Hugging Face's logo

unsloth
/
SmolLM2-1.7B-Instruct-bnb-4bit

Text Generation
Transformers
Safetensors
English
llama
unsloth
conversational
text-generation-inference
Inference Endpoints
4-bit precision
bitsandbytes
Model card Files Community
danielhanchen commited on
Commit
a1fb25e
•
1 Parent(s): 58e4e35

Upload LlamaForCausalLM

Browse files
Files changed (3) hide show
  1. config.json +2 -2
  2. generation_config.json +1 -1
  3. model.safetensors +2 -2
config.json CHANGED
@@ -18,7 +18,7 @@
18
  "num_attention_heads": 32,
19
  "num_hidden_layers": 24,
20
  "num_key_value_heads": 32,
21
- "pad_token_id": 0,
22
  "pretraining_tp": 1,
23
  "quantization_config": {
24
  "_load_in_4bit": true,
@@ -48,5 +48,5 @@
48
  },
49
  "transformers_version": "4.46.1",
50
  "use_cache": true,
51
- "vocab_size": 49152
52
  }
 
18
  "num_attention_heads": 32,
19
  "num_hidden_layers": 24,
20
  "num_key_value_heads": 32,
21
+ "pad_token_id": 49152,
22
  "pretraining_tp": 1,
23
  "quantization_config": {
24
  "_load_in_4bit": true,
 
48
  },
49
  "transformers_version": "4.46.1",
50
  "use_cache": true,
51
+ "vocab_size": 49153
52
  }
generation_config.json CHANGED
@@ -3,6 +3,6 @@
3
  "bos_token_id": 1,
4
  "eos_token_id": 2,
5
  "max_length": 8192,
6
- "pad_token_id": 0,
7
  "transformers_version": "4.46.1"
8
  }
 
3
  "bos_token_id": 1,
4
  "eos_token_id": 2,
5
  "max_length": 8192,
6
+ "pad_token_id": 49152,
7
  "transformers_version": "4.46.1"
8
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:459475d54e48144a4d544f5ca09a67a31fbdda5190583e4443eeb7f72efbd75b
3
- size 1032728619
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d330e205a217da37afa0b78e7abfacc989698338888570659f3543904555907
3
+ size 1032732715