Hugging Face's logo

Shaleen123
/
code-yi-6b

Text Generation
Transformers
Safetensors
mixtral
text-generation-inference
4-bit precision
bitsandbytes
Model card Files
xet
Community
Shaleen123 commited on
Commit
06a0340
·
verified ·
1 Parent(s): c2a2c35

Upload MixtralForCausalLM

Browse files
Files changed (5) hide show
  1. config.json +18 -11
  2. generation_config.json +4 -4
  3. model-00001-of-00002.safetensors +3 -0
  4. model-00002-of-00002.safetensors +3 -0
  5. model.safetensors.index.json +0 -0
config.json CHANGED
@@ -1,23 +1,28 @@
1
  {
2
- "_name_or_path": "01-ai/Yi-6B-Chat",
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": 4096,
12
  "initializer_range": 0.02,
13
- "intermediate_size": 11008,
14
- "max_position_embeddings": 4096,
15
- "model_type": "llama",
16
  "num_attention_heads": 32,
 
17
  "num_hidden_layers": 32,
18
- "num_key_value_heads": 4,
19
- "pretraining_tp": 1,
 
 
20
  "quantization_config": {
 
 
21
  "bnb_4bit_compute_dtype": "bfloat16",
22
  "bnb_4bit_quant_type": "nf4",
23
  "bnb_4bit_use_double_quant": true,
@@ -30,11 +35,13 @@
30
  "quant_method": "bitsandbytes"
31
  },
32
  "rms_norm_eps": 1e-05,
33
- "rope_scaling": null,
34
- "rope_theta": 5000000.0,
 
35
  "tie_word_embeddings": false,
36
  "torch_dtype": "float32",
37
  "transformers_version": "4.38.0.dev0",
 
38
  "use_cache": false,
39
- "vocab_size": 64000
40
  }
 
1
  {
2
+ "_name_or_path": "TomGrc/FusionNet_7Bx2_MoE_14B",
3
  "architectures": [
4
+ "MixtralForCausalLM"
5
  ],
 
6
  "attention_dropout": 0.0,
7
  "bos_token_id": 1,
8
+ "do_sample": true,
9
  "eos_token_id": 2,
10
  "hidden_act": "silu",
11
  "hidden_size": 4096,
12
  "initializer_range": 0.02,
13
+ "intermediate_size": 14336,
14
+ "max_position_embeddings": 32768,
15
+ "model_type": "mixtral",
16
  "num_attention_heads": 32,
17
+ "num_experts_per_tok": 2,
18
  "num_hidden_layers": 32,
19
+ "num_key_value_heads": 8,
20
+ "num_local_experts": 2,
21
+ "output_router_logits": false,
22
+ "pad_token_id": 2,
23
  "quantization_config": {
24
+ "_load_in_4bit": true,
25
+ "_load_in_8bit": false,
26
  "bnb_4bit_compute_dtype": "bfloat16",
27
  "bnb_4bit_quant_type": "nf4",
28
  "bnb_4bit_use_double_quant": true,
 
35
  "quant_method": "bitsandbytes"
36
  },
37
  "rms_norm_eps": 1e-05,
38
+ "rope_theta": 10000.0,
39
+ "router_aux_loss_coef": 0.001,
40
+ "sliding_window": null,
41
  "tie_word_embeddings": false,
42
  "torch_dtype": "float32",
43
  "transformers_version": "4.38.0.dev0",
44
+ "unsloth_version": "2024.1",
45
  "use_cache": false,
46
+ "vocab_size": 32000
47
  }
generation_config.json CHANGED
@@ -1,10 +1,10 @@
1
  {
2
- "bos_token_id": 6,
 
3
  "do_sample": true,
4
- "eos_token_id": 64001,
5
- "max_length": 4096,
6
  "max_new_tokens": 200,
7
- "pad_token_id": 64001,
8
  "temperature": 0.7,
9
  "top_p": 0.7,
10
  "transformers_version": "4.38.0.dev0"
 
1
  {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
  "do_sample": true,
5
+ "eos_token_id": 2,
 
6
  "max_new_tokens": 200,
7
+ "pad_token_id": 2,
8
  "temperature": 0.7,
9
  "top_p": 0.7,
10
  "transformers_version": "4.38.0.dev0"
model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c55375e926519c728b04fec1f75ed92ca5b71cace13ca42a3d4151621ae4a52
3
+ size 5000158420
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:98aca662b4f3c2c3d6b54dc27bed091712b387f09cad237aa5e5b2451414e6a1
3
+ size 2558791315
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff