huggingkot commited on
Commit
3ce4698
·
1 Parent(s): 9a7da16

add files

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ *.json filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ ---
3
+ base_model:
4
+ - TroyDoesAI/BlackSheep-24B
5
+ ---
6
+
7
+ This is a converted weight from [BlackSheep-24B](https://huggingface.co/TroyDoesAI/BlackSheep-24B) model in [unsloth 4-bit dynamic quant](https://archive.is/EFz7P) using this [collab notebook](https://colab.research.google.com/drive/1P23C66j3ga49kBRnDNlmRce7R_l_-L5l?usp=sharing).
8
+
9
+ ## About this Conversion
10
+
11
+ This conversion uses **Unsloth** to load the model in **4-bit** format and force-save it in the same **4-bit** format.
12
+
13
+ ### How 4-bit Quantization Works
14
+ - The actual **4-bit quantization** is handled by **BitsAndBytes (bnb)**, which works under **Torch** via **AutoGPTQ** or **BitsAndBytes**.
15
+ - **Unsloth** acts as a wrapper, simplifying and optimizing the process for better efficiency.
16
+
17
+ This allows for reduced memory usage and faster inference while keeping the model compact.
chat_template.jinja ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- set today = strftime_now("%Y-%m-%d") %}
2
+ {%- set default_system_message = "Mistral Small 3, an Uncensored Large Language Model created by TroyDoesAI. The current date is " + today + ".\n\nWhen not sure of some information, say I don't have the information.\nIf the user's question is not clear, ambiguous, or does not provide enough context to accurately answer the question, do not try to answer it right away, ask the user to clarify their request (e.g. \"Where can I get some good ass tacos near me?\" => \"Where are you?\" or \"When's the next flight to Tokyo\" => \"Where you traveling from?\")" %}
3
+
4
+ {{- bos_token }}
5
+
6
+ {%- if messages[0]['role'] == 'system' %}
7
+ {%- set system_message = messages[0]['content'] %}
8
+ {%- set loop_messages = messages[1:] %}
9
+ {%- else %}
10
+ {%- set system_message = default_system_message %}
11
+ {%- set loop_messages = messages %}
12
+ {%- endif %}
13
+ {{- '[SYSTEM_PROMPT]' + system_message + '[/SYSTEM_PROMPT]' }}
14
+
15
+ {%- for message in loop_messages %}
16
+ {%- if message['role'] == 'user' %}
17
+ {{- '[INST]' + message['content'] + '[/INST]' }}
18
+ {%- elif message['role'] == 'system' %}
19
+ {{- '[SYSTEM_PROMPT]' + message['content'] + '[/SYSTEM_PROMPT]' }}
20
+ {%- elif message['role'] == 'assistant' %}
21
+ {{- message['content'] + eos_token }}
22
+ {%- else %}
23
+ {{- raise_exception('Only user, system and assistant roles are supported!') }}
24
+ {%- endif %}
25
+ {%- endfor %}
config.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a80eea64e4f533495038d084a2dab236cb4aa04154f0488637b2ec40e0a8ab56
3
+ size 1079
generation_config.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:006fb887c5d0d33de21d25144ac1691f1680c7fd51b20c2cdd073c749baf3c95
3
+ size 199
model-00001-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:80964144246947f480c9bfd4c72541d5e7259cfb432598a6efdb7ad0f58a20c2
3
+ size 4983049324
model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4af1cff658561d53bcf50060105e8a1837064c2793e1f245674995b0b3dd2936
3
+ size 4987974536
model-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc2a26afd0bb1ce28aae0979573aea492eca3e6a1ff14486a90fed1fa6f5ec10
3
+ size 4182397548
model.safetensors.index.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3278c76dc96ef03b97bc99b1e2c8602b49b08dd994f533241434cf523e202284
3
+ size 165421
special_tokens_map.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e2723cf0c325652adb19cf4cadaa265054fc44c106e161bee36f13ce1b21a9b
3
+ size 21335
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b76085f9923309d873994d444989f7eb6ec074b06f25b58f1e8d7b7741070949
3
+ size 17078037
tokenizer_config.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e6d43894e22793841d73b4d16e3a2218edda4c4e18b0e625c58309a386695e9
3
+ size 198079