Update README.md
Browse files
README.md
CHANGED
@@ -18,11 +18,11 @@ It's a very small LLAMA2 model with only 460M parameters trained with 1T tokens.
|
|
18 |
|
19 |
**Context Length:** 1024 tokens
|
20 |
|
21 |
-
**Prompt Format:**
|
22 |
|
23 |
```
|
24 |
<human>: {{prompt}}
|
25 |
-
<bot>:
|
26 |
```
|
27 |
|
28 |
**Template Name:** TinyLlama
|
@@ -56,10 +56,10 @@ The TinyLlama project aims to pretrain a 1.1B Llama model on 3 trillion tokens.
|
|
56 |
|
57 |
**Context Length:** 4096 tokens
|
58 |
|
59 |
-
**Prompt Format:**
|
60 |
|
61 |
```
|
62 |
-
<|system|>You are a friendly chatbot who always responds in the style of a pirate.</s><|user|>{{prompt}}</s><|assistant|>
|
63 |
```
|
64 |
|
65 |
**Template Name:** TinyLlama
|
@@ -93,10 +93,10 @@ The Mistral-7B-v0.2 Large Language Model (LLM) is a pretrained generative text m
|
|
93 |
|
94 |
**Context Length:** 4096 tokens
|
95 |
|
96 |
-
**Prompt Format:**
|
97 |
|
98 |
```
|
99 |
-
<s>[INST]{{prompt}}[/INST]</s>
|
100 |
```
|
101 |
|
102 |
**Template Name:** Mistral
|
@@ -130,10 +130,10 @@ OpenChat is an innovative library of open-source language models, fine-tuned wit
|
|
130 |
|
131 |
**Context Length:** 4096 tokens
|
132 |
|
133 |
-
**Prompt Format:**
|
134 |
|
135 |
```
|
136 |
-
<s>[INST]{{prompt}}[/INST]</s>
|
137 |
```
|
138 |
|
139 |
**Template Name:** Mistral
|
@@ -167,11 +167,11 @@ Phi-2 is a Transformer with 2.7 billion parameters. It was trained using the sam
|
|
167 |
|
168 |
**Context Length:** 4096 tokens
|
169 |
|
170 |
-
**Prompt Format:**
|
171 |
|
172 |
```
|
173 |
Instruct: {{prompt}}
|
174 |
-
Output:
|
175 |
```
|
176 |
|
177 |
**Template Name:** PHI
|
@@ -205,14 +205,14 @@ The Yi series models are the next generation of open-source large language model
|
|
205 |
|
206 |
**Context Length:** 200000 tokens
|
207 |
|
208 |
-
**Prompt Format:**
|
209 |
|
210 |
```
|
211 |
<|im_start|>user
|
212 |
<|im_end|>
|
213 |
{{prompt}}
|
214 |
<|im_start|>assistant
|
215 |
-
|
216 |
```
|
217 |
|
218 |
**Template Name:** yi
|
@@ -246,13 +246,13 @@ Gemma is a family of lightweight, state-of-the-art open models built from the sa
|
|
246 |
|
247 |
**Context Length:** 8192 tokens
|
248 |
|
249 |
-
**Prompt Format:**
|
250 |
|
251 |
```
|
252 |
<bos><start_of_turn>user
|
253 |
{{prompt}}<end_of_turn>
|
254 |
<start_of_turn>model
|
255 |
-
|
256 |
```
|
257 |
|
258 |
**Template Name:** gemma
|
@@ -286,12 +286,12 @@ StarCoder2-3B model is a 3B parameter model trained on 17 programming languages
|
|
286 |
|
287 |
**Context Length:** 8192 tokens
|
288 |
|
289 |
-
**Prompt Format:**
|
290 |
|
291 |
```
|
292 |
### Instruction
|
293 |
{{prompt}}### Response
|
294 |
-
|
295 |
```
|
296 |
|
297 |
**Template Name:** starcoder
|
@@ -325,14 +325,14 @@ Chinese Tiny LLM 2B 是首个以中文为中心的大型语言模型,主要在
|
|
325 |
|
326 |
**Context Length:** 4096 tokens
|
327 |
|
328 |
-
**Prompt Format:**
|
329 |
|
330 |
```
|
331 |
