Hugging Face's logo

prince-canuma
/
mixtral-8x22b-instruct-oh-4bit

Text Generation
Transformers
Safetensors
mixtral
conversational
text-generation-inference
Inference Endpoints
4-bit precision
bitsandbytes
Model card Files Community
prince-canuma commited on
Commit
513288d
•
1 Parent(s): b06d13e

Upload MixtralForCausalLM

Browse files
Files changed (20) hide show
  1. config.json +45 -0
  2. generation_config.json +6 -0
  3. model-00001-of-00017.safetensors +3 -0
  4. model-00002-of-00017.safetensors +3 -0
  5. model-00003-of-00017.safetensors +3 -0
  6. model-00004-of-00017.safetensors +3 -0
  7. model-00005-of-00017.safetensors +3 -0
  8. model-00006-of-00017.safetensors +3 -0
  9. model-00007-of-00017.safetensors +3 -0
  10. model-00008-of-00017.safetensors +3 -0
  11. model-00009-of-00017.safetensors +3 -0
  12. model-00010-of-00017.safetensors +3 -0
  13. model-00011-of-00017.safetensors +3 -0
  14. model-00012-of-00017.safetensors +3 -0
  15. model-00013-of-00017.safetensors +3 -0
  16. model-00014-of-00017.safetensors +3 -0
  17. model-00015-of-00017.safetensors +3 -0
  18. model-00016-of-00017.safetensors +3 -0
  19. model-00017-of-00017.safetensors +3 -0
  20. model.safetensors.index.json +0 -0
config.json ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "fireworks-ai/mixtral-8x22b-instruct-oh",
3
+ "architectures": [
4
+ "MixtralForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 6144,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 16384,
13
+ "max_position_embeddings": 65536,
14
+ "model_type": "mixtral",
15
+ "num_attention_heads": 48,
16
+ "num_experts_per_tok": 2,
17
+ "num_hidden_layers": 56,
18
+ "num_key_value_heads": 8,
19
+ "num_local_experts": 8,
20
+ "output_router_logits": false,
21
+ "quantization_config": {
22
+ "_load_in_4bit": true,
23
+ "_load_in_8bit": false,
24
+ "bnb_4bit_compute_dtype": "bfloat16",
25
+ "bnb_4bit_quant_type": "nf4",
26
+ "bnb_4bit_use_double_quant": false,
27
+ "llm_int8_enable_fp32_cpu_offload": false,
28
+ "llm_int8_has_fp16_weight": false,
29
+ "llm_int8_skip_modules": null,
30
+ "llm_int8_threshold": 6.0,
31
+ "load_in_4bit": true,
32
+ "load_in_8bit": false,
33
+ "quant_method": "bitsandbytes"
34
+ },
35
+ "rms_norm_eps": 1e-05,
36
+ "rope_theta": 1000000,
37
+ "router_aux_loss_coef": 0.001,
38
+ "router_jitter_noise": 0.0,
39
+ "sliding_window": null,
40
+ "tie_word_embeddings": false,
41
+ "torch_dtype": "float16",
42
+ "transformers_version": "4.38.2",
43
+ "use_cache": true,
44
+ "vocab_size": 32000
45
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "transformers_version": "4.38.2"
6
+ }
model-00001-of-00017.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d669fe20b1d74f9ce49da2f194114edf7c392714b025b0b54df6bd3db46aa85
3
+ size 4951626618
model-00002-of-00017.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:396427aa66c1f851132010de501ec41846708a3b08a7341354cab996908f6614
3
+ size 4961824784
model-00003-of-00017.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41715657d631dd7363173fbe06ab310fd11bcaf8456675acd8b2d29b064cd40c
3
+ size 4954801840
model-00004-of-00017.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02125077a97f43824a5c8d2d8d7cedb5f2c2de9e7f741b537e85e6ac46e01881
3
+ size 4961825192
model-00005-of-00017.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f198d33210cc0633619205385e491d8ae32f580f140862cb6bade3d5a081872e
3
+ size 4954802256
model-00006-of-00017.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2911adad0662c93dae8ad731281ad04e4869f3542fb146f42147268280a6c22
3
+ size 4961825192
model-00007-of-00017.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d294f5ee257bf04bf7f3344f01b112178c1587102181abf33cd6f01cb04857e
3
+ size 4954802256
model-00008-of-00017.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3e41de2d8b90dbb6625445f08aaff54664322ebe68d4a46a434be5d22544faf
3
+ size 4961825192
model-00009-of-00017.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a16b9197fde15a5eb1141f99830a3aabb13840ab6a505e7dcb6da52b5253211
3
+ size 4954802256
model-00010-of-00017.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:484f789cc9ec0fd662cb6980ded79fdc93082d4c8a0177419bab4c577d0678ae
3
+ size 4961825192
model-00011-of-00017.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:726c092f9cc13664caf08c9ff5e08ef85b54c0808318dbe489914056ee5d0412
3
+ size 4954802256
model-00012-of-00017.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4e5cfa9e327f26e9df973d3ab5af92359978759da83a14961a97e91d28e2d4d
3
+ size 4961825192
model-00013-of-00017.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:97720bb61423432d4e0bf34c4701b31f545ce172753a9bbab3003976626096c9
3
+ size 4954802256
model-00014-of-00017.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:53e88e9bd7dd5b5d257aae26dbfd1091c94c185bab5e8fdf2388de4a5c05b486
3
+ size 4990163459
model-00015-of-00017.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2e06bd2f9c6e9547b1904342046101d233a4942f986692b90c209f05a925e06
3
+ size 4983087791
model-00016-of-00017.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:899bad7082d27b04e0b3e7156129ebb3c8324b9f6a02ba3cd37ad1fcaa31b2fa
3
+ size 4848614772
model-00017-of-00017.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a9b656fa319bc8871482483a1345f0a9c4cf80cd53554668b81946e9b74223e
3
+ size 393216128
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff