Hugging Face's logo

nroggendorff
/
vegetarian-mayo

Text Generation
Transformers
Safetensors
English
llama
trl
sft
sgd
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
nroggendorff commited on
Commit
89e3179
•
1 Parent(s): d35ebb6

Upload MistralForCausalLM

Browse files
Files changed (4) hide show
  1. README.md +5 -5
  2. config.json +26 -13
  3. generation_config.json +1 -2
  4. model.safetensors +2 -2
README.md CHANGED
@@ -1,17 +1,17 @@
1
  ---
 
 
2
  license: mit
3
- base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
4
  tags:
5
  - trl
6
  - sft
7
  - sgd
 
 
 
8
  model-index:
9
  - name: mayo
10
  results: []
11
- datasets:
12
- - nroggendorff/mayo
13
- language:
14
- - en
15
  ---
16
 
17
  # Mayonnaise LLM
 
1
  ---
2
+ language:
3
+ - en
4
  license: mit
 
5
  tags:
6
  - trl
7
  - sft
8
  - sgd
9
+ base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
10
+ datasets:
11
+ - nroggendorff/mayo
12
  model-index:
13
  - name: mayo
14
  results: []
 
 
 
 
15
  ---
16
 
17
  # Mayonnaise LLM
config.json CHANGED
@@ -1,28 +1,41 @@
1
  {
2
- "_name_or_path": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
3
  "architectures": [
4
- "LlamaForCausalLM"
5
  ],
6
- "attention_bias": false,
7
  "attention_dropout": 0.0,
8
  "bos_token_id": 1,
9
  "eos_token_id": 2,
10
  "hidden_act": "silu",
11
- "hidden_size": 2048,
12
  "initializer_range": 0.02,
13
- "intermediate_size": 5632,
14
- "max_position_embeddings": 2048,
15
- "model_type": "llama",
16
  "num_attention_heads": 32,
17
- "num_hidden_layers": 22,
18
- "num_key_value_heads": 4,
19
- "pretraining_tp": 1,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
20
  "rms_norm_eps": 1e-05,
21
- "rope_scaling": null,
22
- "rope_theta": 10000.0,
23
  "tie_word_embeddings": false,
24
  "torch_dtype": "float32",
25
  "transformers_version": "4.39.3",
26
  "use_cache": true,
27
- "vocab_size": 32000
28
  }
 
1
  {
2
+ "_name_or_path": "mistralai/Mistral-7B-Instruct-v0.3",
3
  "architectures": [
4
+ "MistralForCausalLM"
5
  ],
 
6
  "attention_dropout": 0.0,
7
  "bos_token_id": 1,
8
  "eos_token_id": 2,
9
  "hidden_act": "silu",
10
+ "hidden_size": 4096,
11
  "initializer_range": 0.02,
12
+ "intermediate_size": 14336,
13
+ "max_position_embeddings": 32768,
14
+ "model_type": "mistral",
15
  "num_attention_heads": 32,
16
+ "num_hidden_layers": 32,
17
+ "num_key_value_heads": 8,
18
+ "quantization_config": {
19
+ "_load_in_4bit": true,
20
+ "_load_in_8bit": false,
21
+ "bnb_4bit_compute_dtype": "bfloat16",
22
+ "bnb_4bit_quant_storage": "uint8",
23
+ "bnb_4bit_quant_type": "nf4",
24
+ "bnb_4bit_use_double_quant": true,
25
+ "llm_int8_enable_fp32_cpu_offload": false,
26
+ "llm_int8_has_fp16_weight": false,
27
+ "llm_int8_skip_modules": null,
28
+ "llm_int8_threshold": 6.0,
29
+ "load_in_4bit": true,
30
+ "load_in_8bit": false,
31
+ "quant_method": "bitsandbytes"
32
+ },
33
  "rms_norm_eps": 1e-05,
34
+ "rope_theta": 1000000.0,
35
+ "sliding_window": null,
36
  "tie_word_embeddings": false,
37
  "torch_dtype": "float32",
38
  "transformers_version": "4.39.3",
39
  "use_cache": true,
40
+ "vocab_size": 32768
41
  }
generation_config.json CHANGED
@@ -1,7 +1,6 @@
1
  {
 
2
  "bos_token_id": 1,
3
  "eos_token_id": 2,
4
- "max_length": 2048,
5
- "pad_token_id": 0,
6
  "transformers_version": "4.39.3"
7
  }
 
1
  {
2
+ "_from_model_config": true,
3
  "bos_token_id": 1,
4
  "eos_token_id": 2,
 
 
5
  "transformers_version": "4.39.3"
6
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f12a3986dca4a2d8406fdb25af0f46a9a83b2e7b3daab798068571c736d36175
3
- size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e0a7d4042dcb6473f1ee08c4f3ac5e79d93db40ef2876d39fa5ec0b750efd5b
3
+ size 4675678992