<|im_start|>user
|
332 |
{{prompt}}
|
333 |
<|im_end|>
|
334 |
<|im_start|>assistant
|
335 |
-
|
336 |
```
|
337 |
|
338 |
**Template Name:** chatml
|
@@ -366,14 +366,14 @@ This model is based on Mistral-7b-v0.2 with 16k context lengths. It's a uncensor
|
|
366 |
|
367 |
**Context Length:** 16384 tokens
|
368 |
|
369 |
-
**Prompt Format:**
|
370 |
|
371 |
```
|
372 |
<|im_start|>user
|
373 |
{{prompt}}
|
374 |
<|im_end|>
|
375 |
<|im_start|>assistant
|
376 |
-
|
377 |
```
|
378 |
|
379 |
**Template Name:** chatml
|
|
|
18 |
|
19 |
**Context Length:** 1024 tokens
|
20 |
|
21 |
+
**Prompt Format:**
|
22 |
|
23 |
```
|
24 |
<human>: {{prompt}}
|
25 |
+
<bot>:
|
26 |
```
|
27 |
|
28 |
**Template Name:** TinyLlama
|
|
|
56 |
|
57 |
**Context Length:** 4096 tokens
|
58 |
|
59 |
+
**Prompt Format:**
|
60 |
|
61 |
```
|
62 |
+
<|system|>You are a friendly chatbot who always responds in the style of a pirate.</s><|user|>{{prompt}}</s><|assistant|>
|
63 |
```
|
64 |
|
65 |
**Template Name:** TinyLlama
|
|
|
93 |
|
94 |
**Context Length:** 4096 tokens
|
95 |
|
96 |
+
**Prompt Format:**
|
97 |
|
98 |
```
|
99 |
+
<s>[INST]{{prompt}}[/INST]</s>
|
100 |
```
|
101 |
|
102 |
**Template Name:** Mistral
|
|
|
130 |
|
131 |
**Context Length:** 4096 tokens
|
132 |
|
133 |
+
**Prompt Format:**
|
134 |
|
135 |
```
|
136 |
+
<s>[INST]{{prompt}}[/INST]</s>
|
137 |
```
|
138 |
|
139 |
**Template Name:** Mistral
|
|
|
167 |
|
168 |
**Context Length:** 4096 tokens
|
169 |
|
170 |
+
**Prompt Format:**
|
171 |
|
172 |
```
|
173 |
Instruct: {{prompt}}
|
174 |
+
Output:
|
175 |
```
|
176 |
|
177 |
**Template Name:** PHI
|
|
|
205 |
|
206 |
**Context Length:** 200000 tokens
|
207 |
|
208 |
+
**Prompt Format:**
|
209 |
|
210 |
```
|
211 |
<|im_start|>user
|
212 |
<|im_end|>
|
213 |
{{prompt}}
|
214 |
<|im_start|>assistant
|
215 |
+
|
216 |
```
|
217 |
|
218 |
**Template Name:** yi
|
|
|
246 |
|
247 |
**Context Length:** 8192 tokens
|
248 |
|
249 |
+
**Prompt Format:**
|
250 |
|
251 |
```
|
252 |
<bos><start_of_turn>user
|
253 |
{{prompt}}<end_of_turn>
|
254 |
<start_of_turn>model
|
255 |
+
|
256 |
```
|
257 |
|
258 |
**Template Name:** gemma
|
|
|
286 |
|
287 |
**Context Length:** 8192 tokens
|
288 |
|
289 |
+
**Prompt Format:**
|
290 |
|
291 |
```
|
292 |
### Instruction
|
293 |
{{prompt}}### Response
|
294 |
+
|
295 |
```
|
296 |
|
297 |
**Template Name:** starcoder
|
|
|
325 |
|
326 |
**Context Length:** 4096 tokens
|
327 |
|
328 |
+
**Prompt Format:**
|
329 |
|
330 |
```
|
331 |
<|im_start|>user
|
332 |
{{prompt}}
|
333 |
<|im_end|>
|
334 |
<|im_start|>assistant
|
335 |
+
|
336 |
```
|
337 |
|
338 |
**Template Name:** chatml
|
|
|
366 |
|
367 |
**Context Length:** 16384 tokens
|
368 |
|
369 |
+
**Prompt Format:**
|
370 |
|
371 |
```
|
372 |
<|im_start|>user
|
373 |
{{prompt}}
|
374 |
<|im_end|>
|
375 |
<|im_start|>assistant
|
376 |
+
|
377 |
```
|
378 |
|
379 |
**Template Name:** chatml
|