Hugging Face's logo

unsloth
/
zephyr-sft

Text Generation
Transformers
Safetensors
English
mistral
unsloth
zephyr
sft
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
danielhanchen commited on
Commit
4b04a63
•
1 Parent(s): 8dee568

Upload MistralForCausalLM

Browse files
Files changed (5) hide show
  1. config.json +2 -3
  2. generation_config.json +0 -2
  3. model-00001-of-00003.safetensors +1 -1
  4. model-00002-of-00003.safetensors +1 -1
  5. model-00003-of-00003.safetensors +1 -1
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "unsloth/zephyr-sft",
3
  "architectures": [
4
  "MistralForCausalLM"
5
  ],
@@ -16,14 +16,13 @@
16
  "num_attention_heads": 32,
17
  "num_hidden_layers": 32,
18
  "num_key_value_heads": 8,
19
- "pad_token_id": 0,
20
  "rms_norm_eps": 1e-05,
21
  "rope_theta": 10000.0,
22
  "sliding_window": 4096,
23
  "tie_word_embeddings": false,
24
  "torch_dtype": "bfloat16",
25
  "transformers_version": "4.44.0",
26
- "unsloth_version": "2024.8",
27
  "use_cache": true,
28
  "vocab_size": 32000
29
  }
 
1
  {
2
+ "_name_or_path": "HuggingFaceH4/zephyr-7b-beta",
3
  "architectures": [
4
  "MistralForCausalLM"
5
  ],
 
16
  "num_attention_heads": 32,
17
  "num_hidden_layers": 32,
18
  "num_key_value_heads": 8,
19
+ "pad_token_id": 2,
20
  "rms_norm_eps": 1e-05,
21
  "rope_theta": 10000.0,
22
  "sliding_window": 4096,
23
  "tie_word_embeddings": false,
24
  "torch_dtype": "bfloat16",
25
  "transformers_version": "4.44.0",
 
26
  "use_cache": true,
27
  "vocab_size": 32000
28
  }
generation_config.json CHANGED
@@ -2,7 +2,5 @@
2
  "_from_model_config": true,
3
  "bos_token_id": 1,
4
  "eos_token_id": 2,
5
- "max_length": 32768,
6
- "pad_token_id": 0,
7
  "transformers_version": "4.44.0"
8
  }
 
2
  "_from_model_config": true,
3
  "bos_token_id": 1,
4
  "eos_token_id": 2,
 
 
5
  "transformers_version": "4.44.0"
6
  }
model-00001-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ac50b319fdc43192d8a1f67b0fd21e8e1a8de1696977f8d48850e326163bdaaf
3
  size 4943162336
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d5233b965d72decb86a89d67f5ae5204bee716b72f3e4b31acc04f0e52028538
3
  size 4943162336
model-00002-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bbafeb558b6e04d12f73c05015acd574015d843a37d899cf5fa99248563208bf
3
  size 4999819336
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:623833e9b3707ff65682c04754818f8b7a9acd024508727a6f411de28301b44b
3
  size 4999819336
model-00003-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2fe824bc51c088b671e855db56949868d9390af6d8859044d5359268cdaa8b9d
3
  size 4540516344
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11e90704947ba17b2e1be7e66723efd013c308415ba42b4f4231e258b7d4f5a0
3
  size 4540516344