Hugging Face's logo

jan-hq
/
llama3-s-instruct-v0.3-checkpoint-7000-phase-3-10-24

Text Generation
Transformers
Safetensors
English
llama
text-generation-inference
unsloth
trl
sft
conversational
Inference Endpoints
Model card Files Community
jan-hq commited on
Commit
fa82405
•
1 Parent(s): 9d06dbd

Upload LlamaForCausalLM

Browse files
Files changed (6) hide show
  1. config.json +1 -3
  2. generation_config.json +0 -2
  3. model-00001-of-00004.safetensors +1 -1
  4. model-00002-of-00004.safetensors +1 -1
  5. model-00003-of-00004.safetensors +1 -1
  6. model-00004-of-00004.safetensors +1 -1
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "jan-hq/llama3-s-instruct-v0.3-checkpoint-7000",
3
  "architectures": [
4
  "LlamaForCausalLM"
5
  ],
@@ -21,7 +21,6 @@
21
  "num_attention_heads": 32,
22
  "num_hidden_layers": 32,
23
  "num_key_value_heads": 8,
24
- "pad_token_id": 128004,
25
  "pretraining_tp": 1,
26
  "rms_norm_eps": 1e-05,
27
  "rope_scaling": {
@@ -35,7 +34,6 @@
35
  "tie_word_embeddings": false,
36
  "torch_dtype": "bfloat16",
37
  "transformers_version": "4.44.2",
38
- "unsloth_version": "2024.9",
39
  "use_cache": true,
40
  "vocab_size": 128771
41
  }
 
1
  {
2
+ "_name_or_path": "llama3-s-instruct-v0.3-checkpoint-7000-phase-3/",
3
  "architectures": [
4
  "LlamaForCausalLM"
5
  ],
 
21
  "num_attention_heads": 32,
22
  "num_hidden_layers": 32,
23
  "num_key_value_heads": 8,
 
24
  "pretraining_tp": 1,
25
  "rms_norm_eps": 1e-05,
26
  "rope_scaling": {
 
34
  "tie_word_embeddings": false,
35
  "torch_dtype": "bfloat16",
36
  "transformers_version": "4.44.2",
 
37
  "use_cache": true,
38
  "vocab_size": 128771
39
  }
generation_config.json CHANGED
@@ -6,7 +6,5 @@
6
  128008,
7
  128009
8
  ],
9
- "max_length": 131072,
10
- "pad_token_id": 128004,
11
  "transformers_version": "4.44.2"
12
  }
 
6
  128008,
7
  128009
8
  ],
 
 
9
  "transformers_version": "4.44.2"
10
  }
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4d34b439acd53f7c34f5fe134f05c61ffa11c5b4397823b4bee4353e5ab8d3bd
3
  size 4980917552
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:469745dc0647ff6b103b9b53c70276cc2df9b4ebc747fb922c3d88dec7a5d14a
3
  size 4980917552
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d64b486dbb93df21ce0d17043662c40b2870bca541f2a0800d60881d829c0749
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e89a9c6124d362b10143751d1e428e27ceffaa765c60d9926485fb17c20d9822
3
  size 4999802720
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:17fcee4b6a1f1b7e41ba62759bc621cdefb87ee7e61061caf0a7586bb8fd468c
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05a36f9d447e192bbc9d784abee94a5f09a2c0bdac50ab4d47b840e432dc1c02
3
  size 4915916176
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:65519c883d7e69ca0dac8a1694c0a73e9ccae302c0fa3ba33a5fa363a4c39eff
3
  size 1172357688
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:351e27932dd5389d6d6e704b594ecf1dbd2b41718a21cb150a7f04b907c880af
3
  size 1172357688