Hugging Face's logo

ajibawa-2023
/
carl-llama-2-13b

Text Generation
Transformers
PyTorch
English
llama
text-generation-inference
Inference Endpoints
Model card Files Community
6

Carl_Quantz

#2
by Feanix - opened
base: refs/heads/main
←
from: refs/pr/2
Discussion Files changed
+0
-53
Files changed (16) hide show
  1. Carl_L2_13B_GGML_F16.bin +0 -3
  2. Carl_L2_13B_GGML_Q2_K.bin +0 -3
  3. Carl_L2_13B_GGML_Q3_K_L.bin +0 -3
  4. Carl_L2_13B_GGML_Q3_K_M.bin +0 -3
  5. Carl_L2_13B_GGML_Q3_K_S.bin +0 -3
  6. Carl_L2_13B_GGML_Q4_0.bin +0 -3
  7. Carl_L2_13B_GGML_Q4_1.bin +0 -3
  8. Carl_L2_13B_GGML_Q4_K_M.bin +0 -3
  9. Carl_L2_13B_GGML_Q4_K_S.bin +0 -3
  10. Carl_L2_13B_GGML_Q5_0.bin +0 -3
  11. Carl_L2_13B_GGML_Q5_1.bin +0 -3
  12. Carl_L2_13B_GGML_Q5_K_M.bin +0 -3
  13. Carl_L2_13B_GGML_Q5_K_S.bin +0 -3
  14. Carl_L2_13B_GGML_Q6_K.bin +0 -3
  15. Carl_L2_13B_GGML_Q8_0.bin +0 -3
  16. README.md +0 -8
Carl_L2_13B_GGML_F16.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:53b2462cc0a6dfde7343452c8cac8fcd1e533e5e760513bc5755d76d4d8cef61
3
- size 25839733888
 
 
 
 
Carl_L2_13B_GGML_Q2_K.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:7ad592c9a74b81891bed05aae15c0814742acce31c90803b841325502f42dfd4
3
- size 5508521088
 
 
 
 
Carl_L2_13B_GGML_Q3_K_L.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:a908b78e4962848687357ce1d550bb5debc60557b269d4e664d27567580bea05
3
- size 6929269888
 
 
 
 
Carl_L2_13B_GGML_Q3_K_M.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:1caa43ea3ad4fab8a767ac5a3cfbf1c777bf630e5860dbb0acac1e24b35025d6
3
- size 6313231488
 
 
 
 
Carl_L2_13B_GGML_Q3_K_S.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:0a055d6f03b0d5375bc069f394b9af8003fb14f996b1b2ea0ddbe7e5feec648a
3
- size 5658690688
 
 
 
 
Carl_L2_13B_GGML_Q4_0.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:3dc0e1df0cb04198350d8918d76f304334e9d36e4ddea2ddde3f4ac1c1e79216
3
- size 7365545088
 
 
 
 
Carl_L2_13B_GGML_Q4_1.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:ae884920f6829889b5af08c5350a387f8ca3430068303ad37bdb069f4bc0c7f3
3
- size 8168770688
 
 
 
 
Carl_L2_13B_GGML_Q4_K_M.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:ee4aed68898d2475c7b443cd82e8d518af334317dfc5336ef35c3ca9a554c248
3
- size 7865666688
 
 
 
 
Carl_L2_13B_GGML_Q4_K_S.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:2d0d3e284c4741e0d1923f387cd8a16dd265e250ed5c2c628b0f8fa5c4eec064
3
- size 7365545088
 
 
 
 
Carl_L2_13B_GGML_Q5_0.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:6bb7b74ca965113b060ddc94d48c15102f5feca90172b562147d88d749f339cb
3
- size 8971996288
 
 
 
 
Carl_L2_13B_GGML_Q5_1.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:5420e208c0415ae8348d760da63eb21947580bc7a2768d8faa5f9ca307b7910c
3
- size 9775221888
 
 
 
 
Carl_L2_13B_GGML_Q5_K_M.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:59701815707453d9ef22a50981df571d557b3002f275d8c583e88c96b9d5172a
3
- size 9229634688
 
 
 
 
Carl_L2_13B_GGML_Q5_K_S.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:07d7385b968756c7c06c8caf7964e072091d566f82a44ee0476871fff0d30d75
3
- size 8971996288
 
 
 
 
Carl_L2_13B_GGML_Q6_K.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:fcd5349eda6860b4ff76be19d414514dbc7dea37cac9aca3456d2474ea4c03d7
3
- size 10678850688
 
 
 
 
Carl_L2_13B_GGML_Q8_0.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:9ffe7d7a595dac3e5f79d292eab6e36fa3df7d6276664ce2e56f451da71107a2
3
- size 13791349888
 
 
 
 
README.md CHANGED
@@ -16,14 +16,6 @@ This by means a no replacement to a Doctor or professional therapist. If you are
16
 
17
  **Training:**
18
  Entire dataset was trained on Azure 4 x A100 80GB. For 3 epoch, training took 50 hours. DeepSpeed codebase was used for training purpose. This was trained on Llama-2 by Meta.
19
- GGML Quant models are converted by Kijana Mitchell. Extremely thankful to him.
20
-
21
- **GPTQ**
22
-
23
- GPTQ: [TheBloke](https://huggingface.co/TheBloke/Carl-Llama-2-13B-GPTQ)
24
-
25
-
26
- Special Thanks to [TheBloke](https://huggingface.co/TheBloke) for guiding me and making this model available.
27
 
28
  **Example Prompt:**
29
  ```
 
16
 
17
  **Training:**
18
  Entire dataset was trained on Azure 4 x A100 80GB. For 3 epoch, training took 50 hours. DeepSpeed codebase was used for training purpose. This was trained on Llama-2 by Meta.
 
 
 
 
 
 
 
 
19
 
20
  **Example Prompt:**
21
  ```