
| **attn.o_proj.min_weights.3** | 3: 1.36 |
|
||||
| **attn.o_proj.min_weights.4** | 4: 0.19 |
|
||||
| **attn.o_proj.min_weights.5** | 5: 1.09 |
|
||||
| **attn.o_proj.min_weights.6** | 6: 0.87 |
|
||||
| **attn.o_proj.min_weights.7** | 7: 1.14 |
|
||||
| **attn.o_proj.min_weight_distance** | 15.91 |
|
||||
| **mlp.down_proj.max_weights.0** | 0: 1.38 |
|
||||
| **mlp.down_proj.max_weights.1** | 1: 1.26 |
|
||||
| **mlp.down_proj.max_weights.2** | 2: 1.10 |
|
||||
| **mlp.down_proj.max_weights.3** | 3: 0.85 |
|
||||
| **mlp.down_proj.max_weights.4** | 4: 1.12 |
|
||||
| **mlp.down_proj.max_weights.5** | 5: 1.31 |
|
||||
| **mlp.down_proj.max_weights.6** | 6: 1.25 |
|
||||
| **mlp.down_proj.max_weights.7** | 7: 0.94 |
|
||||
| **mlp.down_proj.max_weight_position** | 30.75 |
|
||||
| **mlp.down_proj.min_weights.0** | 0: 0.27 |
|
||||
| **mlp.down_proj.min_weights.1** | 1: 0.56 |
|
||||
| **mlp.down_proj.min_weights.2** | 2: 0.77 |
|
||||
| **mlp.down_proj.min_weights.3** | 3: 0.47 |
|
||||
| **mlp.down_proj.min_weights.4** | 4: 0.93 |
|
||||
| **mlp.down_proj.min_weights.5** | 5: 0.67 |
|
||||
| **mlp.down_proj.min_weights.6** | 6: 1.19 |
|
||||
| **mlp.down_proj.min_weights.7** | 7: 0.01 |
|
||||
| **mlp.down_proj.min_weight_distance** | 6.58 |
|
||||
|
||||
## Performance
|
||||
|
||||
| Metric | This model | Original model ([shb777/Llama-3.3-8B-Instruct-128K](https://huggingface.co/shb777/Llama-3.3-8B-Instruct-128K)) |
|
||||
| :----- | :--------: | :---------------------------: |
|
||||
| **KL divergence** | 0.0563 | 0 *(by definition)* |
|
||||
| **Refusals** | 3/100 | 93/100 |
|
||||
|
||||
-----
|
||||
|
||||
|
||||
# Llama 3.3 8B 128K Instruct (Fixed)
|
||||
|
||||
> [!IMPORTANT]
|
||||
> Original [allura-forge/Llama-3.3-8B-Instruct](https://huggingface.co/allura-forge/Llama-3.3-8B-Instruct), Thanks!
|
||||
|
||||
> [!TIP]
|
||||
> [imatrix GGUF's by mradermacher (Recommended)](https://huggingface.co/mradermacher/Llama-3.3-8B-Instruct-128K-i1-GGUF)
|
||||
>
|
||||
> [static GGUF's](https://huggingface.co/shb777/Llama-3.3-8B-Instruct-128K-GGUF)
|
||||
>
|
||||
> [Evals](https://huggingface.co/datasets/shb777/Llama-3.3-8B-Instruct-128K-Evals)
|
||||
|
||||
Additional Fixes:
|
||||
- Added `rope_scaling`
|
||||
- Added chat template (Unsloth) in tokenizer config
|
||||
- Updated generation config
|
||||
- Enabled full context length
|
||||
107
chat_template.jinja
Normal file
107
chat_template.jinja
Normal file
@@ -0,0 +1,107 @@
|
||||
{{- 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 = "30 Dec 2025" %}
|
||||
{%- 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) %}
|
||||
{%- if message['role'] == 'assistant' %}
|
||||
{{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'}}{% generation %}{{- message['content'] | trim + '<|eot_id|>' }}{% endgeneration %}
|
||||
{%- else %}
|
||||
{{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n' + message['content'] | trim + '<|eot_id|>' }}
|
||||
{%- endif %}
|
||||
{%- 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' }}{% generation %}{%- if builtin_tools is defined and tool_call.name in builtin_tools %}
|
||||
{{- "<|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 %}
|
||||
{{- '{"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 %}{% endgeneration %}
|
||||
{%- 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 %}
|
||||
36
config.json
Normal file
36
config.json
Normal file
@@ -0,0 +1,36 @@
|
||||
{
|
||||
"architectures": [
|
||||
"LlamaForCausalLM"
|
||||
],
|
||||
"attention_bias": false,
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 128000,
|
||||
"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": null,
|
||||
"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,
|
||||
"transformers_version": "5.3.0",
|
||||
"use_cache": true,
|
||||
"vocab_size": 128256
|
||||
}
|
||||
13
generation_config.json
Normal file
13
generation_config.json
Normal file
@@ -0,0 +1,13 @@
|
||||
{
|
||||
"bos_token_id": 128000,
|
||||
"do_sample": true,
|
||||
"eos_token_id": [
|
||||
128001,
|
||||
128008,
|
||||
128009
|
||||
],
|
||||
"max_length": 131072,
|
||||
"temperature": 0.6,
|
||||
"top_p": 0.9,
|
||||
"transformers_version": "5.3.0"
|
||||
}
|
||||
3
model.safetensors
Normal file
3
model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:12ebaf0b91f4f4195b6cd2abe7208bab09df9c53052581465d01b1b442338fb8
|
||||
size 16060556616
|
||||
16
special_tokens_map.json
Normal file
16
special_tokens_map.json
Normal file
@@ -0,0 +1,16 @@
|
||||
{
|
||||
"bos_token": {
|
||||
"content": "<|begin_of_text|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"eos_token": {
|
||||
"content": "<|eot_id|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
3
tokenizer.json
Normal file
3
tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:e134af98b985517b4f068e3755ae90d4e9cd2d45d328325dc503f1c6b2d06cc7
|
||||
size 9085698
|
||||
2063
tokenizer_config.json
Normal file
2063
tokenizer_config.json
Normal file
File diff suppressed because it is too large
Load Diff
Reference in New Issue
Block a user