oliver-aizip commited on
Commit
481fe8b
·
1 Parent(s): bc93ed3

disable bitnet and set models to previous status

Browse files
Files changed (1) hide show
  1. utils/models.py +17 -17
utils/models.py CHANGED
@@ -17,25 +17,25 @@ from .prompts import format_rag_prompt
17
  from .shared import generation_interrupt
18
 
19
  models = {
20
- # "Qwen2.5-1.5b-Instruct": "qwen/qwen2.5-1.5b-instruct",
21
- # "Qwen2.5-3b-Instruct": "qwen/qwen2.5-3b-instruct",
22
- # "Llama-3.2-1b-Instruct": "meta-llama/llama-3.2-1b-instruct",
23
- # "Llama-3.2-3b-Instruct": "meta-llama/llama-3.2-3b-instruct",
24
- # "Gemma-3-1b-it": "google/gemma-3-1b-it",
25
- # "Gemma-3-4b-it": "google/gemma-3-4b-it",
26
- # "Gemma-2-2b-it": "google/gemma-2-2b-it",
27
- # "Phi-4-mini-instruct": "microsoft/phi-4-mini-instruct",
28
- # "Cogito-v1-preview-llama-3b": "deepcogito/cogito-v1-preview-llama-3b",
29
- # "IBM Granite-3.3-2b-instruct": "ibm-granite/granite-3.3-2b-instruct",
30
- "Bitnet-b1.58-2B4T": "microsoft/bitnet-b1.58-2B-4T",
31
  # #"MiniCPM3-RAG-LoRA": "openbmb/MiniCPM3-RAG-LoRA",
32
  "Qwen3-0.6b": "qwen/qwen3-0.6b",
33
- # "Qwen3-1.7b": "qwen/qwen3-1.7b",
34
- # "Qwen3-4b": "qwen/qwen3-4b",
35
- # "SmolLM2-1.7b-Instruct": "HuggingFaceTB/SmolLM2-1.7B-Instruct",
36
- # "EXAONE-3.5-2.4B-instruct": "LGAI-EXAONE/EXAONE-3.5-2.4B-Instruct",
37
- # "OLMo-2-1B-Instruct": "allenai/OLMo-2-0425-1B-Instruct",
38
- # "icecream-3b": "aizip-dev/icecream-3b",
39
  }
40
 
41
  tokenizer_cache = {}
 
17
  from .shared import generation_interrupt
18
 
19
  models = {
20
+ "Qwen2.5-1.5b-Instruct": "qwen/qwen2.5-1.5b-instruct",
21
+ "Qwen2.5-3b-Instruct": "qwen/qwen2.5-3b-instruct",
22
+ "Llama-3.2-1b-Instruct": "meta-llama/llama-3.2-1b-instruct",
23
+ "Llama-3.2-3b-Instruct": "meta-llama/llama-3.2-3b-instruct",
24
+ "Gemma-3-1b-it": "google/gemma-3-1b-it",
25
+ "Gemma-3-4b-it": "google/gemma-3-4b-it",
26
+ "Gemma-2-2b-it": "google/gemma-2-2b-it",
27
+ "Phi-4-mini-instruct": "microsoft/phi-4-mini-instruct",
28
+ "Cogito-v1-preview-llama-3b": "deepcogito/cogito-v1-preview-llama-3b",
29
+ "IBM Granite-3.3-2b-instruct": "ibm-granite/granite-3.3-2b-instruct",
30
+ # "Bitnet-b1.58-2B4T": "microsoft/bitnet-b1.58-2B-4T",
31
  # #"MiniCPM3-RAG-LoRA": "openbmb/MiniCPM3-RAG-LoRA",
32
  "Qwen3-0.6b": "qwen/qwen3-0.6b",
33
+ "Qwen3-1.7b": "qwen/qwen3-1.7b",
34
+ "Qwen3-4b": "qwen/qwen3-4b",
35
+ "SmolLM2-1.7b-Instruct": "HuggingFaceTB/SmolLM2-1.7B-Instruct",
36
+ "EXAONE-3.5-2.4B-instruct": "LGAI-EXAONE/EXAONE-3.5-2.4B-Instruct",
37
+ "OLMo-2-1B-Instruct": "allenai/OLMo-2-0425-1B-Instruct",
38
+ "icecream-3b": "aizip-dev/icecream-3b",
39
  }
40
 
41
  tokenizer_cache = {}