Hugging Face's logo

Severian
/
Jamba-Nexus-4xMoE

Text Generation
Transformers
Safetensors
English
jamba
text-generation-inference
mixture of experts
custom_code
Inference Endpoints
Model card Files Community
Severian commited on
Commit
31578d7
•
1 Parent(s): fd90531

Upload JambaForCausalLM

Browse files
Files changed (10) hide show
  1. README.md +2 -2
  2. config.json +3 -1
  3. model-00001-of-00007.safetensors +3 -0
  4. model-00002-of-00007.safetensors +3 -0
  5. model-00003-of-00007.safetensors +3 -0
  6. model-00004-of-00007.safetensors +3 -0
  7. model-00005-of-00007.safetensors +3 -0
  8. model-00006-of-00007.safetensors +3 -0
  9. model-00007-of-00007.safetensors +3 -0
  10. model.safetensors.index.json +0 -0
README.md CHANGED
@@ -8,10 +8,10 @@ tags:
8
  - unsloth
9
  - mixture of experts
10
  - jamba
11
- base_model: ai21labs/Jamba-v0.1
12
- pipeline_tag: text-generation
13
  datasets:
14
  - Severian/Internal-Knowledge-Map
 
 
15
  ---
16
 
17
  <img src="https://cdn-uploads.huggingface.co/production/uploads/64740cf7485a7c8e1bd51ac9/SwdXRoyi08neRiI8pJrYI.webp" width="500" height="500">
 
8
  - unsloth
9
  - mixture of experts
10
  - jamba
 
 
11
  datasets:
12
  - Severian/Internal-Knowledge-Map
13
+ base_model: ai21labs/Jamba-v0.1
14
+ pipeline_tag: text-generation
15
  ---
16
 
17
  <img src="https://cdn-uploads.huggingface.co/production/uploads/64740cf7485a7c8e1bd51ac9/SwdXRoyi08neRiI8pJrYI.webp" width="500" height="500">
config.json CHANGED
@@ -46,7 +46,9 @@
46
  "bnb_4bit_use_double_quant": false,
47
  "llm_int8_enable_fp32_cpu_offload": false,
48
  "llm_int8_has_fp16_weight": false,
49
- "llm_int8_skip_modules": null,
 
 
50
  "llm_int8_threshold": 6.0,
51
  "load_in_4bit": true,
52
  "load_in_8bit": false,
 
46
  "bnb_4bit_use_double_quant": false,
47
  "llm_int8_enable_fp32_cpu_offload": false,
48
  "llm_int8_has_fp16_weight": false,
49
+ "llm_int8_skip_modules": [
50
+ "mamba"
51
+ ],
52
  "llm_int8_threshold": 6.0,
53
  "load_in_4bit": true,
54
  "load_in_8bit": false,
model-00001-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5cf49a29bbfe163104bbc884a49ced6c79d386886a023bf013fa6b2a97e960ba
3
+ size 4873003499
model-00002-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f716276068242d53f89ffc0ec7abe86a74be5db95b6d2b323879a2167df6ac55
3
+ size 4984623421
model-00003-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:286b676e8605280991577b24b197396dfef581953feaf6228cd39989eb7e5eef
3
+ size 4983413929
model-00004-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26cb0f2404d63b728c1dfbd0f65db71fa1b4126a3fdb0198107f154134262a25
3
+ size 4997975699
model-00005-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46d155ea2b804f565f8d55cb3b5640ef7ce9b6ed5313c8510bd73a7f0c1588b1
3
+ size 4983414017
model-00006-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d30a2bf6784ad0f44485cfe01405141fe78e57c966f38e14fce8f194cba302e
3
+ size 4975844938
model-00007-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa92b3e6fbb3c846a1c1f161aec14e9118469e193057a59dc3acce1e3c93f7b7
3
+ size 3842901948
model.safetensors.index.json CHANGED
The diff for this file is too large to render. See raw diff