updated usernames
Browse files
README.md
CHANGED
@@ -13,7 +13,7 @@ tags:
|
|
13 |
base_model: SicariusSicariiStuff/Impish_LLAMA_3B
|
14 |
datasets:
|
15 |
- KingNish/reasoning-base-20k
|
16 |
-
-
|
17 |
model-index:
|
18 |
- name: thea-rp-3b-25r
|
19 |
results:
|
@@ -30,7 +30,7 @@ model-index:
|
|
30 |
value: 65.78
|
31 |
name: strict accuracy
|
32 |
source:
|
33 |
-
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=
|
34 |
name: Open LLM Leaderboard
|
35 |
- task:
|
36 |
type: text-generation
|
@@ -45,7 +45,7 @@ model-index:
|
|
45 |
value: 20.01
|
46 |
name: normalized accuracy
|
47 |
source:
|
48 |
-
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=
|
49 |
name: Open LLM Leaderboard
|
50 |
- task:
|
51 |
type: text-generation
|
@@ -60,7 +60,7 @@ model-index:
|
|
60 |
value: 11.71
|
61 |
name: exact match
|
62 |
source:
|
63 |
-
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=
|
64 |
name: Open LLM Leaderboard
|
65 |
- task:
|
66 |
type: text-generation
|
@@ -75,7 +75,7 @@ model-index:
|
|
75 |
value: 3.24
|
76 |
name: acc_norm
|
77 |
source:
|
78 |
-
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=
|
79 |
name: Open LLM Leaderboard
|
80 |
- task:
|
81 |
type: text-generation
|
@@ -90,7 +90,7 @@ model-index:
|
|
90 |
value: 5.93
|
91 |
name: acc_norm
|
92 |
source:
|
93 |
-
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=
|
94 |
name: Open LLM Leaderboard
|
95 |
- task:
|
96 |
type: text-generation
|
@@ -107,7 +107,7 @@ model-index:
|
|
107 |
value: 22.89
|
108 |
name: accuracy
|
109 |
source:
|
110 |
-
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=
|
111 |
name: Open LLM Leaderboard
|
112 |
---
|
113 |
|
@@ -125,7 +125,7 @@ from transformers import AutoModelForCausalLM, AutoTokenizer
|
|
125 |
MAX_REASONING_TOKENS = 1024
|
126 |
MAX_RESPONSE_TOKENS = 512
|
127 |
|
128 |
-
model_name = "
|
129 |
|
130 |
model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype="auto", device_map="auto")
|
131 |
tokenizer = AutoTokenizer.from_pretrained(model_name)
|
@@ -153,7 +153,7 @@ response_output = tokenizer.decode(response_ids[0, response_inputs.input_ids.sha
|
|
153 |
print("ANSWER: " + response_output)
|
154 |
```
|
155 |
|
156 |
-
- **Trained by:** [Piotr Zalewski](https://huggingface.co/
|
157 |
- **License:** llama3.2
|
158 |
- **Finetuned from model:** [SicariusSicariiStuff/Impish_LLAMA_3B](https://huggingface.co/SicariusSicariiStuff/Impish_LLAMA_3B)
|
159 |
- **Dataset used:** [KingNish/reasoning-base-20k](https://huggingface.co/datasets/KingNish/reasoning-base-20k)
|
|
|
13 |
base_model: SicariusSicariiStuff/Impish_LLAMA_3B
|
14 |
datasets:
|
15 |
- KingNish/reasoning-base-20k
|
16 |
+
- lunahr/thea-name-overrides
|
17 |
model-index:
|
18 |
- name: thea-rp-3b-25r
|
19 |
results:
|
|
|
30 |
value: 65.78
|
31 |
name: strict accuracy
|
32 |
source:
|
33 |
+
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=lunahr/thea-rp-3b-25r
|
34 |
name: Open LLM Leaderboard
|
35 |
- task:
|
36 |
type: text-generation
|
|
|
45 |
value: 20.01
|
46 |
name: normalized accuracy
|
47 |
source:
|
48 |
+
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=lunahr/thea-rp-3b-25r
|
49 |
name: Open LLM Leaderboard
|
50 |
- task:
|
51 |
type: text-generation
|
|
|
60 |
value: 11.71
|
61 |
name: exact match
|
62 |
source:
|
63 |
+
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=lunahr/thea-rp-3b-25r
|
64 |
name: Open LLM Leaderboard
|
65 |
- task:
|
66 |
type: text-generation
|
|
|
75 |
value: 3.24
|
76 |
name: acc_norm
|
77 |
source:
|
78 |
+
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=lunahr/thea-rp-3b-25r
|
79 |
name: Open LLM Leaderboard
|
80 |
- task:
|
81 |
type: text-generation
|
|
|
90 |
value: 5.93
|
91 |
name: acc_norm
|
92 |
source:
|
93 |
+
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=lunahr/thea-rp-3b-25r
|
94 |
name: Open LLM Leaderboard
|
95 |
- task:
|
96 |
type: text-generation
|
|
|
107 |
value: 22.89
|
108 |
name: accuracy
|
109 |
source:
|
110 |
+
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=lunahr/thea-rp-3b-25r
|
111 |
name: Open LLM Leaderboard
|
112 |
---
|
113 |
|
|
|
125 |
MAX_REASONING_TOKENS = 1024
|
126 |
MAX_RESPONSE_TOKENS = 512
|
127 |
|
128 |
+
model_name = "lunahr/thea-rp-3b-25r"
|
129 |
|
130 |
model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype="auto", device_map="auto")
|
131 |
tokenizer = AutoTokenizer.from_pretrained(model_name)
|
|
|
153 |
print("ANSWER: " + response_output)
|
154 |
```
|
155 |
|
156 |
+
- **Trained by:** [Piotr Zalewski](https://huggingface.co/lunahr)
|
157 |
- **License:** llama3.2
|
158 |
- **Finetuned from model:** [SicariusSicariiStuff/Impish_LLAMA_3B](https://huggingface.co/SicariusSicariiStuff/Impish_LLAMA_3B)
|
159 |
- **Dataset used:** [KingNish/reasoning-base-20k](https://huggingface.co/datasets/KingNish/reasoning-base-20k)
|