Hugging Face's logo

prince-canuma
/
Mixtral-8x22B-Instruct-v0.1-4bit

Text Generation
Transformers
Safetensors
mixtral
conversational
text-generation-inference
Inference Endpoints
4-bit precision
bitsandbytes
Model card Files Community
prince-canuma commited on
Commit
1ee1e0c
·
verified ·
1 Parent(s): 7777e5a

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": "mistralai/Mixtral-8x22B-Instruct-v0.1",
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_storage": "uint8",
26
+ "bnb_4bit_quant_type": "nf4",
27
+ "bnb_4bit_use_double_quant": false,
28
+ "llm_int8_enable_fp32_cpu_offload": false,
29
+ "llm_int8_has_fp16_weight": false,
30
+ "llm_int8_skip_modules": null,
31
+ "llm_int8_threshold": 6.0,
32
+ "load_in_4bit": true,
33
+ "load_in_8bit": false,
34
+ "quant_method": "bitsandbytes"
35
+ },
36
+ "rms_norm_eps": 1e-05,
37
+ "rope_theta": 1000000.0,
38
+ "router_aux_loss_coef": 0.001,
39
+ "sliding_window": null,
40
+ "tie_word_embeddings": false,
41
+ "torch_dtype": "float16",
42
+ "transformers_version": "4.39.3",
43
+ "use_cache": true,
44
+ "vocab_size": 32768
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": "4.39.3"
6
+ }
model-00001-of-00017.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3effb856ab4deaf8ca3a44ee2cda14516a83f404e75229b4da96cf9bd61504f7
3
+ size 4961063802
model-00002-of-00017.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae72c1942d663758e4d362985a5d3a291fd60d4a91f0781a55fde1a0a18c90e4
3
+ size 4961824784
model-00003-of-00017.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81b42f291b751e088ec72b7309752b8cd072efbd041834f8bc7366b2a556efa0
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:a089eb9fed013793f48d910515f16e3194ed805e6ac583012a434fab258eb6e8
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:cebf63fc90bfc0b69a35e099174131b320933ea90c68dae8dd0fc03ab6017129
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:c879068ab39e0e5c6211faddb44ebadeb924a8cb2f6a0843db469d846fd3ed93
3
+ size 4961825192
model-00007-of-00017.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ea69035056a913d1780cb9df15613755014ac2cd633e4471c099aa9afcdfbd8
3
+ size 4954802256
model-00008-of-00017.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:788c8277664eb9c8d9daae4fe10442180ebdf8cf63e2a0f555bace15b8b328d8
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:dad40002d277c55138f9222512be85ead54aa221a9c7672e1aa6a6f98a29e800
3
+ size 4954802256
model-00010-of-00017.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e59c525c287e23bbb843f35370f18dedf9f89943032bb7b512dd908227e9b27
3
+ size 4961825192
model-00011-of-00017.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9822ae1968915087d143aa05afaea583431de741300dbe8897279991e4db01e7
3
+ size 4954802256
model-00012-of-00017.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b5a764f0d5840de84dfbfb00937624a89b4a3517192ce1ab2b3262c1763cc08
3
+ size 4961825192
model-00013-of-00017.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ac38d6a2d7d934ae220e7ae1c49accee57d27ff9bb2ddb7498a6987eeeb6e14
3
+ size 4954802256
model-00014-of-00017.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:228a62309613fb5edd15dccb268d757489cba974f979b16c6b64ad3aa52c1a89
3
+ size 4990163459
model-00015-of-00017.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7bc2b651c1ec9f93ffa1ca0d9bc0ce51620bc748d00ed820d0c9818912f3f55c
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:a4a4e953b46a31db63c3505c11aaab420932753fba639833a9255076e12e2125
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:b4ecccfca8d27805cf6d41efb530aabcf41b7c5c1db9c557d5e07c1754e05cf4
3
+ size 402653312
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff