Hugging Face's logo

unsloth
/
SmolLM2-360M-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
79f7001
·
verified ·
1 Parent(s): bbfd98f

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
@@ -19,7 +19,7 @@
19
  "num_attention_heads": 15,
20
  "num_hidden_layers": 32,
21
  "num_key_value_heads": 5,
22
- "pad_token_id": 0,
23
  "pretraining_tp": 1,
24
  "quantization_config": {
25
  "_load_in_4bit": true,
@@ -50,5 +50,5 @@
50
  },
51
  "transformers_version": "4.46.1",
52
  "use_cache": true,
53
- "vocab_size": 49152
54
  }
 
19
  "num_attention_heads": 15,
20
  "num_hidden_layers": 32,
21
  "num_key_value_heads": 5,
22
+ "pad_token_id": 49152,
23
  "pretraining_tp": 1,
24
  "quantization_config": {
25
  "_load_in_4bit": true,
 
50
  },
51
  "transformers_version": "4.46.1",
52
  "use_cache": true,
53
+ "vocab_size": 49153
54
  }
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 sha256:8cdf9148e7b925fb949d2a6b510996cfc614e22d502bb3adb985c9db89790ba7
3
- size 257221834
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de3b6e2e829abc8ea6a441ab4d4b2d73cd275857a6363a596fb83cec9c76e561
3
+ size 257223754