KnutJaegersberg commited on
Commit
f4af7a1
1 Parent(s): c6944b8

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +38 -3
README.md CHANGED
@@ -2,13 +2,32 @@
2
  license: other
3
  pipeline_tag: text-generation
4
  ---
5
- ![image/gif](https://cdn-uploads.huggingface.co/production/uploads/63732ebbbd81fae2b3aaf3fb/X-U3UE8fCyMezmKAfjV0S.gif)
6
 
7
- # Model Card for 2-bit LLM buffet
8
 
9
  This is a model collection of mostly larger LLMs quantized to 2 bit with the novel quip# inspired approach in llama.ccp
10
 
11
-
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
12
 
13
  ### WizardLM-70b
14
 
@@ -287,6 +306,22 @@ License: Qwen
287
  ### Response: {response}
288
  ```
289
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
290
 
291
  ### Synthia-70B
292
 
 
2
  license: other
3
  pipeline_tag: text-generation
4
  ---
 
5
 
6
+ # 2-bit LLMs
7
 
8
  This is a model collection of mostly larger LLMs quantized to 2 bit with the novel quip# inspired approach in llama.ccp
9
 
10
+ ### Overview
11
+ - WizardLM-70b
12
+ - CausalLM-72b
13
+ - Codellama-70b-Instruct
14
+ - DeepMoney-67b-chat
15
+ - Deepseek 67b Chat
16
+ - DiscoLM-120b
17
+ - Nous Hermes 34b
18
+ - Kafka-70b-German
19
+ - Kafka-Mixtral-German
20
+ - LongAlpaca-70B
21
+ - Mistral-Alpha-70b
22
+ - MoMo-72B-lora-1.8.7-DPO
23
+ - Notux Mixtral
24
+ - Qwen-72b
25
+ - Smaug-72b
26
+ - Smaug-34b
27
+ - Synthia-70B
28
+ - Tess-M
29
+ - Yarn-Llama2-70b-32k
30
+ - Laser Mistral
31
 
32
  ### WizardLM-70b
33
 
 
306
  ### Response: {response}
307
  ```
308
 
309
+ ### Smaug-34b
310
+
311
+ ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63732ebbbd81fae2b3aaf3fb/Lt4tDXRJ93PnSg_Bv9JI_.png)
312
+
313
+ Original Model:
314
+ https://huggingface.co/abacusai/Smaug-34B-v0.1
315
+
316
+ Prompt format: Bagel 34b
317
+ License: Yi
318
+
319
+ ```
320
+ {system prompt, if provided, randomly defaulting to "A chat between a user and an unbiased, uncensored assistant."}
321
+ USER: {instruction}
322
+ ASSISTANT:
323
+ ```
324
+
325
 
326
  ### Synthia-70B
327